AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhu, Wenyu, Wang, Jianhui, Gao, Bowen, Jia, Yinjun, Tan, Haichuan, Zhang, Ya-Qin, Ma, Wei-Ying, Lan, Yanyan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911239966294016
author Zhu, Wenyu
Wang, Jianhui
Gao, Bowen
Jia, Yinjun
Tan, Haichuan
Zhang, Ya-Qin
Ma, Wei-Ying
Lan, Yanyan
author_facet Zhu, Wenyu
Wang, Jianhui
Gao, Bowen
Jia, Yinjun
Tan, Haichuan
Zhang, Ya-Qin
Ma, Wei-Ying
Lan, Yanyan
contents Virtual screening (VS) is a critical component of modern drug discovery, yet most existing methods--whether physics-based or deep learning-based--are developed around holo protein structures with known ligand-bound pockets. Consequently, their performance degrades significantly on apo or predicted structures such as those from AlphaFold2, which are more representative of real-world early-stage drug discovery, where pocket information is often missing. In this paper, we introduce an alignment-and-aggregation framework to enable accurate virtual screening under structural uncertainty. Our method comprises two core components: (1) a tri-modal contrastive learning module that aligns representations of the ligand, the holo pocket, and cavities detected from structures, thereby enhancing robustness to pocket localization error; and (2) a cross-attention based adapter for dynamically aggregating candidate binding sites, enabling the model to learn from activity data even without precise pocket annotations. We evaluated our method on a newly curated benchmark of apo structures, where it significantly outperforms state-of-the-art methods in blind apo setting, improving the early enrichment factor (EF1%) from 11.75 to 37.19. Notably, it also maintains strong performance on holo structures. These results demonstrate the promise of our approach in advancing first-in-class drug discovery, particularly in scenarios lacking experimentally resolved protein-ligand complexes. Our implementation is publicly available at https://github.com/Wiley-Z/AANet.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05768
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation
Zhu, Wenyu
Wang, Jianhui
Gao, Bowen
Jia, Yinjun
Tan, Haichuan
Zhang, Ya-Qin
Ma, Wei-Ying
Lan, Yanyan
Machine Learning
Biomolecules
Virtual screening (VS) is a critical component of modern drug discovery, yet most existing methods--whether physics-based or deep learning-based--are developed around holo protein structures with known ligand-bound pockets. Consequently, their performance degrades significantly on apo or predicted structures such as those from AlphaFold2, which are more representative of real-world early-stage drug discovery, where pocket information is often missing. In this paper, we introduce an alignment-and-aggregation framework to enable accurate virtual screening under structural uncertainty. Our method comprises two core components: (1) a tri-modal contrastive learning module that aligns representations of the ligand, the holo pocket, and cavities detected from structures, thereby enhancing robustness to pocket localization error; and (2) a cross-attention based adapter for dynamically aggregating candidate binding sites, enabling the model to learn from activity data even without precise pocket annotations. We evaluated our method on a newly curated benchmark of apo structures, where it significantly outperforms state-of-the-art methods in blind apo setting, improving the early enrichment factor (EF1%) from 11.75 to 37.19. Notably, it also maintains strong performance on holo structures. These results demonstrate the promise of our approach in advancing first-in-class drug discovery, particularly in scenarios lacking experimentally resolved protein-ligand complexes. Our implementation is publicly available at https://github.com/Wiley-Z/AANet.
title AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation
topic Machine Learning
Biomolecules
url https://arxiv.org/abs/2506.05768