MolFeSCue: Enhancing Molecular Property Prediction in Data-Limited and Imbalanced Contexts using Few-Shot and Contrastive Learning

Fengfeng Zhou

Abstract:

Motivation: Predicting molecular properties is a pivotal task in various scientific domains, including drug
discovery, material science, and computational chemistry. This problem is often hindered by the lack
of annotated data and imbalanced class distributions, which pose significant challenges in developing
accurate and robust predictive models.
Results: This study tackles these issues by employing pre-trained molecular models within a few-shot
learning framework. A novel dynamic contrastive loss function is utilized to further improve model
performance in the situation of class imbalance. The proposed MolFeSCue framework not only
facilitates rapid generalization from minimal samples, but also employs a contrastive loss function to
extract meaningful molecular representations from imbalanced datasets. Extensive evaluations and
comparisons of MolFeSCue and state-of-the-art algorithms have been conducted on multiple
benchmark datasets, and the experimental data demonstrate our algorithm’s effectiveness in molecular
representations and its broad applicability across various pre-trained models. Our findings underscore
MolFeSCue’s potential to accelerate advancements in drug discovery.
Contacts: Fengfeng Zhou ([e-mail]) and Kewei Li ([e-mail]).
Availability: We have made all the source code utilized in this study publicly accessible via GitHub at
http://www.healthinformaticslab.org/supp/ or https://github.com/zhangruochi/MolFeSCue .