Targeting protein-ligand neosurfaces using a generalizable deep learning approach
Source check: Needs source check. Not independent scientific confirmation.
Finding: Targeting protein-ligand neosurfaces using a generalizable deep learning approach. Fingerprints trained on proteins were applied to protein-ligand neosurfaces to design binders. Binders were experimentally validated against three drug-bound protein complexes. Evidence limits: Preprint; affinities, failure rates and peer review not assessed (later journal version not checked). Reviewed from Europe PMC abstract only.
Technology: Surface-fingerprint deep learning on learned molecular surface representations
Publication: Preprint · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- Fingerprints trained on proteins were applied to protein-ligand neosurfaces to design binders.
- Test and result
- Binders were experimentally validated against three drug-bound protein complexes.
- Limitation / still unknown
- Preprint; affinities, failure rates and peer review not assessed (later journal version not checked).
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://europepmc.org/article/PPR/PPR828881
Needs source check · editorial details
The source has not been fully checked or contains conflicting information. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review scope and date are not recorded; source checked does not establish full-text review.
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.