Contextual Representation Anchor Network to Alleviate Selection Bias in Few-Shot Drug Discovery

TL;DR

This paper introduces CRA, a novel method that uses contextual anchors and dual-augmentation to improve few-shot molecular property prediction by addressing sample selection bias, achieving better performance and generalization.

Contribution

CRA is a new approach that incorporates contextual representation anchors and dual-augmentation to mitigate selection bias in few-shot drug discovery tasks.

Findings

CRA outperforms state-of-the-art methods on MoleculeNet and FS-Mol benchmarks.

CRA achieves 2.60% and 3.28% improvements in AUC and ΔAUC-PR metrics.

CRA demonstrates superior generalization in domain transfer experiments.

Abstract

In the drug discovery process, the low success rate of drug candidate screening often leads to insufficient labeled data, causing the few-shot learning problem in molecular property prediction. Existing methods for few-shot molecular property prediction overlook the sample selection bias, which arises from non-random sample selection in chemical experiments. This bias in data representativeness leads to suboptimal performance. To overcome this challenge, we present a novel method named contextual representation anchor Network (CRA), where an anchor refers to a cluster center of the representations of molecules and serves as a bridge to transfer enriched contextual knowledge into molecular representations and enhance their expressiveness. CRA introduces a dual-augmentation mechanism that includes context augmentation, which dynamically retrieves analogous unlabeled molecules and captures their task-specific contextual knowledge to enhance the anchors, and anchor augmentation, which leverages the anchors to augment the molecular representations. We evaluate our approach on the MoleculeNet and FS-Mol benchmarks, as well as in domain transfer experiments. The results demonstrate that CRA outperforms the state-of-the-art by 2.60% and 3.28% in AUC and $\Delta$AUC-PR metrics, respectively, and exhibits superior generalization capabilities.