Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gao, Bowen, Jia, Yinjun, Mo, Yuanle, Ni, Yuyan, Ma, Weiying, Ma, Zhiming, Lan, Yanyan
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2310.07229
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911790677360640
author Gao, Bowen
Jia, Yinjun
Mo, Yuanle
Ni, Yuyan
Ma, Weiying
Ma, Zhiming
Lan, Yanyan
author_facet Gao, Bowen
Jia, Yinjun
Mo, Yuanle
Ni, Yuyan
Ma, Weiying
Ma, Zhiming
Lan, Yanyan
contents Pocket representations play a vital role in various biomedical applications, such as druggability estimation, ligand affinity prediction, and de novo drug design. While existing geometric features and pretrained representations have demonstrated promising results, they usually treat pockets independent of ligands, neglecting the fundamental interactions between them. However, the limited pocket-ligand complex structures available in the PDB database (less than 100 thousand non-redundant pairs) hampers large-scale pretraining endeavors for interaction modeling. To address this constraint, we propose a novel pocket pretraining approach that leverages knowledge from high-resolution atomic protein structures, assisted by highly effective pretrained small molecule representations. By segmenting protein structures into drug-like fragments and their corresponding pockets, we obtain a reasonable simulation of ligand-receptor interactions, resulting in the generation of over 5 million complexes. Subsequently, the pocket encoder is trained in a contrastive manner to align with the representation of pseudo-ligand furnished by some pretrained small molecule encoders. Our method, named ProFSA, achieves state-of-the-art performance across various tasks, including pocket druggability prediction, pocket matching, and ligand binding affinity prediction. Notably, ProFSA surpasses other pretraining methods by a substantial margin. Moreover, our work opens up a new avenue for mitigating the scarcity of protein-ligand complex data through the utilization of high-quality and diverse protein structure databases.
format Preprint
id arxiv_https___arxiv_org_abs_2310_07229
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ProFSA: Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment
Gao, Bowen
Jia, Yinjun
Mo, Yuanle
Ni, Yuyan
Ma, Weiying
Ma, Zhiming
Lan, Yanyan
Machine Learning
Pocket representations play a vital role in various biomedical applications, such as druggability estimation, ligand affinity prediction, and de novo drug design. While existing geometric features and pretrained representations have demonstrated promising results, they usually treat pockets independent of ligands, neglecting the fundamental interactions between them. However, the limited pocket-ligand complex structures available in the PDB database (less than 100 thousand non-redundant pairs) hampers large-scale pretraining endeavors for interaction modeling. To address this constraint, we propose a novel pocket pretraining approach that leverages knowledge from high-resolution atomic protein structures, assisted by highly effective pretrained small molecule representations. By segmenting protein structures into drug-like fragments and their corresponding pockets, we obtain a reasonable simulation of ligand-receptor interactions, resulting in the generation of over 5 million complexes. Subsequently, the pocket encoder is trained in a contrastive manner to align with the representation of pseudo-ligand furnished by some pretrained small molecule encoders. Our method, named ProFSA, achieves state-of-the-art performance across various tasks, including pocket druggability prediction, pocket matching, and ligand binding affinity prediction. Notably, ProFSA surpasses other pretraining methods by a substantial margin. Moreover, our work opens up a new avenue for mitigating the scarcity of protein-ligand complex data through the utilization of high-quality and diverse protein structure databases.
title ProFSA: Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment
topic Machine Learning
url https://arxiv.org/abs/2310.07229