Zero-shot Learning of Drug Response Prediction for Preclinical Drug Screening

TL;DR

This paper introduces a zero-shot learning approach for drug response prediction that enables models to predict responses for novel compounds without labeled data, improving preclinical drug screening efficiency.

Contribution

The paper presents MSDA, a novel domain adaptation plug-in that enhances existing DRP models to predict responses for unseen drugs using invariant features from similar drugs.

Findings

Achieved 5-10% performance improvement on GDSCv2 and CellMiner datasets.

MSDA effectively predicts responses for novel compounds.

Enhances drug discovery process efficiency.

Abstract

Conventional deep learning methods typically employ supervised learning for drug response prediction (DRP). This entails dependence on labeled response data from drugs for model training. However, practical applications in the preclinical drug screening phase demand that DRP models predict responses for novel compounds, often with unknown drug responses. This presents a challenge, rendering supervised deep learning methods unsuitable for such scenarios. In this paper, we propose a zero-shot learning solution for the DRP task in preclinical drug screening. Specifically, we propose a Multi-branch Multi-Source Domain Adaptation Test Enhancement Plug-in, called MSDA. MSDA can be seamlessly integrated with conventional DRP methods, learning invariant features from the prior response data of similar drugs to enhance real-time predictions of unlabeled compounds. We conducted experiments using the GDSCv2 and CellMiner datasets. The results demonstrate that MSDA efficiently predicts drug responses for novel compounds, leading to a general performance improvement of 5-10\% in the preclinical drug screening phase. The significance of this solution resides in its potential to accelerate the drug discovery process, improve drug candidate assessment, and facilitate the success of drug discovery.