CCPL: Cross-modal Contrastive Protein Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zheng, Jiangbin, Li, Stan Z.
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909303708844032
author Zheng, Jiangbin
Li, Stan Z.
author_facet Zheng, Jiangbin
Li, Stan Z.
contents Effective protein representation learning is crucial for predicting protein functions. Traditional methods often pretrain protein language models on large, unlabeled amino acid sequences, followed by finetuning on labeled data. While effective, these methods underutilize the potential of protein structures, which are vital for function determination. Common structural representation techniques rely heavily on annotated data, limiting their generalizability. Moreover, structural pretraining methods, similar to natural language pretraining, can distort actual protein structures. In this work, we introduce a novel unsupervised protein structure representation pretraining method, cross-modal contrastive protein learning (CCPL). CCPL leverages a robust protein language model and uses unsupervised contrastive alignment to enhance structure learning, incorporating self-supervised structural constraints to maintain intrinsic structural information. We evaluated our model across various benchmarks, demonstrating the framework's superiority.
format Preprint
id arxiv_https___arxiv_org_abs_2303_11783
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CCPL: Cross-modal Contrastive Protein Learning
Zheng, Jiangbin
Li, Stan Z.
Biomolecules
Artificial Intelligence
Machine Learning
Effective protein representation learning is crucial for predicting protein functions. Traditional methods often pretrain protein language models on large, unlabeled amino acid sequences, followed by finetuning on labeled data. While effective, these methods underutilize the potential of protein structures, which are vital for function determination. Common structural representation techniques rely heavily on annotated data, limiting their generalizability. Moreover, structural pretraining methods, similar to natural language pretraining, can distort actual protein structures. In this work, we introduce a novel unsupervised protein structure representation pretraining method, cross-modal contrastive protein learning (CCPL). CCPL leverages a robust protein language model and uses unsupervised contrastive alignment to enhance structure learning, incorporating self-supervised structural constraints to maintain intrinsic structural information. We evaluated our model across various benchmarks, demonstrating the framework's superiority.
title CCPL: Cross-modal Contrastive Protein Learning
topic Biomolecules
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2303.11783