TY - UNPB
T1 - ReDisX: a Continuous Max Flow-based framework to redefine the diagnosis of diseases based on identified patterns of genomic signatures
AU - Yip, Hiu Fung
AU - Chowdhury, Debajyoti
AU - Wang, Kexin
AU - Liu, Yujie
AU - Gao, Yao
AU - Lan, Liang
AU - Zheng, Chaochao
AU - Guan, Daogang
AU - Lam, Kei Fong
AU - Zhu, Hailong
AU - Tai, Xuecheng
AU - Lu, Aiping
N1 - This study was funded by the General Research Fund from the Research Grants Council of Hong Kong (12201818), National Natural Science Foundation of China (31871315), Natural Science Foundation of Guangdong, China (2018A030310693), The 2020 Guangdong Provincial Science and Technology Innovation Strategy Special Fund (2020B1212030006) by Guangdong-Hong Kong-Macau Joint Lab on Chinese Medicine and Immune Disease Research. Part of this project is also supported by RG(R)-RC/17-18/02-MATH, HKBU12300819, NSF/RGC Grant N-HKBU214-19 and RC-FNRA-IG/19-20/SCI/01, The Natural Science Foundation Council of China (31501080, 32070676), Natural Science Foundation of Guangdong Province (2021A1515010737), Hong Kong Baptist University Strategic Development Fund (SDF13-1209-P01, SDF15-0324-P02(b), SDF19-0402-P02), Guangzhou Basic and Applied Basic Research Foundation (202102020550).
PY - 2022/4/11
Y1 - 2022/4/11
N2 - Diseases originate at the molecular-genetic layer, manifest through altered biochemical homeostasis, and develop symptoms later. Hence, symptomatic diagnosis is inadequate to explain the underlying molecular-genetic abnormality and individual genomic disparities. The current trends include molecular-genetic information relying on algorithms to recognize the disease subtypes through gene expressions. Despite their disposition toward disease-specific heterogeneity and cross-disease homogeneity, a gap still exists in describing the extent of homogeneity within the heterogeneous subpopulation of different diseases. They are limited to obtaining the holistic sense of the whole genome-based diagnosis resulting in inaccurate diagnosis and subsequent management. Addressing those ambiguities, our proposed framework, ReDisX, introduces a unique classification system for the patients based on their genomic signatures. In this study, it is a scalable machine learning algorithm deployed to re-categorize the patients with rheumatoid arthritis and coronary artery disease. It reveals heterogeneous subpopulations within a disease and homogenous subpopulations across different diseases. Besides, it identifies granzyme B (GZMB) as a subpopulation-differentiation marker that plausibly serves as a prominent indicator for GZMB-targeted drug repurposing. The ReDisX framework offers a novel strategy to redefine disease diagnosis through characterizing personalized genomic signatures. It may rejuvenate the landscape of precision and personalized diagnosis and a clue to drug repurposing.
AB - Diseases originate at the molecular-genetic layer, manifest through altered biochemical homeostasis, and develop symptoms later. Hence, symptomatic diagnosis is inadequate to explain the underlying molecular-genetic abnormality and individual genomic disparities. The current trends include molecular-genetic information relying on algorithms to recognize the disease subtypes through gene expressions. Despite their disposition toward disease-specific heterogeneity and cross-disease homogeneity, a gap still exists in describing the extent of homogeneity within the heterogeneous subpopulation of different diseases. They are limited to obtaining the holistic sense of the whole genome-based diagnosis resulting in inaccurate diagnosis and subsequent management. Addressing those ambiguities, our proposed framework, ReDisX, introduces a unique classification system for the patients based on their genomic signatures. In this study, it is a scalable machine learning algorithm deployed to re-categorize the patients with rheumatoid arthritis and coronary artery disease. It reveals heterogeneous subpopulations within a disease and homogenous subpopulations across different diseases. Besides, it identifies granzyme B (GZMB) as a subpopulation-differentiation marker that plausibly serves as a prominent indicator for GZMB-targeted drug repurposing. The ReDisX framework offers a novel strategy to redefine disease diagnosis through characterizing personalized genomic signatures. It may rejuvenate the landscape of precision and personalized diagnosis and a clue to drug repurposing.
U2 - 10.1101/2022.04.11.487592
DO - 10.1101/2022.04.11.487592
M3 - Preprint
BT - ReDisX: a Continuous Max Flow-based framework to redefine the diagnosis of diseases based on identified patterns of genomic signatures
PB - Cold Spring Harbor Laboratory Press
ER -