Research Progress of Artificial Intelligence Deep Learning Technology in the Field of Network Pharmacology

Lu Sijie and Sreemoy Kanti Das

Seminars in Medical Writing and Education, 2025, vol. 4, 457

Abstract: Rheumatoid arthritis (RA), a complex autoimmune disease, results in chronic inflammation and progressive joint degradation. While resveratrol has shown considerable therapeutic potential due to its anti-inflammatory properties, the precise molecular mechanisms underlying its effects in RA remain unknown. To improve the identification and validation of resveratrol's therapeutic targets in RA, a deep learning (DL)-enhanced approach is proposed, building on current research that combines bioinformatics, network pharmacology (NP), and artificial intelligence (AI). The method integrates RA patients' transcriptome data with PharmMapper-based medication target identification and DL powered protein structure modeling using AlphaFold. To increase prediction accuracy, a Deep Neural Network (DNN) model is used, trained on known drug-target interactions and gene expression data. This enables more precise identification of potential therapeutic genes (PT-genes), such as PIK3CA, AKT1, MAPK1, JUN, PTGS2, CXCL8, and CCL2, which are associated with RA-related pathways such as chemokine signaling, PI3K-Akt, and MAPK. These targets are verified through the analysis of protein interactions, the use of AutoDock Vina to run simulations to determine how well they fit with particular molecules, the Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) analysis to investigate gene functions, and the use of Cytoscape's Molecular Complex Detection (MCODE) tool to identify significant genes that express themselves differently. When compared to existing techniques, the suggested model has higher sensitivity and specificity in predicting important therapeutic genes. The framework finds new hub targets with high resveratrol binding affinity, implicating them in RA pathways. This hybrid computational process improves the accuracy and scalability of therapeutic mechanism discovery and helps the development of tailored RA therapies.

Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:dbk:medicw:v:4:y:2025:i::p:457:id:457

DOI: 10.56294/mw2025457

Access Statistics for this article

More articles in Seminars in Medical Writing and Education from AG Editor (Argentina)
Bibliographic data for series maintained by Javier Gonzalez-Argote ().