Machine-learning-based integrative –‘omics analyses reveal immunologic and metabolic dysregulation in environmental enteric dysfunction

Fatima Zulqarnain; Xueheng Zhao; Kenneth D.R. Setchell; Yash Sharma; Phillip Fernandes; Sanjana Srivastava; Aman Shrivastava; Lubaina Ehsan; Varun Jain; Shyam Raghavan; Christopher Moskaluk; Yael Haberman; Lee A. Denson; Khyati Mehta; Najeeha T. Iqbal; Najeeb Rahman; Kamran Sadiq; Zubair Ahmad; Romana Idress; Junaid Iqbal; Sheraz Ahmed; Aneeta Hotwani; Fayyaz Umrani; Beatrice Amadi; Paul Kelly; Donald E. Brown; Sean R. Moore; Syed Asad Ali; Sana Syed

doi:10.1016/j.isci.2024.110013

Machine-learning-based integrative –‘omics analyses reveal immunologic and metabolic dysregulation in environmental enteric dysfunction

Fatima Zulqarnain, Xueheng Zhao, Kenneth D.R. Setchell, Yash Sharma, Phillip Fernandes, Sanjana Srivastava, Aman Shrivastava, Lubaina Ehsan, Varun Jain, Shyam Raghavan, Christopher Moskaluk, Yael Haberman, Lee A. Denson, Khyati Mehta, Najeeha T. Iqbal, Najeeb Rahman, Kamran Sadiq, Zubair Ahmad, Romana Idress, Junaid IqbalSheraz Ahmed, Aneeta Hotwani, Fayyaz Umrani, Beatrice Amadi, Paul Kelly, Donald E. Brown, Sean R. Moore, Syed Asad Ali, Sana Syed^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Environmental enteric dysfunction (EED) is a subclinical enteropathy challenging to diagnose due to an overlap of tissue features with other inflammatory enteropathies. EED subjects (n = 52) from Pakistan, controls (n = 25), and a validation EED cohort (n = 30) from Zambia were used to develop a machine-learning-based image analysis classification model. We extracted histologic feature representations from the Pakistan EED model and correlated them to transcriptomics and clinical biomarkers. In-silico metabolic network modeling was used to characterize alterations in metabolic flux between EED and controls and validated using untargeted lipidomics. Genes encoding beta-ureidopropionase, CYP4F3, and epoxide hydrolase 1 correlated to numerous tissue feature representations. Fatty acid and glycerophospholipid metabolism-related reactions showed altered flux. Increased phosphatidylcholine, lysophosphatidylcholine (LPC), and ether-linked LPCs, and decreased ester-linked LPCs were observed in the duodenal lipidome of Pakistan EED subjects, while plasma levels of glycine-conjugated bile acids were significantly increased. Together, these findings elucidate a multi-omic signature of EED.

Original language	English
Article number	110013
Journal	iScience
Volume	27
Issue number	6
DOIs	https://doi.org/10.1016/j.isci.2024.110013
State	Published - 21 Jun 2024
Externally published	Yes

Funding

Funders	Funder number
National Institutes of Health
Fogarty International Center
National Institute of Diabetes and Digestive and Kidney Diseases	K23DK117061, D43TW007585, R01DK139491, R01DK132369, F31DK131885
National Institute of Diabetes and Digestive and Kidney Diseases

Keywords

Gastroenterology
Lipidomics
Machine learning
Medical imaging
Metabolic flux analysis
Transcriptomics

Access to Document

10.1016/j.isci.2024.110013

Cite this

Zulqarnain, F., Zhao, X., Setchell, K. D. R., Sharma, Y., Fernandes, P., Srivastava, S., Shrivastava, A., Ehsan, L., Jain, V., Raghavan, S., Moskaluk, C., Haberman, Y., Denson, L. A., Mehta, K., Iqbal, N. T., Rahman, N., Sadiq, K., Ahmad, Z., Idress, R., ... Syed, S. (2024). Machine-learning-based integrative –‘omics analyses reveal immunologic and metabolic dysregulation in environmental enteric dysfunction. iScience, 27(6), Article 110013. https://doi.org/10.1016/j.isci.2024.110013

@article{c28889d5ba064254b6799a45c1bb8579,

title = "Machine-learning-based integrative –{\textquoteleft}omics analyses reveal immunologic and metabolic dysregulation in environmental enteric dysfunction",

abstract = "Environmental enteric dysfunction (EED) is a subclinical enteropathy challenging to diagnose due to an overlap of tissue features with other inflammatory enteropathies. EED subjects (n = 52) from Pakistan, controls (n = 25), and a validation EED cohort (n = 30) from Zambia were used to develop a machine-learning-based image analysis classification model. We extracted histologic feature representations from the Pakistan EED model and correlated them to transcriptomics and clinical biomarkers. In-silico metabolic network modeling was used to characterize alterations in metabolic flux between EED and controls and validated using untargeted lipidomics. Genes encoding beta-ureidopropionase, CYP4F3, and epoxide hydrolase 1 correlated to numerous tissue feature representations. Fatty acid and glycerophospholipid metabolism-related reactions showed altered flux. Increased phosphatidylcholine, lysophosphatidylcholine (LPC), and ether-linked LPCs, and decreased ester-linked LPCs were observed in the duodenal lipidome of Pakistan EED subjects, while plasma levels of glycine-conjugated bile acids were significantly increased. Together, these findings elucidate a multi-omic signature of EED.",

keywords = "Gastroenterology, Lipidomics, Machine learning, Medical imaging, Metabolic flux analysis, Transcriptomics",

author = "Fatima Zulqarnain and Xueheng Zhao and Setchell, {Kenneth D.R.} and Yash Sharma and Phillip Fernandes and Sanjana Srivastava and Aman Shrivastava and Lubaina Ehsan and Varun Jain and Shyam Raghavan and Christopher Moskaluk and Yael Haberman and Denson, {Lee A.} and Khyati Mehta and Iqbal, {Najeeha T.} and Najeeb Rahman and Kamran Sadiq and Zubair Ahmad and Romana Idress and Junaid Iqbal and Sheraz Ahmed and Aneeta Hotwani and Fayyaz Umrani and Beatrice Amadi and Paul Kelly and Brown, {Donald E.} and Moore, {Sean R.} and Ali, {Syed Asad} and Sana Syed",

note = "Publisher Copyright: {\textcopyright} 2024 The Authors",

year = "2024",

month = jun,

day = "21",

doi = "10.1016/j.isci.2024.110013",

language = "אנגלית",

volume = "27",

journal = "iScience",

issn = "2589-0042",

publisher = "Elsevier Inc.",

number = "6",

}

Zulqarnain, F, Zhao, X, Setchell, KDR, Sharma, Y, Fernandes, P, Srivastava, S, Shrivastava, A, Ehsan, L, Jain, V, Raghavan, S, Moskaluk, C, Haberman, Y, Denson, LA, Mehta, K, Iqbal, NT, Rahman, N, Sadiq, K, Ahmad, Z, Idress, R, Iqbal, J, Ahmed, S, Hotwani, A, Umrani, F, Amadi, B, Kelly, P, Brown, DE, Moore, SR, Ali, SA & Syed, S 2024, 'Machine-learning-based integrative –‘omics analyses reveal immunologic and metabolic dysregulation in environmental enteric dysfunction', iScience, vol. 27, no. 6, 110013. https://doi.org/10.1016/j.isci.2024.110013

TY - JOUR

T1 - Machine-learning-based integrative –‘omics analyses reveal immunologic and metabolic dysregulation in environmental enteric dysfunction

AU - Zulqarnain, Fatima

AU - Zhao, Xueheng

AU - Setchell, Kenneth D.R.

AU - Sharma, Yash

AU - Fernandes, Phillip

AU - Srivastava, Sanjana

AU - Shrivastava, Aman

AU - Ehsan, Lubaina

AU - Jain, Varun

AU - Raghavan, Shyam

AU - Moskaluk, Christopher

AU - Haberman, Yael

AU - Denson, Lee A.

AU - Mehta, Khyati

AU - Iqbal, Najeeha T.

AU - Rahman, Najeeb

AU - Sadiq, Kamran

AU - Ahmad, Zubair

AU - Idress, Romana

AU - Iqbal, Junaid

AU - Ahmed, Sheraz

AU - Hotwani, Aneeta

AU - Umrani, Fayyaz

AU - Amadi, Beatrice

AU - Kelly, Paul

AU - Brown, Donald E.

AU - Moore, Sean R.

AU - Ali, Syed Asad

AU - Syed, Sana

PY - 2024/6/21

Y1 - 2024/6/21

N2 - Environmental enteric dysfunction (EED) is a subclinical enteropathy challenging to diagnose due to an overlap of tissue features with other inflammatory enteropathies. EED subjects (n = 52) from Pakistan, controls (n = 25), and a validation EED cohort (n = 30) from Zambia were used to develop a machine-learning-based image analysis classification model. We extracted histologic feature representations from the Pakistan EED model and correlated them to transcriptomics and clinical biomarkers. In-silico metabolic network modeling was used to characterize alterations in metabolic flux between EED and controls and validated using untargeted lipidomics. Genes encoding beta-ureidopropionase, CYP4F3, and epoxide hydrolase 1 correlated to numerous tissue feature representations. Fatty acid and glycerophospholipid metabolism-related reactions showed altered flux. Increased phosphatidylcholine, lysophosphatidylcholine (LPC), and ether-linked LPCs, and decreased ester-linked LPCs were observed in the duodenal lipidome of Pakistan EED subjects, while plasma levels of glycine-conjugated bile acids were significantly increased. Together, these findings elucidate a multi-omic signature of EED.

AB - Environmental enteric dysfunction (EED) is a subclinical enteropathy challenging to diagnose due to an overlap of tissue features with other inflammatory enteropathies. EED subjects (n = 52) from Pakistan, controls (n = 25), and a validation EED cohort (n = 30) from Zambia were used to develop a machine-learning-based image analysis classification model. We extracted histologic feature representations from the Pakistan EED model and correlated them to transcriptomics and clinical biomarkers. In-silico metabolic network modeling was used to characterize alterations in metabolic flux between EED and controls and validated using untargeted lipidomics. Genes encoding beta-ureidopropionase, CYP4F3, and epoxide hydrolase 1 correlated to numerous tissue feature representations. Fatty acid and glycerophospholipid metabolism-related reactions showed altered flux. Increased phosphatidylcholine, lysophosphatidylcholine (LPC), and ether-linked LPCs, and decreased ester-linked LPCs were observed in the duodenal lipidome of Pakistan EED subjects, while plasma levels of glycine-conjugated bile acids were significantly increased. Together, these findings elucidate a multi-omic signature of EED.

KW - Gastroenterology

KW - Lipidomics

KW - Machine learning

KW - Medical imaging

KW - Metabolic flux analysis

KW - Transcriptomics

UR - http://www.scopus.com/inward/record.url?scp=85194395912&partnerID=8YFLogxK

U2 - 10.1016/j.isci.2024.110013

DO - 10.1016/j.isci.2024.110013

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

C2 - 38868190

AN - SCOPUS:85194395912

SN - 2589-0042

VL - 27

JO - iScience

JF - iScience

IS - 6

M1 - 110013

ER -

Machine-learning-based integrative –‘omics analyses reveal immunologic and metabolic dysregulation in environmental enteric dysfunction

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this