01
Agentic AI Scientists
Autonomous LLM agents that reason across chemical space, orchestrate docking and MD pipelines, and design molecules with minimal human steering - the lab partner of the next decade.
Agentic AI · Foundation Models · Longevity
The next decade of drug discovery will be written by autonomous agents.
From 2026 to 2036, the Giri Pillai Lab is building agentic AI co-scientists, biology foundation models, and GPU-native chemistry that collapse the path from target to clinic - with longevity, rare disease, and global health at the centre.
"Great challenge in science is how to best incorporate the existing knowledge."
Giri Pillai Lab · Science for Society
10yr
Vision horizon 2026–2036
41
Peer-reviewed papers
15+
Years in discovery
2k+
Talks & training sessions
2026 - 2036 · A decade of agentic science
The technology shaping the next ten years
Three converging frontiers - autonomous AI agents, biology foundation models, and GPU/quantum-native chemistry - rewriting how medicines are discovered.
02
Foundation Models for Biology
Protein, molecule, and cell-state foundation models (AlphaFold-class, ESM, Boltz) fused with mechanistic ML to map disease biology and longevity targets at unprecedented scale.
03
Quantum & GPU-Native Chemistry
Diffusion-based generative chemistry, GPU-accelerated MD, and early quantum-assisted free-energy methods - compressing lead optimisation from years to weeks by 2030.
The 10-year roadmap
Milestones we're building toward - from today's agentic prototypes to autonomous, clinic-ready discovery by 2036.
- 2036Goal - autonomous discovery loops delivering clinic-ready candidates
- 2030Foundation-model-native SAR & longevity pipelines in routine use
- 2026Agentic AI co-scientists deployed across active discovery programmes
- NowLead Scientist, Sygnature Discovery - UK
AI Expertise Explorer
Explore projects by topic
Filter the lab's active work — from agentic co-scientists to diffusion chemistry, longevity, and GPU-native simulation. Click a topic or search the stack.
Active2026
Autonomous SAR Co-Scientist
LangGraph-orchestrated LLM agent that proposes analogues, runs docking + ADMET tools, critiques its own hypotheses, and returns ranked design rounds with audit trails.
LangGraphGPT-class LLMsRDKitSchrödinger
Active2026
AlphaFold 3 / Boltz Target Triage
Foundation-model pipeline for complex prediction across protein–ligand–nucleic systems, feeding structure-aware ML scoring into early-stage lead identification.
AlphaFold 3BoltzChai-1PyTorch
Prototype2027
Diffusion-Native De Novo Design
Equivariant diffusion and flow-matching generators with built-in synthetic-accessibility filters — pushing de novo chemistry from curiosity to production tool.
Diffusion modelsEquivariant NNRDKitJAX
Active2028
Longevity Target Atlas
ESM-3 + cell-state foundation models mapped against hallmarks-of-ageing targets, with senolytic and partial-reprogramming triage informed by AI biomarker discovery.
ESM-3Hugging FaceAgeing clocksPython
Active2027
GPU-Native Free Energy Engine
OpenMM + MACE / NequIP neural-network potentials compressing physics-grade free-energy calculations from weeks to hours on commodity GPUs.
OpenMMMACENequIPCUDA
Vision2030
Quantum-Assisted Lead Optimisation
Early integration of quantum-assisted free-energy methods with classical MD to push accuracy boundaries on tough congeneric series.
Quantum kernelsHybrid QM/MMJAX
PublishedNow
SARS-CoV-2 & Tyrosinase Open Datasets
Curated, reproducible SAR & docking datasets released with KNIME / Jupyter notebooks so the community can rebuild every model end-to-end.
KNIMEJupyterMLflowHugging Face
PublishedNow
Insect Attractant / Repellent SAR
ML-driven SAR modelling for vector-borne disease control — combining classical descriptors with modern molecular representation learning.
RDKitPyTorchscikit-learn
Vision2030
Agentic Longevity Trial Designer
Agentic system reading longitudinal ageing biomarkers and literature to propose mechanism-anchored intervention arms for healthspan studies.
LLM agentsLangGraphAgeing biomarkers
Showing 9 of 9 projects · Horizons reflect the 2026–2036 lab roadmap.
Live AI demo · Powered by Lovable AI
Ask Giri AI
An agentic assistant grounded in Dr. Pillai's research areas — agentic AI, foundation models for biology, generative chemistry, and longevity. A live demonstration of the same tooling driving the lab's 2026–2036 vision.
Try a question
Responses are generated by a language model grounded on Dr. Pillai's public research areas — not a substitute for peer-reviewed sources.