Investigating Cellular Trajectories in the Severity of COVID-19 and Their Transcriptional Programs Using Machine Learning Approaches
Single-cell RNA sequencing of the bronchoalveolar lavage fluid (BALF) samples from COVID-19 patients has enabled us to examine gene expression changes of human tissue in response to the SARS-CoV-2 virus infection. However, the underlying mechanisms of COVID-19 pathogenesis at single-cell resolution,...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Genes |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4425/12/5/635 |
_version_ | 1797536533733965824 |
---|---|
author | Hyun-Hwan Jeong Johnathan Jia Yulin Dai Lukas M. Simon Zhongming Zhao |
author_facet | Hyun-Hwan Jeong Johnathan Jia Yulin Dai Lukas M. Simon Zhongming Zhao |
author_sort | Hyun-Hwan Jeong |
collection | DOAJ |
description | Single-cell RNA sequencing of the bronchoalveolar lavage fluid (BALF) samples from COVID-19 patients has enabled us to examine gene expression changes of human tissue in response to the SARS-CoV-2 virus infection. However, the underlying mechanisms of COVID-19 pathogenesis at single-cell resolution, its transcriptional drivers, and dynamics require further investigation. In this study, we applied machine learning algorithms to infer the trajectories of cellular changes and identify their transcriptional programs. Our study generated cellular trajectories that show the COVID-19 pathogenesis of healthy-to-moderate and healthy-to-severe on macrophages and T cells, and we observed more diverse trajectories in macrophages compared to T cells. Furthermore, our deep-learning algorithm DrivAER identified several pathways (e.g., xenobiotic pathway and complement pathway) and transcription factors (e.g., MITF and GATA3) that could be potential drivers of the transcriptomic changes for COVID-19 pathogenesis and the markers of the COVID-19 severity. Moreover, macrophages-related functions corresponded more to the disease severity compared to T cells-related functions. Our findings more proficiently dissected the transcriptomic changes leading to the severity of a COVID-19 infection. |
first_indexed | 2024-03-10T12:01:07Z |
format | Article |
id | doaj.art-a33b713bba50424bb6294275a2562267 |
institution | Directory Open Access Journal |
issn | 2073-4425 |
language | English |
last_indexed | 2024-03-10T12:01:07Z |
publishDate | 2021-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Genes |
spelling | doaj.art-a33b713bba50424bb6294275a25622672023-11-21T16:57:16ZengMDPI AGGenes2073-44252021-04-0112563510.3390/genes12050635Investigating Cellular Trajectories in the Severity of COVID-19 and Their Transcriptional Programs Using Machine Learning ApproachesHyun-Hwan Jeong0Johnathan Jia1Yulin Dai2Lukas M. Simon3Zhongming Zhao4Center for Precision Health, School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USACenter for Precision Health, School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USACenter for Precision Health, School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USACenter for Precision Health, School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USACenter for Precision Health, School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USASingle-cell RNA sequencing of the bronchoalveolar lavage fluid (BALF) samples from COVID-19 patients has enabled us to examine gene expression changes of human tissue in response to the SARS-CoV-2 virus infection. However, the underlying mechanisms of COVID-19 pathogenesis at single-cell resolution, its transcriptional drivers, and dynamics require further investigation. In this study, we applied machine learning algorithms to infer the trajectories of cellular changes and identify their transcriptional programs. Our study generated cellular trajectories that show the COVID-19 pathogenesis of healthy-to-moderate and healthy-to-severe on macrophages and T cells, and we observed more diverse trajectories in macrophages compared to T cells. Furthermore, our deep-learning algorithm DrivAER identified several pathways (e.g., xenobiotic pathway and complement pathway) and transcription factors (e.g., MITF and GATA3) that could be potential drivers of the transcriptomic changes for COVID-19 pathogenesis and the markers of the COVID-19 severity. Moreover, macrophages-related functions corresponded more to the disease severity compared to T cells-related functions. Our findings more proficiently dissected the transcriptomic changes leading to the severity of a COVID-19 infection.https://www.mdpi.com/2073-4425/12/5/635COVID-19bronchoalveolar lavage fluidsingle cell RNA-seqtrajectory inferencemachine learningdeep learning |
spellingShingle | Hyun-Hwan Jeong Johnathan Jia Yulin Dai Lukas M. Simon Zhongming Zhao Investigating Cellular Trajectories in the Severity of COVID-19 and Their Transcriptional Programs Using Machine Learning Approaches Genes COVID-19 bronchoalveolar lavage fluid single cell RNA-seq trajectory inference machine learning deep learning |
title | Investigating Cellular Trajectories in the Severity of COVID-19 and Their Transcriptional Programs Using Machine Learning Approaches |
title_full | Investigating Cellular Trajectories in the Severity of COVID-19 and Their Transcriptional Programs Using Machine Learning Approaches |
title_fullStr | Investigating Cellular Trajectories in the Severity of COVID-19 and Their Transcriptional Programs Using Machine Learning Approaches |
title_full_unstemmed | Investigating Cellular Trajectories in the Severity of COVID-19 and Their Transcriptional Programs Using Machine Learning Approaches |
title_short | Investigating Cellular Trajectories in the Severity of COVID-19 and Their Transcriptional Programs Using Machine Learning Approaches |
title_sort | investigating cellular trajectories in the severity of covid 19 and their transcriptional programs using machine learning approaches |
topic | COVID-19 bronchoalveolar lavage fluid single cell RNA-seq trajectory inference machine learning deep learning |
url | https://www.mdpi.com/2073-4425/12/5/635 |
work_keys_str_mv | AT hyunhwanjeong investigatingcellulartrajectoriesintheseverityofcovid19andtheirtranscriptionalprogramsusingmachinelearningapproaches AT johnathanjia investigatingcellulartrajectoriesintheseverityofcovid19andtheirtranscriptionalprogramsusingmachinelearningapproaches AT yulindai investigatingcellulartrajectoriesintheseverityofcovid19andtheirtranscriptionalprogramsusingmachinelearningapproaches AT lukasmsimon investigatingcellulartrajectoriesintheseverityofcovid19andtheirtranscriptionalprogramsusingmachinelearningapproaches AT zhongmingzhao investigatingcellulartrajectoriesintheseverityofcovid19andtheirtranscriptionalprogramsusingmachinelearningapproaches |