🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Link to preprint: biorxiv.org/content/10.110… github: github.com/microsoft/scFM…

This project was completed during an amazing internship at Microsoft Research New England with the invaluable guidance of Lorin Crawford and Ava Amini as part of the Ex Vivo project, with collaborators at Broad Institute Peter Winter and Sri Raghavan. Amazing science, amazing mentorship, with a view!

🎉 📷 Excited to announce our 2025 COPSS Emerging Leader Award (ELA) winners. The COPSS ELA recognizes early career statistical scientists who show evidence of and potential for leadership and who will help shape and strengthen the field.

Yes, Lester Mackey!!! 🐐🎉

Great to see our paper presenting recall, a framework which calibrates clustering for the impact of data "double-dipping" in single-cell studies, out today in AJHG! Congratulations, Alan DenAdel and co-authors!

How can artificial variables improve clustering in single-cell RNA sequencing?Cell Press "Artificial variables help to avoid over-clustering in single-cell RNA sequencing" - Recent advances in single-cell RNA sequencing (scRNA-seq) have enabled large-scale transcriptomic

Over-clustering of single-cell RNA-seq data can produce spurious results. Alan DenAdel, Lorin Crawford, & co of AJHG latest study introduce recall, a new method, protecting against over-clustering & enables rapid analysis of single-cell RNA-seq data: cell.com/ajhg/abstract/…

TYRESE PROCTOR. That's the tweet.

EAST CHAMPS #DUKEDUB 🕺🕺🕺🕺

Register for April 29: COPSS-NISS Leadership Webinar: Leadership in Trustworthy AI - mailchi.mp/niss.org/https…

Our paper has been published Nature Genetics! Through new statistical methods, we shed light on fundamental questions about cellular response to genetic perturbations. Our work is a substantial advance towards rigorous characterization and comparison of massive perturbation atlases.

🎉 Congratulations to Eric and Wendy Schmidt Center postdoctoral fellow Sebastiano Cultrera di Montesano and his team on their latest preprint! Learn more: doi.org/10.1101/2025.0…

How well do single-cell foundation models perform w/o finetuning? Our work Genome Biology shows that in zero-shot settings, scGPT and Geneformer often underperform traditional methods, raising questions about their utility for biological discovery. 📰 genomebiology.biomedcentral.com/articles/10.11…

Trainable subnetworks reveal insights into structure knowledge organization in protein language models １．This paper introduces trainable subnetworks to investigate how protein language models (PLMs), specifically ESM-2, internally organize structural knowledge. Subnetworks are

Do protein language models store different structural elements in factorizable subnetworks? To find out, we masked out PLM weights to suppress performance on CATH subcategories or secondary structure elements while maintaining performance on other sequences or residues.

#MachineLearning is fueling new discoveries in #medicine, enabling more precise and effective care. Join us on June 11 for a conversation on supporting further research on predictive, simulation-based medicine and potential impacts on #policymaking: ow.ly/Vmv950W482B

So awesome to see this finally out—huge congrats to all the authors! If interested, we covered the highlights in a recent News & Views piece in Nature Cardiovascular Research (s/o to Julian Stamp for jumping in as co-author) 🔗 rdcu.be/epxFW