Adapting differential molecular representation with hierarchical prompts for multi-label property prediction

Abstract Accurate prediction of molecular properties is crucial in drug discovery. Traditional methods often overlook that real-world molecules typically exhibit multiple property labels with complex correlations. To this end, we propose a novel framework, HiPM, which stands for Hierarchical Prompte...

Full description

Saved in:
Bibliographic Details
Published in:Briefings in bioinformatics 2024-07, Vol.25 (5)
Main Authors: Kang, Linjia, Zhou, Songhua, Fang, Shuyan, Liu, Shichao
Format: Article
Language:English
Subjects:
Algorithms
Cluster Analysis
Clustering
Computational Biology - methods
Drug Discovery - methods
Information processing
Labels
Learning
Machine Learning
Message passing
Molecular properties
Predictions
Problem Solving Protocol
Representations
Task complexity
Transfer learning
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract Accurate prediction of molecular properties is crucial in drug discovery. Traditional methods often overlook that real-world molecules typically exhibit multiple property labels with complex correlations. To this end, we propose a novel framework, HiPM, which stands for Hierarchical Prompted Molecular representation learning framework. HiPM leverages task-aware prompts to enhance the differential expression of tasks in molecular representations and mitigate negative transfer caused by conflicts in individual task information. Our framework comprises two core components: the Molecular Representation Encoder (MRE) and the Task-Aware Prompter (TAP). MRE employs a hierarchical message-passing network architecture to capture molecular features at both the atom and motif levels. Meanwhile, TAP utilizes agglomerative hierarchical clustering algorithm to construct a prompt tree that reflects task affinity and distinctiveness, enabling the model to consider multi-granular correlation information among tasks, thereby effectively handling the complexity of multi-label property prediction. Extensive experiments demonstrate that HiPM achieves state-of-the-art performance across various multi-label datasets, offering a novel perspective on multi-label molecular representation learning.
ISSN:1467-5463
1477-4054
1477-4054
DOI:10.1093/bib/bbae438