AI-biology convergence gains momentum at India AI summit

At the India AI Impact Summit 2026, a session titled “AI Meets Biology to Power the Future of Biomanufacturing” explored how artificial intelligence is reshaping research, therapeutics and sustainable industrial production. The discussion brought together Dr Anand Deshpande (Persistent Systems), Dr Anurag Agrawal (Ashoka University), Dr Aravind Penmatsa (IISc Bengaluru), Dr Ashish M Gaikwad (Praj Industries), Dr Debasisa Mohanty (BRIC-NII), Dr Lipi Thukral (IGIB), Dr Madhura Vipra (Medvolt), Dr Manju Tanwar (Organic Recycling Systems), Dr Rajesh S. Gokhale (DBT, DG BRIC and Chairman BIRAC), and Prof. Santanu Chaudhury (School of Advanced Computing, Ashoka University).

  BioAI as a National Strategy

The session positioned BioAI as a strategic priority under the BioE3 policy, led by the Department of Biotechnology (DBT) and the Biotechnology Industry Research Assistance Council (BIRAC), with infrastructure support through collaboration with the IndiaAI Mission.

Speakers emphasised that BioAI is not limited to laboratory research but represents an ecosystem effort, linking academia, start-ups and industry. The rapid scaling of vaccine development during the COVID-19 period was cited as evidence of what coordinated biomanufacturing can achieve when supported by policy and infrastructure.

From Biological Complexity to AI-Enabled Design

Panellists highlighted the inherent complexity of biological systems, which operate across multiple scales, from molecules and proteins to cells, organisms and ecosystems. Traditional experimental approaches often struggle to interpret such layered systems at speed.

AI, they argued, now enables researchers to model, design and interpret biological interventions in iterative “design–build–test–learn” loops. Rather than replacing laboratory experiments, computational tools can narrow down viable candidates, reducing time and cost before wet-lab validation begins.

The discussion also addressed the shift from narrow machine learning models to generative systems capable of optimising multiple parameters simultaneously. In areas such as enzyme engineering and antibody design, models must account for efficacy, toxicity, immunogenicity and manufacturability at the same time. However, speakers cautioned that generative models require continuous experimental feedback to avoid inaccurate outputs and ensure reliability.

Genomics and Data Infrastructure

A recurring theme was the importance of high-quality biological data. Participants referred to ongoing national genomics efforts and the availability of thousands of sequenced healthy genomes through dedicated data platforms, with plans to scale significantly in the coming years.

Such datasets are expected to support precision medicine, therapeutic development and population-level disease modelling. However, speakers stressed that in biology, curated and metadata-rich datasets are more valuable than simply large volumes of data. Human oversight in dataset design and validation remains essential.

Two Tracks: Therapeutics and Sustainable Biofactories

The conversation focused on two principal application areas.

The first is next-generation therapeutics, where AI tools are being used to accelerate molecule discovery, improve prediction accuracy and shorten development timelines. Computational modelling in silico can refine candidates before laboratory validation, improving efficiency across the pipeline.

The second is sustainable biomanufacturing. With increasing pressure to reduce reliance on petrochemical inputs, AI-assisted strain engineering and process optimisation are being applied to develop bio-based chemicals, biodegradable materials and carbon capture solutions. India’s agricultural biodiversity was cited as a potential advantage in building such bio-based industrial systems.

Compute, Simulation and the Next Frontier

Beyond structure prediction, the panel discussed the emerging need for AI systems capable of biological reasoning,simulating binding interactions, molecular dynamics and complex cellular behaviour. Achieving this will require substantial computational resources and integration with first-principles science.

Automation, including robotic experimentation and closed-loop optimisation systems, is expanding. Yet speakers agreed that human expertise remains central, particularly in curating datasets, defining experimental questions and interpreting results.

Building Interdisciplinary Talent

The session concluded with a focus on skills and institutional reform. Delivering BioAI at scale will require breaking down silos between biology, chemistry, computing and engineering. Training programmes must prepare researchers to operate across computational modelling, laboratory science and industrial production constraints.

Overall, the panel framed BioAI as a capability shift rather than a niche research trend. With coordinated policy support, robust data infrastructure and interdisciplinary collaboration, AI could compress discovery cycles and expand India’s role in therapeutics and sustainable materials. However, progress will depend on rigorous validation, governance and alignment across the broader ecosystem.