JSON
Bryant P, Noé F
PLoS Comput Biol 20 (7) e1012253 [2024-07-00; online 2024-07-25]
Structure prediction of protein complexes has improved significantly with AlphaFold2 and AlphaFold-multimer (AFM), but only 60% of dimers are accurately predicted. Here, we learn a bias to the MSA representation that improves the predictions by performing gradient descent through the AFM network. We demonstrate the performance on seven difficult targets from CASP15 and increase the average MMscore to 0.76 compared to 0.63 with AFM. We evaluate the procedure on 487 protein complexes where AFM fails and obtain an increased success rate (MMscore>0.75) of 33% on these difficult targets. Our protocol, AFProfile, provides a way to direct predictions towards a defined target function guided by the MSA. We expect gradient descent over the MSA to be useful for different tasks.
PubMed 39052676
DOI 10.1371/journal.pcbi.1012253
Crossref 10.1371/journal.pcbi.1012253
pmc: PMC11302914
pii: PCOMPBIOL-D-23-01693