ACF：面向 Apo 结构隐式口袋检测的可审计代数计数场

View PDF HTML (experimental)

Abstract:Cryptic ligand-binding pockets are not apparent in experimentally determined apo structures, making them difficult to identify from unbound receptor geometry. A complementary challenge is to make the structural measurements and learned evidence behind each prediction directly inspectable. We introduce a supervised algebraic counting field (ACF) for predicting cryptic-pocket residues from apo structures. ACF compiles explicit geometric, physicochemical, and topological features into compact, integer-weighted lookup tables. Each prediction score can be reconstructed from feature values, training counts, table weights, and spatial aggregation, without sequence search, structural-template transfer, or a protein language model at inference. We evaluate ACF on CryptoBench and two locked external collections, separating ranking performance from the effects of residue-calling budgets. On an external set of 57 post-CryptoBench apo-holo units, ACF exceeded P2Rank by +0.044 in mean paired ROC-AUC (multiplicity-adjusted 95% CI [+0.010, +0.079]). The advantage was dataset-dependent: official-fold ROC-AUC and matched-budget F1 differences against P2Rank remained unresolved, and a second external evaluation did not confirm gains from added structural features. ACF thus provides a compact predictor with externally validated signal and an inspectable path from structural measurements and training counts to residue scores.

Comments:	Accepted for publication in Pacific Symposium on Biocomputing (PSB) 2027
Subjects:	Machine Learning (cs.LG); Biomolecules (q-bio.BM)
Cite as:	arXiv:2610.00988 [cs.LG]
	(or arXiv:2610.00988v1 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2610.00988 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xuening Wu [view email]
[v1] Thu, 1 Oct 2026 03:22:43 UTC (1,513 KB)