Molecular docking versus co-folding for protein–peptide pose prediction: effects of protein flexibility and training set overlap
Mark Fonteyne, Nada Badr, Peter J. K. Kuppen, Alexander L. Vahrmeijer, Gerard J. P. van Westen, Willem Jespers · 2026
Read Molecular docking versus co-folding for protein–peptide pose prediction: effects of protein flexibility and training set overlap by Mark Fonteyne, Nada Badr, Peter J. K. Kuppen, Alexander L. Vahrmeijer, Gerard J. P. van Westen, Willem Jespers (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13592151.txt.
Description
Short chain drugs bind their marks in bent poses that a sum must guess, and new fold tools now guess pose and shape in one run. Mark Fonteyne and co-authors race those tools in a 2026 test: three fold tools next to two dock tools built for chains. Their track is a known set of bent marks.
When kin of a test pair sat in the fold tools' school set, the fold tools won on pose truth and rank. When no kin sat there, a dock tool beat them all. One fold tool shone at home and slid far from it. A pair of score marks, one for the seam and one for chain build, split the ranks well. Choice, the team says, turns on school kin.
Catalog record
| CREATOR | Mark Fonteyne, Nada Badr, Peter J. K. Kuppen, Alexander L. Vahrmeijer, Gerard J. P. van Westen, Willem Jespers |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 75 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |