Adapting Boltz-2 with limited experimental activity data improves early enrichment in virtual screening
Abstract
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.
Related
- Discovery of Novel HDAC8 Inhibitors Through Shape-Based Virtual Screening: Experimental Validation and Characterization of a Promising Quinoline-Based Hit Scaffold
- Experimental validation of computationally prioritized bisphosphonates reveals no direct in vitro antiviral activity against SARS-CoV-2
- Dichloroacetate Improves Animal Survival, Growth, Neuromuscular Activity, Mitochondrial Stress and Physiology, and Elevated Lactate in C. elegans pdha-1 and dld-1 RNAi Models of Pyruvate Dehydrogenase Complex Deficiency (PDCD).
- An activity‑based high‑throughput screening platform for identifying functional modulators of OFF‑type riboswitches
- Ceranib-2 potentiates cisplatin activity under an experimental in vitro hipec-like model by inducing integrated stress and cell death pathways in ovarian cancer
BibTeX
@misc{furui2026adapting,
title = {{Adapting Boltz-2 with limited experimental activity data improves early enrichment in virtual screening}},
author = {Kairi Furui and Masahito Ohue},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.24302},
eprint = {2609.24302},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.24302},
}
RIS
TY - UNPB
TI - Adapting Boltz-2 with limited experimental activity data improves early enrichment in virtual screening
AU - Kairi Furui
AU - Masahito Ohue
PY - 2026
DA - 2026/09/21
PB - arXiv
DO - 10.48550/arxiv.2609.24302
UR - https://arxiv.org/abs/2609.24302
AB - 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.
ER -