A two-step approach-machine learning, variational autoencoder, and weighted gene co-expression network analysis identify key signature genes and pathways implicated in active visceral leishmaniasis

Author:

Verma Ram Nayan1ORCID,Subbarao Naidu1,Singh Gajendra Pratap1

Affiliation:

1. School of Computational and Integrative Sciences, Jawaharlal Nehru University, New Delhi-110067.

Abstract

Abstract Leishmania donovani, a kinetoplastid parasite causing leishmaniasis, is an opportunistic parasitic pathogen that affects immunocompromised individuals and is a common cause of Kala-azar. Specific parasite molecules can be delivered into host epithelial cells and may act as effector molecules for intracellular parasite development. So, there is a need to develop new approaches to understanding the interaction between the host and the pathogen. In our study, we built a weighted gene co-expression network using differentially expressed genes obtained through analysis of leishmaniasis-infected patients. Our goal was to identify key signature genes and pathways associated with visceral leishmaniasis infection by network biology analysis which can identify the most influential genes in the gene co-expression interaction network. We identified five prominent genes, IFNG, SC5D, LSM1, CMC2, and SAR1B, with higher interamodular connectivity, as the key signature genes. A deep neural network model- variational autoencoder was utilized to create new features, and a support vector machine validated the key signature genes. These key signature genes are involved in various biological processes like cytokine-cytokine receptor interaction, TGF-beta signaling pathway, antigen processing and presentation, IL-17 signaling pathway, Th1 and Th2 cell differentiation, and T-cell receptor signaling pathway. Besides, we also identified 04 significant miRNAs targeted with key signature genes, including hsa-miR-340-5p, hsa-miR-325-3p, hsa-miR-182-5p, hsa-miR-1271-5p/hsa-miR-96-5p. Further, analysis of the differentially expressed genes revealed that many critical cellular responses were triggered by visceral leishmaniasis infection, including immune responses and inflammatory and cell apoptosis. We get FDA-approved anti-inflammatory agents Emapalumab and Methylprednisolone as a re-proposed drug for leishmaniasis cure. Our study can enhance the understanding of the molecular pathogenesis of visceral leishmaniasis infection and have implications for the plan and execution of mRNA expression tools to support early diagnostics and treatment of visceral leishmaniasis infection.

Funder

Department of Science and Technology, Ministry of Science and Technology, India

Publisher

Research Square Platform LLC

Reference39 articles.

1. WHO: Leishmaniasis Fact Sheet - Google Scholar https://www.who.int/news-room/fact-sheets/detail/leishmaniasis

2. Drug Resistance in Leishmaniasis;Croft SL;Clinical Microbiology Reviews,2006

3. Drug target inference through pathway analysis of genomics data;Ma H;Advanced Drug Delivery Reviews,2013

4. Metabolomics in Drug Target Discovery;Rabinowitz JD;Cold Spring Harbor Symposia on Quantitative Biology,2011

5. Targeting protein–protein interactions for therapeutic intervention: A challenge for the future;Zinzalla G;Future Medicinal Chemistry,2009

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3