Charactering hescs organoids from electrical signals with machine learning

Musaddaqul Hasib, Zane Lybrand, Vanesa Nieto Estevez, Jenny Hsieh, Yufei Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Three-dimensional brain organoids offer an unprecedented opportunity to study human brain development and disease. Characterizing context-specific organoid behaviors from local field potential (LFP) signals presents many machine learning challenges yet to be adequately addressed. We present in this paper classical machine learning and deep learning solutions to identify the LFP signatures unique to CHD2-mutant hESCs organoids and characterize their changes over time. We showed that a support vector machine (SVM) approach selected five frequency band-power features for 6 and 9-month-old organoids and achieved respective 99.3% and 88.1% area under the curve (AUC) performances in differentiating CHD2-mutant organoids from control using top five band-power features. We also proposed a convolutional neural network (CNN) that successfully classified both month 6 and month 9 CHD2 mutant organoids from controlled organoids using raw LFP signals with AUCs of with 99.6% and 99.7% respectively. We also reconstructed the discriminate features learned by CNN and showed their similarity and uniqueness compared with features selected by SVM.

Original languageEnglish (US)
Title of host publication2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728108483
DOIs
StatePublished - May 2019
Externally publishedYes
Event2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Chicago, United States
Duration: May 19 2019May 22 2019

Publication series

Name2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings

Conference

Conference2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019
CountryUnited States
CityChicago
Period5/19/195/22/19

Fingerprint

Organoids
Support vector machines
Learning systems
Brain
Neural networks
Frequency bands
Area Under Curve
Brain Diseases
Human Development
Machine Learning
Machine learning
Learning
Support vector machine
Deep learning

Keywords

  • CHD2 gene
  • CNN
  • HESCs Organoid
  • Local field potential
  • Multi electrode array
  • SVM Deep Learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Signal Processing
  • Information Systems and Management
  • Biomedical Engineering
  • Health Informatics
  • Radiology Nuclear Medicine and imaging

Cite this

Hasib, M., Lybrand, Z., Estevez, V. N., Hsieh, J., & Huang, Y. (2019). Charactering hescs organoids from electrical signals with machine learning. In 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings [8834587] (2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BHI.2019.8834587

Charactering hescs organoids from electrical signals with machine learning. / Hasib, Musaddaqul; Lybrand, Zane; Estevez, Vanesa Nieto; Hsieh, Jenny; Huang, Yufei.

2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8834587 (2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hasib, M, Lybrand, Z, Estevez, VN, Hsieh, J & Huang, Y 2019, Charactering hescs organoids from electrical signals with machine learning. in 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings., 8834587, 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019, Chicago, United States, 5/19/19. https://doi.org/10.1109/BHI.2019.8834587
Hasib M, Lybrand Z, Estevez VN, Hsieh J, Huang Y. Charactering hescs organoids from electrical signals with machine learning. In 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8834587. (2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings). https://doi.org/10.1109/BHI.2019.8834587
Hasib, Musaddaqul ; Lybrand, Zane ; Estevez, Vanesa Nieto ; Hsieh, Jenny ; Huang, Yufei. / Charactering hescs organoids from electrical signals with machine learning. 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings).
@inproceedings{d84d01e453b04889a8fced6444c39483,
title = "Charactering hescs organoids from electrical signals with machine learning",
abstract = "Three-dimensional brain organoids offer an unprecedented opportunity to study human brain development and disease. Characterizing context-specific organoid behaviors from local field potential (LFP) signals presents many machine learning challenges yet to be adequately addressed. We present in this paper classical machine learning and deep learning solutions to identify the LFP signatures unique to CHD2-mutant hESCs organoids and characterize their changes over time. We showed that a support vector machine (SVM) approach selected five frequency band-power features for 6 and 9-month-old organoids and achieved respective 99.3{\%} and 88.1{\%} area under the curve (AUC) performances in differentiating CHD2-mutant organoids from control using top five band-power features. We also proposed a convolutional neural network (CNN) that successfully classified both month 6 and month 9 CHD2 mutant organoids from controlled organoids using raw LFP signals with AUCs of with 99.6{\%} and 99.7{\%} respectively. We also reconstructed the discriminate features learned by CNN and showed their similarity and uniqueness compared with features selected by SVM.",
keywords = "CHD2 gene, CNN, HESCs Organoid, Local field potential, Multi electrode array, SVM Deep Learning",
author = "Musaddaqul Hasib and Zane Lybrand and Estevez, {Vanesa Nieto} and Jenny Hsieh and Yufei Huang",
year = "2019",
month = "5",
doi = "10.1109/BHI.2019.8834587",
language = "English (US)",
series = "2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings",

}

TY - GEN

T1 - Charactering hescs organoids from electrical signals with machine learning

AU - Hasib, Musaddaqul

AU - Lybrand, Zane

AU - Estevez, Vanesa Nieto

AU - Hsieh, Jenny

AU - Huang, Yufei

PY - 2019/5

Y1 - 2019/5

N2 - Three-dimensional brain organoids offer an unprecedented opportunity to study human brain development and disease. Characterizing context-specific organoid behaviors from local field potential (LFP) signals presents many machine learning challenges yet to be adequately addressed. We present in this paper classical machine learning and deep learning solutions to identify the LFP signatures unique to CHD2-mutant hESCs organoids and characterize their changes over time. We showed that a support vector machine (SVM) approach selected five frequency band-power features for 6 and 9-month-old organoids and achieved respective 99.3% and 88.1% area under the curve (AUC) performances in differentiating CHD2-mutant organoids from control using top five band-power features. We also proposed a convolutional neural network (CNN) that successfully classified both month 6 and month 9 CHD2 mutant organoids from controlled organoids using raw LFP signals with AUCs of with 99.6% and 99.7% respectively. We also reconstructed the discriminate features learned by CNN and showed their similarity and uniqueness compared with features selected by SVM.

AB - Three-dimensional brain organoids offer an unprecedented opportunity to study human brain development and disease. Characterizing context-specific organoid behaviors from local field potential (LFP) signals presents many machine learning challenges yet to be adequately addressed. We present in this paper classical machine learning and deep learning solutions to identify the LFP signatures unique to CHD2-mutant hESCs organoids and characterize their changes over time. We showed that a support vector machine (SVM) approach selected five frequency band-power features for 6 and 9-month-old organoids and achieved respective 99.3% and 88.1% area under the curve (AUC) performances in differentiating CHD2-mutant organoids from control using top five band-power features. We also proposed a convolutional neural network (CNN) that successfully classified both month 6 and month 9 CHD2 mutant organoids from controlled organoids using raw LFP signals with AUCs of with 99.6% and 99.7% respectively. We also reconstructed the discriminate features learned by CNN and showed their similarity and uniqueness compared with features selected by SVM.

KW - CHD2 gene

KW - CNN

KW - HESCs Organoid

KW - Local field potential

KW - Multi electrode array

KW - SVM Deep Learning

UR - http://www.scopus.com/inward/record.url?scp=85073008460&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073008460&partnerID=8YFLogxK

U2 - 10.1109/BHI.2019.8834587

DO - 10.1109/BHI.2019.8834587

M3 - Conference contribution

AN - SCOPUS:85073008460

T3 - 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings

BT - 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -