🔥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

Every time I get an update from the Latent Labs team, I have to rewrite my expectations for how the next few years of biology will evolve. Honestly, I'm still coming to terms with it. Join the team -- roles in both London and SF!

Congrats to Alyssa Morrow and others on this latest work: a model for designing full-length mRNA sequences for a given protein sequence 🧬

do you have strong thoughts about protein engineering and ML?? help us organize this year's competition!!

I am reviewing papers for GEMBio Workshop this morning and genuinely having such a good time -- y'all get ready for a wild set of papers to drop soon!! quality is honestly through the roof this year! 📈🐂

What's better than 1 deep mutational scanning (DMS) library? 2! In a new pre-print Brittney Thornton and Rachel F Weissman et al. map the mutational landscape of ISDra2 TnpB protein and reRNA and leverage these datasets to engineer highly active variants (1/9)

don't chase benchmarks 🚨🔊🤌

🚀 New proposal from Align! The experimental platform aims to standardize #microbial #phenotyping & support predictive modeling. :🦠 Capturing data across 1k strains & 1k conditions; using BacterAI; generating high-quality datasets for ML Jensen Lab buff.ly/3rO55fA

What an awesome resource!!

Really happy that our work on conditioning diffusion models is published - have a read if you fancy hearing how we tried to encourage models to generate more physically plausible compounds by training conditionally with synthetic, distorted molecules!

Q1 newsletter!!

In @nature we describe the use of scalable #proteinengineering & #machinelearning to predict millions of bespoke CRISPR-Cas9 enzymes, offering safer & more genome editing tools. 🧬🖥️ Rachel Silverstein CGM at MGH @MGH_RI MassGeneral News Harvard Medical School nature.com/articles/s4158…

Machine Learning Engineers Bespoke Cas9 Enzymes for Gene Editing Read more of what Ben Kleinstiver and Rachel Silverstein from HMS had to say in an interview with GEN's Fay Lin, PhD. MassGeneral News Harvard Medical School hubs.li/Q03jt42N0

This proposal is really interesting. Can you measure enzyme kinetics by adjusting substrate concentration *inside* the cell? On one hand, cells are noisy. On the other, enzymes behave differently in vitro & in vivo. Best to measure in the conditions you care about!

🚨 New in Immunity ! EVE-Vax, an AI model that anticipates future viral evolution and designs antigens to proactively test vaccines + therapeutics—before variants even emerge. We envision this work will help make future-proofed vaccines and therapeutics. 👇 (1/7)

Can AI enable safe vaccines at scale that last? Can we anticipate immune response? We tested this .. See cell.com/immunity/fullt… and hms.harvard.edu/news/building-… And big thx to CEPI for funding

We are hiring!! Bioinformatics Scientist & Director of Protein Projects

Align's GROQ-seq platform just turned 1🎂 it now supports 7 protein function projects across 6 labs worldwide. 300k variants measured per run @ <$0.05 each, and it works. Not theory. Real infrastructure. Open to the world. 🔗 1-year technical report → hubs.la/Q03mSrW_0

Can protein expression be ‘solved’? We review current methods for measuring and predicting protein expression (wet lab + ML techniques!) & propose how this ubiquitously interesting problem could be solved. What do you think? sciencedirect.com/science/articl…

🧬 😴 TIRED: Scaling protein models to billions of parameters hoping they'll memorize all of evolution and generalize beyond 🔥 WIRED: Smart retrieval-augmented models that dynamically access what they need from sequence databases

is Protriever the end of MSAs??? excited about this Ruben Weitzman @ ICLR 2025 also, Pascal Notin has a phenomenal substack that I can't recommend enough. He goes through this paper and does a deeeeeep dive on the rationale! pascalnotin.substack.com