Computational Science Expert, India

Girinath
G. Pillai

PhD · Computational Drug Discovery

Pioneering the intersection of Agentic AI, machine learning, and structural biology to accelerate target identification and drug discovery focusing on undruggable targets. Based in India, building pipelines and tools trusted by researchers worldwide.

41+
Publications
921+
Citations
106
Repositories
Current Focus
Agentic AI Target Identification Molecular Glues Generative AI MD Simulation Longevity & Aging Virtual Screening QSAR / ML-SAR Cryptic Pockets BioAI

Areas of Expertise

Agentic AI Pipelines

Building autonomous AI agents for drug discovery workflows — from target identification to lead optimisation — leveraging LLMs, PyTorch, and TensorFlow for end-to-end automation.

Target Identification & Validation

Applying computational genomics, structural bioinformatics, and ML to identify and validate novel drug targets — including cryptic pockets, undruggable targets, and aging-related biology.

Structure-Based Drug Design

Expert in molecular docking, pharmacophore modelling, and gigascale virtual screening against vendor libraries (Enamine REAL, LCC) using cloud HPC infrastructure.

Molecular Dynamics Simulation

Deep expertise in NAMD, GROMACS, AMBER, and OpenMM. Open-source MD Notebooks repository with 42 stars used by researchers globally.

ML-Based SAR Modelling

Developing QSAR/QSPR models, cheminformatics pipelines, and ML-SAR workflows using KNIME and Jupyter. 1 US patent and extensive published models.

Longevity & Aging Research

One of India's first researchers to computationally study aging and longevity targets. Leading work on combinatorial therapies for age-linked dysfunctions and Indian population studies.


Scientific Journey

Dr. Girinath G. Pillai is an Expert Computational Chemist, where he drives computational drug discovery projects spanning giga-scale virtual screening, generative AI chemistry, Molecular Glues, PROTAC modelling, and SAR optimisation.

He completed his PhD jointly at the University of Florida (with Prof. Katritzky) and the University of Tartu, Estonia (with Prof. Karelson), and subsequently held a Marie Curie Research Fellowship at Molcode Ltd., Estonia.

A recognised researcher, educator and mentor, Dr. Pillai has delivered 2000+ training sessions globally, coordinates India's Drug Discovery Hackathon, and mentors through NITI Aayog's Atal Tinkering Labs. His open MD Jupyter Notebooks, Orange Workflows and KNIME resources are widely used by the global research community.

1 US Patent 41+ Papers Marie Curie Fellow Gov. of India's DDH2020 Coordinator Arctic Code Vault
Now

Lead Scientist — Sygnature Discovery, UK

Agentic AI, gigascale VS, PROTAC modelling, Generative AI chemistry

2020

Coordinator — Drug Discovery Hackathon, Govt. of India

National lead for computational drug discovery mentorship

2018

Chief Scientific Officer and Board of Directors — Zastra Innovations, Bengaluru

Drug discovery Software startup; ML-SAR and medicinal chemistry

2014

Marie Curie Research Fellow — Molcode Ltd., Estonia

EU FP7 programme; molecular modelling & QSAR

2013

Research Specialist — University of Tartu, Estonia

Prof. Mati Karelson's group; computational chemistry

2010

PhD Researcher — University of Florida, USA

Prof. Alan R. Katritzky's group; QSAR & medicinal chem


Tools & Technologies

AI / ML

PyTorch / TF
Agentic AI
Generative AI
QSAR / ML-SAR

Molecular Modelling

GROMACS / NAMD
AMBER / OpenMM
Glide / Docking
Modeller / VMD

Programming

Python
Jupyter
KNIME
Tcl / Shell

Bioinformatics

scRNA-seq
Target ID
Cheminformatics
HPC / Cloud

Featured Repositories

MDNotebooks ★ 42

Jupyter Notebooks for Molecular Dynamics — GROMACS, AMBER, NAMD, OpenMM and docking workflows in a single reproducible environment.

Tcl · Jupyter · Python
ModellerNotebooks ★ 9

Running Modeller for protein homology modelling using Python and Jupyter Notebooks. Beginner-friendly entry point to structural biology.

Jupyter Notebook · Python
QSAR ★ 6

QSAR/QSPR management tools and workflows for building quantitative structure-activity relationship models using ML pipelines.

Python · Jupyter
basics ★ 13

Getting started with Jupyter, Python, scientific libraries, GitHub and computational models — a guide for life science researchers.

Jupyter Notebook
agingdata ★ 3

Datasets and models for designing novel molecules targeting aging-related biological pathways — longevity enrichment and inhibition.

Data · Python
knime ★ 1

Free KNIME workflows for cheminformatics, drug discovery data analysis and machine learning pipelines, contributed to community.

KNIME Workflow

Selected Publications

Integrated Ligand and Structure-Based Approaches Towards Novel Janus Kinase 2 Inhibitors for Myeloproliferative Neoplasms

Computational Medicinal Chemistry · JAK2 · Target-Based Drug Discovery

Design, Synthesis, and Molecular Docking Studies of Curcumin Hybrid Conjugates as Potential Therapeutics for Breast Cancer

Medicinal Chemistry · Molecular Docking · Anticancer

Computational Design of Chemicals for the Control of Mosquitoes and Their Diseases

Book Chapter · QSAR · Pharmacophore Modelling · Vector-Borne Disease

DNA Gyrase and Topoisomerase IV Inhibitors: Computational Binding Site Prediction, Molecular Modelling, and Biological Evaluation

Antibacterial · Multidisciplinary · Molecular Modelling · Green Synthesis

Molecular Field Topology Analysis, Scaffold Hopping and Molecular Docking for Repellent Design Against Aedes aegypti

Virtual Screening · Glide · Insect Repellents · MFTA
View all on Google Scholar

Connect & Collaborate

GitHub
@giribio
LinkedIn
in/giribio
Drug Discovery Podcast
Spotify
Email
giribio@aol.in
YouTube Lectures
Tutorials & Talks · @giribio
X (Twitter)
Drug Discovery · CompChem · AI