Abstract

DRUG TARGET IDENTIFICATION BY USING ARTIFICIAL INTELLIGENCE

Dr. Y. Anil Kumar*, B. Kalyani, D. Arshiya, S. K. Sony Begum, T. Komali, Karan Dhungana, Laishram Jaichandra Singh

ABSTRACT

Artificial intelligence (AI) has now Became a revolutionary technology in contemporary medicine discovery, especially in target identification and confirmation. Natural products (NPs) have been a rich source of anticancer and remedial agents in the history, but deconvoluting their molecular targets is a daunting challenge. Recent developments in chemical proteomics, including marker- Based and marker-free ways, have Improved the identification of NP- protein relations, allowing Perception into their mechanisms of action. Marker- Based ways Became high particularity by chemical trailing, but they can disrupt NP structure or bioactivity. Marker-free technologies maintain molecular integrity but struggle with low- cornucopia or flash relations. The confluence of AI- Based analytics- including machine literacy (ML) and deep literacy (DL) — has immensely Improved the interpretability of advanced proteomic datasets and medicine- target commerce vaticination delicacy. These computer models like neural networks, support vectormachines, and arbitrary timbers have been effectively Became to Perception implicit remedial targets for both cancer and rare inherited conditions throughmulti-omics data integration (genetic, Expressionomic, protein mapping, and medically). Also, optimization algorithms likequasi-oppositional firefly optimization have enhanced AI performance in vaticination and model tuning tasks. Significantly, the AI- driven channel prioritizes ethical conformity, cross-disciplinary exploration, and iterative literacy toward ongoing refinement as new natural information come available. Combined, the union of chemical proteomics and AI is a potent paradigm for medicine target identification acceleration, remedial these confirmation, and substantiated drug advancement through data- driven discovery.

Keywords: Artificial intelligence; Machine literacy; Chemical proteomics; Natural products; Identification of medicine targets; Cancer; Rare conditions; Integration of multi-omics.