Excited to share our now published paper @cp-cell.bsky.social highlighting advances in modeling the evolution of protein-protein interactions with MSA Pairformer. Big thanks to Zhidian Zhang, Olivia Tang, @eunbelivable.bsky.social @milot.bsky.social @martinsteinegger.bsky.social and @sokrypton.org!

Expanding the scope of protein language modeling to protein-protein interactions with MSA Pairformer

Protein language models have excelled at modeling individual proteins, but extending these capabilities to protein complexes remains a major challenge. MSA Pairformer, a parameter-efficient protein la...

cell.com

I'm super excited to announce the first preprint of my PhD, together with Chenxi Ou and @sokrypton.org! ML has revolutionized protein modeling, but crucial challenges remain. For example, we can't reliably predict complicated protein structures without MSAs, which limits what we can design.

MMseqs2-GPU sets new standards in single query search speed, allows near instant search of big databases, scales to multiple GPUs and is fast beyond VRAM. It enables ColabFold MSA generation in seconds and sub-second Foldseek search against AFDB50. 1/n 📄 www.nature.com/articles/s41... 💿 mmseqs.com

GPU-accelerated homology search with MMseqs2 - Nature Methods

Graphics processing unit-accelerated MMseqs2 offers tremendous speedups for homology retrieval from metagenomic databases, query-centered multiple sequence alignment generation for structure predictio...

nature.com

MMseqs2 v18 is out - SIMD FW/BW alignment (preprint soon!) - Sub. Mat. λ calculator by Eric Dawson - Faster ARM SW by Alexander Nesterovskiy - MSA-Pairformer’s proximity-based pairing for multimer prediction (www.biorxiv.org/content/10.1...; avail. in ColabFold API) 💾 github.com/soedinglab/M... & 🐍

Side story: While working on the Google Colab notebook for MSA pairformer. We encountered a problem: The MMseqs2 ColabFold MSA did not show any contacts at protein interfaces, while our old HHblits alignments showed clear contacts 🫥... (2/4)

Excited to share work with Zhidian Zhang, @milot.bsky.social, @martinsteinegger.bsky.social, and @sokrypton.org biorxiv.org/content/10.1... TLDR: We introduce MSA Pairformer, a 111M parameter protein language model that challenges the scaling paradigm in self-supervised protein language modeling🧵

Scaling down protein language modeling with MSA Pairformer

Recent efforts in protein language modeling have focused on scaling single-sequence models and their training data, requiring vast compute resources that limit accessibility. Although models that use ...

biorxiv.org