Excited to share latest ✨Med-Gemini✨ additions - our new research unlocks possibilities in medical data analysis with 3 new models built upon Gemini 1.5 that can handle 2D medical images, and for the first time genomic risk score & 3D radiology scans. arxiv.org/pdf/2405.03162

So proud of Yuchen Zhou for being a main contributor to Med-Gemini-Polygenic! arxiv.org/abs/2405.03162

my artwork is featured on front page of Nature Human Behaviour !! commissioned for Uma Mohan’s brilliant traveling waves paper 🧠🌊 pls DM for any other neuro x art opportunities I had so much fun and am so thankful for this opportunity 🎨 nature.com/nathumbehav/

Excited to share our latest work in Science Magazine. We describe how a structure-informed language model can be used for diverse protein engineering tasks, and guide the evolution of therapeutic antibodies for improved potency and resilience against viral escape.

As a doctor who strives to cure cancer, HMS oncologist Wolfram Goessling found himself as a patient at Dana-Farber and Brigham and Women's Hospital when he was diagnosed with angiosarcoma. “Facing Cancer,” a film that that tells his inspiring story, will premiere at the Coolidge Corner

Applications for the second AIM cohort are open and due December 1st at 5pm ET! Join us for a virtual information session on October 30th, 5-6pm ET. Register to attend here: harvard.zoom.us/webinar/regist…

Making a case for thoughtful collaboration with the computational community to enhance cancer research via AACR translational biology course😬🍎

More amazing work from Yuchen Zhou

1/ 🚀 Excited to kick off the new year with our latest study, now published in Nature Medicine! 🌟Presenting CRAFT-MD, a novel framework to rigorously evaluate LLMs for clinical conversational reasoning! Let's dive in! 🧵 #HNY2025

Thank you Jim. I might be just as excited but the students even more than the two of us. They are seeing how they can change our future healthcare for the better.

Thrilled to announce the publication of our work on a new approach for grading mutations for antibiotic resistance diagnostics for #TB a collaborative project with international scientists from FIND World Health Organization (WHO) funded by Unitaid DBMI at Harvard Med Harvard Medical School nature.com/articles/s4146…

Excited to share what we've been working on!

Check out this work led by the incredible Ada Fang ATOMICA constructs representations of molecular interactions at the atomic scale, capturing universal physiochemical principles. Read about the exciting insights from applying ATOMICA below 👇

M-REGLE is an AI method that simultaneously analyzes multiple health data streams, including ECGs and PPGs, to jointly learn rich representations and significantly boost the discovery of genetic links to disease. Learn all about it at goo.gle/4ehDwp4

1/ 🧵Can protein language models reason about evolution, not just model it? We built a 24 M-param PLM, Phyla, that reconstructs phylogenetic trees better than existing PLMs. Details & links in 2/👇

Google presents an AI system to write expert-level scientific software. Using LLMs + tree search, it invented novel methods in bioinformatics, epidemiology, geospatial analysis & more, often surpassing human SOTA. (1/4)

Had a blast giving the current Fifty Years cohort a tour of Plasmidsaurus yesterday. Just a few years ago I was in their shoes - now it’s an honor to host future founders at our office. Excited to see the startups you’ll build!

100 companies started from an accelerator. 96% raise success rate. How much equity do they take? None. That’s 5050. No equity. No fees. No weird clauses. Applications open.