Milken Institute

Artificial intelligence (AI) and computational biology are revolutionizing biomedical innovation and its impact on health care. Two assistant professors of biomedical informatics in the Blavatnik Institute at Harvard Medical School are at the forefront of this revolution.

Pranav Rajpurkar, PhD, is leading the Medical AI Data for All (MAIDA) initiative, collecting medical imaging data from diverse populations and clinical settings worldwide. “In Hindi, ‘maida’ means ‘flour’, and just as flour is a key ingredient in many recipes, MAIDA serves to be a key ingredient in medical AI,” Rajpurkar says. The vision for MAIDA is to drive equitable AI advancement worldwide and ultimately improve diagnosis and treatment for patients everywhere by developing an open global data repository that represents diverse patient populations.

Marinka Zitnik, PhD, meanwhile, aims to build a comprehensive benchmark for evaluating computational drug repurposing systems, with the goal of developing AI models to identify molecules or biological targets that result in therapeutic effects when modulated by a drug.

Drug repurposing offers significant advantages compared to traditional drug development, such as lower cost, reduced risk for safety and efficacy issues, and faster integration into the clinic. “Our overarching goal is to lay the foundation for AI to enable drug repurposing at scale,” says Zitnik, who is also an associate faculty member at the Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University.

Both projects are made possible by the Biswas Family Foundation, a private grant-making foundation committed to supporting research and innovative programs at the intersection of emerging technology and global health.

In 2023, the Biswas Family Foundation, in partnership with the Milken Institute Science Philanthropy Accelerator for Research and Collaboration (SPARC), conducted a comprehensive review of the computational biology field and identified opportunities for philanthropy to advance the integration of computational tools in biomedical research and clinical care. The findings led to the creation of the Transformative Computational Biology Grant Program, which funds research using computational tools across a range of focus areas, including AI for genomic medicine, diagnosis of cardiovascular disease, precision oncology therapies, enhancement of clinical datasets, and drug repurposing systems.

This past March, during the first cycle of this grant program, five research teams were selected to receive nearly $14 million. Rajpurkar and Zitnik each received $1 million for their project teams. Zitnik is also collaborating with another funded team at the Massachusetts Institute of Technology. That team aims to advance high-throughput single-cell spatial sequencing discovery loops with rapid machine learning approaches to identify candidate genes for precision therapeutics in metastatic melanoma.

“It is now possible to bring together data from millions of patients, identify new mechanisms of disease, and turn those insights into translational impact,” says Sanjit Biswas, CEO of Samsara and co-founder of the Biswas Family Foundation with his wife, Hope Biswas, PhD, an infectious disease and maternal health epidemiologist.