illustration of DNA strand and abstract shapes on a computer screen on a green gradient background

Medical, health, and genomics

Digital pathology helps decode tumor microenvironments for precision immunotherapy. GigaPath is a novel vision transformer that can scale to gigapixel whole-slide images by adapting dilated attention for digital pathology. In joint work with Providence and UW, we’re sharing Prov-GigaPath, the first whole-slide pathology foundation model pretrained on large-scale real-world data, for advancing clinical research and discovery.

GigaPath: Whole-Slide Foundation Model for Digital Pathology

Research Forum Ep2 | Panel | Transforming the Natural Sciences with AI

Research Forum 2 | Panel Discussion: Transforming the Natural Sciences with AI

white icons of first aid kit, DNA strand, laptop monitor with overlapping eye, and microscope on a blue and green gradient background

Scaling early detection of esophageal cancer with AI

female doctor / nurse reviewing a tablet

Microsoft Health Futures

Current selections

Sort by: Most recent

Clear selections

Search within these results

Content Types

Published Date

Microsoft Research Blog

Advancing biomedical discovery: Overcoming data challenges in precision medicine

March 5, 2025 | Mandi Hall

Our recent study in Nature Scientific Reports identified key challenges in the biomedical data lifecycle and offered 7 actionable recommendations.

white line icon of a medical paper and of a computer with a person in front of it on a blue and green gradient background

Publication

Deep learning guided design of protease substrates

Carmen Martin-Alonso, Sarah Alamdari, Tahoura S. Samad, Kevin Kaichuang Yang, Sangeeta N. Bhatia, Ava P. Amini

bioRxiv | March 2025

Publication

Scalable Universal T-Cell Receptor Embeddings from Adaptive Immune Repertoires

Paidamoyo Chapfuwa, Ilker Demirel, Lorenzo Pisani, Javier Zazo, Elon Portugaly, H. Jabran Zahid, Julia Greissl

ICLR 2025 | March 2025

Github

Publication

Rapid and accurate prediction of protein homo-oligomer symmetry using Seq2Symm

Meghana Kshirsagar, Artur Meller, Ian R. Humphreys, Samuel Sledzieski, Yixi Xu, Rahul Dodhia, Eric Horvitz, Bonnie Berger, Gregory R. Bowman, Juan M. Lavista Ferres, David Baker, Minkyung Baek

Nature Communications | February 2025

Project

Video

AI for Precision Health: Learning the language of nature and patients

February 25, 2025 | Hoifung Poon, Ava Amini, Lili Qiu, Matthew Lungren, Carlo Bifulco

Hosted by Hoifung Poon, with Lili Qiu, Ava Amini, Carlo Bifulco (opens in new tab), and Matthew Lungren at Microsoft Research Forum, Episode 5 This panel discussion with Microsoft researchers and external guests explores the transformative potential of generative AI in…

44:59

Video

Keynote: Multimodal Generative AI for Precision Health

February 25, 2025 | Hoifung Poon

Presented by Hoifung Poon at Microsoft Research Forum, Episode 5 Hoifung Poon, General Manager of Microsoft Health Futures, introduces an agenda in precision health, utilizing generative AI to pretrain high-fidelity patient embeddings from multimodal, longitudinal patient journeys. This…

17:14

Event

Microsoft Research Forum

February 25, 2025 | Virtual

Microsoft Research Forum Location: Virtual Microsoft Research Forum is a virtual series highlighting purposeful research and its real-world impact, from fundamental exploration to advancing AI responsibly, scaling innovation through products and open source, and driving…

Research Forum | abstract background with colorful hexagons

Publication

Consequences of training data composition for deep learning models in single-cell biology

Ajay Nadig, Akshaya Thoutam, Madeline Hughes, Anay Gupta, Andrew W. Navia, Nicolo Fusi, Srivatsan Raghavan, Peter S. Winter, Ava P. Amini, Lorin Crawford

bioRxiv | February 2025

Project

Microsoft Research Blog

Exploring the structural changes driving protein function with BioEmu-1

February 20, 2025 | Sarah Lewis, Tim Hempel, Jose Jimenez-Luna, Michael Gastegger, Yu Xie, Victor García Satorras, Osama Abdin, Bas Veeling, Ryota Tomioka, Frank Noé

Meet BioEmu-1 from Microsoft Research. This deep learning model can generate thousands of protein structures per hour, unlocking new possibilities for protein scientists and drug discovery and research.

The image shows eight different 3D models of protein structures. Each model is color-coded with various segments in blue, green, orange, and other colors to highlight different parts of the protein.

Publication

Addressing biomedical data challenges and opportunities to inform a large-scale data lifecycle for enhanced data sharing, interoperability, analysis, and collaboration across stakeholders

Vivek Sriram, Ashley Conard, Ilyana Rosenberg, Dokyoon Kim, Scott Saponas, Amanda K. Hall

Scientific Reports | February 2025, Vol 15

Medical, health, and genomics

Highlights