Metraipolis › archive › dc_e28720e1b9ee
Adapting Boltz-2 with limited experimental activity data improves early enrichment in virtual screening — arXiv:2609.24302
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24302
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T07:08:45.575Z
- SHA-256 of the archived text
a975928dbe516011439687801823f87151301c078ec951f2666e7b4b5763a6b9- Stable URL of this page
https://metraipolis.com/documento/dc_e28720e1b9ee
How to cite
Adapting Boltz-2 with limited experimental activity data improves early enrichment in virtual screening — arXiv:2609.24302 — arXiv (en), https://arxiv.org/abs/2609.24302 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e28720e1b9ee (Metraipolis archive dc_e28720e1b9ee, sha256 a975928dbe516011439687801823f87151301c078ec951f2666e7b4b5763a6b9)
BibTeX
@misc{dce28720e1b9ee,
title = {Adapting Boltz-2 with limited experimental activity data improves early enrichment in virtual screening — arXiv:2609.24302},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24302},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e28720e1b9ee; sha256 a975928dbe516011439687801823f87151301c078ec951f2666e7b4b5763a6b9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24302. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Virtual screening aims to prioritize active compounds from large chemical libraries within a limited experimental budget. When applying Boltz-2 to virtual screening, a key challenge is how to use limited experimental data from the target assay to improve the prioritization of active compounds. We investigated whether fine-tuning the Boltz-2 affinity heads with a small number of binary activity labels could improve early enrichment of active compounds in hit discovery. We compared fine-tuning with 40-300 labels in a retrospective evaluation on eight MF-PCBA targets. With 300 activity measurements, fine-tuning increased the number of actives in the top 1% by a geometric mean of 1.77-fold across the eight targets and improved average precision (AP) by 2.14-fold relative to the control without fine-tuning. We also investigated whether rescoring a subset of candidates could retain the improvement in hit recovery by reranking only the top-ranked Boltz-2 candidates with the fine-tuned head. Restricting rescoring to approximately 10% of the evaluation set retained hit recovery comparable to full rescoring. These findings show that affinity-head fine-tuning with limited activity labels improves early enrichment with Boltz-2 and that this benefit can be retained when rescoring a restricted set of candidates. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG). Categorie arXiv: Biomolecules (q-bio.BM) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Quantitative Methods (q-bio.QM). Pagina del lavoro: https://arxiv.org/abs/2609.24302 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:58:09.637Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).