Ph.D. in Computational Biology | AI/ML/MD Specialist | Drug Discovery Expert
I am a computational biologist specializing in the integration of artificial intelligence, machine learning, and molecular dynamics (AI/ML/MD) for advanced drug discovery and protein-ligand interaction studies. My expertise spans from fundamental computational chemistry to cutting-edge deep learning applications in structural biology and pharmaceutical research.
My research portfolio includes the development of three major computational platforms: MetaDOCK, MLDoV, and DbNSP, which have significantly advanced the field of computer-aided drug design (CADD). These platforms integrate state-of-the-art molecular docking algorithms with machine learning validation techniques, achieving over 90% accuracy in binding pose prediction.
Currently engaged in post-doctoral research focusing on advanced AI/ML/DL methodologies for drug discovery, protein design, and molecular property prediction. My work bridges computational chemistry with modern artificial intelligence, contributing to the development of next-generation therapeutic compounds and understanding complex biological systems through computational approaches.
Research Focus: Deep learning architectures for protein folding prediction, transformer models for molecular property prediction, generative AI for novel drug design, and advanced molecular dynamics simulations with machine learning-enhanced sampling techniques.
Key Projects: Development of AI-driven platforms for CADD, implementation of graph neural networks for molecular property prediction, and integration of large language models for chemical space exploration.
Supervisor: Dr. Saikat Chakrabarti
Thesis: "Meta-docking approach for protein-ligand complexes and validation using machine learning techniques"
Research Contributions: Developed novel computational frameworks integrating multiple docking algorithms with ML validation, published in high-impact journals, and created open-access research platforms.
Specialization: Biochemistry and Molecular Biology
Academic Excellence: Graduated with first class honors, focusing on structural biology and computational approaches to biological systems.
Foundation: Strong background in biological sciences with emphasis on cellular and molecular biology, providing the fundamental knowledge for advanced computational biology research.
A revolutionary combinatorial molecular docking platform integrating AutoDock4.2, LeDock, and rDOCK algorithms. Features a sophisticated web application with RESTful API, comprehensive database backend, and advanced visualization tools. Achieved >90% accuracy in binding pose prediction through ensemble docking methodologies.
🔗 Explore PlatformAn advanced machine learning pipeline for molecular docking validation utilizing state-of-the-art algorithms including SVM, Random Forest, and XGBoost. Incorporates automated data processing, feature engineering, and cross-validation techniques for robust binding prediction and drug-target interaction analysis.
📋 Patent PendingComprehensive database and analysis platform for viral protein structures and interactions. Built with modern web technologies (PHP, MySQL, Python) featuring automated data pipelines, advanced search capabilities, and interactive visualization tools for COVID-19 and other viral research.
🔗 Access DatabasePost-doctoral project implementing deep learning architectures for molecular property prediction and drug design. Integrates transformer models, graph neural networks, and generative AI for novel compound discovery and optimization. Focus on developing interpretable AI models for pharmaceutical applications.
🚀 In Development
Training Impact: Successfully trained and mentored over 300 M.Sc. and Ph.D. students in computational drug design, molecular modeling, and bioinformatics methodologies.
Conference Presentations: Presented research findings at major national and international conferences including Society of Biological Chemist (India), contributing to the advancement of computational biology research.
Research Leadership: Led interdisciplinary research teams for the development of three major computational platforms, fostering collaboration between computational and experimental biologists.