rewire.it
Paper-reported evidence

Molecular embedding-based algorithm selection in protein-ligand docking

2026 · Peer-reviewed · PMC archival version PMC13104262.1

Paper-reported results. The values below come from this source, not an independent rewire.it run.

Open primary paper →DOI: 10.1186/s13321-026-01168-8

Primary full text verified using Europe PMC XML; venue: Journal of Cheminformatics; PMC ID: PMC13104262.

2 verified numerical rows · source checked 2026-09-15

Paper-reportedAuthor's model

MolAS

Physically valid protein–ligand pose selection

Reported score
36.69%
Metric
RMSD ≤1 Å and PB-valid success
Dataset / split
PoseBusters

Averaged five-fold algorithm-selection performance on PoseBusters; joint RMSD and validity criterion.

Table 3, PoseBusters / Mixed / AutoDock row, MolAS success columnVerify at source →
Paper-reportedIndependent paper evaluation

Single best solver

Physically valid protein–ligand pose selection

Reported score
34.34%
Metric
RMSD ≤1 Å and PB-valid success
Dataset / split
PoseBusters

Single best solver baseline under the same averaged five-fold selection test.

Table 3, PoseBusters / Mixed / AutoDock row, SBS success columnVerify at source →