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

Scientists use machine learning to predict DNA binding rates from sequence

November 8, 2017

By Microsoft Research Lab – Cambridge and Department of Bioengineering, Rice University The binding of DNA strands by Watson-Crick base pairing is a fundamental process in biotechnology, which is used around the world for reading…

hand drawn image of ICTA dna strand beating CCTA around a racetrack

Publication

Predicting DNA hybridization kinetics from sequence

Jinny X. Zhang, John Z. Fang, Wei Duan, Lucia R. Wu, Angela W. Zhang, Neil Dalchau, Boyan Yordanov, Rasmus Petersen, Andrew Phillips, David Yu Zhang

Nature Chemistry | November 2017

Project Project Project

Publication

Weaker HLA footprints on HIV in the unique and highly genetically admixed host population of Mexico

Maribel Soto-Nava, Santiago Avila-Ríos, Humberto Valenzuela-Ponce, Claudia García-Morales, Jonathan M. Carlson, Daniela Tapia-Trejo, Daniela Garrido-Rodriguez, Selma N. Alva-Hernández, Thalía A. García-Tellez, Akio Murakami-Ogasawara, the International HIV Adaptation Collaborative, Simon A Mallal, Mina John, Mark A. Brockman, Chanson J. Brumme, Zabrina L. Brumme, Gustavo Reyes-Teran, the HIV MexNet Group

Journal of Virology | November 2017

Github Project

Publication

Constrained Deep Weak Supervision for Histopathology Image Segmentation

Zhipeng Jia, Xingyi Huang, Eric Chang, Yan Xu

IEEE Transactions on Medical Imaging | November 2017

Project

Publication

Host genotype and time dependent antigen presentation of viral peptides: predictions from theory

Ruth Charlotte Eccleston, Peter V. Coveney, Neil Dalchau

Scientific Reports | October 2017, Vol 7: pp. 14367

Project Project

Event

Microsoft @ LISA 2017

October 29, 2017 – November 3, 2017 | San Francisco, CA

Microsoft is a silver sponsor of LISA17, the annual vendor-neutral meeting place for the wider system administration community. The program will address the overlap and differences between traditional and modern IT operations and engineering, curated…

Publication

Adverse Reactions Associated With Cannabis Consumption as Evident From Search Engine Queries

Elad Yom-Tov

JMIR Public Health and Surveillance | October 2017, Vol 3(4): pp. e77

Project

Video

Three Principles of Data Science: Predictability, Stability, and Computability

October 26, 2017 | Bin Yu

In this talk, I will discuss intertwining importance and connections of three principles of data science. The three principles will be demonstrated in the context of two neuroscience projects and through analytical connections. In particular,…

Three Principles of Data Science: Predictability, Stability, and Computability

0:51:01

Publication

Designing Opportune Stress Intervention Delivery Timing using Multi-modal Data

Akane Sano, Paul Johns, Mary Czerwinski

Proceedings of the Seventh International Conference on Affective Computing and Intelligent Interaction (ACII ’17) | October 2017

Event

Microsoft Research @ HCOMP 2017

October 24, 2017 – October 26, 2017 | Quebec City, Quebec

We are excited to be a gold sponsor of Human Computation and Crowdsourcing (HCOMP) 2017, the premier venue for disseminating the latest research findings on crowdsourcing and human computation. While artificial intelligence (AI) and human-computer…

Medical, health, and genomics

Highlights