The elimination of #affirmativeaction at the same time some key funding sources for marginalized trainees in #STEM are being dissolved (or made increasingly inaccessible) nationally and globally...is a horrible combination of events.

Black students on your campus did not take someone else's spot. #FalseNarrative Truth is that selective schools (that admit less than 25% of apps) grossly under-enrolled Blacks, Hispanics, and Native Americans relative to their % of the US population. chronicle.com/article/the-su…

Out now in Cell! doi.org/10.1016/j.cell… Historically marginalized student representation drastically drops from undergrad to grad school. Are underrepresented students unqualified? Or are grad school admissions unnecessarily confusing, costly, & gatekeeping? 1/🧵

EvoDiff combines evolutionary-scale data with diffusion models for controllable protein sequence generation. In addition to generating plausible proteins, we can scaffold structural motifs in sequence space! Preprint: biorxiv.org/cgi/content/sh… Code: github.com/microsoft/evod…

presenting EvoDiff: new generative models for controllable protein design from sequence data alone! ✅generate high-quality proteins ✅scaffold functional motifs 🤩apply to therapeutic design + more! 👉biorxiv.org/content/10.110… 💻github.com/microsoft/evod… 🎙️microsoft.com/en-us/research…

Microsoft open sources EvoDiff, a novel protein-generating AI tcrn.ch/44YodLr by @kyle_l_wiggers

We're looking forward to kicking off the fall this week! First up, Kevin K. Yang 楊凱筌 is presenting EvoDiff tomorrow (9/19) at 4 pm ET! Sign up here to receive the Zoom link in your inbox later today: ml4proteinengineering.com/sept-19

Hot off the press - our new commentary on "Early career Latinas in STEM: Challenges and solutions" Download for free until Dec 29, 2023. Please RT authors.elsevier.com/c/1i3TWL7PXme7-

Come join the BioML group Microsoft Research New England as an applied scientist! You'll get to work with me, Nicolo Fusi Alex Lu Ava Amini Sarah Alamdari Lorin Crawford Neil Tenenholtz Kristen Severson and others on problems at the intersection of machine learning, biology, and healthcare Also: mochi.

The Rosetta Commons Molecular ML Reading Group is hosting Sarah Alamdari from Microsoft Research New England and working with Kevin K. Yang 楊凱筌 to present EvoDiff, a diffusion model for controllable protein generation. Join us! Tomorrow Wed. 1/31 at 11am EST Website and zoom link: maomlab.github.io/mol_ml_reading…

Available today: the final journal version of FoldingDiffusion in Nature Communications Led by former intern Kevin Wu with Alex Lu Rianne van den Berg Sarah Alamdari James Zou and Ava Amini

Out today: the final version of our paper showing that CNNs are competitive to transformers as pretrained protein language models. with Alex Lu and Nicolo Fusi

Curious about AI's role in predicting and customizing protein structures and functions? Our panelists will explore how #AI and #biotechnology are paving the way for novel #healthcare solutions at #SynBioBeta2024: synbiobeta.com/events/synbiob…

we've got a packed house tonight at Massachusetts Institute of Technology (MIT) for Sarah Alamdari's seminar!

What a stellar crowd, thanks for having me :)

the girl math of protein engineering is picking structures to design simply because they’re pretty

We’re excited to share our latest work with Paige on (vision) foundation models of pathology. In this study, we introduce Virchow2 and Virchow2G, significantly increasing the scale of our previous work both in terms of data and parameters, with Virchow 2G reaching 1.85B

Hear from Kevin Yang where he will share how deep learning is enabling us to generate novel and useful biomolecules, enabling researchers and practitioners to better understand biology. Register and join us on September 3. msft.it/6010lS2J0