https://t.co/7iVBqWksLR

Excited to be part of this work! We used ColabSaprot to finetune and run inference on an experimental sequence-to-expression dataset for another work — the results aligned well with experimental validation and the process was quite smooth.

Westlake University deeply mourns the passing of Professor Chen-Ning Yang — Nobel laureate in Physics, Honorary Chair of the Board of Trustees of Westlake University, and a member of Westlake’s Advisory Board. Professor Yang’s century-long life was a bridge between East and West,

Small Molecule Approach to RNA Targeting Binder Discovery (SMARTBind) Using Deep Learning Without Structural Input 1. SMARTBind is a novel framework that identifies RNA-binding small molecules using only RNA sequences, eliminating the need for structural data. This approach

Congratulations to the team!

New paper on Biorxiv is a massive and long term collaboration with Yanjun Li and Chenglong Li on using AL/ML to design small molecules targeting RNA. @UFHealth and @UFHealthCancer the approach is broadly applicable and an advance on current approaches. We are exited for apps.

Small Molecule Approach to RNA Targeting Binder Discovery (SMARTBind) Using Deep Learning Without Structural Input https://t.co/RmE6Qn10j0 #biorxiv_bioinfo

De novo Design of All-atom Biomolecular Interactions with RFdiffusion3 🚀 New preprint from David Baker!🚀 1. A groundbreaking study introduces RFdiffusion3 (RFD3), a novel diffusion model that generates protein structures in the context of ligands, nucleic acids, and other

Many of the most complex and useful functions in biology emerge at the scale of whole genomes. Today, we share our preprint “Generative design of novel bacteriophages with genome language models”, where we validate the first, functional AI-generated genomes 🧵

MIT Course announcement: Machine Learning for Computational Biology #MLCB25 Fall'24 Lecture Videos: https://t.co/Puzq59oni4 Fall'24 Lecture Notes: https://t.co/RRNRY1SZaZ (a) Genomes: Statistical genomics, gene regulation, genome language models, chromatin structure, 3D genome

BioEmu now published in @ScienceMagazine !! What is BioEmu? Check out this video: https://t.co/PAj96iKvR7

The past few years of "AI for life sciences" has been all about the models: AF3, NNPs, PLMs, binder generation, docking, co-folding, ADMET, &c. But Chai-2, and lots of related work, shows us that the vibes are shifting. Models themselves are becoming just a building block; the

🚨 New paper 🚨 RNA modeling just got its own Gym! 🏋️ Introducing RNAGym, large-scale benchmarks for RNA fitness and structure prediction. 🧵 1/9

Predicting function of evolutionarily implausible DNA sequences １．This work introduces NULLSETTES, the first benchmark to evaluate genomic language models (gLMs) on their ability to predict loss-of-function (LOF) mutations in synthetic DNA sequences that lack evolutionary

It’s finally happening!!! Diffusion is so much more satisfying than autoregressive for protein & DNA sequences that don’t really have directionality 🥹 Waiting for this to empirically land & replace BERT/one-step discrete diffusion for protein foundation models 👀

RLXF is on @biorxivpreprint! We introduce a PPO-based workflow to align the logits of any protein language model away from evolutionary plausibility and towards biochemical function. Not only does this seem to be more robust than other preference optimization methods... (1/3)

Interested in single cell genomics but need help getting started? Check out the full agenda for our Single Cell Genomics Day on Friday 4/25. All talks will be live-streamed (no registration required) at https://t.co/JqaO6urVPF

#RNA structure prediction remains unsolved -- nice tech feature incl #deeplearning and #CASP16 in @Nature

Announcing Neo-1: the world’s most advanced atomistic foundation model, unifying structure prediction and all-atom de novo generation for the first time - to decode and design the structure of life 🧵(1/10)

🧬 Meet Lyra, a new paradigm for accessible, powerful modeling of biological sequences. Lyra is a lightweight SSM achieving SOTA performance across DNA, RNA, and protein tasks—yet up to 120,000x smaller than foundation models (ESM, Evo). Bonus: you can train it on your Mac. read