India is making a significant bet on artificial intelligence to transform genomics research and precision medicine, launching a coordinated national effort that combines AI with DNA sequencing, computational biology, and healthcare innovation. The Government of India has substantially expanded AI-enabled biotechnology research across genomics, healthcare, bioinformatics, computational biology, and biomanufacturing, according to Dr. Jitendra Singh, Union Minister of State (Independent Charge), Science and Technology.

Dr. Jitendra Singh, Union Minister of State (Independent Charge), Science and Technology

The initiatives align with NITI Aayog's "AI for All" strategy and aim to promote inclusive economic growth through AI-driven scientific research and innovation. This coordinated approach represents a shift toward building national infrastructure for genomic research rather than isolated projects, with multiple government agencies, universities, and research institutions working together on shared goals.

What Has India Actually Accomplished in Genomics So Far?

India's GenomeIndia project has achieved several major milestones that demonstrate the scale of the effort. The project has completed sequencing 10,174 Indian genomes, created a national genomic variation catalogue, established a biobank with over 20,000 biospecimens, and identified nearly 180 million genetic variants, including around 7 million novel variants that had never been documented before. These novel variants are particularly important because they represent genetic differences unique to Indian populations, which could help researchers understand disease susceptibility and treatment responses in these communities.

To support this research infrastructure, the government has established the Indian Biological Data Centre (IBDC) with high-performance computing facilities and seven specialized biological data repositories. This centralized approach enables equitable data sharing and creates a foundation for AI research that would be difficult for individual institutions to build alone.

How Is AI Being Applied to Solve Real Health Problems?

• Cancer Imaging: The Department of Biotechnology is backing AI-powered cancer imaging research and has established a national imaging biobank to develop precision diagnostic algorithms that can identify tumors earlier and more accurately.
• Maternal and Fetal Health: The AI for Ultrasound (AI for USG) initiative, implemented with the Bill and Melinda Gates Foundation, is improving maternal and fetal healthcare through AI-enabled ultrasound solutions that can be deployed in resource-limited settings.
• Precision Medicine: The government is promoting AI and machine learning-based precision medicine applications using the genomic datasets from GenomeIndia, enabling doctors to tailor treatments based on individual genetic profiles.
• Agricultural Disease Detection: AI tools have been developed for crop disease diagnosis, helping farmers identify and treat plant diseases before they spread across fields.
• Diabetic Retinopathy Screening: AI systems are being deployed to screen for diabetic retinopathy, a leading cause of blindness, by analyzing retinal images automatically.

The Bio-AI Hub supports AI-driven biological design, bioprocess optimization, and translational research under the BioE3 programme, creating a bridge between basic research and practical applications.

Why Does Structural Genomics Matter Beyond Just Reading DNA Sequences?

While India's initiative focuses on sequencing and computational analysis, a parallel conversation is emerging in the global genomics community about the limitations of sequence-only approaches. According to Claude E. Gagna, Ph.D., Professor at the New York Institute of Technology, DNA and RNA are not merely repositories of sequence information.

"DNA and RNA are dynamic molecules capable of adopting alternative and multistranded conformations that influence gene regulation, genome stability, cellular function, and disease," explained Claude E. Gagna.

Claude E. Gagna, Ph.D., Professor, Department of Biological and Chemical Sciences, New York Institute of Technology

Research has linked unusual DNA structures like G-quadruplexes, i-motifs, left-handed Z-DNA, and triplex structures to transcriptional regulation, chromatin organization, DNA repair, and genomic instability. These structures are increasingly recognized as contributors to both normal cellular function and human disease. However, the tools that predict these structures often operate independently, use different scoring systems, and require specialized expertise, making them inaccessible to many researchers.

Gagna argues that the next major advance in genomics may not come from creating yet another prediction algorithm, but from integrated structural genomics platforms that bring together prediction, visualization, annotation, comparison, and interpretation within a unified environment. This mirrors the early days of genomics itself, when fragmented data across specialized resources eventually gave way to integrated genome browsers and standardized databases that made complex information accessible to a broad scientific community.

How Are AI-Designed Gene Editors Improving Gene Therapy?

Beyond genomic analysis, AI is also accelerating the design of gene-editing tools themselves. A research team at Sungkyunkwan University has successfully advanced AI-designed base editors, which are tools that locate incorrect letters in DNA and correct them to proper letters. The team developed "OpenABE" (Open Adenine Base Editor) by precisely engineering AI-derived next-generation base editors using structure-guided protein engineering.

The results were dramatic. The team elevated gene editing efficiency by up to 36 times compared to conventional AI-designed models. The resulting next-generation gene editors, OpenABE 1.1 and OpenABE 1.2, demonstrated editing capabilities 16 to 36 times stronger than existing AI-designed gene editors, putting them on par with ABE8e, currently considered the gold-standard gene editor used in laboratories worldwide.

"This study represents a landmark innovation where human scientists overcame the limitations of early AI-designed gene editors using structure-guided protein engineering. By opening a path to safely cure the causes of genetic diseases in both the nucleus and mitochondria, we expect this work to significantly accelerate the development of therapeutics for genetic disorders," stated Professor Daesik Kim of Sungkyunkwan University.

Professor Daesik Kim, Department of Medicine, Sungkyunkwan University

What makes this breakthrough particularly significant is that it addresses a critical safety concern. Early AI-designed gene editors suffered from off-target and bystander effects, where unintended genetic letters outside the target site were altered, limiting their safety for clinical applications. The Sungkyunkwan team dramatically reduced these off-target effects, achieving high precision that cleanly corrects only the intended genes.

The team also proved that precise editing is achievable not only for DNA inside the nucleus, the center of the cell, but also for DNA within mitochondria, which produce cellular energy but have proven difficult to edit due to their unique structure. By encapsulating these gene editors into engineered virus-like particles for cellular delivery, the team secured high safety standards that allow the selective editing of only one or two target genes needing treatment.

What Does This Mean for the Future of Genetic Disease Treatment?

India's comprehensive approach to AI-driven genomics, combined with advances in AI-designed gene editors, suggests that the next decade could see significant progress in treating previously intractable genetic diseases. The combination of large-scale genomic databases, AI-powered analysis tools, and improved gene-editing technologies creates a foundation for precision medicine that could eventually reach patients with rare genetic conditions.

The research team at Sungkyunkwan also recently revealed that "OpenCRISPR-1," a next-generation gene editor designed by AI, maintains gene-editing efficiency comparable to conventional Cas9 while reducing off-target mutations by up to 553 times. By applying OpenCRISPR-1 to prime editing technology and engineered virus-like particle delivery systems, they demonstrated its potential for expansion into a highly efficient and precise next-generation gene therapy platform.

As these technologies mature, the bottleneck is likely to shift from scientific capability to practical implementation. Researchers will need user-friendly prediction tools, transparency about how AI predictions are generated, and confidence in the results. The successful implementation of AI in genomics requires more than predictive power; it requires platforms that balance automation with interpretability, allowing scientists to understand how predictions relate to established biological knowledge.