Transformative Computational Biology Grant Program: Partnership with the Biswas Family Foundation

Computational tools, like AI, hold both the power and the potential to advance human health significantly. SPARC began our partnership with the Biswas Family Foundation in 2023 to analyze and understand the state of computational biology in biomedical research and identify where philanthropic investments could be deployed to advance global health by overcoming barriers to scientific progress. Using the findings and insights from this analysis, which are published in  Transformative Computational Biology: A Giving Smarter Guide, the Biswas Family Foundation launched the Transformative Computational Biology Grant Program. SPARC provides strategic guidance and operational support for the program, which ultimately strengthens the vital bridge between data and medical breakthroughs and transforms the landscape of biomedical research and patient care.

Scientific Priorities

The Biswas Family Foundation’s Transformative Computational Biology Grant Program prioritizes the following:

using large-scale data to deepen our understanding of the causes and progression of disease
advancing new technologies that enable the identification of novel diagnostics and treatments
supporting global health research that has the potential to improve the lives of millions of people

Funding Details

In March 2024, five research teams, with a total of 15 multidisciplinary investigators, were awarded grants through the Biswas Family Foundation’s Transformative Computational Biology Grant Program. The $14 million in scientific investments will advance global health through the development, validation, and application of computational biology tools.

Awardees and Projects

Project

AI for Genomic Medicine: Circuitry, Treatment, Personalization

Manolis Kellis, PhD Massachusetts Institute of Technology

Co-Investigator: Brad Pentelute, PhD; Marinka Zitnik, PhD

Overview

Enhancing biomarker selection, de novo drug synthesis, and drug repurposing is essential for identifying and generating more effective therapeutics. By integrating single-cell and spatial sequencing with machine learning approaches, this project aims to predict target genes to inform the development of precision therapeutics in cancer, neuroscience, and metabolic disorders.

Project

A Chatbot Assistant for Genetic Diagnosis and Interpretation of Common and Rare Cardiovascular Diseases

Anshul Kundaje, PhD Stanford University

Co-Investigator: Jesse Engreitz, PhD

Overview

In the clinical diagnostic workflow, the impact of genomic mutations is unknown in many cardiovascular diseases. This project uses machine learning models to develop an artificial intelligence chatbot interfaced with genomic knowledge to improve the diagnostic process and accelerate the diagnosis of patients with cardiovascular diseases.

Project

The MAIDA Initiative: Democratizing Global Medical Imaging Data Sharing for Safer and Fairer AI

Pranav Rajpurkar, PhD Harvard Medical School

Overview

Project: Datasets representative of diverse patient populations enable the development and deployment of reliable, equitable, and inclusive artificial intelligence tools. This project aims to collect medical imaging data, notably chest x-rays and chest CT images, from a variety of clinical settings to facilitate the use of artificial intelligence that analyzes images and improves diagnosis and treatment.

Project

Biswas Center for Transformative Computational Cancer Biology

Katherine Pollard, PhD Gladstone Institutes

Co-Investigator: Alex Marson, MD, PhD; Barbara Engelhardt, PhD; Catherine Tcheandjieu Gueliatcha, DVM, PhD; Christina Theodoris, MD, PhD; Karin Pelka, PhD; Ryan Corces, PhD; Seth Shipman, PhD; Vijay Ramani, PhD

Overview

Personalized medicine informs and subsequently tailors disease prevention, diagnosis, and treatment efforts based on an understanding of an individual’s unique biology. This project aims to support personalized diagnosis and treatment for colorectal and skin cancers through the development of machine learning models trained to predict how a patient’s genetic mutation can alter tumor cell biology and evaluate the effectiveness of candidate immunotherapies.

Project

CURE-Bench: Universal Benchmark for All-Disease Drug Repurposing

Marinka Zitnik, PhD Harvard Medical School

Overview

Drug repurposing could expand the utility of existing drugs and, thus, therapeutic options for patients across a variety of diseases. This project aims to develop foundation artificial intelligence models and an accompanying evaluation framework that benchmarks models across diseases to promote the development, evaluation, and widespread use of artificial intelligence models that identify clinically relevant drug repurposing hits.

Publications

Peer-Reviewed Publications by Grantees

ReXamine-Global: A Framework for Uncovering Inconsistencies in Radiology Report Generation Metrics.

Banerjee, Oishi, Agustina Saenz, Kay Wu, et al.

Version 1. Preprint, arXiv, 2024. https://doi.org/10.48550/ARXIV.2408.16208.

Quantized Multi-Task Learning for Context-Specific Representations of Gene Network Dynamics.

Chen, Han, Madhavan S. Venkatesh, Javier Gómez Ortega, et al.

Preprint, Cold Spring Harbor Laboratory, August 19, 2024. https://doi.org/10.1101/2024.08.16.608180.

Deep-Learning Prediction of Gene Expression from Personal Genomes.

Drusinsky, Shiron, Sean Whalen, and Katherine S. Pollard.

Preprint, Cold Spring Harbor Laboratory, July 27, 2024. https://doi.org/10.1101/2024.07.27.605449.

Learning Universal Representations of Intermolecular Interactions with ATOMICA.

Fang, Ada, Michael Desgagné, Zaixi Zhang, et al.

Preprint, Cold Spring Harbor Laboratory, April 8, 2025. https://doi.org/10.1101/2025.04.02.646906.

Empowering Biomedical Discovery with AI Agents.

Gao, Shanghua, Ada Fang, Yepeng Huang, et al.

Cell 187, no. 22 (2024): 6125–51. https://doi.org/10.1016/j.cell.2024.09.022.

TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools.

Gao, Shanghua, Richard Zhu, Zhenglun Kong, et al.

Version 1. Preprint, arXiv, 2025. https://doi.org/10.48550/ARXIV.2503.10970.

A Foundation Model for Clinician-Centered Drug Repurposing.

Huang, Kexin, Payal Chandak, Qianwen Wang, et al.

Nature Medicine 30 (2024): 3601–13. https://doi.org/10.1038/s41591-024-03233-x.

Multimodal AI Predicts Clinical Outcomes of Drug Combinations from Preclinical Data

Huang, Yepeng, Xiaorui Su, Varun Ullanat, et al.

Version 1. Preprint, arXiv, 2025. https://doi.org/10.48550/ARXIV.2503.02781.

ClinVec: Unified Embeddings of Clinical Codes Enable Knowledge-Grounded AI in Medicine.

Johnson, Ruth, Uri Gottlieb, Galit Shaham, et al.

Preprint, Cold Spring Harbor Laboratory, December 5, 2024. https://doi.org/10.1101/2024.12.03.24318322.

SPATIA: Multimodal Model for Prediction and Generation of Spatial Cell Phenotypes.

Kong, Zhenglun, Mufan Qiu, John Boesen, et al.

Version 1. Preprint, arXiv, 2025. https://doi.org/10.48550/ARXIV.2507.04704.

Neighborhood Nonnegative Matrix Factorization Identifies Patterns and Spatially-Variable Genes in Large-Scale Spatial Transcriptomics Data.

Laursen, Ragnhild, Han Chen, Jack Demaray, Karin Pelka, and Barbara E. Engelhardt.

Preprint, Cold Spring Harbor Laboratory, April 27, 2025. https://doi.org/10.1101/2025.04.26.650724.

Contextual AI Models for Single-Cell Protein Biology.

Li, Michelle M., Yepeng Huang, Marissa Sumathipala, et al.

Nature Methods 21 (2024): 1546–57. https://doi.org/10.1038/s41592-024-02341-3.

Controllable Sequence Editing for Biological and Clinical Trajectories.

Li, Michelle M., Kevin Li, Yasha Ektefaie, et al.

Version 2. Preprint, arXiv, 2025. https://doi.org/10.48550/ARXIV.2502.03569.

One Patient, Many Contexts: Scaling Medical AI Through Contextual Intelligence.

Li, Michelle M., Ben Y. Reis, Adam Rodman, et al.

Version 1. Preprint, arXiv, 2025. https://doi.org/10.48550/ARXIV.2506.10157.

ReXVQA: A Large-Scale Visual Question Answering Benchmark for Generalist Chest X-ray Understanding.

Pal, Ankit, Jung-Oh Lee, Xiaoman Zhang, et al.

Version 1. Preprint, arXiv, 2025. https://doi.org/10.48550/ARXIV.2506.04353.

ProCyon: A Multimodal Foundation Model for Protein Phenotypes.

Queen, Owen, Yepeng Huang, Robert Calef, et al.

Preprint, Cold Spring Harbor Laboratory, December 15, 2024. https://doi.org/10.1101/2024.12.10.627665.

Generalizable AI Predicts Immunotherapy Outcomes Across Cancers and Treatments.

Shen, Wanxiang, Thinh H. Nguyen, Michelle M. Li, et al.

Preprint, Cold Spring Harbor Laboratory, May 5, 2025. https://doi.org/10.1101/2025.05.01.25326820.

Multimodal Medical Code Tokenizer.

Su, Xiaorui, Shvat Messica, Yepeng Huang, et al

Version 3. Preprint, arXiv, 2025. https://doi.org/10.48550/ARXIV.2502.04397.

An AI Agent for Knowledge-Intensive Biomedical QA.

Su, Xiaorui, Yibo Wang, Shanghua Gao, et al. “KGARevion

Version 2. ArXiv, 2024. https://doi.org/10.48550/ARXIV.2410.04660.

Signals in the Cells: Multimodal and Contextualized Machine Learning Foundations for Therapeutics.

Velez-Arce, Alejandro, Xiang Lin, Michelle M. Li, et al

Preprint, Cold Spring Harbor Laboratory, June 14, 2024. https://doi.org/10.1101/2024.06.12.598655.

Cellular Behavior Analysis from Live-Cell Imaging of TCR T Cell–Cancer Cell Interactions.

Verma, Archit, Changhua Yu, Stefanie Bachl, et al.

Preprint, Cold Spring Harbor Laboratory, November 21, 2024. https://doi.org/10.1101/2024.11.19.624390.

ReXGradient-160K: A Large-Scale Publicly Available Dataset of Chest Radiographs with Free-Text Reports.

Zhang, Xiaoman, Julián N. Acosta, Josh Miller, Ouwen Huang, and Pranav Rajpurkar.

Version 2. Preprint, arXiv, 2025. https://doi.org/10.48550/ARXIV.2505.00228.

FAQs

I am a researcher looking for funding for my artificial intelligence and computational biology work. Can I apply for funding right now?

Funding is not currently available via the Biswas Family Foundation’s Transformative Computational Biology Grant Program. Please check the RFPs page for a list of current and past RFPs, eligibility requirements, and application information.

How many researchers has this program funded to date?

The Biswas Family Foundation Transformative Computational Biology Grant Program has disbursed $14 million to five research teams.

How can I learn more about artificial intelligence in health?

Please visit our AI in Health page.