Publications
Our published Work!
2024
Shi, Wei-Pei; Nordling, Torbjörn E M
Combining old school autoencoder with Cotracker for improved skin feature tracking Proceedings Article
In: The 19th IEEE Conference on Industrial Electronics and Applications (ICIEA 2024), IEEE, Kristiansand, Norway, 2024.
Abstract | BibTeX | Tags: autoencoder, Convolutional neural network, Cotracker, Deep feature encoder, human motion assessment, Skin feature tracking, Transformer
@inproceedings{Shi2024ICIEA,
title = {Combining old school autoencoder with Cotracker for improved skin feature tracking},
author = {Wei-Pei Shi and Torbjörn E M Nordling},
year = {2024},
date = {2024-08-01},
urldate = {2024-08-01},
booktitle = {The 19th IEEE Conference on Industrial Electronics and Applications (ICIEA 2024)},
publisher = {IEEE},
address = {Kristiansand, Norway},
series = {IEEE Conference on Industrial Electronics and Applications (ICIEA 2024)},
abstract = {Abstract—Background: Skin feature tracking enables quantification of human
motion in an explainable way, making it suitable for clinical assessments.
Accuracy is crucial, but no study has investigated state-of-the-art deep neural
network-based point tracking models such as Cotracker. Cotracker jointly tracks
points and has been shown to have better 3-pixel accuracy than five other
state-of-the-art deep learning methods on the two most commonly used datasets
for evaluation of single target point tracking. In 2021, Chang and Nordling
introduced the Deep Feature Encoder (DFE) and demonstrated skin feature tracking
so accurate that the errors cannot be excluded to stem from the manual labeling
of the videos based on a χ2-test.
Problem: How accurately can different methods track skin features and how to avoid
the intrinsic weaknesses of the methods?
Methods: We use videos of the Unified Parkinson’s Disease Rating Scale postural
tremor test recorded at two hospitals for benchmarking. DFE utilizes the encoder
part of an autoencoder consisting of a five-layer convolutional neural network
trained to reproduce skin crops without supervision. The residual squared error
of the latent features of the encoder is then compared with crops to obtain a
predicted position. We also propose Cotracker DFE, using Cotracker to obtain an
approximate position and subsequently cropping a small area that is fed to DFE
to obtain a position predicted with a lower mean pixel error.
Results: The mean Euclidean distance errors of Cotracker, DFE, and Cotracker-DFE
are 1.2, 0.8, and 0.8 pixels, respectively. DFE requires time-consuming computations,
making it 35 times slower than Cotracker.
Conclusion: The old school DFE provided more accurate skin feature tracking, while
combining DFE with Cotracker provides the best overall performance, circumventing
the lack of labeled data and computational resources required to fine-tune Cotracker.},
howpublished = {The 19th IEEE Conference on Industrial Electronics and Applications (ICIEA 2024), in Kristiansand, Norway 05-08 August 2024},
keywords = {autoencoder, Convolutional neural network, Cotracker, Deep feature encoder, human motion assessment, Skin feature tracking, Transformer},
pubstate = {published},
tppubtype = {inproceedings}
}
Abstract—Background: Skin feature tracking enables quantification of human
motion in an explainable way, making it suitable for clinical assessments.
Accuracy is crucial, but no study has investigated state-of-the-art deep neural
network-based point tracking models such as Cotracker. Cotracker jointly tracks
points and has been shown to have better 3-pixel accuracy than five other
state-of-the-art deep learning methods on the two most commonly used datasets
for evaluation of single target point tracking. In 2021, Chang and Nordling
introduced the Deep Feature Encoder (DFE) and demonstrated skin feature tracking
so accurate that the errors cannot be excluded to stem from the manual labeling
of the videos based on a χ2-test.
Problem: How accurately can different methods track skin features and how to avoid
the intrinsic weaknesses of the methods?
Methods: We use videos of the Unified Parkinson’s Disease Rating Scale postural
tremor test recorded at two hospitals for benchmarking. DFE utilizes the encoder
part of an autoencoder consisting of a five-layer convolutional neural network
trained to reproduce skin crops without supervision. The residual squared error
of the latent features of the encoder is then compared with crops to obtain a
predicted position. We also propose Cotracker DFE, using Cotracker to obtain an
approximate position and subsequently cropping a small area that is fed to DFE
to obtain a position predicted with a lower mean pixel error.
Results: The mean Euclidean distance errors of Cotracker, DFE, and Cotracker-DFE
are 1.2, 0.8, and 0.8 pixels, respectively. DFE requires time-consuming computations,
making it 35 times slower than Cotracker.
Conclusion: The old school DFE provided more accurate skin feature tracking, while
combining DFE with Cotracker provides the best overall performance, circumventing
the lack of labeled data and computational resources required to fine-tune Cotracker.
motion in an explainable way, making it suitable for clinical assessments.
Accuracy is crucial, but no study has investigated state-of-the-art deep neural
network-based point tracking models such as Cotracker. Cotracker jointly tracks
points and has been shown to have better 3-pixel accuracy than five other
state-of-the-art deep learning methods on the two most commonly used datasets
for evaluation of single target point tracking. In 2021, Chang and Nordling
introduced the Deep Feature Encoder (DFE) and demonstrated skin feature tracking
so accurate that the errors cannot be excluded to stem from the manual labeling
of the videos based on a χ2-test.
Problem: How accurately can different methods track skin features and how to avoid
the intrinsic weaknesses of the methods?
Methods: We use videos of the Unified Parkinson’s Disease Rating Scale postural
tremor test recorded at two hospitals for benchmarking. DFE utilizes the encoder
part of an autoencoder consisting of a five-layer convolutional neural network
trained to reproduce skin crops without supervision. The residual squared error
of the latent features of the encoder is then compared with crops to obtain a
predicted position. We also propose Cotracker DFE, using Cotracker to obtain an
approximate position and subsequently cropping a small area that is fed to DFE
to obtain a position predicted with a lower mean pixel error.
Results: The mean Euclidean distance errors of Cotracker, DFE, and Cotracker-DFE
are 1.2, 0.8, and 0.8 pixels, respectively. DFE requires time-consuming computations,
making it 35 times slower than Cotracker.
Conclusion: The old school DFE provided more accurate skin feature tracking, while
combining DFE with Cotracker provides the best overall performance, circumventing
the lack of labeled data and computational resources required to fine-tune Cotracker.
Chang, Jose Ramon; Nordling, Torbjörn E. M.
Unsupervised Skin Feature Tracking with Deep Neural Networks Journal Article
In: arXiv preprint, 2024.
Abstract | Links | BibTeX | Tags: autoencoder, Cotracker, feature matching, feature tracking, image registration, Lucas-Kanade method, PIPs, SIFT, SURF
@article{chang2021skin,
title = {Unsupervised Skin Feature Tracking with Deep Neural Networks},
author = {Jose Ramon Chang and Torbjörn E. M. Nordling},
url = {https://arxiv.org/abs/2405.04943},
year = {2024},
date = {2024-05-08},
journal = {arXiv preprint},
publisher = {Cornell University},
abstract = {Facial feature tracking is essential in imaging ballistocardiography for accurate heart rate estimation and enables motor degradation quantification in Parkinson's disease through skin feature tracking. While deep convolutional neural networks have shown remarkable accuracy in tracking tasks, they typically require extensive labeled data for supervised training. Our proposed pipeline employs a convolutional stacked autoencoder to match image crops with a reference crop containing the target feature, learning deep feature encodings specific to the object category in an unsupervised manner, thus reducing data requirements. To overcome edge effects making the performance dependent on crop size, we introduced a Gaussian weight on the residual errors of the pixels when calculating the loss function. Training the autoencoder on facial images and validating its performance on manually labeled face and hand videos, our Deep Feature Encodings (DFE) method demonstrated superior tracking accuracy with a mean error ranging from 0.6 to 3.3 pixels, outperforming traditional methods like SIFT, SURF, Lucas Kanade, and the latest transformers like PIPs++ and CoTracker. Overall, our unsupervised learning approach excels in tracking various skin features under significant motion conditions, providing superior feature descriptors for tracking, matching, and image registration compared to both traditional and state-of-the-art supervised learning methods.},
keywords = {autoencoder, Cotracker, feature matching, feature tracking, image registration, Lucas-Kanade method, PIPs, SIFT, SURF},
pubstate = {published},
tppubtype = {article}
}
Facial feature tracking is essential in imaging ballistocardiography for accurate heart rate estimation and enables motor degradation quantification in Parkinson's disease through skin feature tracking. While deep convolutional neural networks have shown remarkable accuracy in tracking tasks, they typically require extensive labeled data for supervised training. Our proposed pipeline employs a convolutional stacked autoencoder to match image crops with a reference crop containing the target feature, learning deep feature encodings specific to the object category in an unsupervised manner, thus reducing data requirements. To overcome edge effects making the performance dependent on crop size, we introduced a Gaussian weight on the residual errors of the pixels when calculating the loss function. Training the autoencoder on facial images and validating its performance on manually labeled face and hand videos, our Deep Feature Encodings (DFE) method demonstrated superior tracking accuracy with a mean error ranging from 0.6 to 3.3 pixels, outperforming traditional methods like SIFT, SURF, Lucas Kanade, and the latest transformers like PIPs++ and CoTracker. Overall, our unsupervised learning approach excels in tracking various skin features under significant motion conditions, providing superior feature descriptors for tracking, matching, and image registration compared to both traditional and state-of-the-art supervised learning methods.
Nordling, Torbjörn E M
Shortage of artillery rounds in Ukraine—a reminder of the importance of mass manufacturing Miscellaneous
The 9th International Conference on Precision Machinery and Manufacturing Technology (ICPMMT 2024), Kenting, Pingtung, Taiwan, May 24-26, 2024, 2024.
Abstract | Links | BibTeX | Tags: 3D printing, Artillery Rounds, CNC, Mass Manufacturing, Supply chain
@misc{Nordling2024IPCMMT,
title = {Shortage of artillery rounds in Ukraine—a reminder of the importance of mass manufacturing},
author = {Torbjörn E M Nordling},
url = {https://icpmmt.org/},
year = {2024},
date = {2024-05-01},
booktitle = {The 9th International Conference on Precision Machinery and Manufacturing Technology (ICPMMT 2024), Kenting, Pingtung, Taiwan, May 24-26, 2024},
pages = {1},
publisher = {Prof. Gow-Yi Tzou, ICPMMT, Taiwan},
abstract = {“For both Russia and Ukraine, artillery is the primary means of destruction of troops. Whoever retains fire superiority retains the initiative.” This is stated in an Estonian Ministry of Defence discussion paper “A military strategy for Ukraine's victory and Russia's defeat” (Dec. 2023), where they estimate that Ukraine requires a minimum of 200 000 rounds a month to maintain local fire superiority. Ukraine has asked EU for 250 000 rounds a month. This rate would deplete U.S. and European stockpiles in 2024, with current production estimated at 28 000 and 50 000 rounds a month, respectively. Russia is estimated to reach 3.5 million rounds produced or restored in 2023, i.e. 290 000 rounds a month, and expected to increase it to 375 000 rounds a month in 2024. Meanwhile U.S. aim to reach 100 000 per month in end of 2025. The EU seems to have ordered only 60 000 rounds via the European Defence Agency and it is unclear if EU will deliver the promised 1 million shells by March 2024.
While some suggest that orders are not being placed and a need to rethink process-centered procurement, most talk about a lack of manufacturing capacity and supply chain bottlenecks, e.g. a French parliamentary report (No. 865, 2023) mention delivery times of 10-20 months of unguided 155 mm artillery shells. EU has 15 companies capable of producing such shells, like Rheinmetall and Expal. U.S. has two facilities in Pennsylvania, with machinery dating back to the 2nd World War, and is building a new, largely automated one in Texas. U.S. has also contracted companies in Canada, India, Bulgaria, and Poland.
Manufacturing of the metal body of the shell takes the longest time to build up. This highlight the need to expand and maintain mass manufacturing capacity and also to investigate use of alternative manufacturing techniques to temporarily boost production. Could abundant CNC machines or metal 3D printing be used and at what price point? Rheinmetall has received $3 300 apiece for high-explosive rounds. The later could perhaps be used to make long-range precision guided shells, similar to Excalibur with an initial price of $150 000. Can they stand the pressure and heat?},
howpublished = {The 9th International Conference on Precision Machinery and Manufacturing Technology (ICPMMT 2024), Kenting, Pingtung, Taiwan, May 24-26, 2024},
keywords = {3D printing, Artillery Rounds, CNC, Mass Manufacturing, Supply chain},
pubstate = {published},
tppubtype = {misc}
}
“For both Russia and Ukraine, artillery is the primary means of destruction of troops. Whoever retains fire superiority retains the initiative.” This is stated in an Estonian Ministry of Defence discussion paper “A military strategy for Ukraine's victory and Russia's defeat” (Dec. 2023), where they estimate that Ukraine requires a minimum of 200 000 rounds a month to maintain local fire superiority. Ukraine has asked EU for 250 000 rounds a month. This rate would deplete U.S. and European stockpiles in 2024, with current production estimated at 28 000 and 50 000 rounds a month, respectively. Russia is estimated to reach 3.5 million rounds produced or restored in 2023, i.e. 290 000 rounds a month, and expected to increase it to 375 000 rounds a month in 2024. Meanwhile U.S. aim to reach 100 000 per month in end of 2025. The EU seems to have ordered only 60 000 rounds via the European Defence Agency and it is unclear if EU will deliver the promised 1 million shells by March 2024.
While some suggest that orders are not being placed and a need to rethink process-centered procurement, most talk about a lack of manufacturing capacity and supply chain bottlenecks, e.g. a French parliamentary report (No. 865, 2023) mention delivery times of 10-20 months of unguided 155 mm artillery shells. EU has 15 companies capable of producing such shells, like Rheinmetall and Expal. U.S. has two facilities in Pennsylvania, with machinery dating back to the 2nd World War, and is building a new, largely automated one in Texas. U.S. has also contracted companies in Canada, India, Bulgaria, and Poland.
Manufacturing of the metal body of the shell takes the longest time to build up. This highlight the need to expand and maintain mass manufacturing capacity and also to investigate use of alternative manufacturing techniques to temporarily boost production. Could abundant CNC machines or metal 3D printing be used and at what price point? Rheinmetall has received $3 300 apiece for high-explosive rounds. The later could perhaps be used to make long-range precision guided shells, similar to Excalibur with an initial price of $150 000. Can they stand the pressure and heat?
While some suggest that orders are not being placed and a need to rethink process-centered procurement, most talk about a lack of manufacturing capacity and supply chain bottlenecks, e.g. a French parliamentary report (No. 865, 2023) mention delivery times of 10-20 months of unguided 155 mm artillery shells. EU has 15 companies capable of producing such shells, like Rheinmetall and Expal. U.S. has two facilities in Pennsylvania, with machinery dating back to the 2nd World War, and is building a new, largely automated one in Texas. U.S. has also contracted companies in Canada, India, Bulgaria, and Poland.
Manufacturing of the metal body of the shell takes the longest time to build up. This highlight the need to expand and maintain mass manufacturing capacity and also to investigate use of alternative manufacturing techniques to temporarily boost production. Could abundant CNC machines or metal 3D printing be used and at what price point? Rheinmetall has received $3 300 apiece for high-explosive rounds. The later could perhaps be used to make long-range precision guided shells, similar to Excalibur with an initial price of $150 000. Can they stand the pressure and heat?
Meher, Jagmohan; Wang, Chien-Chih; Nordling, Torbjörn E. M.
Acquisition and Synchronisation of Cardiography Signals from a Clinical Patient Monitor with Facial Video Recordings Proceedings Article
In: Pino, Esteban; Magjarević, Ratko; Carvalho, Paulo (Ed.): International Conference on Biomedical and Health Informatics 2022, pp. 254–261, Springer Nature Switzerland, Cham, 2024, ISBN: 978-3-031-59216-4.
Abstract | Links | BibTeX | Tags: Clinical informatics, data extraction, patient monitor, Philips IntelliVue, remote photoplethysmography (rPPG), Software, vital signs
@inproceedings{Meher2024PDME,
title = {Acquisition and Synchronisation of Cardiography Signals from a Clinical Patient Monitor with Facial Video Recordings},
author = {Jagmohan Meher and Chien-Chih Wang and Torbjörn E. M. Nordling},
editor = {Esteban Pino and Ratko Magjarević and Paulo Carvalho},
url = {https://doi.org/10.1007/978-3-031-59216-4_28},
isbn = {978-3-031-59216-4},
year = {2024},
date = {2024-04-01},
urldate = {2024-04-01},
booktitle = {International Conference on Biomedical and Health Informatics 2022},
pages = {254–261},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {A far too frequent practical challenge in clinical informatics research and method development for acquiring vital signs is the extraction and synchronisation of signals from proprietary devices for the clinical monitoring of patients. In an ongoing study evaluating methods for video-based remote photoplethysmography (rPPG), we needed to extract ground truth values of electrocardiogram (ECG) and pulse oximetry (SpO2) signals from the Philips vitals monitor while recording the facial video of the subject, simultaneously. This ground truth data will be used to train the model that will perform rPPG. Various software can extract data from the Philips vitals monitor with features like data acquisition, parsing, and visualisation, but they lack synchronisation with the facial video. Therefore, we developed the Patient Monitor Data Extractor (PMDE), which collects data from the Philips IntelliVue monitors following the Data export interface programming guide provided by Philips. We set up a DHCP server on a Windows 7 computer with a webcam and interfaced with the monitor through LAN with UDP/IP. We used C++ and Windows Sockets API to develop our software and communicate over UDP. For synchronisation with the video cameras, we turned off the light in the room and used this sudden brightness drop as a trigger. The timestamp of the monitor was recorded when the webcam detected the trigger. The PMDE software records ECG at 500 Hz and SpO2 at 125 Hz with a synchronisation error of less than two sampling periods, which is about 40 ms for a 50 fps video. We conclude that PMDE is uniquely suited for recording data for rPPG evaluation because of its synchronisation feature. We have used PMDE to collect a dataset of facial videos with ground truth ECG and SpO2 signals. We intend to make PMDE available as open source to save other researchers time.},
keywords = {Clinical informatics, data extraction, patient monitor, Philips IntelliVue, remote photoplethysmography (rPPG), Software, vital signs},
pubstate = {published},
tppubtype = {inproceedings}
}
A far too frequent practical challenge in clinical informatics research and method development for acquiring vital signs is the extraction and synchronisation of signals from proprietary devices for the clinical monitoring of patients. In an ongoing study evaluating methods for video-based remote photoplethysmography (rPPG), we needed to extract ground truth values of electrocardiogram (ECG) and pulse oximetry (SpO2) signals from the Philips vitals monitor while recording the facial video of the subject, simultaneously. This ground truth data will be used to train the model that will perform rPPG. Various software can extract data from the Philips vitals monitor with features like data acquisition, parsing, and visualisation, but they lack synchronisation with the facial video. Therefore, we developed the Patient Monitor Data Extractor (PMDE), which collects data from the Philips IntelliVue monitors following the Data export interface programming guide provided by Philips. We set up a DHCP server on a Windows 7 computer with a webcam and interfaced with the monitor through LAN with UDP/IP. We used C++ and Windows Sockets API to develop our software and communicate over UDP. For synchronisation with the video cameras, we turned off the light in the room and used this sudden brightness drop as a trigger. The timestamp of the monitor was recorded when the webcam detected the trigger. The PMDE software records ECG at 500 Hz and SpO2 at 125 Hz with a synchronisation error of less than two sampling periods, which is about 40 ms for a 50 fps video. We conclude that PMDE is uniquely suited for recording data for rPPG evaluation because of its synchronisation feature. We have used PMDE to collect a dataset of facial videos with ground truth ECG and SpO2 signals. We intend to make PMDE available as open source to save other researchers time.
Wu, Yu-Heng; Nordling, Torbjörn E. M.
A structured course of disease dataset with contact tracing information in Taiwan for COVID-19 modelling Journal Article
In: medRxiv, 2024.
Abstract | Links | BibTeX | Tags: COVID-19, Epidemiology, SARS-CoV-2, Structured dataset, Taiwan
@article{Wu2024COVID19dataMedRxiv,
title = {A structured course of disease dataset with contact tracing information in Taiwan for COVID-19 modelling},
author = {Yu-Heng Wu and Torbjörn E. M. Nordling},
url = {https://www.medrxiv.org/content/10.1101/2024.02.28.24303518v1},
doi = {10.1101/2024.02.28.24303518},
year = {2024},
date = {2024-02-01},
journal = {medRxiv},
publisher = {Cold Spring Harbor Laboratory Press},
abstract = {The COVID-19 pandemic has flooded open databases with population-level data. However, individual-level structured data, such as the course of disease and contact tracing information, is almost non-existent in open databases. Publish a structured and cleaned COVID-19 dataset with the course of disease and contact tracing information for easy benchmarking of COVID-19 models. We gathered data from Taiwanese open databases and daily news reports. The outcome is a structured quantitative dataset encompassing the course of the disease of Taiwanese individuals, alongside their contact tracing information. Our dataset comprises 579 confirmed cases covering the period from January 21, to November 9, 2020, when the original SARS-CoV-2 virus was most prevalent in Taiwan. The data include features such as travel history, age, gender, symptoms, contact types between cases, date of symptoms onset, confirmed, critically ill, recovered, and dead. We also include the daily summary data at population-level from January 21, 2020, to May 23, 2022. Our data can help enhance epidemiological modelling.},
keywords = {COVID-19, Epidemiology, SARS-CoV-2, Structured dataset, Taiwan},
pubstate = {published},
tppubtype = {article}
}
The COVID-19 pandemic has flooded open databases with population-level data. However, individual-level structured data, such as the course of disease and contact tracing information, is almost non-existent in open databases. Publish a structured and cleaned COVID-19 dataset with the course of disease and contact tracing information for easy benchmarking of COVID-19 models. We gathered data from Taiwanese open databases and daily news reports. The outcome is a structured quantitative dataset encompassing the course of the disease of Taiwanese individuals, alongside their contact tracing information. Our dataset comprises 579 confirmed cases covering the period from January 21, to November 9, 2020, when the original SARS-CoV-2 virus was most prevalent in Taiwan. The data include features such as travel history, age, gender, symptoms, contact types between cases, date of symptoms onset, confirmed, critically ill, recovered, and dead. We also include the daily summary data at population-level from January 21, 2020, to May 23, 2022. Our data can help enhance epidemiological modelling.
Ashyani, Akram; Wu, Yu-Heng; Hsu, Huan-Wei; Nordling, Torbjörn E. M.
Ideal adaptive control in biological systems–an analysis of P-invariance and dynamical compensation properties Journal Article
In: BMC Bioinformatics, vol. Accepted, 2024.
Abstract | BibTeX | Tags: adaptive proportional-integral feedback, Dynamical compensation property, Ordinary differential equations, P-invariance property
@article{Ashyani2024DC,
title = {Ideal adaptive control in biological systems–an analysis of P-invariance and dynamical compensation properties},
author = {Akram Ashyani and Yu-Heng Wu and Huan-Wei Hsu and Torbjörn E. M. Nordling},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
journal = {BMC Bioinformatics},
volume = {Accepted},
abstract = {Background: Dynamical compensation (DC) provides robustness to parameter fluctuations. As an example, DC enables control of the functional mass of endocrine or neuronal tissue essential for controlling blood glucose by insulin through a nonlinear feedback loop. Researchers have shown that DC is related to the structural unidentifiability and the P-invariance property. The P-invariance property is a sufficient and necessary condition for the DC property. DC has been seen in systems with at least three dimensions. In this article, we discuss DC and P-invariance from an adaptive control perspective. An adaptive controller automatically adjusts its parameters to optimise performance, maintain stability, and deal with uncertainties in a system.
Results: We initiate our analysis by introducing a simplified two-dimensional dynamical model with DC, fostering experimentation and understanding of the system's behavior. We explore the system's behavior with time-varying input and disturbance signals, with a focus on illustrating the system's P-invariance properties in phase portraits and step-like response graphs.
Conclusions: We show that DC can be seen as a case of ideal adaptive control since the system is invariant to the compensated parameter.},
keywords = {adaptive proportional-integral feedback, Dynamical compensation property, Ordinary differential equations, P-invariance property},
pubstate = {published},
tppubtype = {article}
}
Background: Dynamical compensation (DC) provides robustness to parameter fluctuations. As an example, DC enables control of the functional mass of endocrine or neuronal tissue essential for controlling blood glucose by insulin through a nonlinear feedback loop. Researchers have shown that DC is related to the structural unidentifiability and the P-invariance property. The P-invariance property is a sufficient and necessary condition for the DC property. DC has been seen in systems with at least three dimensions. In this article, we discuss DC and P-invariance from an adaptive control perspective. An adaptive controller automatically adjusts its parameters to optimise performance, maintain stability, and deal with uncertainties in a system.
Results: We initiate our analysis by introducing a simplified two-dimensional dynamical model with DC, fostering experimentation and understanding of the system's behavior. We explore the system's behavior with time-varying input and disturbance signals, with a focus on illustrating the system's P-invariance properties in phase portraits and step-like response graphs.
Conclusions: We show that DC can be seen as a case of ideal adaptive control since the system is invariant to the compensated parameter.
Results: We initiate our analysis by introducing a simplified two-dimensional dynamical model with DC, fostering experimentation and understanding of the system's behavior. We explore the system's behavior with time-varying input and disturbance signals, with a focus on illustrating the system's P-invariance properties in phase portraits and step-like response graphs.
Conclusions: We show that DC can be seen as a case of ideal adaptive control since the system is invariant to the compensated parameter.
Irias, Jose Ramon Chang; Yao, Zai-Fu; Hsieh, Shulan; Nordling, Torbjörn E. M.
Age prediction using resting-state functional MRI Journal Article
In: Neuroinformatics, Accepted, 2024.
Abstract | BibTeX | Tags: Abnormal Brain Aging, Brain Aging, Default Mode Network, feature matching, Least Absolute Shrinkage and Selection Operator, Resting-State Functional MRI
@article{Chang2024AgePrediction,
title = {Age prediction using resting-state functional MRI},
author = {Jose Ramon Chang Irias and Zai-Fu Yao and Shulan Hsieh and Torbjörn E. M. Nordling},
year = {2024},
date = {2024-01-01},
journal = {Neuroinformatics, Accepted},
publisher = {Springer},
abstract = {The increasing lifespan and large individual differences in cognitive capability highlight the importance of comprehending the aging process of the brain. Contrary to visible signs of bodily ageing, like greying of hair and loss of muscle mass, the internal changes that occur within our brains remain less apparent until they impair function. Brain age, distinct from chronological age, reflects our brain's health status and may deviate from our actual chronological age.
Notably, brain age has been associated with mortality and depression. The brain is plastic and can compensate even for severe structural damage by rewiring. Functional characterization offers insights that structural cannot provide. Contrary to the multitude of studies relying on structural magnetic resonance imaging (MRI), we utilize resting-state functional MRI (rsfMRI). We also address the issue of inclusion of subjects with abnormal brain ageing through outlier removal.
In this study, we employ the Least Absolute Shrinkage and Selection Operator (LASSO) to identify the 39 most predictive correlations derived from the rsfMRI data. The data is from a cohort of 176 healthy right-handed volunteers, aged 18-78 years (95/81 male/female, mean age 48, SD 17) collected at the Mind Research Imaging Center at the National Cheng Kung University.
We establish a normal reference model by excluding 68 outliers, which achieves a leave-one-out mean absolute error of 2.48 years. By asking which additional features that are needed to predict the chronological age of the outliers with a smaller error, we identify correlations predictive of abnormal aging. These are associated with the Default Mode Network (DMN).
Our normal reference model has the lowest prediction error among published models evaluated on adult subjects of almost all ages and is thus a candidate for screening for abnormal brain aging that has not yet manifested in cognitive decline. This study advances our ability to predict brain aging and provides insights into potential biomarkers for assessing brain age, suggesting that the role of DMN in brain aging should be studied further.},
keywords = {Abnormal Brain Aging, Brain Aging, Default Mode Network, feature matching, Least Absolute Shrinkage and Selection Operator, Resting-State Functional MRI},
pubstate = {published},
tppubtype = {article}
}
The increasing lifespan and large individual differences in cognitive capability highlight the importance of comprehending the aging process of the brain. Contrary to visible signs of bodily ageing, like greying of hair and loss of muscle mass, the internal changes that occur within our brains remain less apparent until they impair function. Brain age, distinct from chronological age, reflects our brain's health status and may deviate from our actual chronological age.
Notably, brain age has been associated with mortality and depression. The brain is plastic and can compensate even for severe structural damage by rewiring. Functional characterization offers insights that structural cannot provide. Contrary to the multitude of studies relying on structural magnetic resonance imaging (MRI), we utilize resting-state functional MRI (rsfMRI). We also address the issue of inclusion of subjects with abnormal brain ageing through outlier removal.
In this study, we employ the Least Absolute Shrinkage and Selection Operator (LASSO) to identify the 39 most predictive correlations derived from the rsfMRI data. The data is from a cohort of 176 healthy right-handed volunteers, aged 18-78 years (95/81 male/female, mean age 48, SD 17) collected at the Mind Research Imaging Center at the National Cheng Kung University.
We establish a normal reference model by excluding 68 outliers, which achieves a leave-one-out mean absolute error of 2.48 years. By asking which additional features that are needed to predict the chronological age of the outliers with a smaller error, we identify correlations predictive of abnormal aging. These are associated with the Default Mode Network (DMN).
Our normal reference model has the lowest prediction error among published models evaluated on adult subjects of almost all ages and is thus a candidate for screening for abnormal brain aging that has not yet manifested in cognitive decline. This study advances our ability to predict brain aging and provides insights into potential biomarkers for assessing brain age, suggesting that the role of DMN in brain aging should be studied further.
Notably, brain age has been associated with mortality and depression. The brain is plastic and can compensate even for severe structural damage by rewiring. Functional characterization offers insights that structural cannot provide. Contrary to the multitude of studies relying on structural magnetic resonance imaging (MRI), we utilize resting-state functional MRI (rsfMRI). We also address the issue of inclusion of subjects with abnormal brain ageing through outlier removal.
In this study, we employ the Least Absolute Shrinkage and Selection Operator (LASSO) to identify the 39 most predictive correlations derived from the rsfMRI data. The data is from a cohort of 176 healthy right-handed volunteers, aged 18-78 years (95/81 male/female, mean age 48, SD 17) collected at the Mind Research Imaging Center at the National Cheng Kung University.
We establish a normal reference model by excluding 68 outliers, which achieves a leave-one-out mean absolute error of 2.48 years. By asking which additional features that are needed to predict the chronological age of the outliers with a smaller error, we identify correlations predictive of abnormal aging. These are associated with the Default Mode Network (DMN).
Our normal reference model has the lowest prediction error among published models evaluated on adult subjects of almost all ages and is thus a candidate for screening for abnormal brain aging that has not yet manifested in cognitive decline. This study advances our ability to predict brain aging and provides insights into potential biomarkers for assessing brain age, suggesting that the role of DMN in brain aging should be studied further.
2023
Irias, Jose Ramon Chang; Yao, Zai-Fu; Hsieh, Shulan; Nordling, Torbjörn E. M.
Age prediction using resting-state functional MRI Journal Article
In: medRxiv, 2023.
Abstract | Links | BibTeX | Tags: Abnormal Brain Aging, Brain Aging, Default Mode Network, feature matching, Least Absolute Shrinkage and Selection Operator, Resting-State Functional MRI
@article{Chang2023AgePredictionMedRxiv,
title = {Age prediction using resting-state functional MRI},
author = {Jose Ramon Chang Irias and Zai-Fu Yao and Shulan Hsieh and Torbjörn E. M. Nordling},
url = {https://www.medrxiv.org/content/early/2023/12/28/2023.12.26.23300530},
doi = {10.1101/2023.12.26.23300530},
year = {2023},
date = {2023-12-01},
journal = {medRxiv},
publisher = {Cold Spring Harbor Laboratory Press},
abstract = {The increasing lifespan and large individual differences in cognitive capability highlight the importance of comprehending the aging process of the brain. Contrary to visible signs of bodily ageing, like greying of hair and loss of muscle mass, the internal changes that occur within our brains remain less apparent until they impair function. Brain age, distinct from chronological age, reflects our brain’s health status and may deviate from our actual chronological age. Notably, brain age has been associated with mortality and depression. The brain is plastic and can compensate even for severe structural damage by rewiring. Functional characterization offers insights that structural cannot provide. Contrary to the multitude of studies relying on structural magnetic resonance imaging (MRI), we utilize resting-state functional MRI (rsfMRI). We also address the issue of inclusion of subjects with abnormal brain ageing through outlier removal. In this study, we employ the Least Absolute Shrinkage and Selection Operator (LASSO) to identify the 39 most predictive correlations derived from the rsfMRI data. The data is from a cohort of 176 healthy right-handed volunteers, aged 18-78 years (95/81 male/female, mean age 48, SD 17) collected at the Mind Research Imaging Center at the National Cheng Kung University. We establish a normal reference model by excluding 68 outliers, which achieves a leave-one-out mean absolute error of 2.48 years. By asking which additional features that are needed to predict the chronological age of the outliers with a smaller error, we identify correlations predictive of abnormal aging. These are associated with the Default Mode Network (DMN). Our normal reference model has the lowest prediction error among published models evaluated on adult subjects of almost all ages and is thus a candidate for screening for abnormal brain aging that has not yet manifested in cognitive decline. This study advances our ability to predict brain aging and provides insights into potential biomarkers for assessing brain age, suggesting that the role of DMN in brain aging should be studied further.
Competing Interest Statement
The authors have declared no competing interest.
Funding Statement
This study was funded by the Ministry of Science and Technology (MOST) of Taiwan (grant number MOST 104-2410-H-006-021-MY2; MOST 106-2410-H-006-031-MY2; MOST 107-2634-F-006-009; MOST 111-2221-E-006-186), and by the National Science and Technology Council (NSTC) of Taiwan (grant number NSTC 112-2321-B-006-013; NSTC 112-2314-B-006-079).
Author Declarations
I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes
The details of the IRB/oversight body that provided approval or exemption for the research described are given below:
Ethics committee/IRB of National Cheng Kung University Research Ethics Committee gave ethical approval for this workI confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes
I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes
The data used in this study is not publicly available due to ethical and privacy considerations. The data utilized for our research is the property of the Mind Research Imaging Center at National Cheng Kung University. Access to the data may be granted in accordance with the ethical and legal guidelines established by the institution. For inquiries or requests regarding data access, interested parties should contact the Mind Research Imaging Center at National Cheng Kung University for further information and permissions.},
keywords = {Abnormal Brain Aging, Brain Aging, Default Mode Network, feature matching, Least Absolute Shrinkage and Selection Operator, Resting-State Functional MRI},
pubstate = {published},
tppubtype = {article}
}
The increasing lifespan and large individual differences in cognitive capability highlight the importance of comprehending the aging process of the brain. Contrary to visible signs of bodily ageing, like greying of hair and loss of muscle mass, the internal changes that occur within our brains remain less apparent until they impair function. Brain age, distinct from chronological age, reflects our brain’s health status and may deviate from our actual chronological age. Notably, brain age has been associated with mortality and depression. The brain is plastic and can compensate even for severe structural damage by rewiring. Functional characterization offers insights that structural cannot provide. Contrary to the multitude of studies relying on structural magnetic resonance imaging (MRI), we utilize resting-state functional MRI (rsfMRI). We also address the issue of inclusion of subjects with abnormal brain ageing through outlier removal. In this study, we employ the Least Absolute Shrinkage and Selection Operator (LASSO) to identify the 39 most predictive correlations derived from the rsfMRI data. The data is from a cohort of 176 healthy right-handed volunteers, aged 18-78 years (95/81 male/female, mean age 48, SD 17) collected at the Mind Research Imaging Center at the National Cheng Kung University. We establish a normal reference model by excluding 68 outliers, which achieves a leave-one-out mean absolute error of 2.48 years. By asking which additional features that are needed to predict the chronological age of the outliers with a smaller error, we identify correlations predictive of abnormal aging. These are associated with the Default Mode Network (DMN). Our normal reference model has the lowest prediction error among published models evaluated on adult subjects of almost all ages and is thus a candidate for screening for abnormal brain aging that has not yet manifested in cognitive decline. This study advances our ability to predict brain aging and provides insights into potential biomarkers for assessing brain age, suggesting that the role of DMN in brain aging should be studied further.
Competing Interest Statement
The authors have declared no competing interest.
Funding Statement
This study was funded by the Ministry of Science and Technology (MOST) of Taiwan (grant number MOST 104-2410-H-006-021-MY2; MOST 106-2410-H-006-031-MY2; MOST 107-2634-F-006-009; MOST 111-2221-E-006-186), and by the National Science and Technology Council (NSTC) of Taiwan (grant number NSTC 112-2321-B-006-013; NSTC 112-2314-B-006-079).
Author Declarations
I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes
The details of the IRB/oversight body that provided approval or exemption for the research described are given below:
Ethics committee/IRB of National Cheng Kung University Research Ethics Committee gave ethical approval for this workI confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes
I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes
The data used in this study is not publicly available due to ethical and privacy considerations. The data utilized for our research is the property of the Mind Research Imaging Center at National Cheng Kung University. Access to the data may be granted in accordance with the ethical and legal guidelines established by the institution. For inquiries or requests regarding data access, interested parties should contact the Mind Research Imaging Center at National Cheng Kung University for further information and permissions.
Competing Interest Statement
The authors have declared no competing interest.
Funding Statement
This study was funded by the Ministry of Science and Technology (MOST) of Taiwan (grant number MOST 104-2410-H-006-021-MY2; MOST 106-2410-H-006-031-MY2; MOST 107-2634-F-006-009; MOST 111-2221-E-006-186), and by the National Science and Technology Council (NSTC) of Taiwan (grant number NSTC 112-2321-B-006-013; NSTC 112-2314-B-006-079).
Author Declarations
I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes
The details of the IRB/oversight body that provided approval or exemption for the research described are given below:
Ethics committee/IRB of National Cheng Kung University Research Ethics Committee gave ethical approval for this workI confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes
I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes
The data used in this study is not publicly available due to ethical and privacy considerations. The data utilized for our research is the property of the Mind Research Imaging Center at National Cheng Kung University. Access to the data may be granted in accordance with the ethical and legal guidelines established by the institution. For inquiries or requests regarding data access, interested parties should contact the Mind Research Imaging Center at National Cheng Kung University for further information and permissions.
Meher, Jagmohan; Allende-Cid, Hector; Nordling, Torbjörn E. M.
A survey and classification of face alignment methods based on face models Journal Article
In: arXiv preprint, 2023.
Abstract | Links | BibTeX | Tags: Face alignment, face models, heatmaps, morphable models, point distribution models
@article{meher2023surveyarxivb,
title = {A survey and classification of face alignment methods based on face models},
author = {Jagmohan Meher and Hector Allende-Cid and Torbjörn E. M. Nordling},
doi = {10.48550/arXiv.2311.03082},
year = {2023},
date = {2023-11-07},
journal = {arXiv preprint},
publisher = {Cornell University},
abstract = {A face model is a mathematical representation of the distinct features of a human face. Traditionally, face models were built using a set of fiducial points or landmarks, each point ideally located on a facial feature, i.e., corner of the eye, tip of the nose, etc. Face alignment is the process of fitting the landmarks in a face model to the respective ground truth positions in an input image containing a face. Despite significant research on face alignment in the past decades, no review analyses various face models used in the literature. Catering to three types of readers - beginners, practitioners and researchers in face alignment, we provide a comprehensive analysis of different face models used for face alignment. We include the interpretation and training of the face models along with the examples of fitting the face model to a new face image. We found that 3D-based face models are preferred in cases of extreme face pose, whereas deep learning-based methods often use heatmaps. Moreover, we discuss the possible future directions of face models in the field of face alignment.},
keywords = {Face alignment, face models, heatmaps, morphable models, point distribution models},
pubstate = {published},
tppubtype = {article}
}
A face model is a mathematical representation of the distinct features of a human face. Traditionally, face models were built using a set of fiducial points or landmarks, each point ideally located on a facial feature, i.e., corner of the eye, tip of the nose, etc. Face alignment is the process of fitting the landmarks in a face model to the respective ground truth positions in an input image containing a face. Despite significant research on face alignment in the past decades, no review analyses various face models used in the literature. Catering to three types of readers - beginners, practitioners and researchers in face alignment, we provide a comprehensive analysis of different face models used for face alignment. We include the interpretation and training of the face models along with the examples of fitting the face model to a new face image. We found that 3D-based face models are preferred in cases of extreme face pose, whereas deep learning-based methods often use heatmaps. Moreover, we discuss the possible future directions of face models in the field of face alignment.
Meher, Jagmohan; Chen, Yan-Cheng; Nordling, Torbjörn E M
Development of Smart Technology Exemplified Through Non-contact Heart Rate Monitoring Miscellaneous
47th Conference on Theoretical and Applied Mechanics (CTAM 2023), Yunlin, Taiwan, Nov. 17-18, 2023, 2023.
Abstract | Links | BibTeX | Tags: Non-contact HR Monitoring; rPPG Methods; Reliability in Healthcare Technology; Smart Machines; Cognitive Computing; Data Collection Challenges
@misc{Meher2023CTAM,
title = {Development of Smart Technology Exemplified Through Non-contact Heart Rate Monitoring},
author = {Jagmohan Meher and Yan-Cheng Chen and Torbjörn E M Nordling},
url = {https://ctam2023.conf.tw/},
year = {2023},
date = {2023-11-01},
booktitle = {47th Conference on Theoretical and Applied Mechanics (CTAM 2023), Yunlin, Taiwan, Nov. 17-18, 2023},
pages = {1},
publisher = {National Formosa University, Yunlin, Taiwan},
address = {No. 64, Wenhua Road, Huwei Township, Yunlin County 63201, Taiwan},
abstract = {The rise of smart machines, driven by technologies like AI and ML, has the potential to transform various sectors, including healthcare. However, their development comes with challenges in data gathering, reliability, and adaptability. Conventional heart rate (HR) monitoring requires skin contact, which can cause discomfort and, in rare cases, infections due to the electrodes used for measuring electrocardiograms. To overcome these challenges, we develop remote photoplethysmography (rPPG) that uses computer vision to enable non-contact HR monitoring. rPPG relies heavily on data because of the wide variety in human skin tones, facial features, expressions, and external factors like changing light conditions and movement. Since there isn’t any dataset that tackled all these challenges, we designed an experiment to capture both facial videos and physiological signals, with systematic variations in lighting, motion, and camera angles, aiming to create a more effective training set for rPPG models. Precise synchronization of facial videos with ECG and PPG signals is challenging, and existing open-source software fell short. Thus, we developed our own software tailored to synchronize facial video with physiological signals recorded using a Philips patient monitor. Using this dataset, we benchmarked seven rPPG methods. The accuracy of rPPG depends on the video quality. We used VIIDEO (Video Intrinsic Integrity and Distortion Evaluation Oracle) to quantify the quality of the recorded video. We manually reduced the video quality, by adding noise and then used it to predict the HR. There remain hurdles before rPPG can be used in all clinical settings. However, through systematic validation against trusted heart rate monitors, transparent presentation of intermediate data processes, and rigorous testing across varied conditions, we are paving the way for rPPG's acceptance. Our challenges are hallmarks of development of smart technology.},
howpublished = {47th Conference on Theoretical and Applied Mechanics (CTAM 2023), Yunlin, Taiwan, Nov. 17-18, 2023},
keywords = {Non-contact HR Monitoring; rPPG Methods; Reliability in Healthcare Technology; Smart Machines; Cognitive Computing; Data Collection Challenges},
pubstate = {published},
tppubtype = {misc}
}
The rise of smart machines, driven by technologies like AI and ML, has the potential to transform various sectors, including healthcare. However, their development comes with challenges in data gathering, reliability, and adaptability. Conventional heart rate (HR) monitoring requires skin contact, which can cause discomfort and, in rare cases, infections due to the electrodes used for measuring electrocardiograms. To overcome these challenges, we develop remote photoplethysmography (rPPG) that uses computer vision to enable non-contact HR monitoring. rPPG relies heavily on data because of the wide variety in human skin tones, facial features, expressions, and external factors like changing light conditions and movement. Since there isn’t any dataset that tackled all these challenges, we designed an experiment to capture both facial videos and physiological signals, with systematic variations in lighting, motion, and camera angles, aiming to create a more effective training set for rPPG models. Precise synchronization of facial videos with ECG and PPG signals is challenging, and existing open-source software fell short. Thus, we developed our own software tailored to synchronize facial video with physiological signals recorded using a Philips patient monitor. Using this dataset, we benchmarked seven rPPG methods. The accuracy of rPPG depends on the video quality. We used VIIDEO (Video Intrinsic Integrity and Distortion Evaluation Oracle) to quantify the quality of the recorded video. We manually reduced the video quality, by adding noise and then used it to predict the HR. There remain hurdles before rPPG can be used in all clinical settings. However, through systematic validation against trusted heart rate monitors, transparent presentation of intermediate data processes, and rigorous testing across varied conditions, we are paving the way for rPPG's acceptance. Our challenges are hallmarks of development of smart technology.
Wu, Yu-Heng; Nordling, Torbjörn E. M.
Towards course of disease based epidemiological modelling: motivation and computational optimization Proceedings Article
In: Proceedings 2023 IEEE 47th Annual International Computer Software and Applications Conference (COMPSAC), pp. 213-222, IEEE, Torino, Italy, 2023, ISSN: 07303157.
Abstract | Links | BibTeX | Tags: COVID-19, epidemiological model, firefly optimization, individual data, synthetic dataset
@inproceedings{Wu2023COMPSAC,
title = {Towards course of disease based epidemiological modelling: motivation and computational optimization},
author = {Yu-Heng Wu and Torbjörn E. M. Nordling},
doi = {10.1109/COMPSAC57700.2023.00035},
issn = {07303157},
year = {2023},
date = {2023-06-01},
booktitle = {Proceedings 2023 IEEE 47th Annual International Computer Software and Applications Conference (COMPSAC)},
pages = {213-222},
publisher = {IEEE},
address = {Torino, Italy},
series = {IEEE Annual International Computer Software and Applications Conference (COMPSAC)},
abstract = {The ongoing COVID-19 pandemic has demonstrated the shortcoming of epidemiological modelling for guiding policy decisions.
Due to the lack of public data on infection spread in contact networks and individual courses of disease, current forecasting models rely heavily on unreliable population statistics and ad hoc parameters, resulting in forecasts with high uncertainty. To tackle the problem of insufficient public individual data, we develop an agent-based model to generate a synthetic Taiwanese COVID-19 dataset. We collected COVID-19 data from Taiwanese public databases for the period when the original SARS-CoV-2 virus was most prevalent (Jan.-Oct., 2020) and fit our model to it. We used the Firefly algorithm to optimize the 194 epidemiological parameters and validated the synthetic dataset by comparing it to Taiwanese public data. Here we study the difference between population statistics and individual course of disease data, and computational optimization of our code to reduce run time. The discrepancy between serum prevalence and reported cases, as well as excess deaths and reported deaths, show that population statistics are unreliable. Monte Carlo simulations using our model further exemplify the discrepancy between actual and reported infections. By using Python CProfiler and Snakeviz packages, we iteratively optimize our algorithm and has so far decreased the computation time of the core code from 0.11s to 0.07s. The large computation time implies that we need further optimize the algorithm.},
howpublished = {IEEE 47th Annual International Computer Software and Applications Conference (COMPSAC), Torino, Italy 26-30 Jun. 2023},
keywords = {COVID-19, epidemiological model, firefly optimization, individual data, synthetic dataset},
pubstate = {published},
tppubtype = {inproceedings}
}
The ongoing COVID-19 pandemic has demonstrated the shortcoming of epidemiological modelling for guiding policy decisions.
Due to the lack of public data on infection spread in contact networks and individual courses of disease, current forecasting models rely heavily on unreliable population statistics and ad hoc parameters, resulting in forecasts with high uncertainty. To tackle the problem of insufficient public individual data, we develop an agent-based model to generate a synthetic Taiwanese COVID-19 dataset. We collected COVID-19 data from Taiwanese public databases for the period when the original SARS-CoV-2 virus was most prevalent (Jan.-Oct., 2020) and fit our model to it. We used the Firefly algorithm to optimize the 194 epidemiological parameters and validated the synthetic dataset by comparing it to Taiwanese public data. Here we study the difference between population statistics and individual course of disease data, and computational optimization of our code to reduce run time. The discrepancy between serum prevalence and reported cases, as well as excess deaths and reported deaths, show that population statistics are unreliable. Monte Carlo simulations using our model further exemplify the discrepancy between actual and reported infections. By using Python CProfiler and Snakeviz packages, we iteratively optimize our algorithm and has so far decreased the computation time of the core code from 0.11s to 0.07s. The large computation time implies that we need further optimize the algorithm.
Due to the lack of public data on infection spread in contact networks and individual courses of disease, current forecasting models rely heavily on unreliable population statistics and ad hoc parameters, resulting in forecasts with high uncertainty. To tackle the problem of insufficient public individual data, we develop an agent-based model to generate a synthetic Taiwanese COVID-19 dataset. We collected COVID-19 data from Taiwanese public databases for the period when the original SARS-CoV-2 virus was most prevalent (Jan.-Oct., 2020) and fit our model to it. We used the Firefly algorithm to optimize the 194 epidemiological parameters and validated the synthetic dataset by comparing it to Taiwanese public data. Here we study the difference between population statistics and individual course of disease data, and computational optimization of our code to reduce run time. The discrepancy between serum prevalence and reported cases, as well as excess deaths and reported deaths, show that population statistics are unreliable. Monte Carlo simulations using our model further exemplify the discrepancy between actual and reported infections. By using Python CProfiler and Snakeviz packages, we iteratively optimize our algorithm and has so far decreased the computation time of the core code from 0.11s to 0.07s. The large computation time implies that we need further optimize the algorithm.
Nordling, Torbjörn E M
Forecasting Mega Trends Impact on Specialisation and Additive Manufacturing in Four Future Scenarios Miscellaneous
The 8th International Conference on Precision Machinery and Manufacturing Technology (ICPMMT 2023), Kenting, Pingtung, Taiwan, May 19-21, 2023, 2023.
Abstract | Links | BibTeX | Tags: 3D printing, Additive Manufacturing, Economic Models, Energy, Future Scenarios, Intellectual Property, Labor, Specialised Manufacturing, Sustainability
@misc{Nordling2023ICPMMT,
title = {Forecasting Mega Trends Impact on Specialisation and Additive Manufacturing in Four Future Scenarios},
author = {Torbjörn E M Nordling},
url = {https://icpmmt.org/},
year = {2023},
date = {2023-05-01},
booktitle = {The 8th International Conference on Precision Machinery and Manufacturing Technology (ICPMMT 2023), Kenting, Pingtung, Taiwan, May 19-21, 2023},
pages = {1},
publisher = {National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan},
abstract = {The dominating trend in manufacturing from early making of stone tools 2.5 million years ago until today is specialisation. Individuals, corporations, and regions are specialising in the making of a particular set of products or parts. Specialisation is the key enabler of learning and labour productivity gains. Additive manufacturing is a recent trend that, in part, counter specialisation. To some additive manufacturing is synonymous with 3D printing, but I argue, based on the underlaying principle, that e.g. modular building also is additive manufacturing. To me any deposition and joining of material or blocks is additive manufacturing. A hallmark of additive manufacturing is that it does not require specialised labour—at least not once the machine and designs used are made. This means that additive manufacturing machines/plants can be placed almost everywhere. Moreover, the total cost of the end customer is reduced by placing such manufacturing near the consumption.
Energy, knowledge, and transportation set the basis for both specialised and additive manufacturing. I define four future scenarios based on the former two: (A) energy abundance and open standards, (B) energy abundance with strong intellectual property enforcement, (C) energy scarcity and open standards, and (D) energy scarcity with strong intellectual property enforcement. To set the stage for analysis and discussion, I present historic examples and current mega trends that lead to the scenarios. E.g. energy abundance based on solar, wind, and hydro will most probably be achieved by countries that let the market forces guide energy investments based on current trends. The shrinking working age population make it challenging to maintain high specialisation. Current intellectual property enforcement slows technical progress and open sharing of models that is needed in additive manufacturing. The development of additive manufacturing is affected by energy price and intellectual property enforcement. Automated additive manufacturing remove advantages of both low labour cost and specialisation, raising questions about the feasibility of the current export model for prosperity.},
howpublished = {The 8th International Conference on Precision Machinery and Manufacturing Technology (ICPMMT 2023), Kenting, Pingtung, Taiwan, May 19-21, 2023},
keywords = {3D printing, Additive Manufacturing, Economic Models, Energy, Future Scenarios, Intellectual Property, Labor, Specialised Manufacturing, Sustainability},
pubstate = {published},
tppubtype = {misc}
}
The dominating trend in manufacturing from early making of stone tools 2.5 million years ago until today is specialisation. Individuals, corporations, and regions are specialising in the making of a particular set of products or parts. Specialisation is the key enabler of learning and labour productivity gains. Additive manufacturing is a recent trend that, in part, counter specialisation. To some additive manufacturing is synonymous with 3D printing, but I argue, based on the underlaying principle, that e.g. modular building also is additive manufacturing. To me any deposition and joining of material or blocks is additive manufacturing. A hallmark of additive manufacturing is that it does not require specialised labour—at least not once the machine and designs used are made. This means that additive manufacturing machines/plants can be placed almost everywhere. Moreover, the total cost of the end customer is reduced by placing such manufacturing near the consumption.
Energy, knowledge, and transportation set the basis for both specialised and additive manufacturing. I define four future scenarios based on the former two: (A) energy abundance and open standards, (B) energy abundance with strong intellectual property enforcement, (C) energy scarcity and open standards, and (D) energy scarcity with strong intellectual property enforcement. To set the stage for analysis and discussion, I present historic examples and current mega trends that lead to the scenarios. E.g. energy abundance based on solar, wind, and hydro will most probably be achieved by countries that let the market forces guide energy investments based on current trends. The shrinking working age population make it challenging to maintain high specialisation. Current intellectual property enforcement slows technical progress and open sharing of models that is needed in additive manufacturing. The development of additive manufacturing is affected by energy price and intellectual property enforcement. Automated additive manufacturing remove advantages of both low labour cost and specialisation, raising questions about the feasibility of the current export model for prosperity.
Energy, knowledge, and transportation set the basis for both specialised and additive manufacturing. I define four future scenarios based on the former two: (A) energy abundance and open standards, (B) energy abundance with strong intellectual property enforcement, (C) energy scarcity and open standards, and (D) energy scarcity with strong intellectual property enforcement. To set the stage for analysis and discussion, I present historic examples and current mega trends that lead to the scenarios. E.g. energy abundance based on solar, wind, and hydro will most probably be achieved by countries that let the market forces guide energy investments based on current trends. The shrinking working age population make it challenging to maintain high specialisation. Current intellectual property enforcement slows technical progress and open sharing of models that is needed in additive manufacturing. The development of additive manufacturing is affected by energy price and intellectual property enforcement. Automated additive manufacturing remove advantages of both low labour cost and specialisation, raising questions about the feasibility of the current export model for prosperity.
Wu, Yu-Heng; Nordling, Torbjörn E. M.
Towards course of disease based epidemiological modelling: motivation and computational optimization Journal Article
In: medRxiv, 2023.
Abstract | Links | BibTeX | Tags: COVID-19, epidemiological model, firefly optimization, individual data, synthetic dataset
@article{Wu2023COMPSACMedRxiv,
title = {Towards course of disease based epidemiological modelling: motivation and computational optimization},
author = {Yu-Heng Wu and Torbjörn E. M. Nordling},
url = {https://www.medrxiv.org/content/early/2023/05/28/2023.05.24.23290318},
doi = {10.1101/2023.05.24.23290318},
year = {2023},
date = {2023-05-01},
journal = {medRxiv},
publisher = {Cold Spring Harbor Laboratory Press},
abstract = {The ongoing COVID-19 pandemic has demonstrated the shortcoming of epidemiological modelling for guiding policy decisions. Due to the lack of public data on infection spread in contact networks and individual courses of disease, current forecasting models rely heavily on unreliable population statistics and ad hoc parameters, resulting in forecasts with high uncertainty. To tackle the problem of insufficient public individual data, we develop an agent-based model to generate a synthetic Taiwanese COVID-19 dataset. We collected COVID-19 data from Taiwanese public databases for the period when the original SARS-CoV-2 virus was most prevalent (Jan.-Oct., 2020) and fit our model to it. We used the Firefly algorithm to optimize the 194 epidemiological parameters and validated the synthetic dataset by comparing it to Taiwanese public data. Here we study the difference between population statistics and individual course of disease data, and computational optimization of our code to reduce run time. The discrepancy between serum prevalence and reported cases, as well as excess deaths and reported deaths, show that population statistics are unreliable. Monte Carlo simulations further exemplify the discrepancy between actual and reported infections. By using Python CProfiler and Snakeviz packages, we iteratively optimize our algorithm and has so far decreased the computation time of the core code from 0.11s to 0.07s. The large computation time implies that we need to further optimize the algorithm.},
keywords = {COVID-19, epidemiological model, firefly optimization, individual data, synthetic dataset},
pubstate = {published},
tppubtype = {article}
}
The ongoing COVID-19 pandemic has demonstrated the shortcoming of epidemiological modelling for guiding policy decisions. Due to the lack of public data on infection spread in contact networks and individual courses of disease, current forecasting models rely heavily on unreliable population statistics and ad hoc parameters, resulting in forecasts with high uncertainty. To tackle the problem of insufficient public individual data, we develop an agent-based model to generate a synthetic Taiwanese COVID-19 dataset. We collected COVID-19 data from Taiwanese public databases for the period when the original SARS-CoV-2 virus was most prevalent (Jan.-Oct., 2020) and fit our model to it. We used the Firefly algorithm to optimize the 194 epidemiological parameters and validated the synthetic dataset by comparing it to Taiwanese public data. Here we study the difference between population statistics and individual course of disease data, and computational optimization of our code to reduce run time. The discrepancy between serum prevalence and reported cases, as well as excess deaths and reported deaths, show that population statistics are unreliable. Monte Carlo simulations further exemplify the discrepancy between actual and reported infections. By using Python CProfiler and Snakeviz packages, we iteratively optimize our algorithm and has so far decreased the computation time of the core code from 0.11s to 0.07s. The large computation time implies that we need to further optimize the algorithm.
Ashyani, Akram; Wu, Yu-Heng; Hsu, Huan-Wei; Nordling, Torbjörn E. M.
An analysis of $mathbbP$-invariance and dynamical compensation properties from a control perspective Journal Article
In: arXiv preprint, 2023.
Abstract | Links | BibTeX | Tags: $mathbb{P}$-invariance, Adaptive control, Dynamical compensation, Ordinary differential equations
@article{ashyani2023DCArxiv,
title = {An analysis of $mathbbP$-invariance and dynamical compensation properties from a control perspective},
author = {Akram Ashyani and Yu-Heng Wu and Huan-Wei Hsu and Torbjörn E. M. Nordling},
url = {https://arxiv.org/abs/2303.10996},
doi = {10.48550/arXiv.2303.10996},
year = {2023},
date = {2023-03-20},
journal = {arXiv preprint},
publisher = {Cornell University},
abstract = {Dynamical compensation (DC) provides robustness to parameter fluctuations. As an example, DC enable control of the functional mass of endocrine or neuronal tissue essential for controlling blood glucose by insulin through a nonlinear feedback loop. Researchers have shown that DC is related to structural unidentifiability and $mathbbP$-invariance property, and $mathbbP$-invariance property is a sufficient and necessary condition for the DC property. In this article, we discuss DC and $mathbbP$-invariancy from an adaptive control perspective. An adaptive controller is a self-tuning controller used to compensate for changes in a dynamical system. To design an adaptive controller with the DC property, it is easier to start with a two-dimensional dynamical model. We introduce a simplified system of ordinary differential equations (ODEs) with the DC property and extend it to a general form. The value of the ideal adaptive control lies in developing methods to synthesize DC to variations in multiple parameters. Then we investigate the stability of the system with time-varying input and disturbance signals, with a focus on the system's $mathbbP$-invariance properties. This study provides phase portraits and step-like response graphs to visualize the system's behavior and stability properties.},
keywords = {$mathbb{P}$-invariance, Adaptive control, Dynamical compensation, Ordinary differential equations},
pubstate = {published},
tppubtype = {article}
}
Dynamical compensation (DC) provides robustness to parameter fluctuations. As an example, DC enable control of the functional mass of endocrine or neuronal tissue essential for controlling blood glucose by insulin through a nonlinear feedback loop. Researchers have shown that DC is related to structural unidentifiability and $mathbbP$-invariance property, and $mathbbP$-invariance property is a sufficient and necessary condition for the DC property. In this article, we discuss DC and $mathbbP$-invariancy from an adaptive control perspective. An adaptive controller is a self-tuning controller used to compensate for changes in a dynamical system. To design an adaptive controller with the DC property, it is easier to start with a two-dimensional dynamical model. We introduce a simplified system of ordinary differential equations (ODEs) with the DC property and extend it to a general form. The value of the ideal adaptive control lies in developing methods to synthesize DC to variations in multiple parameters. Then we investigate the stability of the system with time-varying input and disturbance signals, with a focus on the system's $mathbbP$-invariance properties. This study provides phase portraits and step-like response graphs to visualize the system's behavior and stability properties.
Huang, Hui-Ling; Weng, Chong-Heng; Nordling, Torbjörn E. M.; Liou, Yi-Fan
ThermalProGAN: A sequence-based thermally stable protein generator trained using unpaired data Journal Article
In: Journal of Bioinformatics and Computational Biology, vol. 21, no. 01, pp. 2350008, 2023, ISSN: 0219-7200.
Abstract | Links | BibTeX | Tags: CycleGAN, Generative adversarial neural network, Protein synthesis, Thermal stability
@article{Huang2023ThermalProGAN,
title = {ThermalProGAN: A sequence-based thermally stable protein generator trained using unpaired data},
author = {Hui-Ling Huang and Chong-Heng Weng and Torbjörn E. M. Nordling and Yi-Fan Liou},
url = {https://www.worldscientific.com/doi/10.1142/S0219720023500087},
doi = {10.1142/S0219720023500087},
issn = {0219-7200},
year = {2023},
date = {2023-02-01},
journal = {Journal of Bioinformatics and Computational Biology},
volume = {21},
number = {01},
pages = {2350008},
abstract = {Motivation: The synthesis of proteins with novel desired properties is challenging but sought after by the industry and academia. The dominating approach is based on trial-and-error inducing point mutations, assisted by structural information or predictive models built with paired data that are difficult to collect. This study proposes a sequence-based unpaired-sample of novel protein inventor (SUNI) to build ThermalProGAN for generating thermally stable proteins based on sequence information. Results: The ThermalProGAN can strongly mutate the input sequence with a median number of 32 residues. A known normal protein, 1RG0, was used to generate a thermally stable form by mutating 51 residues. After superimposing the two structures, high similarity is shown, indicating that the basic function would be conserved. Eighty four molecular dynamics simulation results of 1RG0 and the COVID-19 vaccine candidates with a total simulation time of 840[Formula: see text]ns indicate that the thermal stability increased. Conclusion: This proof of concept demonstrated that transfer of a desired protein property from one set of proteins is feasible.},
keywords = {CycleGAN, Generative adversarial neural network, Protein synthesis, Thermal stability},
pubstate = {published},
tppubtype = {article}
}
Motivation: The synthesis of proteins with novel desired properties is challenging but sought after by the industry and academia. The dominating approach is based on trial-and-error inducing point mutations, assisted by structural information or predictive models built with paired data that are difficult to collect. This study proposes a sequence-based unpaired-sample of novel protein inventor (SUNI) to build ThermalProGAN for generating thermally stable proteins based on sequence information. Results: The ThermalProGAN can strongly mutate the input sequence with a median number of 32 residues. A known normal protein, 1RG0, was used to generate a thermally stable form by mutating 51 residues. After superimposing the two structures, high similarity is shown, indicating that the basic function would be conserved. Eighty four molecular dynamics simulation results of 1RG0 and the COVID-19 vaccine candidates with a total simulation time of 840[Formula: see text]ns indicate that the thermal stability increased. Conclusion: This proof of concept demonstrated that transfer of a desired protein property from one set of proteins is feasible.
2022
Chou, Hsi-Wei; Mavropoulos, Timotheos; Lee, Yi-Yun; Lin, Tzu-Ching; Nordling, Torbjörn E. M.
Property Tax Capitalization in Sweden Evidence from the 2008 Reform Miscellaneous
2022.
Abstract | Links | BibTeX | Tags: Property taxation reform, Representative data sample, Single-family house, Tax capitalization
@misc{Chou2022Advance,
title = {Property Tax Capitalization in Sweden Evidence from the 2008 Reform},
author = {Hsi-Wei Chou and Timotheos Mavropoulos and Yi-Yun Lee and Tzu-Ching Lin and Torbjörn E. M. Nordling},
url = {https://advance.sagepub.com/articles/preprint/_/21781712/0},
doi = {10.31124/advance.21781712},
year = {2022},
date = {2022-12-28},
journal = {Advance preprint},
publisher = {Advance},
abstract = {The paper investigates the effect of the property taxation reform introduced in Sweden from 2006 to 2008 on the market price of the affected properties (one-family houses). We make an extensive empirical analysis of the tax capitalization effect, given that prior research has detected only partial capitalization and that there has been an extensive debate regarding the extent to which the tax gets capitalized into property market prices. In particular, the tax capitalization effect for single-family house prices was investigated by looking into various sub-groups of properties and doing extensive statistical inquiries into the property transaction data. Despite a relatively broad time period in which the reform took place, a jump in the market values of the affected properties is detectable in the fourth quarter of 2006. Our findings emphasise the importance of creating a representative data sample in analyzing and assessing the outcomes and impacts of policy interventions such as a taxation reform.},
keywords = {Property taxation reform, Representative data sample, Single-family house, Tax capitalization},
pubstate = {published},
tppubtype = {misc}
}
The paper investigates the effect of the property taxation reform introduced in Sweden from 2006 to 2008 on the market price of the affected properties (one-family houses). We make an extensive empirical analysis of the tax capitalization effect, given that prior research has detected only partial capitalization and that there has been an extensive debate regarding the extent to which the tax gets capitalized into property market prices. In particular, the tax capitalization effect for single-family house prices was investigated by looking into various sub-groups of properties and doing extensive statistical inquiries into the property transaction data. Despite a relatively broad time period in which the reform took place, a jump in the market values of the affected properties is detectable in the fourth quarter of 2006. Our findings emphasise the importance of creating a representative data sample in analyzing and assessing the outcomes and impacts of policy interventions such as a taxation reform.
Huang, Hui-Ling; Weng, Chong-Heng; Nordling, Torbjörn E. M.; Liou, Yi-Fan
ThermalProGAN: a sequence-based thermally stable protein generator trained using un-paired data Miscellaneous
31st International Conference on Genome Informatics (GIW) and 5th International Society for Computational Biology (ISCB) Asia conference (GIW XXXI/ISCB-Asia V), 2022.
Abstract | Links | BibTeX | Tags: Generative adversial network, Protein, synthetic biology
@misc{Huang2022ThermalProGAN,
title = {ThermalProGAN: a sequence-based thermally stable protein generator trained using un-paired data},
author = {Hui-Ling Huang and Chong-Heng Weng and Torbjörn E. M. Nordling and Yi-Fan Liou},
url = {https://www.iscb.org/giw-iscb-asia2022},
year = {2022},
date = {2022-12-01},
booktitle = {GIW XXXI/ISCB-Asia V},
publisher = {International Society for Computational Biology},
address = {Tainan, Taiwan},
abstract = {Motivation: The synthesis of proteins with novel desired properties is challenging but sought after by the industry and academia. The dominating approach is based on trial-and-error-inducing point mutations, assisted by structural information or predictive models built with paired data that are difficult to collect. This study proposes a sequence-based unpaired sample of novel protein inventor (SUNI) to build ThermalProGAN for generating thermally stable proteins based on sequence information. Results: The ThermalProGAN can strongly mutate the input sequence with a median number of 32 residues. A known normal protein,1RG0, was used to generate a thermally stable form by mutating 51 residues. After superimposing the two structures high similarity is shown, indicating that the basic function would be conserved. 84 molecular dynamics simulation results of 1RG0 and the Covid-19 vaccine candidates with a total simulation time of 840 ns indicate that the thermal stability increased. Conclusion: This proof of concept demonstrated that the transfer of a desired protein property from one set of proteins is feasible. Availability and implementation: The source code of ThermalProGAN can be freely accessed at https://github.com/markliou/ThermalProGAN/ with an MIT license. The website is https:// thermalprogan.markliou.tw:433. Supplementary information: Supplementary data are available on Github.},
howpublished = {31st International Conference on Genome Informatics (GIW) and 5th International Society for Computational Biology (ISCB) Asia conference (GIW XXXI/ISCB-Asia V)},
keywords = {Generative adversial network, Protein, synthetic biology},
pubstate = {published},
tppubtype = {misc}
}
Motivation: The synthesis of proteins with novel desired properties is challenging but sought after by the industry and academia. The dominating approach is based on trial-and-error-inducing point mutations, assisted by structural information or predictive models built with paired data that are difficult to collect. This study proposes a sequence-based unpaired sample of novel protein inventor (SUNI) to build ThermalProGAN for generating thermally stable proteins based on sequence information. Results: The ThermalProGAN can strongly mutate the input sequence with a median number of 32 residues. A known normal protein,1RG0, was used to generate a thermally stable form by mutating 51 residues. After superimposing the two structures high similarity is shown, indicating that the basic function would be conserved. 84 molecular dynamics simulation results of 1RG0 and the Covid-19 vaccine candidates with a total simulation time of 840 ns indicate that the thermal stability increased. Conclusion: This proof of concept demonstrated that the transfer of a desired protein property from one set of proteins is feasible. Availability and implementation: The source code of ThermalProGAN can be freely accessed at https://github.com/markliou/ThermalProGAN/ with an MIT license. The website is https:// thermalprogan.markliou.tw:433. Supplementary information: Supplementary data are available on Github.
Meher, Jagmohan; Wang, Chien-Chih; Nordling, Torbjörn E M
Acquisition and synchronisation of cardiography signals from a clinical patient monitor with facial video recordings Journal Article
In: Research Square preprint, 2022.
Abstract | Links | BibTeX | Tags: Biomedical Engineering, Clinical informatics, data extraction, patient monitor., remote photoplethysmography (rPPG), Software, vital signs
@article{meher2022pmde,
title = {Acquisition and synchronisation of cardiography signals from a clinical patient monitor with facial video recordings},
author = {Jagmohan Meher and Chien-Chih Wang and Torbjörn E M Nordling},
url = {https://doi.org/10.21203/rs.3.rs-3588812/v1},
doi = {10.21203/rs.3.rs-3588812/v1},
year = {2022},
date = {2022-11-01},
journal = {Research Square preprint},
abstract = {A far too frequent practical challenge in clinical informatics research and method development for acquiring vital signs is the extraction and synchronisation of signals from proprietary devices for the clinical monitoring of patients. In an ongoing study evaluating methods for video-based remote photoplethysmography (rPPG), we needed to extract ground truth values of electrocardiogram (ECG) and pulse oximetry (SpO2) signals from the Philips vitals monitor while recording the facial video of the subject, simultaneously. This ground truth data will be used to train the model that will perform rPPG. Various software can extract data from the Philips vitals monitor with features like data acquisition, parsing, and visualisation, but they lack synchronisation with the facial video. Therefore, we developed the Patient Monitor Data Extractor (PMDE), which collects data from the Philips IntelliVue monitors following the Data export interface programming guide provided by Philips. We set up a DHCP server on a Windows 7 computer with a webcam and interfaced with the monitor through LAN with UDP/IP. We used C++ and Windows Sockets API to develop our software and communicate over UDP. For synchronisation with the video cameras, we turned off the light in the room and used this sudden brightness drop as a trigger. The timestamp of the monitor was recorded when the webcam detected the trigger. The PMDE software records ECG at 500 Hz and SpO2 at 125 Hz with a synchronisation error of less than two sampling periods, which is about 40 ms for a 50 fps video. We conclude that PMDE is uniquely suited for recording data for rPPG evaluation because of its synchronisation feature. We have used PMDE to collect a dataset of facial videos with ground truth ECG and SpO2 signals. We intend to make PMDE available as open source to save other researchers time.},
keywords = {Biomedical Engineering, Clinical informatics, data extraction, patient monitor., remote photoplethysmography (rPPG), Software, vital signs},
pubstate = {published},
tppubtype = {article}
}
A far too frequent practical challenge in clinical informatics research and method development for acquiring vital signs is the extraction and synchronisation of signals from proprietary devices for the clinical monitoring of patients. In an ongoing study evaluating methods for video-based remote photoplethysmography (rPPG), we needed to extract ground truth values of electrocardiogram (ECG) and pulse oximetry (SpO2) signals from the Philips vitals monitor while recording the facial video of the subject, simultaneously. This ground truth data will be used to train the model that will perform rPPG. Various software can extract data from the Philips vitals monitor with features like data acquisition, parsing, and visualisation, but they lack synchronisation with the facial video. Therefore, we developed the Patient Monitor Data Extractor (PMDE), which collects data from the Philips IntelliVue monitors following the Data export interface programming guide provided by Philips. We set up a DHCP server on a Windows 7 computer with a webcam and interfaced with the monitor through LAN with UDP/IP. We used C++ and Windows Sockets API to develop our software and communicate over UDP. For synchronisation with the video cameras, we turned off the light in the room and used this sudden brightness drop as a trigger. The timestamp of the monitor was recorded when the webcam detected the trigger. The PMDE software records ECG at 500 Hz and SpO2 at 125 Hz with a synchronisation error of less than two sampling periods, which is about 40 ms for a 50 fps video. We conclude that PMDE is uniquely suited for recording data for rPPG evaluation because of its synchronisation feature. We have used PMDE to collect a dataset of facial videos with ground truth ECG and SpO2 signals. We intend to make PMDE available as open source to save other researchers time.
Peralta, Tomas Melo; Nordling, Torbjörn E M
A literature review of methods for assessment of reproducibility in science Journal Article
In: Research Square preprint, 2022.
Abstract | Links | BibTeX | Tags: AI reproducibility assessment, replicability, reproducibility
@article{peralta2022review,
title = {A literature review of methods for assessment of reproducibility in science},
author = {Tomas Melo Peralta and Torbjörn E M Nordling},
url = {https://doi.org/10.21203/rs.3.rs-2267847/v1},
doi = {10.21203/rs.3.rs-2267847},
year = {2022},
date = {2022-11-01},
journal = {Research Square preprint},
abstract = {In response to the US Congress petition, the National Academies of Sciences, Engineering, and Medicine investigated the status of reproducibility and replicability in science. A piece of work is reproducible if the same results can be obtained while following the methods under the same conditions and using the same data. Unavailable data, missing code, and unclear or incomplete method descriptions are common reasons for failure to reproduce results. The motivation behind this review is to investigate the current methods for reproducibility assessment and analyze their strengths and weaknesses so that we can determine where there is room for improvement. We followed the PRISMA 2020 standard and conducted a literature review to find the current methods to assess the reproducibility of scientific articles. We made use of three databases for our search: Web of Science, Scopus, and Engineering Village. Our criteria to find relevant articles was to look for methods, algorithms, or techniques to evaluate, assess, or predict reproducibility in science. We discarded methods that were specific to a single study, or that could not be adapted to scientific articles in general. We found ten articles describing methods to evaluate reproducibility and classified them as either a prediction market, a survey, a machine learning algorithm, or a numerical method. A prediction market requires participants to bet on the reproducibility of a study. The surveys are simple and straightforward, but their performance has not been assessed rigorously. Two types of machine learning methods have been applied: handpicked features and natural language processing. While the machine learning methods are promising because they can be scaled to reduce time and cost for researchers, none of the models reviewed achieved an accuracy above 75%. Given the prominence of transformer models for state-of-the-art NLP tasks, we believe a transformer model can achieve better accuracy.},
keywords = {AI reproducibility assessment, replicability, reproducibility},
pubstate = {published},
tppubtype = {article}
}
In response to the US Congress petition, the National Academies of Sciences, Engineering, and Medicine investigated the status of reproducibility and replicability in science. A piece of work is reproducible if the same results can be obtained while following the methods under the same conditions and using the same data. Unavailable data, missing code, and unclear or incomplete method descriptions are common reasons for failure to reproduce results. The motivation behind this review is to investigate the current methods for reproducibility assessment and analyze their strengths and weaknesses so that we can determine where there is room for improvement. We followed the PRISMA 2020 standard and conducted a literature review to find the current methods to assess the reproducibility of scientific articles. We made use of three databases for our search: Web of Science, Scopus, and Engineering Village. Our criteria to find relevant articles was to look for methods, algorithms, or techniques to evaluate, assess, or predict reproducibility in science. We discarded methods that were specific to a single study, or that could not be adapted to scientific articles in general. We found ten articles describing methods to evaluate reproducibility and classified them as either a prediction market, a survey, a machine learning algorithm, or a numerical method. A prediction market requires participants to bet on the reproducibility of a study. The surveys are simple and straightforward, but their performance has not been assessed rigorously. Two types of machine learning methods have been applied: handpicked features and natural language processing. While the machine learning methods are promising because they can be scaled to reduce time and cost for researchers, none of the models reviewed achieved an accuracy above 75%. Given the prominence of transformer models for state-of-the-art NLP tasks, we believe a transformer model can achieve better accuracy.
Wang, Torbjörn Nordling Jagmohan Meher Chien-Chih
Acquisition and synchronisation of cardiography signals from a clinical patient monitor with facial video recordings Proceedings Article
In: Magjarevic, Ratko (Ed.): Proceedings of the International Conference on Health and Bioinformatics 2022 (ICBHI2022), University of Concepcion, Concepcion, Chile, 2022.
Abstract | BibTeX | Tags: Clinical informatics, data extraction, patient monitor, Philips IntelliVue, remote photoplethysmography (rPPG), Software, vital signs
@inproceedings{Meher2022Sync,
title = {Acquisition and synchronisation of cardiography signals from a clinical patient monitor with facial video recordings},
author = {Torbjörn Nordling Jagmohan Meher Chien-Chih Wang},
editor = {Ratko Magjarevic},
year = {2022},
date = {2022-11-01},
booktitle = {Proceedings of the International Conference on Health and Bioinformatics 2022 (ICBHI2022)},
publisher = {University of Concepcion},
address = {Concepcion, Chile},
series = {IFMBE Proceedings},
abstract = {A far too frequent practical challenge in clinical informatics research and method development for acquiring vital signs is the extraction and synchronisation of signals from proprietary devices for the clinical monitoring of patients. In an ongoing study evaluating methods for video-based remote photoplethysmography (rPPG), we needed to extract ground truth values of electrocardiogram (ECG) and pulse oximetry (SpO2) signals from the Philips vitals monitor while recording the facial video of the subject, simultaneously. This ground truth data will be used to train the model that will perform rPPG. Various software can extract data from the Philips vitals monitor with features like data acquisition, parsing, and visualisation, but they lack synchronisation with the facial video. Therefore, we developed the Patient Monitor Data Extractor (PMDE), which collects data from the Philips IntelliVue monitors following the Data export interface programming guide provided by Philips. We set up a DHCP server on a Windows 7 computer with a webcam and interfaced with the monitor through LAN with UDP/IP. We used C++ and Windows Sockets API to develop our software and communicate over UDP. For synchronisation with the video cameras, we turned off the light in the room and used this sudden brightness drop as a trigger.The timestamp of the monitor was recorded when the webcam detected the trigger. The PMDE software records ECG at 500 Hz and SpO2 at 125 Hz with a synchronisation error of less than two sampling periods, which is about 40 ms for a 50 fps video. We conclude that PMDE is uniquely suited for recording data for rPPG evaluation because of its synchronisation feature. We have used PMDE to collect a dataset of facial videos with ground truth ECG and SpO2 signals. We intend to make PMDE available as open source to save other researchers time.},
howpublished = {The International Conference on Health and Bioinformatics 2022 (ICBHI2022) at University of Concepcion, Concepcion, Chile 24-26 Nov. 2022},
keywords = {Clinical informatics, data extraction, patient monitor, Philips IntelliVue, remote photoplethysmography (rPPG), Software, vital signs},
pubstate = {published},
tppubtype = {inproceedings}
}
A far too frequent practical challenge in clinical informatics research and method development for acquiring vital signs is the extraction and synchronisation of signals from proprietary devices for the clinical monitoring of patients. In an ongoing study evaluating methods for video-based remote photoplethysmography (rPPG), we needed to extract ground truth values of electrocardiogram (ECG) and pulse oximetry (SpO2) signals from the Philips vitals monitor while recording the facial video of the subject, simultaneously. This ground truth data will be used to train the model that will perform rPPG. Various software can extract data from the Philips vitals monitor with features like data acquisition, parsing, and visualisation, but they lack synchronisation with the facial video. Therefore, we developed the Patient Monitor Data Extractor (PMDE), which collects data from the Philips IntelliVue monitors following the Data export interface programming guide provided by Philips. We set up a DHCP server on a Windows 7 computer with a webcam and interfaced with the monitor through LAN with UDP/IP. We used C++ and Windows Sockets API to develop our software and communicate over UDP. For synchronisation with the video cameras, we turned off the light in the room and used this sudden brightness drop as a trigger.The timestamp of the monitor was recorded when the webcam detected the trigger. The PMDE software records ECG at 500 Hz and SpO2 at 125 Hz with a synchronisation error of less than two sampling periods, which is about 40 ms for a 50 fps video. We conclude that PMDE is uniquely suited for recording data for rPPG evaluation because of its synchronisation feature. We have used PMDE to collect a dataset of facial videos with ground truth ECG and SpO2 signals. We intend to make PMDE available as open source to save other researchers time.
Seçilmiş, Deniz; Hillerton, Thomas; Tjärnberg, Andreas; Nelander, Sven; Nordling, Torbjörn E. M.; Sonnhammer, Erik L. L.
Knowledge of the perturbation design is essential for accurate gene regulatory network inference Journal Article
In: Scientific Reports, vol. 12, no. 1, pp. 16531, 2022, ISSN: 2045-2322.
Abstract | Links | BibTeX | Tags: Network Inference, Perturbation experiments
@article{Secilmis2022,
title = {Knowledge of the perturbation design is essential for accurate gene regulatory network inference},
author = {Deniz Seçilmiş and Thomas Hillerton and Andreas Tjärnberg and Sven Nelander and Torbjörn E. M. Nordling and Erik L. L. Sonnhammer},
url = {https://www.nature.com/articles/s41598-022-19005-x},
doi = {10.1038/s41598-022-19005-x},
issn = {2045-2322},
year = {2022},
date = {2022-10-01},
journal = {Scientific Reports},
volume = {12},
number = {1},
pages = {16531},
abstract = {The gene regulatory network (GRN) of a cell executes genetic programs in response to environmental and internal cues. Two distinct classes of methods are used to infer regulatory interactions from gene expression: those that only use observed changes in gene expression, and those that use both the observed changes and the perturbation design, i.e. the targets used to cause the changes in gene expression. Considering that the GRN by definition converts input cues to changes in gene expression, it may be conjectured that the latter methods would yield more accurate inferences but this has not previously been investigated. To address this question, we evaluated a number of popular GRN inference methods that either use the perturbation design or not. For the evaluation we used targeted perturbation knockdown gene expression datasets with varying noise levels generated by two different packages, GeneNetWeaver and GeneSpider. The accuracy was evaluated on each dataset using a variety of measures. The results show that on all datasets, methods using the perturbation design matrix consistently and significantly outperform methods not using it. This was also found to be the case on a smaller experimental dataset from E. coli . Targeted gene perturbations combined with inference methods that use the perturbation design are indispensable for accurate GRN inference.},
keywords = {Network Inference, Perturbation experiments},
pubstate = {published},
tppubtype = {article}
}
The gene regulatory network (GRN) of a cell executes genetic programs in response to environmental and internal cues. Two distinct classes of methods are used to infer regulatory interactions from gene expression: those that only use observed changes in gene expression, and those that use both the observed changes and the perturbation design, i.e. the targets used to cause the changes in gene expression. Considering that the GRN by definition converts input cues to changes in gene expression, it may be conjectured that the latter methods would yield more accurate inferences but this has not previously been investigated. To address this question, we evaluated a number of popular GRN inference methods that either use the perturbation design or not. For the evaluation we used targeted perturbation knockdown gene expression datasets with varying noise levels generated by two different packages, GeneNetWeaver and GeneSpider. The accuracy was evaluated on each dataset using a variety of measures. The results show that on all datasets, methods using the perturbation design matrix consistently and significantly outperform methods not using it. This was also found to be the case on a smaller experimental dataset from E. coli . Targeted gene perturbations combined with inference methods that use the perturbation design are indispensable for accurate GRN inference.
Nordling, Torbjörn E. M.
Feature Selection under Uncertainty–Avoiding the Combinatorial Explosion by Making the Problem Seemingly Harder Miscellaneous
Conference on Advance Topics and Auto Tuning in High-Performance Scientific Computing, 2022.
Abstract | Links | BibTeX | Tags: Feature selection
@misc{Nordling2022ATAT,
title = {Feature Selection under Uncertainty–Avoiding the Combinatorial Explosion by Making the Problem Seemingly Harder},
author = {Torbjörn E. M. Nordling},
url = {https://sites.google.com/site/atathpsc/},
year = {2022},
date = {2022-03-01},
booktitle = {Conference on Advance Topics and Auto Tuning in High-Performance Scientific Computing},
pages = {0},
publisher = {Dept. of Math., National Cheng Kung University (NCKU), Tainan City, Taiwan},
address = {No. 1 University Rd., 701 Tainan, Taiwan (R.O.C.)},
abstract = {Feature selection is a challenging fundamental problem encountered every time one constructs a model of a system. Typically prior knowledge on which features that are essential to measure and include is used. In lack of such knowledge, various feature selection methods based on trying different feature combinations, ranging from exhaustive testing of every possible combination of features to various heuristic search algorithms, are used. In this presentation, I discuss feature selection under uncertainty caused by measurement noise in a linear regression problem. I demonstrate that despite the noise seemingly making the feature selection harder, it can be used to estimate uncertainty sets of each feature and convert the problem into a feature selection under uncertainty problem for which a provably necessary subset of features can be found. To encourage discussion and hopefully provide intuitive understanding this is all presented using one single example motivated by the need to infer gene regulatory networks.},
howpublished = {Conference on Advance Topics and Auto Tuning in High-Performance Scientific Computing},
keywords = {Feature selection},
pubstate = {published},
tppubtype = {misc}
}
Feature selection is a challenging fundamental problem encountered every time one constructs a model of a system. Typically prior knowledge on which features that are essential to measure and include is used. In lack of such knowledge, various feature selection methods based on trying different feature combinations, ranging from exhaustive testing of every possible combination of features to various heuristic search algorithms, are used. In this presentation, I discuss feature selection under uncertainty caused by measurement noise in a linear regression problem. I demonstrate that despite the noise seemingly making the feature selection harder, it can be used to estimate uncertainty sets of each feature and convert the problem into a feature selection under uncertainty problem for which a provably necessary subset of features can be found. To encourage discussion and hopefully provide intuitive understanding this is all presented using one single example motivated by the need to infer gene regulatory networks.
2021
Nordling, Torbjörn E. M.; Baptiste, Shemon
Use of AI and machine learning for efficient growth of high-quality single-wall carbon nanotubes Miscellaneous
45th Conference on Theoretical and Applied Mechanics (CTAM 2021), 2021.
Abstract | Links | BibTeX | Tags: single-wall carbon nanotube; high throughput; machine learning; artificial intelligence; optimization; chemical vapor deposition
@misc{Nordling2021CTAM,
title = {Use of AI and machine learning for efficient growth of high-quality single-wall carbon nanotubes},
author = {Torbjörn E. M. Nordling and Shemon Baptiste},
url = {https://ctam2021.conf.tw/},
year = {2021},
date = {2021-11-19},
booktitle = {45th Conference on Theoretical and Applied Mechanics (CTAM 2021)},
pages = {0},
publisher = {National Taiwan University, Taipei, Taiwan},
address = {Xinhai Road Section 188, Taipei, Taiwan},
abstract = {Optimisation of the growth conditions for manufacturing of single-wall carbon nanotubes (SWCNTs) was challenging until recent demonstration of “High-throughput screening and machine learning for the efficient growth of high-quality single-wall carbon nanotubes” by Ji et al. 2021 in Nano Research (DOI:10.1007/s12274-021-3387-y). The high-throughput screening of growth conditions was conducted by depositing patterned cobalt (Co) nanoparticles on a marked silicon wafer catalysts and varying the temperature, reduction time, carbon precursor, and growth time during chemical vapor deposition. The quality (crystallinity) of the SWCNTs was characterised by the G/D peak intensity (IG/ID) measured by Raman spectroscopy. 1664 samples were used to train and validate machine learning models for prediction of the quality resulting from a particular combination of growth parameters. Here, we expand the work and train an artificial neural network with improved prediction accuracy. The quality depends on the growth parameters in a non-linear fashion with multiple local optima, explaining why it is so hard to optimise the growth conditions without machine learning. With AI growth conditions for high-quality SWCNTs were identified.},
howpublished = {45th Conference on Theoretical and Applied Mechanics (CTAM 2021)},
keywords = {single-wall carbon nanotube; high throughput; machine learning; artificial intelligence; optimization; chemical vapor deposition},
pubstate = {published},
tppubtype = {misc}
}
Optimisation of the growth conditions for manufacturing of single-wall carbon nanotubes (SWCNTs) was challenging until recent demonstration of “High-throughput screening and machine learning for the efficient growth of high-quality single-wall carbon nanotubes” by Ji et al. 2021 in Nano Research (DOI:10.1007/s12274-021-3387-y). The high-throughput screening of growth conditions was conducted by depositing patterned cobalt (Co) nanoparticles on a marked silicon wafer catalysts and varying the temperature, reduction time, carbon precursor, and growth time during chemical vapor deposition. The quality (crystallinity) of the SWCNTs was characterised by the G/D peak intensity (IG/ID) measured by Raman spectroscopy. 1664 samples were used to train and validate machine learning models for prediction of the quality resulting from a particular combination of growth parameters. Here, we expand the work and train an artificial neural network with improved prediction accuracy. The quality depends on the growth parameters in a non-linear fashion with multiple local optima, explaining why it is so hard to optimise the growth conditions without machine learning. With AI growth conditions for high-quality SWCNTs were identified.
Nordling, Torbjörn E. M.
Deep learning for optimisation of growth of high-quality single-wall carbon nanotubes Miscellaneous
2021 International Symposium on Novel and Sustainable Technology (2021 ISNST), 2021.
Abstract | Links | BibTeX | Tags: single-wall carbon nanotube; high throughput; machine learning; artificial intelligence; optimization; chemical vapor deposition
@misc{Nordling2021ISNST,
title = {Deep learning for optimisation of growth of high-quality single-wall carbon nanotubes},
author = {Torbjörn E. M. Nordling},
url = {https://csie.stust.edu.tw/sysid/csie/ISNST2021/},
year = {2021},
date = {2021-11-18},
booktitle = {2021 International Symposium on Novel and Sustainable Technology (2021 ISNST)},
pages = {0},
publisher = {Southern Taiwan University of Science and Technology (STUST), Tainan City, Taiwan},
address = {No.1, Nantai St., Yongkang Dist., Tainan City, Taiwan (R.O.C.)},
abstract = {Manufacturing of single-wall carbon nanotubes (SWCNTs) is challenging, but recently we demonstrated optimisation of the growth conditions in “High-throughput screening and machine learning for the efficient growth of high-quality single-wall carbon nanotubes”, published in Nano Research (DOI:10.1007/s12274-021-3387-y). Our high-throughput screening of growth conditions was conducted by depositing patterned cobalt nanoparticles on a marked silicon wafer catalysts and varying the carbon precursor, growth time, reduction time, and temperature during chemical vapor deposition. We characterised the crystallinity of the SWCNTs by the G/D peak intensity (IG/ID) measured by Raman spectroscopy. We trained and validated machine learning models for prediction of the quality resulting from each combination of growth parameters using 1664 samples. This talk focus on the training of an artificial neural network with improved prediction accuracy. The cost function contain multiple local optima, which make it hard to optimise the growth conditions without machine learning.},
howpublished = {2021 International Symposium on Novel and Sustainable Technology (2021 ISNST)},
keywords = {single-wall carbon nanotube; high throughput; machine learning; artificial intelligence; optimization; chemical vapor deposition},
pubstate = {published},
tppubtype = {misc}
}
Manufacturing of single-wall carbon nanotubes (SWCNTs) is challenging, but recently we demonstrated optimisation of the growth conditions in “High-throughput screening and machine learning for the efficient growth of high-quality single-wall carbon nanotubes”, published in Nano Research (DOI:10.1007/s12274-021-3387-y). Our high-throughput screening of growth conditions was conducted by depositing patterned cobalt nanoparticles on a marked silicon wafer catalysts and varying the carbon precursor, growth time, reduction time, and temperature during chemical vapor deposition. We characterised the crystallinity of the SWCNTs by the G/D peak intensity (IG/ID) measured by Raman spectroscopy. We trained and validated machine learning models for prediction of the quality resulting from each combination of growth parameters using 1664 samples. This talk focus on the training of an artificial neural network with improved prediction accuracy. The cost function contain multiple local optima, which make it hard to optimise the growth conditions without machine learning.
Nordling, Torbjörn E. M.; Wu, Yu-Heng
Taiwan on track to end third COVID-19 community outbreak Journal Article
In: medRxiv, 2021.
Abstract | Links | BibTeX | Tags:
@article{Nordling2021MedRxiv,
title = {Taiwan on track to end third COVID-19 community outbreak},
author = {Torbjörn E. M. Nordling and Yu-Heng Wu},
url = {https://www.medrxiv.org/content/10.1101/2021.06.20.21259178v1},
doi = {10.1101/2021.06.20.21259178},
year = {2021},
date = {2021-06-27},
journal = {medRxiv},
publisher = {Cold Spring Harbor Laboratory Press},
abstract = {Since the start of the COVID-19 pandemic on December 31st, 2019, with the World Health Organization being notified of pneumonia of unknown cause in Wuhan (China), Taiwan has successfully ended two COVID-19 community outbreaks. For 19 days, the third community outbreak has now been successfully suppressed, putting Taiwan on path to end it too around Aug. 16th based on our forecast using an exponential model. Since May 28th the 7-day average of reported confirmed infected, which peaked at 593, has been falling to 204 on June 16th and the 7-day average of reported suspected and excluded cases increased to above 25 000. Resulting in a decrease in the ratio of the 7-day average of local & unknown confirmed to suspected cases–the identified control variable–to less than one third of its peak value. The later is a hallmark of working contact tracing, which together with testing and isolation of infected are the keys to ending the community outbreak.Competing Interest StatementThe authors have declared no competing interest.Funding StatementThis study was supported by Ministry of Science and Technology, Taiwan (MOST 109-2224-E-006-003, 109-2740-B-006-001). The funding has covered a stipend to Yu-Heng Wu and general lab expenses. The funding institution has not been involved in this study.Author DeclarationsI confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.YesThe details of the IRB/oversight body that provided approval or exemption for the research described are given below:The study is completely based on publicly available data so no IRB approval has been sought. Based on the National Cheng Kung University Human Research Ethics Committee guidelines I see no need for IRB.All necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived.YesI understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).YesI have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.YesAll COVID-19 data were collected from the Taiwan Centers for Disease Control (Taiwan CDC), which provided an online platform for downloading datasets, including respiratory syndrome coronavirus-2 (SARS-CoV-2) infection data. Both data downloaded from the online platform and extracted from their News Bulletins were used. https://data.cdc.gov.tw/en/dataset/daily-cases-suspected-sars-cov-2-infection_tested https://www.cdc.gov.tw/Bulletin/List/MmgtpeidAR5Ooai4-fgHzQ},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Since the start of the COVID-19 pandemic on December 31st, 2019, with the World Health Organization being notified of pneumonia of unknown cause in Wuhan (China), Taiwan has successfully ended two COVID-19 community outbreaks. For 19 days, the third community outbreak has now been successfully suppressed, putting Taiwan on path to end it too around Aug. 16th based on our forecast using an exponential model. Since May 28th the 7-day average of reported confirmed infected, which peaked at 593, has been falling to 204 on June 16th and the 7-day average of reported suspected and excluded cases increased to above 25 000. Resulting in a decrease in the ratio of the 7-day average of local & unknown confirmed to suspected cases–the identified control variable–to less than one third of its peak value. The later is a hallmark of working contact tracing, which together with testing and isolation of infected are the keys to ending the community outbreak.Competing Interest StatementThe authors have declared no competing interest.Funding StatementThis study was supported by Ministry of Science and Technology, Taiwan (MOST 109-2224-E-006-003, 109-2740-B-006-001). The funding has covered a stipend to Yu-Heng Wu and general lab expenses. The funding institution has not been involved in this study.Author DeclarationsI confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.YesThe details of the IRB/oversight body that provided approval or exemption for the research described are given below:The study is completely based on publicly available data so no IRB approval has been sought. Based on the National Cheng Kung University Human Research Ethics Committee guidelines I see no need for IRB.All necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived.YesI understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).YesI have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.YesAll COVID-19 data were collected from the Taiwan Centers for Disease Control (Taiwan CDC), which provided an online platform for downloading datasets, including respiratory syndrome coronavirus-2 (SARS-CoV-2) infection data. Both data downloaded from the online platform and extracted from their News Bulletins were used. https://data.cdc.gov.tw/en/dataset/daily-cases-suspected-sars-cov-2-infection_tested https://www.cdc.gov.tw/Bulletin/List/MmgtpeidAR5Ooai4-fgHzQ
Nordling, Torbjörn E. M.
Forecasts of the economic and social implications of AI and Quantum computing Miscellaneous
Symposium for Quantum AI - SQAI 2021, 2021.
Abstract | Links | BibTeX | Tags: artificial intelligence, Quantum Computing
@misc{Nordling2021SQAI,
title = {Forecasts of the economic and social implications of AI and Quantum computing},
author = {Torbjörn E. M. Nordling},
editor = {Seth Austin Harding},
url = {https://sqai.org/},
year = {2021},
date = {2021-05-01},
booktitle = {Symposium for Quantum AI - SQAI 2021},
pages = {0},
publisher = {NTU AI Club},
address = {No.1, Sec. 4, Roosevelt Road, Taipei, Taiwan},
abstract = {In this talk I will discuss the current state of quantum computing, super computing, deep learning, and their implications on society from the perspective of the third industrial revolution.},
howpublished = {Symposium for Quantum AI - SQAI 2021},
keywords = {artificial intelligence, Quantum Computing},
pubstate = {published},
tppubtype = {misc}
}
In this talk I will discuss the current state of quantum computing, super computing, deep learning, and their implications on society from the perspective of the third industrial revolution.
Chang, Jose R; Nordling, Torbjörn E M
Meta-analysis of performance of existing machine learning models for detection of Alzheimer’s disease Miscellaneous
IUBMB Focused Meeting on Neurodegenerative Disease, 2021.
Abstract | Links | BibTeX | Tags: Alzheimers disease, computational biomarkers, machine learning, meta analysis
@misc{Chang2021iubmb,
title = {Meta-analysis of performance of existing machine learning models for detection of Alzheimer’s disease},
author = {Jose R Chang and Torbjörn E M Nordling},
url = {https://iubmb.npas.programs.sinica.edu.tw/},
year = {2021},
date = {2021-04-01},
booktitle = {IUBMB Focused Meeting on Neurodegenerative Disease},
publisher = {Academia Sinica},
address = {Academia Sinica, Taipei, Taiwan},
abstract = {Differentiation between the early stages of Alzheimer's Disease (AD) and normal aging remains a challenging problem. Techniques, such as cerebrospinal fluid assays, magnetic resonance imaging, and positron electron tomography, have helped researchers in the detection of the lesions and changes commonly associated with AD in vivo.
Here we report on our meta-analysis of the performance of machine learning methods using computational biomarkers for detection of mild cognitive impairment and Alzheimer's disease related dementia published 2012-2019. The best reported Bookmaker informedness (BM) score for binary, three-way and four-way classification are 0.994, 0.940 and 0.856; respectively. The reported sensitivity and specificity when doing a four-way classification by distinguishing early and late cognitive impairment is much poorer compared to a binary classification of AD related dementia and normal control.
In conclusion, our analysis shows that the current models are not yet good enough for early diagnosis of AD.},
howpublished = {IUBMB Focused Meeting on Neurodegenerative Disease},
keywords = {Alzheimers disease, computational biomarkers, machine learning, meta analysis},
pubstate = {published},
tppubtype = {misc}
}
Differentiation between the early stages of Alzheimer's Disease (AD) and normal aging remains a challenging problem. Techniques, such as cerebrospinal fluid assays, magnetic resonance imaging, and positron electron tomography, have helped researchers in the detection of the lesions and changes commonly associated with AD in vivo.
Here we report on our meta-analysis of the performance of machine learning methods using computational biomarkers for detection of mild cognitive impairment and Alzheimer's disease related dementia published 2012-2019. The best reported Bookmaker informedness (BM) score for binary, three-way and four-way classification are 0.994, 0.940 and 0.856; respectively. The reported sensitivity and specificity when doing a four-way classification by distinguishing early and late cognitive impairment is much poorer compared to a binary classification of AD related dementia and normal control.
In conclusion, our analysis shows that the current models are not yet good enough for early diagnosis of AD.
Here we report on our meta-analysis of the performance of machine learning methods using computational biomarkers for detection of mild cognitive impairment and Alzheimer's disease related dementia published 2012-2019. The best reported Bookmaker informedness (BM) score for binary, three-way and four-way classification are 0.994, 0.940 and 0.856; respectively. The reported sensitivity and specificity when doing a four-way classification by distinguishing early and late cognitive impairment is much poorer compared to a binary classification of AD related dementia and normal control.
In conclusion, our analysis shows that the current models are not yet good enough for early diagnosis of AD.
Ji, Zhong-Hai; Zhang, Lili; Tang, Dai-Ming; Chen, Chien-Ming; Nordling, Torbjörn E. M.; Zhang, Zheng-De; Ren, Cui-Lan; Da, Bo; Li, Xin; Guo, Shu-Yu; Liu, Chang; Cheng, Hui-Ming
High-throughput screening and machine learning for the efficient growth of high-quality single-wall carbon nanotubes Journal Article
In: Nano Research, 2021, ISSN: 1998-0124.
Abstract | Links | BibTeX | Tags: chemical vapor deposition, high throughput, machine learning, optimization, single-wall carbon nanotube
@article{Ji2020,
title = {High-throughput screening and machine learning for the efficient growth of high-quality single-wall carbon nanotubes},
author = {Zhong-Hai Ji and Lili Zhang and Dai-Ming Tang and Chien-Ming Chen and Torbjörn E. M. Nordling and Zheng-De Zhang and Cui-Lan Ren and Bo Da and Xin Li and Shu-Yu Guo and Chang Liu and Hui-Ming Cheng},
url = {http://link.springer.com/10.1007/s12274-021-3387-y},
doi = {10.1007/s12274-021-3387-y},
issn = {1998-0124},
year = {2021},
date = {2021-03-01},
journal = {Nano Research},
abstract = {It has been a great challenge to optimize the growth conditions toward structure-controlled growth of single-wall carbon nanotubes (SWCNTs). Here, a high-throughput method combined with machine learning is reported that efficiently screens the growth conditions for the synthesis of high-quality SWCNTs. Patterned cobalt (Co) nanoparticles were deposited on a numerically marked silicon wafer as catalysts, and the parameters of temperature, reduction time and carbon precursor were optimized. The crystallinity of the SWCNTs was characterized by Raman spectroscopy where the featured G/D peak intensity (IG/ID) was extracted automatically and mapped to the growth parameters to build a database. 1280 data were collected to train machine learning models. Random forest regression (RFR) showed desirable precision in predicting the growth conditions for high-quality SWCNTs, as validated by further chemical vapor deposition (CVD) growth. This method shows great potential for use in structure-controlled growth of SWCNTs.},
keywords = {chemical vapor deposition, high throughput, machine learning, optimization, single-wall carbon nanotube},
pubstate = {published},
tppubtype = {article}
}
It has been a great challenge to optimize the growth conditions toward structure-controlled growth of single-wall carbon nanotubes (SWCNTs). Here, a high-throughput method combined with machine learning is reported that efficiently screens the growth conditions for the synthesis of high-quality SWCNTs. Patterned cobalt (Co) nanoparticles were deposited on a numerically marked silicon wafer as catalysts, and the parameters of temperature, reduction time and carbon precursor were optimized. The crystallinity of the SWCNTs was characterized by Raman spectroscopy where the featured G/D peak intensity (IG/ID) was extracted automatically and mapped to the growth parameters to build a database. 1280 data were collected to train machine learning models. Random forest regression (RFR) showed desirable precision in predicting the growth conditions for high-quality SWCNTs, as validated by further chemical vapor deposition (CVD) growth. This method shows great potential for use in structure-controlled growth of SWCNTs.
2020
Morgan, Daniel; Studham, Matthew; Tjärnberg, Andreas; Weishaupt, Holger; Swartling, Fredrik J.; Nordling, Torbjörn E. M.; Sonnhammer, Erik L. L.
Perturbation-based gene regulatory network inference to unravel oncogenic mechanisms Journal Article
In: Scientific Reports, vol. 10, no. 1, pp. 14149, 2020, ISSN: 2045-2322.
Abstract | Links | BibTeX | Tags: Network Inference
@article{Morgan2020MYC,
title = {Perturbation-based gene regulatory network inference to unravel oncogenic mechanisms},
author = {Daniel Morgan and Matthew Studham and Andreas Tjärnberg and Holger Weishaupt and Fredrik J. Swartling and Torbjörn E. M. Nordling and Erik L. L. Sonnhammer},
url = {http://www.nature.com/articles/s41598-020-70941-y},
doi = {10.1038/s41598-020-70941-y},
issn = {2045-2322},
year = {2020},
date = {2020-12-01},
journal = {Scientific Reports},
volume = {10},
number = {1},
pages = {14149},
abstract = {The gene regulatory network (GRN) of human cells encodes mechanisms to ensure proper functioning. However, if this GRN is dysregulated, the cell may enter into a disease state such as cancer. Understanding the GRN as a system can therefore help identify novel mechanisms underlying disease, which can lead to new therapies. To deduce regulatory interactions relevant to cancer, we applied a recent computational inference framework to data from perturbation experiments in squamous carcinoma cell line A431. GRNs were inferred using several methods, and the false discovery rate was controlled by the NestBoot framework. We developed a novel approach to assess the predictiveness of inferred GRNs against validation data, despite the lack of a gold standard. The best GRN was significantly more predictive than the null model, both in cross-validated benchmarks and for an independent dataset of the same genes under a different perturbation design. The inferred GRN captures many known regulatory interactions central to cancer-relevant processes in addition to predicting many novel interactions, some of which were experimentally validated, thus providing mechanistic insights that are useful for future cancer research.},
keywords = {Network Inference},
pubstate = {published},
tppubtype = {article}
}
The gene regulatory network (GRN) of human cells encodes mechanisms to ensure proper functioning. However, if this GRN is dysregulated, the cell may enter into a disease state such as cancer. Understanding the GRN as a system can therefore help identify novel mechanisms underlying disease, which can lead to new therapies. To deduce regulatory interactions relevant to cancer, we applied a recent computational inference framework to data from perturbation experiments in squamous carcinoma cell line A431. GRNs were inferred using several methods, and the false discovery rate was controlled by the NestBoot framework. We developed a novel approach to assess the predictiveness of inferred GRNs against validation data, despite the lack of a gold standard. The best GRN was significantly more predictive than the null model, both in cross-validated benchmarks and for an independent dataset of the same genes under a different perturbation design. The inferred GRN captures many known regulatory interactions central to cancer-relevant processes in addition to predicting many novel interactions, some of which were experimentally validated, thus providing mechanistic insights that are useful for future cancer research.
Seçilmiş, Deniz; Hillerton, Thomas; Morgan, Daniel; Tjärnberg, Andreas; Nelander, Sven; Nordling, Torbjörn E M; Sonnhammer, Erik L L
Uncovering cancer gene regulation by accurate regulatory network inference from uninformative data Journal Article
In: npj Systems Biology and Applications, vol. 6, no. 1, pp. 37, 2020, ISSN: 2056-7189.
Abstract | Links | BibTeX | Tags: Network Inference
@article{Secilmis2020,
title = {Uncovering cancer gene regulation by accurate regulatory network inference from uninformative data},
author = {Deniz Seçilmiş and Thomas Hillerton and Daniel Morgan and Andreas Tjärnberg and Sven Nelander and Torbjörn E M Nordling and Erik L L Sonnhammer},
url = {http://www.nature.com/articles/s41540-020-00154-6},
doi = {10.1038/s41540-020-00154-6},
issn = {2056-7189},
year = {2020},
date = {2020-11-01},
journal = {npj Systems Biology and Applications},
volume = {6},
number = {1},
pages = {37},
abstract = {The interactions among the components of a living cell that constitute the gene regulatory network (GRN) can be inferred from perturbation-based gene expression data. Such networks are useful for providing mechanistic insights of a biological system. In order to explore the feasibility and quality of GRN inference at a large scale, we used the L1000 data where $sim$1000 genes have been perturbed and their expression levels have been quantified in 9 cancer cell lines. We found that these datasets have a very low signal-to-noise ratio (SNR) level causing them to be too uninformative to infer accurate GRNs. We developed a gene reduction pipeline in which we eliminate uninformative genes from the system using a selection criterion based on SNR, until reaching an informative subset. The results show that our pipeline can identify an informative subset in an overall uninformative dataset, allowing inference of accurate subset GRNs. The accurate GRNs were functionally characterized and potential novel cancer-related regulatory interactions were identified.},
keywords = {Network Inference},
pubstate = {published},
tppubtype = {article}
}
The interactions among the components of a living cell that constitute the gene regulatory network (GRN) can be inferred from perturbation-based gene expression data. Such networks are useful for providing mechanistic insights of a biological system. In order to explore the feasibility and quality of GRN inference at a large scale, we used the L1000 data where $sim$1000 genes have been perturbed and their expression levels have been quantified in 9 cancer cell lines. We found that these datasets have a very low signal-to-noise ratio (SNR) level causing them to be too uninformative to infer accurate GRNs. We developed a gene reduction pipeline in which we eliminate uninformative genes from the system using a selection criterion based on SNR, until reaching an informative subset. The results show that our pipeline can identify an informative subset in an overall uninformative dataset, allowing inference of accurate subset GRNs. The accurate GRNs were functionally characterized and potential novel cancer-related regulatory interactions were identified.
Mohammadinejad, Hajimohammad; RabieiMotlagh, Omid; Ashyani, Akram
Homoclinical bifurcation of Homiltonian vector fields Book
University of Birjand, Iran, Birjand, University of Birjand, 2020, ISBN: 9786226582148, (In Persian).
BibTeX | Tags:
@book{Mohammadinejad2020,
title = {Homoclinical bifurcation of Homiltonian vector fields},
author = {Hajimohammad Mohammadinejad and Omid RabieiMotlagh and Akram Ashyani},
isbn = {9786226582148},
year = {2020},
date = {2020-04-01},
publisher = {University of Birjand},
address = {Iran, Birjand, University of Birjand},
note = {In Persian},
keywords = {},
pubstate = {published},
tppubtype = {book}
}
2019
Lin, Chia-Ming; Tsai, Po-Jung; Nordling, Torbjörn E M
ProtFunAI–An artificial intelligence for prediction of protein function from protein sequence alone Miscellaneous
The 20th International Conference on Systems Biology (ICSB-2019) in Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan, 2019.
Abstract | Links | BibTeX | Tags: Convolutional neural network, Protein function, Systems Biology
@misc{Nordling2019ICSB,
title = {ProtFunAI–An artificial intelligence for prediction of protein function from protein sequence alone},
author = {Chia-Ming Lin and Po-Jung Tsai and Torbjörn E M Nordling},
url = {https://www2.aeplan.co.jp/icsb2019/images/Program191009.pdf},
year = {2019},
date = {2019-11-01},
booktitle = {The 20th International Conference on Systems Biology (ICSB-2019) in Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan: Abstract book},
pages = {52},
publisher = {Okinawa Institute of Science and Technology (OIST) Graduate University},
address = {Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan},
abstract = {Knowledge about the function of a protein is essential for understanding its role. Prediction of protein functions from the protein sequence alone using computational methods has been attempted. Previously, we created FFANEprot— a deep convolutional neural network trained on a dataset of 81,267 proteins and 1,169 Gene Ontology (GO) terms of the molecular function (MF) from the Swiss-Prot database. It is the best predictor of GO MFs from protein sequence alone, with training and test Matthews correlation coefficients (accuracies) of 0.52 (98.84%) and 0.49 (98.67%), respectively. Based on FFANEprot, we here present the ProtFunAI web service (protfunai.nordlinglab.org) consisting of a database of MF predictions of 20,405 reviewed human proteins and a prediction service that can predict the MF of any supplied protein sequence within roughly a minute.},
howpublished = {The 20th International Conference on Systems Biology (ICSB-2019) in Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan},
keywords = {Convolutional neural network, Protein function, Systems Biology},
pubstate = {published},
tppubtype = {misc}
}
Knowledge about the function of a protein is essential for understanding its role. Prediction of protein functions from the protein sequence alone using computational methods has been attempted. Previously, we created FFANEprot— a deep convolutional neural network trained on a dataset of 81,267 proteins and 1,169 Gene Ontology (GO) terms of the molecular function (MF) from the Swiss-Prot database. It is the best predictor of GO MFs from protein sequence alone, with training and test Matthews correlation coefficients (accuracies) of 0.52 (98.84%) and 0.49 (98.67%), respectively. Based on FFANEprot, we here present the ProtFunAI web service (protfunai.nordlinglab.org) consisting of a database of MF predictions of 20,405 reviewed human proteins and a prediction service that can predict the MF of any supplied protein sequence within roughly a minute.
Chen, Cheng-Hui; Wu, Yu-Heng; Nordling, Torbjörn E. M.
Thermodynamically motivated cell segmentation for single-cell modeling of GAL1 in yeast Miscellaneous
The 20th International Conference on Systems Biology (ICSB-2019) in Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan, 2019.
Links | BibTeX | Tags: Cell segmentation, Convolutional neural network (CNN), Moving approximate entropy (mApEn), Single-cell modeling, Thermodynamic lancet (TL)
@misc{Chen2019ICSB,
title = {Thermodynamically motivated cell segmentation for single-cell modeling of GAL1 in
yeast},
author = {Cheng-Hui Chen and Yu-Heng Wu and Torbjörn E. M. Nordling},
url = {https://www2.aeplan.co.jp/icsb2019/images/Program191009.pdf},
year = {2019},
date = {2019-11-01},
booktitle = {The 20th International Conference on Systems Biology (ICSB-2019) in Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan: Abstract book},
pages = {52},
publisher = {Okinawa Institute of Science and Technology (OIST) Graduate University},
address = {Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan},
howpublished = {The 20th International Conference on Systems Biology (ICSB-2019) in Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan},
keywords = {Cell segmentation, Convolutional neural network (CNN), Moving approximate entropy (mApEn), Single-cell modeling, Thermodynamic lancet (TL)},
pubstate = {published},
tppubtype = {misc}
}
Yu, Jing-Chi `Alan'; Wang, Chien-Chih `Jack'; Wu, Hsi-Chih `Butters'; Zhang, Shun-Jie; Nordling, Torbjörn E. M.
Smart toys and tools for quantification of development of infants and symptoms of Parkinson's patients Miscellaneous
9th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, Oslo (Norway), 2019.
Abstract | Links | BibTeX | Tags: IoT, Smart toys
@misc{Yu2019ICDL-EpiRob,
title = {Smart toys and tools for quantification of development of infants and symptoms of Parkinson's patients},
author = {Jing-Chi `Alan' Yu and Chien-Chih `Jack' Wang and Hsi-Chih `Butters' Wu and Shun-Jie Zhang and Torbjörn E. M. Nordling},
url = {https://icdl-epirob2019.org},
year = {2019},
date = {2019-08-01},
booktitle = {9th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, Oslo (Norway)},
publisher = {IEEE},
address = {Oslo},
abstract = {Despite the revolutionary progress in understanding of human and artificial intelligence over the past five years, characterised by Hawkins' the Thousand Brains Theory of Intelligence and AlphaGo's victory over Go world champions Lee Sedol and Ke Jie, many questions remain. We are interested in the development of the sensorimotor function in infants and degradation of it in Parkinson's patients. We believe that new insights could be gained through long-term longitudinal studies with daily quantification of the motor skills. Towards this aim we here report on four prototype tools for data collection from infants or Parkinson's patients–a smart drum, a smart bongo, a smart pacifier, and an App for quantifying finger tapping. The smart drum and bongo are commercial toys updated with embedded electronics for internet access and two-way communi- cation with the toys through the chat App Telegram. The smart pacifier is based on a Philips Soothie pacifier updated with an inertial measurement unit (IMU) with Bluetooth for tracking of movement in real-time. The App for quantifying finger tapping is based on the Movement Disorder Society-Sponsored Revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) finger tap test that is widely used to evaluate Bradykinesia (slowness and difficulty to start movement). We report on the design and first field test. These tools show potential for long- term longitudinal data collection in the home of children or Parkinson's patients. We welcome suggestions on how to improve the design and new collaborations applying these tools.},
howpublished = {9th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, Oslo (Norway)},
keywords = {IoT, Smart toys},
pubstate = {published},
tppubtype = {misc}
}
Despite the revolutionary progress in understanding of human and artificial intelligence over the past five years, characterised by Hawkins' the Thousand Brains Theory of Intelligence and AlphaGo's victory over Go world champions Lee Sedol and Ke Jie, many questions remain. We are interested in the development of the sensorimotor function in infants and degradation of it in Parkinson's patients. We believe that new insights could be gained through long-term longitudinal studies with daily quantification of the motor skills. Towards this aim we here report on four prototype tools for data collection from infants or Parkinson's patients–a smart drum, a smart bongo, a smart pacifier, and an App for quantifying finger tapping. The smart drum and bongo are commercial toys updated with embedded electronics for internet access and two-way communi- cation with the toys through the chat App Telegram. The smart pacifier is based on a Philips Soothie pacifier updated with an inertial measurement unit (IMU) with Bluetooth for tracking of movement in real-time. The App for quantifying finger tapping is based on the Movement Disorder Society-Sponsored Revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) finger tap test that is widely used to evaluate Bradykinesia (slowness and difficulty to start movement). We report on the design and first field test. These tools show potential for long- term longitudinal data collection in the home of children or Parkinson's patients. We welcome suggestions on how to improve the design and new collaborations applying these tools.
Nordling, Torbjörn E. M.
Automation, Digitalisation, Industry 4.0, and Artificial Intelligence Trends and Case Studies Proceedings Article
In: Mubarok, Fahmi (Ed.): The 4th International Conference on Mechanical Engineering (ICOME 2019) in Yogyakarta (Indonesia), Dept. of Mechanical Engineering, Institut Teknologi Sepuluh Nopember, Yogyakarta, Indonesia, 2019.
Abstract | Links | BibTeX | Tags: artificial intelligence, Automation, deep learning, Digitalisation, Industry 4.0
@inproceedings{Nordling2019ICOME,
title = {Automation, Digitalisation, Industry 4.0, and Artificial Intelligence Trends and Case Studies},
author = {Torbjörn E. M. Nordling},
editor = {Fahmi Mubarok},
url = {https://elib.its.ac.id/conf/icome/?page_id=147},
year = {2019},
date = {2019-08-01},
booktitle = {The 4th International Conference on Mechanical Engineering (ICOME 2019) in Yogyakarta (Indonesia)},
publisher = {Dept. of Mechanical Engineering, Institut Teknologi Sepuluh Nopember},
address = {Yogyakarta, Indonesia},
abstract = {Keynote speech: Manufacturing in the ASEAN region is predicted to have a compound annual growth rate (CAGR) of 6.6% currently. At the same time, major industrial powers are running programs to update their manufacturing industry, e.g. the U.S. “Advanced Manufacturing Partnership”, German “Industrie 4.0”, Japanese “Industry Revitalization Plan”, South Korean “Manufacturing Innovation 3.0”, and Chinese “China Manufacturing 2025”. The U.S. and Korean programs are bottom-up industry lead, while the German and Japanese programs are top-down lead by the government and academic institutions. In particular, the German Industrie 4.0 program, which “refers to the intelligent networking of machines and processes for industry with the help of information and communication technology” has received a lot of attention and the Taiwanese “Productivity 4.0” program is largely based on it. It aims towards flexible production with better coordination of production steps and machine load; convertible factories with modular production lines quickly assembled for tasks; individualized production in small quantities at affordable prices; customer-oriented solutions where the customers design products and smart products send data to the manufacturer; optimised logistics with ideal delivery routes and machines reporting when they need new material; use of data to create new business models and services; to create a resource-efficient circular economy. Currently the Industrie 4.0 market is predicted to grow with a CAGR of 37%, so a large business opportunity exists. The two key drivers of the current update of the manufacturing industry are digitalisation and automation. It is worth noting that this is part of the third industrial revolution, which according to Jeremy Rifkin is characterised by a convergence of how we communicate, power, and move information and goods through digitalisation. Digitalisation is the enabler of exponential growth. Based on the 6D's exponential framework of Peter Diamandis, we can expect the technology to become deceptive and then disruptive, which leads to dematerialisation, demonetisation, and finally democratisation. The development will be challenging for the society due to increased capital demands and reduced employment opportunities until the dematerialisation phase when scarcity is replaced with abundance leading to demonetisation that enable everyone to enjoy the products and thus democratise access. Roughly half of all time spent on work activities, equalling 15 trillion USD in wages, can be automated away using current technology according to McKinsey Global Institute. However, the adoption is predicted to take roughly 15 to 50 years, so all engineers needed to implement the automation will have more work than they can do and new work tasks and professions are created continuously. Therefore, a work shortage is unlikely to occur within the next 15 years, but a mismatch between demanded skills and available skills is already present. Rapid implementation of the third industrial revolution and upgrading of manufacturing to Industrie 4.0 standard is currently the best and only hope I see when it comes to combatting climate change, biodiversity loss, land conversion, and nitrogen & phosphorus loading, and at the same time improving the social conditions. We need to get back within the ecological ceiling of our planet or our civilisation is doomed. Artificial Intelligence (AI), in particular Deep learning, has since the ImageNet LSVRC-2012 contest established itself as one of the core technologies driving the third industrial revolution with many commercial applications. The success of Artificial Narrow Intelligence (ANI) is due to: big labelled data, GPU accelerated distributed computing, open source software, and good algorithms. The transformative power of ANI is best illustrated by how super human solution of the object category classification problem was enabled within 4 years from the best solution being practically worthless. ANI augments the cognitive ability. Therefore, ANI increases the productivity of workers skilled in machine learning exponentially. I believe that prediction will mainly be done by AIs while mechanistic understanding is provided by humans. The data dependency and advantage combined with exponential learning enable first movers to go from zero to global leadership in winner takes all fashion. The technology is likely to increase wealth inequality. To succeed in the AI era it is essential to digitise fast and specialise in a vertical to obtain global leadership within it unless the sales process or regulation provide a barrier of entry.},
keywords = {artificial intelligence, Automation, deep learning, Digitalisation, Industry 4.0},
pubstate = {published},
tppubtype = {inproceedings}
}
Keynote speech: Manufacturing in the ASEAN region is predicted to have a compound annual growth rate (CAGR) of 6.6% currently. At the same time, major industrial powers are running programs to update their manufacturing industry, e.g. the U.S. “Advanced Manufacturing Partnership”, German “Industrie 4.0”, Japanese “Industry Revitalization Plan”, South Korean “Manufacturing Innovation 3.0”, and Chinese “China Manufacturing 2025”. The U.S. and Korean programs are bottom-up industry lead, while the German and Japanese programs are top-down lead by the government and academic institutions. In particular, the German Industrie 4.0 program, which “refers to the intelligent networking of machines and processes for industry with the help of information and communication technology” has received a lot of attention and the Taiwanese “Productivity 4.0” program is largely based on it. It aims towards flexible production with better coordination of production steps and machine load; convertible factories with modular production lines quickly assembled for tasks; individualized production in small quantities at affordable prices; customer-oriented solutions where the customers design products and smart products send data to the manufacturer; optimised logistics with ideal delivery routes and machines reporting when they need new material; use of data to create new business models and services; to create a resource-efficient circular economy. Currently the Industrie 4.0 market is predicted to grow with a CAGR of 37%, so a large business opportunity exists. The two key drivers of the current update of the manufacturing industry are digitalisation and automation. It is worth noting that this is part of the third industrial revolution, which according to Jeremy Rifkin is characterised by a convergence of how we communicate, power, and move information and goods through digitalisation. Digitalisation is the enabler of exponential growth. Based on the 6D's exponential framework of Peter Diamandis, we can expect the technology to become deceptive and then disruptive, which leads to dematerialisation, demonetisation, and finally democratisation. The development will be challenging for the society due to increased capital demands and reduced employment opportunities until the dematerialisation phase when scarcity is replaced with abundance leading to demonetisation that enable everyone to enjoy the products and thus democratise access. Roughly half of all time spent on work activities, equalling 15 trillion USD in wages, can be automated away using current technology according to McKinsey Global Institute. However, the adoption is predicted to take roughly 15 to 50 years, so all engineers needed to implement the automation will have more work than they can do and new work tasks and professions are created continuously. Therefore, a work shortage is unlikely to occur within the next 15 years, but a mismatch between demanded skills and available skills is already present. Rapid implementation of the third industrial revolution and upgrading of manufacturing to Industrie 4.0 standard is currently the best and only hope I see when it comes to combatting climate change, biodiversity loss, land conversion, and nitrogen & phosphorus loading, and at the same time improving the social conditions. We need to get back within the ecological ceiling of our planet or our civilisation is doomed. Artificial Intelligence (AI), in particular Deep learning, has since the ImageNet LSVRC-2012 contest established itself as one of the core technologies driving the third industrial revolution with many commercial applications. The success of Artificial Narrow Intelligence (ANI) is due to: big labelled data, GPU accelerated distributed computing, open source software, and good algorithms. The transformative power of ANI is best illustrated by how super human solution of the object category classification problem was enabled within 4 years from the best solution being practically worthless. ANI augments the cognitive ability. Therefore, ANI increases the productivity of workers skilled in machine learning exponentially. I believe that prediction will mainly be done by AIs while mechanistic understanding is provided by humans. The data dependency and advantage combined with exponential learning enable first movers to go from zero to global leadership in winner takes all fashion. The technology is likely to increase wealth inequality. To succeed in the AI era it is essential to digitise fast and specialise in a vertical to obtain global leadership within it unless the sales process or regulation provide a barrier of entry.
Morgan, Daniel; Tjärnberg, Andreas; Nordling, Torbjörn E M; Sonnhammer, Erik L L
A generalized framework for controlling FDR in gene regulatory network inference Journal Article
In: Bioinformatics, vol. 35, no. 6, pp. 1026–1032, 2019, ISSN: 1367-4803.
Abstract | Links | BibTeX | Tags:
@article{Morgan2019,
title = {A generalized framework for controlling FDR in gene regulatory network inference},
author = {Daniel Morgan and Andreas Tjärnberg and Torbjörn E M Nordling and Erik L L Sonnhammer},
editor = {Bonnie Berger},
url = {https://academic.oup.com/bioinformatics/article/35/6/1026/5086392},
doi = {10.1093/bioinformatics/bty764},
issn = {1367-4803},
year = {2019},
date = {2019-03-01},
journal = {Bioinformatics},
volume = {35},
number = {6},
pages = {1026–1032},
abstract = {Motivation: Inference of gene regulatory networks (GRNs) from perturbation data can give detailed mechanistic insights of a biological system. Many inference methods exist, but the resulting GRN is generally sensitive to the choice of method-specific parameters. Even though the inferred GRN is optimal given the parameters, many links may be wrong or missing if the data is not informative. To make GRN inference reliable, a method is needed to estimate the support of each predicted link as the method parameters are varied. Results: To achieve this we have developed a method called nested bootstrapping, which applies a bootstrapping protocol to GRN inference, and by repeated bootstrap runs assesses the stability of the estimated support values. To translate bootstrap support values to false discovery rates we run the same pipeline with shuffled data as input. This provides a general method to control the false discovery rate of GRN inference that can be applied to any setting of inference parameters, noise level, or data properties. We evaluated nested bootstrapping on a simulated dataset spanning a range of such properties, using the LASSO, Least Squares, RNI, GENIE3 and CLR inference methods. An improved inference accuracy was observed in almost all situations. Nested bootstrapping was incorporated into the GeneSPIDER package, which was also used for generating the simulated networks and data, as well as running and analyzing the inferences. Availability: https://bitbucket.org/sonnhammergrni/genespider/src/NB/%2BMethods/NestBoot.m},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Motivation: Inference of gene regulatory networks (GRNs) from perturbation data can give detailed mechanistic insights of a biological system. Many inference methods exist, but the resulting GRN is generally sensitive to the choice of method-specific parameters. Even though the inferred GRN is optimal given the parameters, many links may be wrong or missing if the data is not informative. To make GRN inference reliable, a method is needed to estimate the support of each predicted link as the method parameters are varied. Results: To achieve this we have developed a method called nested bootstrapping, which applies a bootstrapping protocol to GRN inference, and by repeated bootstrap runs assesses the stability of the estimated support values. To translate bootstrap support values to false discovery rates we run the same pipeline with shuffled data as input. This provides a general method to control the false discovery rate of GRN inference that can be applied to any setting of inference parameters, noise level, or data properties. We evaluated nested bootstrapping on a simulated dataset spanning a range of such properties, using the LASSO, Least Squares, RNI, GENIE3 and CLR inference methods. An improved inference accuracy was observed in almost all situations. Nested bootstrapping was incorporated into the GeneSPIDER package, which was also used for generating the simulated networks and data, as well as running and analyzing the inferences. Availability: https://bitbucket.org/sonnhammergrni/genespider/src/NB/%2BMethods/NestBoot.m
Hsia, Feng-Chun; Tang, Dai-Ming; Jevasuwan, Wipakorn; Fukata, Naoki; Zhou, Xin; Mitome, Masanori; Bando, Yoshio; Nordling, Torbjörn E. M.; Golberg, Dmitri
In: Nanoscale Advances, vol. 1, no. 5, pp. 1784–1790, 2019, ISSN: 2516-0230.
Abstract | Links | BibTeX | Tags:
@article{Hsia2019,
title = {Realization and direct observation of five normal and parametric modes in silicon nanowire resonators by in situ transmission electron microscopy},
author = {Feng-Chun Hsia and Dai-Ming Tang and Wipakorn Jevasuwan and Naoki Fukata and Xin Zhou and Masanori Mitome and Yoshio Bando and Torbjörn E. M. Nordling and Dmitri Golberg},
url = {http://pubs.rsc.org/en/Content/ArticleLanding/2019/NA/C8NA00373D http://xlink.rsc.org/?DOI=C8NA00373D},
doi = {10.1039/C8NA00373D},
issn = {2516-0230},
year = {2019},
date = {2019-02-01},
journal = {Nanoscale Advances},
volume = {1},
number = {5},
pages = {1784–1790},
publisher = {RSC},
abstract = {Mechanical resonators have wide applications in sensing motions, chemical and bio-substances, and provide an accurate method to measure intrinsic elastic properties of the oscillating material. A high resonant order with high response frequency and a small resonator mass is critical for enhancing the sensibility and precision. Here, we report on the realization and direct observation of high-order and high-frequency silicon nanowire (Si NW) resonators. By using an oscillating electric- field inducing a mechanical resonance of the single-crystalline Si NWs inside a transmission electron microscope (TEM), we observed the resonance up to the 5th order, for both normal and parametric modes at $sim$100 MHz frequencies. The precision of the resonant frequency was enhanced from 3.14% at the 1st order to 0.25 % at the 5th order, correlating to the increase of energy dissipation. The elastic modulus of Si NWs was measured to be $sim$169 GPa in [110] direction, size scaling effects were found to be absent down to $sim$20 nm level.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mechanical resonators have wide applications in sensing motions, chemical and bio-substances, and provide an accurate method to measure intrinsic elastic properties of the oscillating material. A high resonant order with high response frequency and a small resonator mass is critical for enhancing the sensibility and precision. Here, we report on the realization and direct observation of high-order and high-frequency silicon nanowire (Si NW) resonators. By using an oscillating electric- field inducing a mechanical resonance of the single-crystalline Si NWs inside a transmission electron microscope (TEM), we observed the resonance up to the 5th order, for both normal and parametric modes at $sim$100 MHz frequencies. The precision of the resonant frequency was enhanced from 3.14% at the 1st order to 0.25 % at the 5th order, correlating to the increase of energy dissipation. The elastic modulus of Si NWs was measured to be $sim$169 GPa in [110] direction, size scaling effects were found to be absent down to $sim$20 nm level.
Bueren, Bart J A; Leenders, Mark A A M; Nordling, Torbjörn E M
Case Study: Taiwan's pathway into a circular future for buildings Journal Article
In: IOP Conference Series: Earth and Environmental Science, vol. 225, pp. 012060, 2019, ISSN: 1755-1315.
Abstract | Links | BibTeX | Tags: Circular buildings, Taiwan
@article{vanBueren2019,
title = {Case Study: Taiwan's pathway into a circular future for buildings},
author = {Bart J A Bueren and Mark A A M Leenders and Torbjörn E M Nordling},
url = {http://stacks.iop.org/1755-1315/225/i=1/a=012060?key=crossref.1fd4cbb2e2f7a49780cb4acf73093d80},
doi = {10.1088/1755-1315/225/1/012060},
issn = {1755-1315},
year = {2019},
date = {2019-02-01},
journal = {IOP Conference Series: Earth and Environmental Science},
volume = {225},
pages = {012060},
publisher = {IOP Publishing},
address = {Brussels, Belgium},
abstract = {The aim of this paper is to explore successful paths and potential obstacles for introducing circular buildings to a region new to the strategy of Circular Economy (CE). For this, the process of circular buildings development in Taiwan is analysed. In 2016, the government of Taiwan passed an act that put a focus on CE. Taiwan entered this field with nearly no prior experience. This paper analyses three cases: The Holland Pavilion for the World Flora Expo Taichung; the TaiSugar Circular Village Tainan; and the CE Social Housing Taipei. Interestingly, Taiwan choose the Netherlands as a country for guidance on best practices and the path to implementation. Our analysis focuses on barriers and opportunities found in the initiation, commissioning, and the ongoing development process of these projects. Data is collected through interviews with 30 stakeholders, from government, industries and academia who are involved in the projects. International collaboration is shown to have speeded up the CE building innovation process in Taiwan.},
howpublished = {SBE19 Brussels - BAMB-CIRCPATH "Buildings as Material Banks - A Pathway For A Circular Future" 5–7 February 2019, Brussels, Belgium},
keywords = {Circular buildings, Taiwan},
pubstate = {published},
tppubtype = {article}
}
The aim of this paper is to explore successful paths and potential obstacles for introducing circular buildings to a region new to the strategy of Circular Economy (CE). For this, the process of circular buildings development in Taiwan is analysed. In 2016, the government of Taiwan passed an act that put a focus on CE. Taiwan entered this field with nearly no prior experience. This paper analyses three cases: The Holland Pavilion for the World Flora Expo Taichung; the TaiSugar Circular Village Tainan; and the CE Social Housing Taipei. Interestingly, Taiwan choose the Netherlands as a country for guidance on best practices and the path to implementation. Our analysis focuses on barriers and opportunities found in the initiation, commissioning, and the ongoing development process of these projects. Data is collected through interviews with 30 stakeholders, from government, industries and academia who are involved in the projects. International collaboration is shown to have speeded up the CE building innovation process in Taiwan.
Morgan, Daniel; Studham, Matthew; Tjärnberg, Andreas; Weishaupt, Holger; Swartling, Fredrik J.; Nordling, Torbjörn E. M.; Sonnhammer, Erik L. L.
Perturbation-based gene regulatory network inference to unravel oncogenic mechanisms Journal Article
In: bioRxiv, 2019.
Abstract | Links | BibTeX | Tags:
@article{Morgan2019BioRxiv,
title = {Perturbation-based gene regulatory network inference to unravel oncogenic mechanisms},
author = {Daniel Morgan and Matthew Studham and Andreas Tjärnberg and Holger Weishaupt and Fredrik J. Swartling and Torbjörn E. M. Nordling and Erik L. L. Sonnhammer},
url = {https://www.biorxiv.org/content/early/2019/10/23/735514},
doi = {10.1101/735514},
year = {2019},
date = {2019-01-01},
journal = {bioRxiv},
publisher = {Cold Spring Harbor Laboratory},
abstract = {The gene regulatory network (GRN) of human cells encodes mechanisms to ensure proper functioning. However, if this GRN is dysregulated, the cell may enter into a disease state such as cancer. Understanding the GRN as a system can therefore help identify novel mechanisms underlying disease, which can lead to new therapies. Reliable inference of GRNs is however still a major challenge in systems biology.To deduce regulatory interactions relevant to cancer, we applied a recent computational inference framework to data from perturbation experiments in squamous carcinoma cell line A431. GRNs were inferred using several methods, and the false discovery rate was controlled by the NestBoot framework. We developed a novel approach to assess the predictiveness of inferred GRNs against validation data, despite the lack of a gold standard. The best GRN was significantly more predictive than the null model, both in crossvalidated benchmarks and for an independent dataset of the same genes under a different perturbation design. It agrees with many known links, in addition to predicting a large number of novel interactions from which a subset was experimentally validated. The inferred GRN captures regulatory interactions central to cancer-relevant processes and thus provides mechanistic insights that are useful for future cancer research.Data available at GSE125958 Inferred GRNs and inference statistics available at https://dcolin.shinyapps.io/CancerGRN/ Software available at https://bitbucket.org/sonnhammergrni/genespider/src/BFECV/Author Summary Cancer is the second most common cause of death globally, and although cancer treatments have improved in recent years, we need to understand how regulatory mechanisms are altered in cancer to combat the disease efficiently. By applying gene perturbations and inference of gene regulatory networks to 40 genes known or suspected to have a role in cancer due to interactions with the oncogene MYC, we deduce their underlying regulatory interactions. Using a recent computational framework for inference together with a novel method for cross validation, we infer a reliable regulatory model of this system in a completely data driven manner, not reliant on literature or priors. The novel interactions add to the understanding of the progressive oncogenic regulatory process and may provide new targets for therapy.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The gene regulatory network (GRN) of human cells encodes mechanisms to ensure proper functioning. However, if this GRN is dysregulated, the cell may enter into a disease state such as cancer. Understanding the GRN as a system can therefore help identify novel mechanisms underlying disease, which can lead to new therapies. Reliable inference of GRNs is however still a major challenge in systems biology.To deduce regulatory interactions relevant to cancer, we applied a recent computational inference framework to data from perturbation experiments in squamous carcinoma cell line A431. GRNs were inferred using several methods, and the false discovery rate was controlled by the NestBoot framework. We developed a novel approach to assess the predictiveness of inferred GRNs against validation data, despite the lack of a gold standard. The best GRN was significantly more predictive than the null model, both in crossvalidated benchmarks and for an independent dataset of the same genes under a different perturbation design. It agrees with many known links, in addition to predicting a large number of novel interactions from which a subset was experimentally validated. The inferred GRN captures regulatory interactions central to cancer-relevant processes and thus provides mechanistic insights that are useful for future cancer research.Data available at GSE125958 Inferred GRNs and inference statistics available at https://dcolin.shinyapps.io/CancerGRN/ Software available at https://bitbucket.org/sonnhammergrni/genespider/src/BFECV/Author Summary Cancer is the second most common cause of death globally, and although cancer treatments have improved in recent years, we need to understand how regulatory mechanisms are altered in cancer to combat the disease efficiently. By applying gene perturbations and inference of gene regulatory networks to 40 genes known or suspected to have a role in cancer due to interactions with the oncogene MYC, we deduce their underlying regulatory interactions. Using a recent computational framework for inference together with a novel method for cross validation, we infer a reliable regulatory model of this system in a completely data driven manner, not reliant on literature or priors. The novel interactions add to the understanding of the progressive oncogenic regulatory process and may provide new targets for therapy.
2018
Fourati, Slim; Talla, Aarthi; Mahmoudian, Mehrad; Burkhart, Joshua G; Klén, Riku; Henao, Ricardo; Yu, Thomas; Aydın, Zafer; Yeung, Ka Yee; Ahsen, Mehmet Eren; Almugbel, Reem; Jahandideh, Samad; Liang, Xiao; Nordling, Torbjörn E M; Shiga, Motoki; Stanescu, Ana; Vogel, Robert; Pandey, Gaurav; Chiu, Christopher; McClain, Micah T; Woods, Christopher W; Ginsburg, Geoffrey S; Elo, Laura L; Tsalik, Ephraim L; Mangravite, Lara M; Sieberts, Solveig K
A crowdsourced analysis to identify ab initio molecular signatures predictive of susceptibility to viral infection Journal Article
In: Nature Communications, vol. 9, no. 1, pp. 4418, 2018, ISSN: 2041-1723.
Abstract | Links | BibTeX | Tags:
@article{Fourati2018,
title = {A crowdsourced analysis to identify ab initio molecular signatures predictive of susceptibility to viral infection},
author = {Slim Fourati and Aarthi Talla and Mehrad Mahmoudian and Joshua G Burkhart and Riku Klén and Ricardo Henao and Thomas Yu and Zafer Aydın and Ka Yee Yeung and Mehmet Eren Ahsen and Reem Almugbel and Samad Jahandideh and Xiao Liang and Torbjörn E M Nordling and Motoki Shiga and Ana Stanescu and Robert Vogel and Gaurav Pandey and Christopher Chiu and Micah T McClain and Christopher W Woods and Geoffrey S Ginsburg and Laura L Elo and Ephraim L Tsalik and Lara M Mangravite and Solveig K Sieberts},
url = {http://biorxiv.org/content/early/2018/04/30/311696.abstract http://www.ncbi.nlm.nih.gov/pubmed/30356117 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC6200745 http://www.nature.com/articles/s41467-018-06735-8},
doi = {10.1038/s41467-018-06735-8},
issn = {2041-1723},
year = {2018},
date = {2018-12-01},
journal = {Nature Communications},
volume = {9},
number = {1},
pages = {4418},
abstract = {The response to respiratory viruses varies substantially between individuals, and there are currently no known molecular predictors from the early stages of infection. Here we conduct a community-based analysis to determine whether pre- or early post-exposure molecular factors could predict physiologic responses to viral exposure. Using peripheral blood gene expression profiles collected from healthy subjects prior to exposure to one of four respiratory viruses (H1N1, H3N2, Rhinovirus, and RSV), as well as up to 24 h following exposure, we find that it is possible to construct models predictive of symptomatic response using profiles even prior to viral exposure. Analysis of predictive gene features reveal little overlap among models; however, in aggregate, these genes are enriched for common pathways. Heme metabolism, the most significantly enriched pathway, is associated with a higher risk of developing symptoms following viral exposure. This study demonstrates that pre-exposure molecular predictors can be identified and improves our understanding of the mechanisms of response to respiratory viruses.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The response to respiratory viruses varies substantially between individuals, and there are currently no known molecular predictors from the early stages of infection. Here we conduct a community-based analysis to determine whether pre- or early post-exposure molecular factors could predict physiologic responses to viral exposure. Using peripheral blood gene expression profiles collected from healthy subjects prior to exposure to one of four respiratory viruses (H1N1, H3N2, Rhinovirus, and RSV), as well as up to 24 h following exposure, we find that it is possible to construct models predictive of symptomatic response using profiles even prior to viral exposure. Analysis of predictive gene features reveal little overlap among models; however, in aggregate, these genes are enriched for common pathways. Heme metabolism, the most significantly enriched pathway, is associated with a higher risk of developing symptoms following viral exposure. This study demonstrates that pre-exposure molecular predictors can be identified and improves our understanding of the mechanisms of response to respiratory viruses.
Celano, Umberto; Hsia, Feng-Chun; Vanhaeren, Danielle; Paredis, Kristof; Nordling, Torbjörn E. M.; Buijnsters, Josephus G.; Hantschel, Thomas; Vandervorst, Wilfried
Mesoscopic physical removal of material using sliding nano-diamond contacts Journal Article
In: Scientific Reports, vol. 8, no. 1, pp. 2994, 2018, ISSN: 2045-2322.
Abstract | Links | BibTeX | Tags: Humanities and Social Sciences, multidisciplinary, Science
@article{Celano2018,
title = {Mesoscopic physical removal of material using sliding nano-diamond contacts},
author = {Umberto Celano and Feng-Chun Hsia and Danielle Vanhaeren and Kristof Paredis and Torbjörn E. M. Nordling and Josephus G. Buijnsters and Thomas Hantschel and Wilfried Vandervorst},
url = {http://www.nature.com/articles/s41598-018-21171-w},
doi = {10.1038/s41598-018-21171-w},
issn = {2045-2322},
year = {2018},
date = {2018-12-01},
journal = {Scientific Reports},
volume = {8},
number = {1},
pages = {2994},
publisher = {Nature Publishing Group},
abstract = {Wear mechanisms including fracture and plastic deformation at the nanoscale are central to understand sliding contacts. Recently, the combination of tip-induced material erosion with the sensing capability of secondary imaging modes of AFM, has enabled a slice-and-view tomographic technique named AFM tomography or Scalpel SPM. However, the elusive laws governing nanoscale wear and the large quantity of atoms involved in the tip-sample contact, require a dedicated mesoscale description to understand and model the tip-induced material removal. Here, we study nanosized sliding contacts made of diamond in the regime whereby thousands of nm3 are removed. We explore the fundamentals of high-pressure tip-induced material removal for various materials. Changes in the load force are systematically combined with AFM and SEM to increase the understanding and the process controllability. The nonlinear variation of the removal rate with the load force is interpreted as a combination of two contact regimes each dominating in a particular force range. By using the gradual transition between the two regimes, (1) the experimental rate of material eroded on each tip passage is modeled, (2) a controllable removal rate below 5 nm/scan for all the materials is demonstrated, thus opening to future development of 3D tomographic AFM.},
keywords = {Humanities and Social Sciences, multidisciplinary, Science},
pubstate = {published},
tppubtype = {article}
}
Wear mechanisms including fracture and plastic deformation at the nanoscale are central to understand sliding contacts. Recently, the combination of tip-induced material erosion with the sensing capability of secondary imaging modes of AFM, has enabled a slice-and-view tomographic technique named AFM tomography or Scalpel SPM. However, the elusive laws governing nanoscale wear and the large quantity of atoms involved in the tip-sample contact, require a dedicated mesoscale description to understand and model the tip-induced material removal. Here, we study nanosized sliding contacts made of diamond in the regime whereby thousands of nm3 are removed. We explore the fundamentals of high-pressure tip-induced material removal for various materials. Changes in the load force are systematically combined with AFM and SEM to increase the understanding and the process controllability. The nonlinear variation of the removal rate with the load force is interpreted as a combination of two contact regimes each dominating in a particular force range. By using the gradual transition between the two regimes, (1) the experimental rate of material eroded on each tip passage is modeled, (2) a controllable removal rate below 5 nm/scan for all the materials is demonstrated, thus opening to future development of 3D tomographic AFM.
Liou, Yi-Fan; Tsai, Po-Jung; Huang, Zi-Yu; Chiou, Po-Chin; Chu, Hsiao-Wei; Ciou, Li-Ping; Nordling, Torbjörn E. M.
FFANEprot: Predicting Protein Functions using a Weight-sharing Multitask Neural Network Optimized by a Firefly Algorithm with Natural Enemy Strategy Proceedings Article
In: 17th International Conference on Bioinformatics (INCoB-2018), Asia Pacific Bioinformatics Network (APBioNet), New Delhi, India, 2018.
Abstract | Links | BibTeX | Tags: Convolutional neural network, deep learning, Evolutionary algorithm, Firefly algorithm, Inhibitory neurons, Natural enemy strategy
@inproceedings{Liou2018,
title = {FFANEprot: Predicting Protein Functions using a Weight-sharing Multitask Neural Network Optimized by a Firefly Algorithm with Natural Enemy Strategy},
author = {Yi-Fan Liou and Po-Jung Tsai and Zi-Yu Huang and Po-Chin Chiou and Hsiao-Wei Chu and Li-Ping Ciou and Torbjörn E. M. Nordling},
url = {http://www.incob2018.org/},
year = {2018},
date = {2018-09-01},
booktitle = {17th International Conference on Bioinformatics (INCoB-2018)},
publisher = {Asia Pacific Bioinformatics Network (APBioNet)},
address = {New Delhi, India},
abstract = {Background: The prediction of multiple functions of several proteins at once from the protein sequence alone is essential, but difficult. To solve this problem, we composed a dataset of 81,267 proteins and 1,169 Gene Ontology (GO) terms of the molecular function (MF) from the Swiss-Prot database, and used weight-sharing and multi-task learning to create FFANEprot. Results: The architecture of FFANEprot was optimised by a Firefly algorithm with a natural enemy strategy (FFANE), i.e. periodic reversals. The training and test Matthews correlation coefficients (accuracies) are 0.52 (98.84%) and 0.49 (98.67%), respectively. When analysing the trained networks, we found many completely inhibitory neurons, which typically have a small kernel size and occupy approximately 30% of the CNNs. Conclusion: FFANEprot can predict GO MF terms with high accuracy from sequence alone. Our FFANEnet source code is available at http://ffanenet.nordlinglab.org.},
keywords = {Convolutional neural network, deep learning, Evolutionary algorithm, Firefly algorithm, Inhibitory neurons, Natural enemy strategy},
pubstate = {published},
tppubtype = {inproceedings}
}
Background: The prediction of multiple functions of several proteins at once from the protein sequence alone is essential, but difficult. To solve this problem, we composed a dataset of 81,267 proteins and 1,169 Gene Ontology (GO) terms of the molecular function (MF) from the Swiss-Prot database, and used weight-sharing and multi-task learning to create FFANEprot. Results: The architecture of FFANEprot was optimised by a Firefly algorithm with a natural enemy strategy (FFANE), i.e. periodic reversals. The training and test Matthews correlation coefficients (accuracies) are 0.52 (98.84%) and 0.49 (98.67%), respectively. When analysing the trained networks, we found many completely inhibitory neurons, which typically have a small kernel size and occupy approximately 30% of the CNNs. Conclusion: FFANEprot can predict GO MF terms with high accuracy from sequence alone. Our FFANEnet source code is available at http://ffanenet.nordlinglab.org.
Wu, Yu-Heng; Yamanaka, Ryu; Hiroi, Noriko; Nordling, Torbjörn E M
Image Analysis for Cell Adaptation Against Environmental Stress Miscellaneous
CELLAB-SOCU Summer Symposium, 2018.
Abstract | Links | BibTeX | Tags: Cell segmentation, Microfluidic
@misc{Rain2018NorikoPoster,
title = {Image Analysis for Cell Adaptation Against Environmental Stress},
author = {Yu-Heng Wu and Ryu Yamanaka and Noriko Hiroi and Torbjörn E M Nordling},
editor = {Noriko Hiroi},
url = {http://pc4ls.rs.socu.ac.jp/cellab-socu_sympo.html},
year = {2018},
date = {2018-09-01},
booktitle = {CELLAB-SOCU Summer Symposium in Sanyo-Onoda, Japan},
publisher = {Sanyo-Onoda City University},
address = {Sanyo-Onoda},
abstract = {When the environment changed, each of the cells react differently. Only parts of the cells will adapt and survive. We aim to understand the hidden mechanism which causes these results and build the dynamical model to predict the phenotype.},
howpublished = {CELLAB-SOCU Summer Symposium},
keywords = {Cell segmentation, Microfluidic},
pubstate = {published},
tppubtype = {misc}
}
When the environment changed, each of the cells react differently. Only parts of the cells will adapt and survive. We aim to understand the hidden mechanism which causes these results and build the dynamical model to predict the phenotype.
Nordling, Torbjörn E. M.
From quantum uncertainty to reliable network inference with and without deep neural networks Miscellaneous
CELLAB-SOCU Summer Symposium, 2018.
Abstract | Links | BibTeX | Tags: Network Inference
@misc{Nordling2018Noriko,
title = {From quantum uncertainty to reliable network inference with and without deep neural networks},
author = {Torbjörn E. M. Nordling},
editor = {Noriko Hiroi},
url = {http://pc4ls.rs.socu.ac.jp/cellab-socu_sympo.html},
year = {2018},
date = {2018-09-01},
booktitle = {CELLAB-SOCU Summer Symposium in Sanyo-Onoda, Japan},
pages = {0},
publisher = {Sanyo-Onoda City University},
address = {Sanyo-Onoda},
abstract = {In this talk I will discuss when an interaction matter from a quantum mechanical to control theoretical perspective. I will also give an introduction to network inference and precent recent advances.},
howpublished = {CELLAB-SOCU Summer Symposium},
keywords = {Network Inference},
pubstate = {published},
tppubtype = {misc}
}
In this talk I will discuss when an interaction matter from a quantum mechanical to control theoretical perspective. I will also give an introduction to network inference and precent recent advances.
Hsu, Chi-Ching; Yu-Heng, Wu; Menolascina, Filippo; Nordling, Torbjörn E. M.
Modelling of the GAL1 Genetic Circuit in Yeast Using Three Equations Proceedings Article
In: Qin, Sizhao Joe; Bequette, B. Wayne; Biegler, Lorenz T.; Guay, Martin; Findeisen, Rolf; Wang, Jin; Zavala, Victor (Ed.): IFAC-PapersOnLine, 10th IFAC Symposium on Advanced Control of Chemical Processes ADCHEM 2018: Shenyang, China, 25–27 July 2018, pp. 185–190, International Federation of Automatic Control (IFAC), Shenyang, China, 2018, ISSN: 24058963.
Abstract | Links | BibTeX | Tags: genetic circuit, parameter estimation, synthetic biology, system identification, Systems Biology
@inproceedings{Hsu2018ADCHEM,
title = {Modelling of the GAL1 Genetic Circuit in Yeast Using Three Equations},
author = {Chi-Ching Hsu and Wu Yu-Heng and Filippo Menolascina and Torbjörn E. M. Nordling},
editor = {Sizhao Joe Qin and B. Wayne Bequette and Lorenz T. Biegler and Martin Guay and Rolf Findeisen and Jin Wang and Victor Zavala},
url = {https://linkinghub.elsevier.com/retrieve/pii/S2405896318319785},
doi = {10.1016/j.ifacol.2018.09.297},
issn = {24058963},
year = {2018},
date = {2018-07-01},
booktitle = {IFAC-PapersOnLine, 10th IFAC Symposium on Advanced Control of Chemical Processes ADCHEM 2018: Shenyang, China, 25–27 July 2018},
volume = {51},
number = {18},
pages = {185–190},
publisher = {International Federation of Automatic Control (IFAC)},
address = {Shenyang, China},
abstract = {Synthetic gene circuits can be used to modify and control existing biological processes and thus e.g. increase drug yields. Currently their use is hampered by the, largely, trial and error approach used to design them. Lack of reliable quantitative dynamical models of genetic circuits e.g. prevents the use of well established control design methods. We aim toward creation of a pipeline for automated closed-loop identification of dynamic models of synthetically engineered genetic circuits in microorganisms. As a step towards this aim, we here study modelling of the input-output behaviour of the yGIL337 strain of S. cerevisiae. In this strain expression of the fluorescent reporter can be turned on by growing the yeast in galactose and off by glucose. We perform parameter estimation on a system of three ordinary differential equations of Michaelis-Menten type based on in vivo data from a microfluidic experiment by Fiore et al. (2013) after redoing the data preprocessing. The parameter estimation is done using AMIGO2–a state of the art Matlab toolbox for iterative identification of dynamical models. We show that the goodness-of-fit of our model is comparable to the five models proposed by Fiore et al. and we hypothesise that the system is an adaptive feedback system.},
keywords = {genetic circuit, parameter estimation, synthetic biology, system identification, Systems Biology},
pubstate = {published},
tppubtype = {inproceedings}
}
Synthetic gene circuits can be used to modify and control existing biological processes and thus e.g. increase drug yields. Currently their use is hampered by the, largely, trial and error approach used to design them. Lack of reliable quantitative dynamical models of genetic circuits e.g. prevents the use of well established control design methods. We aim toward creation of a pipeline for automated closed-loop identification of dynamic models of synthetically engineered genetic circuits in microorganisms. As a step towards this aim, we here study modelling of the input-output behaviour of the yGIL337 strain of S. cerevisiae. In this strain expression of the fluorescent reporter can be turned on by growing the yeast in galactose and off by glucose. We perform parameter estimation on a system of three ordinary differential equations of Michaelis-Menten type based on in vivo data from a microfluidic experiment by Fiore et al. (2013) after redoing the data preprocessing. The parameter estimation is done using AMIGO2–a state of the art Matlab toolbox for iterative identification of dynamical models. We show that the goodness-of-fit of our model is comparable to the five models proposed by Fiore et al. and we hypothesise that the system is an adaptive feedback system.
Nordling, Torbjörn E. M.
Learning from data in machine and man Miscellaneous
MOST-NICT Joint Workshop on AI for ICT in Taipei (Taiwan), 2018.
@misc{Nordling2018NICT,
title = {Learning from data in machine and man},
author = {Torbjörn E. M. Nordling},
year = {2018},
date = {2018-06-01},
booktitle = {MOST-NICT Joint Workshop on AI for ICT in Taipei (Taiwan)},
publisher = {Ministry of Science and Technology in Taiwan},
address = {Taipei, Taiwan},
abstract = {Artificial intelligence (AI), in particular Deep learning, has since the ImageNet LSVRC-2012 contest established itself as a core technology driving the 3rd industrial revolution with many commercial applications. This rapid success of Artificial narrow intelligence (ANI) is due to four factors: big labelled data, GPU accelerated distributed computing, open source software, and algorithms. Training of artificial neural networks (ANNs) in general require thousands, if not millions, of examples, while humans can learn from a single example. Human like unsupervised learning has by Facebook's Yann LeCun been called the “holy grail” of AI research. In my lab, we are currently building smart toys to collect longitudinal data on how children learn with the aim of creating more data efficient training methods. While zero-shot and one-shot learning are powerful methods for particular problems, they do not in general improve data efficiency. We are also exploring the use of evolutionary algorithms to find a good ANN architecture for a specific problem, which I will exemplify through our recent work on prediction of multiple functions of several proteins at once from the protein sequence alone. To solve this problem, we composed a dataset of 81,267 proteins and 1,169 GO terms of molecular function from Swiss-Prot and used weight-sharing and multi-task learning to create FFANEprot. The architecture of the convolutional neural network (CNN) of FFANEprot was optimised by a Firefly algorithm with natural enemy strategy, which can reduce the probability of being trapped in local optima during the evolutionary process. The training and test accuracies are 98.84% and 98.67%, which is better than all the conventional CNN architectures investigated. If time allows, then I will also show some ongoing work on functional magnetic resonance imaging (fMRI) data.},
howpublished = {MOST-NICT Joint Workshop on AI for ICT in Taipei (Taiwan)},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Artificial intelligence (AI), in particular Deep learning, has since the ImageNet LSVRC-2012 contest established itself as a core technology driving the 3rd industrial revolution with many commercial applications. This rapid success of Artificial narrow intelligence (ANI) is due to four factors: big labelled data, GPU accelerated distributed computing, open source software, and algorithms. Training of artificial neural networks (ANNs) in general require thousands, if not millions, of examples, while humans can learn from a single example. Human like unsupervised learning has by Facebook's Yann LeCun been called the “holy grail” of AI research. In my lab, we are currently building smart toys to collect longitudinal data on how children learn with the aim of creating more data efficient training methods. While zero-shot and one-shot learning are powerful methods for particular problems, they do not in general improve data efficiency. We are also exploring the use of evolutionary algorithms to find a good ANN architecture for a specific problem, which I will exemplify through our recent work on prediction of multiple functions of several proteins at once from the protein sequence alone. To solve this problem, we composed a dataset of 81,267 proteins and 1,169 GO terms of molecular function from Swiss-Prot and used weight-sharing and multi-task learning to create FFANEprot. The architecture of the convolutional neural network (CNN) of FFANEprot was optimised by a Firefly algorithm with natural enemy strategy, which can reduce the probability of being trapped in local optima during the evolutionary process. The training and test accuracies are 98.84% and 98.67%, which is better than all the conventional CNN architectures investigated. If time allows, then I will also show some ongoing work on functional magnetic resonance imaging (fMRI) data.
Fourati, Slim; Talla, Aarthi; Mahmoudian, Mehrad; Burkhart, Joshua G.; Klén, Riku; Henao, Ricardo; Aydin, Zafer; Yeung, Ka Yee; Ahsen, Mehmet Eren; Almugbel, Reem; Jahandideh, Samad; Liang, Xiao; Nordling, Torbjörn E. M.; Shiga, Motoki; Stanescu, Ana; Vogel, Robert; Consortium, The Respiratory Viral DREAM Challenge; Pandey, Gaurav; Chiu, Christopher; McClain, Micah T.; Woods, Chris W.; Ginsburg, Geoffrey S.; Elo, Laura L.; Tsalik, Ephraim L.; Mangravite, Lara M.; Sieberts, Solveig K.
A crowdsourced analysis to identify ab initio molecular signatures predictive of susceptibility to viral infection Journal Article
In: bioRxiv, 2018.
Abstract | Links | BibTeX | Tags:
@article{Fourati2018BioRxiv,
title = {A crowdsourced analysis to identify ab initio molecular signatures predictive of susceptibility to viral infection},
author = {Slim Fourati and Aarthi Talla and Mehrad Mahmoudian and Joshua G. Burkhart and Riku Klén and Ricardo Henao and Zafer Aydin and Ka Yee Yeung and Mehmet Eren Ahsen and Reem Almugbel and Samad Jahandideh and Xiao Liang and Torbjörn E. M. Nordling and Motoki Shiga and Ana Stanescu and Robert Vogel and The Respiratory Viral DREAM Challenge Consortium and Gaurav Pandey and Christopher Chiu and Micah T. McClain and Chris W. Woods and Geoffrey S. Ginsburg and Laura L. Elo and Ephraim L. Tsalik and Lara M. Mangravite and Solveig K. Sieberts},
url = {https://www.biorxiv.org/content/early/2018/04/30/311696},
doi = {10.1101/311696},
year = {2018},
date = {2018-01-01},
journal = {bioRxiv},
publisher = {Cold Spring Harbor Laboratory},
abstract = {Respiratory viruses are highly infectious; however, the variation of individuals’ physiologic responses to viral exposure is poorly understood. Most studies examining molecular predictors of response focus on late stage predictors, typically near the time of peak symptoms. To determine whether pre- or early post-exposure factors could predict response, we conducted a community-based analysis to identify predictors of resilience or susceptibility to several respiratory viruses (H1N1, H3N2, Rhinovirus, and RSV) using peripheral blood gene expression profiles collected from healthy subjects prior to viral exposure, as well as up to 24 hours following exposure. This analysis revealed that it is possible to construct models predictive of symptoms using profiles even prior to viral exposure. Analysis of predictive gene features revealed little overlap among models; however, in aggregate, these genes were enriched for common pathways. Heme Metabolism, the most significantly enriched pathway, was associated with higher risk of developing symptoms following viral exposure.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Respiratory viruses are highly infectious; however, the variation of individuals’ physiologic responses to viral exposure is poorly understood. Most studies examining molecular predictors of response focus on late stage predictors, typically near the time of peak symptoms. To determine whether pre- or early post-exposure factors could predict response, we conducted a community-based analysis to identify predictors of resilience or susceptibility to several respiratory viruses (H1N1, H3N2, Rhinovirus, and RSV) using peripheral blood gene expression profiles collected from healthy subjects prior to viral exposure, as well as up to 24 hours following exposure. This analysis revealed that it is possible to construct models predictive of symptoms using profiles even prior to viral exposure. Analysis of predictive gene features revealed little overlap among models; however, in aggregate, these genes were enriched for common pathways. Heme Metabolism, the most significantly enriched pathway, was associated with higher risk of developing symptoms following viral exposure.
Wu, Wei-Sheng; Tu, Hao-Ping; Chu, Yu-Han; Nordling, Torbjörn E M; Tseng, Yan-Yuan; Liaw, Hung-Jiun
YHMI: a web tool to identify histone modifications and histone/chromatin regulators from a gene list in yeast Journal Article
In: Database, vol. 2018, 2018, ISSN: 1758-0463.
Abstract | Links | BibTeX | Tags:
@article{Wu2018YHMI,
title = {YHMI: a web tool to identify histone modifications and histone/chromatin regulators from a gene list in yeast},
author = {Wei-Sheng Wu and Hao-Ping Tu and Yu-Han Chu and Torbjörn E M Nordling and Yan-Yuan Tseng and Hung-Jiun Liaw},
url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6204766/ https://academic.oup.com/database/article/doi/10.1093/database/bay116/5145122},
doi = {10.1093/database/bay116},
issn = {1758-0463},
year = {2018},
date = {2018-01-01},
journal = {Database},
volume = {2018},
abstract = {Post-translational modifications of histones (e.g. acetylation, methylation, phosphorylation and ubiquitination) play crucial roles in regulating gene expression by altering chromatin structures and creating docking sites for histone/chromatin regulators. However, the combination patterns of histone modifications, regulatory proteins and their corresponding target genes remain incompletely understood. Therefore, it is advantageous to have a tool for the enrichment/depletion analysis of histone modifications and histone/chromatin regulators from a gene list. Many ChIP-chip/ChIP-seq datasets of histone modifications and histone/chromatin regulators in yeast can be found in the literature. Knowing the needs and having the data motivate us to develop a web tool, called Yeast Histone Modifications Identifier (YHMI), which can identify the enriched/depleted histone modifications and the enriched histone/chromatin regulators from a list of yeast genes. Both tables and figures are provided to visualize the identification results. Finally, the high-quality and biological insight of the identification results are demonstrated by two case studies. We believe that YHMI is a valuable tool for yeast biologists to do epigenetics research.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Post-translational modifications of histones (e.g. acetylation, methylation, phosphorylation and ubiquitination) play crucial roles in regulating gene expression by altering chromatin structures and creating docking sites for histone/chromatin regulators. However, the combination patterns of histone modifications, regulatory proteins and their corresponding target genes remain incompletely understood. Therefore, it is advantageous to have a tool for the enrichment/depletion analysis of histone modifications and histone/chromatin regulators from a gene list. Many ChIP-chip/ChIP-seq datasets of histone modifications and histone/chromatin regulators in yeast can be found in the literature. Knowing the needs and having the data motivate us to develop a web tool, called Yeast Histone Modifications Identifier (YHMI), which can identify the enriched/depleted histone modifications and the enriched histone/chromatin regulators from a list of yeast genes. Both tables and figures are provided to visualize the identification results. Finally, the high-quality and biological insight of the identification results are demonstrated by two case studies. We believe that YHMI is a valuable tool for yeast biologists to do epigenetics research.
Wu, Wei-Sheng; Jiang, Yu-Xuan; Chang, Jer-Wei; Chu, Yu-Han; Chiu, Yi-Hao; Tsao, Yi-Hong; Nordling, Torbjörn E M; Tseng, Yan-Yuan; Tseng, Joseph T
HRPDviewer: human ribosome profiling data viewer Journal Article
In: Database, vol. 2018, 2018, ISSN: 1758-0463.
Abstract | Links | BibTeX | Tags:
@article{Wu2018HRPDviewer,
title = {HRPDviewer: human ribosome profiling data viewer},
author = {Wei-Sheng Wu and Yu-Xuan Jiang and Jer-Wei Chang and Yu-Han Chu and Yi-Hao Chiu and Yi-Hong Tsao and Torbjörn E M Nordling and Yan-Yuan Tseng and Joseph T Tseng},
url = {https://academic.oup.com/database/article/doi/10.1093/database/bay074/5052387 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6041748/},
doi = {10.1093/database/bay074},
issn = {1758-0463},
year = {2018},
date = {2018-01-01},
journal = {Database},
volume = {2018},
abstract = {Translational regulation plays an important role in protein synthesis. Dysregulation of translation causes abnormal cell physiology and leads to diseases such as inflammatory disorders and cancers. An emerging technique, called ribosome profiling (ribo-seq), was developed to capture a snapshot of translation. It is based on deep sequencing of ribosome-protected mRNA fragments. A lot of ribo-seq data have been generated in various studies, so databases are needed for depositing and visualizing the published ribo-seq data. Nowadays, GWIPS-viz, RPFdb and TranslatomeDB are the three largest databases developed for this purpose. However, two challenges remain to be addressed. First, GWIPS-viz and RPFdb databases align the published ribo-seq data to the genome. Since ribo-seq data aim to reveal the actively translated mRNA transcripts, there are advantages of aligning ribo-req data to the transcriptome over the genome. Second, TranslatomeDB does not provide any visualization and the other two databases only pro- vide visualization of the ribo-seq data around a specific genomic location, while simulta- neous visualization of the ribo-seq data on multiple mRNA transcripts produced from the same gene or different genes is desired. To address these two challenges, we developed the Human Ribosome Profiling Data viewer (HRPDviewer). HRPDviewer (i) contains 610 published human ribo-seq datasets from Gene Expression Omnibus, (ii) aligns the ribo- seq data to the transcriptome and (iii) provides visualization of the ribo-seq data on the selected mRNA transcripts. Using HRPDviewer, researchers can compare the ribosome binding patterns of multiple mRNA transcripts from the same gene or different genes to gain an accurate understanding of protein synthesis in human cells. We believe that HRPDviewer is a useful resource for researchers to study translational regulation in human.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Translational regulation plays an important role in protein synthesis. Dysregulation of translation causes abnormal cell physiology and leads to diseases such as inflammatory disorders and cancers. An emerging technique, called ribosome profiling (ribo-seq), was developed to capture a snapshot of translation. It is based on deep sequencing of ribosome-protected mRNA fragments. A lot of ribo-seq data have been generated in various studies, so databases are needed for depositing and visualizing the published ribo-seq data. Nowadays, GWIPS-viz, RPFdb and TranslatomeDB are the three largest databases developed for this purpose. However, two challenges remain to be addressed. First, GWIPS-viz and RPFdb databases align the published ribo-seq data to the genome. Since ribo-seq data aim to reveal the actively translated mRNA transcripts, there are advantages of aligning ribo-req data to the transcriptome over the genome. Second, TranslatomeDB does not provide any visualization and the other two databases only pro- vide visualization of the ribo-seq data around a specific genomic location, while simulta- neous visualization of the ribo-seq data on multiple mRNA transcripts produced from the same gene or different genes is desired. To address these two challenges, we developed the Human Ribosome Profiling Data viewer (HRPDviewer). HRPDviewer (i) contains 610 published human ribo-seq datasets from Gene Expression Omnibus, (ii) aligns the ribo- seq data to the transcriptome and (iii) provides visualization of the ribo-seq data on the selected mRNA transcripts. Using HRPDviewer, researchers can compare the ribosome binding patterns of multiple mRNA transcripts from the same gene or different genes to gain an accurate understanding of protein synthesis in human cells. We believe that HRPDviewer is a useful resource for researchers to study translational regulation in human.
2017
Sieberts, Solveig; Henao, Ricardo; Fourati, Slim; Klén, Riku; Mahmoudian, Mehrad; Talla, Aarthi; Pandey, Gaurav; Nordling, Torbjörn; Ahsen, Mehmet; Almugbel, Reem; Aydın, Zafer; Burkhart, Joshua; Jahandideh, Samad; Liang, Xiao; Shiga, Motoki; Stanescu, Ana; Vogel, Robert; Yeung, Ka Yee; Yu, Thomas; Elo, Laura; Tsalik, Ephraim; Mangravite, Lara
Respiratory Viral DREAM Challenge: Discovering dynamic molecular signatures in response to viral exposure Proceedings Article
In: 10th Annual RECOMB/ISCB Conference on Regulatory and Systems Genomics, with DREAM Challenges, International Society for Computational Biology, New York City, New York, 2017.
Abstract | Links | BibTeX | Tags: DREAM challenge, Gene expression, Infection susceptibility, Predictive modeling, Respiratory infection, Viral infection
@inproceedings{Sieberts2017RECOMB,
title = {Respiratory Viral DREAM Challenge: Discovering dynamic molecular signatures in response to viral exposure},
author = {Solveig Sieberts and Ricardo Henao and Slim Fourati and Riku Klén and Mehrad Mahmoudian and Aarthi Talla and Gaurav Pandey and Torbjörn Nordling and Mehmet Ahsen and Reem Almugbel and Zafer Aydın and Joshua Burkhart and Samad Jahandideh and Xiao Liang and Motoki Shiga and Ana Stanescu and Robert Vogel and Ka Yee Yeung and Thomas Yu and Laura Elo and Ephraim Tsalik and Lara Mangravite},
url = {https://www.iscb.org/recomb-regsysgen2017},
year = {2017},
date = {2017-11-01},
booktitle = {10th Annual RECOMB/ISCB Conference on Regulatory and Systems Genomics, with DREAM Challenges},
publisher = {International Society for Computational Biology},
address = {New York City, New York},
abstract = {Acute respiratory infections (ARIs) are among the most common reasons for seeking medical attention in the United States. Prediction of susceptibility or early infection can have can have important impacts in terms of treatment decisions or in the prediction or control of pandemics. Following exposure to respiratory viruses, infection rates are variable among individuals, and some patients who exhibit viral shedding never develop clinical symptoms. We developed and ran a DREAM challenge to predict viral shedding and respiratory symptoms in patients exposed to one of four different respiratory viruses (H1N1, H3N2, rhinovirus, or respiratory syncytial virus (RSV)), based on pre- and early-stage post-exposure, longitudinally sampled blood gene expression profiling up to 24 hours post-e. The challenge attracted participation of 118 individuals organized into 36 teams, who were able to demonstrate signal to predict which subjects will become symptomatic following viral exposure, even prior to exposure. This challenge featured an active community phase featuring participant-lead projects exploring gene pathways that contribute to prediction, heterogeneity in prediction across samples, characteristics of well performing models, reproducibility of submitted code, and the assessment of model overfitting in the absence of an independent test data set.},
keywords = {DREAM challenge, Gene expression, Infection susceptibility, Predictive modeling, Respiratory infection, Viral infection},
pubstate = {published},
tppubtype = {inproceedings}
}
Acute respiratory infections (ARIs) are among the most common reasons for seeking medical attention in the United States. Prediction of susceptibility or early infection can have can have important impacts in terms of treatment decisions or in the prediction or control of pandemics. Following exposure to respiratory viruses, infection rates are variable among individuals, and some patients who exhibit viral shedding never develop clinical symptoms. We developed and ran a DREAM challenge to predict viral shedding and respiratory symptoms in patients exposed to one of four different respiratory viruses (H1N1, H3N2, rhinovirus, or respiratory syncytial virus (RSV)), based on pre- and early-stage post-exposure, longitudinally sampled blood gene expression profiling up to 24 hours post-e. The challenge attracted participation of 118 individuals organized into 36 teams, who were able to demonstrate signal to predict which subjects will become symptomatic following viral exposure, even prior to exposure. This challenge featured an active community phase featuring participant-lead projects exploring gene pathways that contribute to prediction, heterogeneity in prediction across samples, characteristics of well performing models, reproducibility of submitted code, and the assessment of model overfitting in the absence of an independent test data set.
Subscribe To Our Newsletter
Nordling Lab News will provide you with irregular updates on our research and topics of interest.