Dr. Deeksha Pandey’s research focuses on uncovering the molecular and evolutionary drivers of antibiotic resistance in microbial pathogens using advanced computational approaches. Her work integrates machine learning, pattern recognition, gene ontology, and molecular modeling to analyze large-scale -omics datasets, transforming complex biological data into actionable insights for diagnostics and therapeutic development. Her core interest lies in developing AI-driven models for the identification and early prediction of antimicrobial resistance (AMR) genes, with the broader aim of supporting clinical decision-making and reducing the spread of resistant pathogens. The tools she develops incorporate advanced algorithms including Support Vector Machines (SVMs), Hidden Markov Models (HMMs), Position-Specific Scoring Matrices (PSSM), molecular docking, and biological database integration, making them applicable to multi-omics research and translational applications. During her Ph.D., she developed several in-silico tools that support the study of AMR, including: β-LacFamPred – for classification of β-lactamase enzyme families, BacARscan – for analyzing the diversity of resistance genes in microbial genomes, BacEffluxPred – for predicting bacterial efflux pump proteins and their subfamilies. During her tenure at ICGEB, she also led projects designing deep learning models for predicting P-glycoprotein inhibitors and substrates, investigating AMR genes in ESKAPE pathogens, and developing computational pipelines for biomarker discovery and systems-level AMR modeling. Dr. Pandey remains committed to advancing research and education at the intersection of bioinformatics, AMR, and translational biology, contributing to global public health solutions.