tepid take: a lotttttt of job postings for bio-AI researchers, not enough job postings for generating-the-extremely-necessary-data-for-bio-AI researchers

Can't find the words so heres a diagram, apologies for bad handwriting. Higher energy states that are in between the two conformations you care about are both more combinatorially plentiful, and rarer, and only a few of them matter. mAb CDRs can interconvert on 10s of µs so it matters for those too

I've not used AI as seriously as Will here, but my experience is similar. Introductory-level assistance is amazing! They always point you in the right direction if you have no clue how to approach a problem. But when expert knowledge is required, lots of serious mistakes, some obvious, others not.

Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀

Reposting this probably-useful tool from LinkedIn that maps UniProt IDs to PDBs

github.com/iriziotis/Un...

I decided to make the datasets I'm generating for my phd project public. For each protein in Swiss-Prot, I'm making available PLM embeddings (ProtTrans, Ankh, ESM2), GO annotations and taxonomy representations. All files follow the same order, one line per protein.

github.com/pentalpha/pr...

Beta-lactoglobulin having a little wiggle. The main whey protein in the milk of many mammals (except humans). Seen here traversing various configurations determined using NMR (1dv9.pdb). Imagine it dancing to music of your choice😂.
🧪⚗️ 🧶🧬🐡 #c4d #CompChemSky #SciComm

turning assignments in early >>>