Many questions in biology aren’t about individual proteins...they’re about how proteins behave together.

This week we launched CoSearch in SeqHub: a user-requested analysis that lets you explore where multiple proteins co-occur across 132,000 microbial genomes, in seconds.

Here's what we've been building:

🔬 SeqHub: protein & genome analysis platform (seqhub.org, free for academic use)

🤖 gLM2: genomic language model (github.com/TattaBio/gLM2)

🧬 OMG: metagenomic dataset containing 3.3B protein sequences and 2.8B intergenic sequences (github.com/TattaBio/OMG)

We're Tatta Bio, a scientific non-profit on a mission to make biological sequence data easy to find, understand, and share. We're building SeqHub, a platform for protein/genome analysis, with a focus on microbial research. Excited to connect with the scientific community here!