Evidence Passport
Predicting protein electrostatics with protein language models
Top story 3 in the issue of 25 October 2026, in 32 AI Biotechnology.
Original source
Predicting protein electrostatics with protein language models
KaML-ESM models predict residue pKa values from sequence alone with errors near 0.5 units, then apply them across the human proteome to spot functional sites.
Evidence
Evidence: Peer-reviewed (evidence step 5 of 6)
Published after review by independent experts.
The story in three lines
- Key finding
- Sequence-only models predicted pKa with about 0.5-unit error for six residue types in native proteins, but did worse on buried engineered mutations.
- Significance
- Shows evolutionary sequence data also carry electrostatic information useful for enzyme and drug design.
- Takeaway
- A free tool for protein engineering, with clear limits on unusual designed proteins.
Later coverage in the journal
No later coverage in the journal yet.
Corrections and updates
No corrections or updates recorded for this item.
This page is generated from the issue and stays at the same address. It adds nothing that is not in the issue, the source link or the corrections log.