Deep learning and natural products for mitigating drug-induced liver injury in HCV, PFIC, PBC, liver fibrosis, neoplasia, and atherosclerosis

The liver plays a major role in maintaining homeostasis of the body by taking part actively in various physiological processes including a breakdown of xenobiotic compounds and thus is also a major site of tissue injury. Natural products isolated from different plants in India have been used for decades for therapeutic use with minimal side effects. The current study aimed to examine the tissue-specific interaction of multiple drugs used for treatment against liver diseases such as Hepatitis C (HCV), Primary Biliary Cholangitis (PBC), Progressive Familial Intrahepatic Cholestasis (PFIC), Liver fibrosis, Neoplasia of liver and Atherosclerosis using structural bioinformatics techniques with deep learning library. Also, based on interaction with the liver, natural products were proposed as potential therapeutic agents against each disease with the goal of minimizing liver toxicity. All the genes and proteins involved in the pathogenesis of the disease are identified and drugs used for treatment. Tissue-specific interaction of commercially available drugs was predicted using the deep learning library DeepPurpose and docking studies were done for these drugs and compared with proposed natural products. This study predicts that all synthetic drugs used in the treatment of their respective diseases have a higher binding score to other proteins found in the liver compared to the target proteins and are associated with major liver side effects. These drugs are ribavirin and sofosbuvir for HCV infection, odevixibat for PFIC, ursodiol for PBC, and inclisiran for atherosclerosis. Biomarker identification of liver fibrosis and atherosclerosis obtained through the Gene Expression Omnibus (GEO) database. Phytochemicals were identified from various plants in India with minimal interaction with the liver based on tissue-specific interactions. Overall, our study found that commercially available drugs being used in the treatment of many diseases are associated with major side effects, hepatic side effects being one area. Therefore, designing drugs based on tissue-specific interaction can help prevent these adverse effects.

Authors

Institutions

Publication Details

Journal
Discover Applied Sciences
Published
2025-05-05
DOI
https://doi.org/10.1007/s42452-025-06741-8
Citations
1
Primary Topic
Computational Drug Discovery Methods
Type
article
Field-Weighted Citation Impact
1.50
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Deep learning and natural products for mitigating drug-induced liver injury in HCV, PFIC, PBC, liver fibrosis, neoplasia, and atherosclerosis

S. Sharma, Jayaprakash Chinnappan
1 citations
Discover Applied Sciences
Computational Drug Discovery Methods
1.50
article

Deep learning and natural products for mitigating drug-induced liver injury in HCV, PFIC, PBC, liver fibrosis, neoplasia, and atherosclerosis

S. Sharma, Jayaprakash Chinnappan
article en
1 citations

Abstract

The liver plays a major role in maintaining homeostasis of the body by taking part actively in various physiological processes including a breakdown of xenobiotic compounds and thus is also a major site of tissue injury. Natural products isolated from different plants in India have been used for decades for therapeutic use with minimal side effects. The current study aimed to examine the tissue-specific interaction of multiple drugs used for treatment against liver diseases such as Hepatitis C (HCV), Primary Biliary Cholangitis (PBC), Progressive Familial Intrahepatic Cholestasis (PFIC), Liver fibrosis, Neoplasia of liver and Atherosclerosis using structural bioinformatics techniques with deep learning library. Also, based on interaction with the liver, natural products were proposed as potential therapeutic agents against each disease with the goal of minimizing liver toxicity. All the genes and proteins involved in the pathogenesis of the disease are identified and drugs used for treatment. Tissue-specific interaction of commercially available drugs was predicted using the deep learning library DeepPurpose and docking studies were done for these drugs and compared with proposed natural products. This study predicts that all synthetic drugs used in the treatment of their respective diseases have a higher binding score to other proteins found in the liver compared to the target proteins and are associated with major liver side effects. These drugs are ribavirin and sofosbuvir for HCV infection, odevixibat for PFIC, ursodiol for PBC, and inclisiran for atherosclerosis. Biomarker identification of liver fibrosis and atherosclerosis obtained through the Gene Expression Omnibus (GEO) database. Phytochemicals were identified from various plants in India with minimal interaction with the liver based on tissue-specific interactions. Overall, our study found that commercially available drugs being used in the treatment of many diseases are associated with major side effects, hepatic side effects being one area. Therefore, designing drugs based on tissue-specific interaction can help prevent these adverse effects.

Discover Applied SciencesVol. 7(5)
Bharathiar University (IN)
Good health and well-being
Openalex Percentile: Top 17%
Computational Drug Discovery Methods
1.50
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.