# A multi-task domain-adapted model to predict chemotherapy response from mutations in recurrently altered cancer genes

## TL;DR

This paper introduces DruID, a machine learning model that predicts chemotherapy response using limited genetic data from clinical-grade sequencing.

## Contribution

The novel contribution is a deep learning model for drug response prediction using restricted gene sets and clinical-grade sequencing data.

## Key findings

- Existing drug response prediction models perform similarly with whole-exome and clinical-grade NGS data.
- DruID outperforms state-of-the-art methods in predicting chemotherapy response using sparse mutation data.
- DruID demonstrates robust performance on real-world clinical datasets for pan-cancer and site-specific cases.

## Abstract

Next-generation sequencing (NGS) is increasingly utilized in oncological practice; however, only a minority of patients benefit from targeted therapy. Developing drug response prediction (DRP) models is important for the “untargetable” majority. Prior DRP models typically use whole-transcriptome and whole-exome sequencing data, which are clinically unavailable. We aim to develop a DRP model toward the repurposing of chemotherapy, requiring only information from clinical-grade NGS (cNGS) panels of restricted gene sets. Data sparsity and limited patient drug response information make this challenging. We firstly show that existing DRPs perform equally with whole-exome versus cNGS (∼300 genes) data. Drug IDentifier (DruID) is then described, a DRP model for restricted gene sets using transfer learning, variant annotations, domain-invariant representation learning, and multi-task learning. DruID outperformed state-of-the-art DRP methods on pan-cancer data and showed robust response classification on two real-world clinical datasets, representing a step toward a clinically applicable DRP tool.

•Clinical-grade next-generation sequencing as predictive as whole-genome sequencing•Deep learning model, DruID, utilizes sparse mutation data with variant annotation•Unsupervised domain adaptation, multi-task learning used for limited labeled data•DruID improves patient response prediction in pan-cancer and site-specific datasets

Clinical-grade next-generation sequencing as predictive as whole-genome sequencing

Deep learning model, DruID, utilizes sparse mutation data with variant annotation

Unsupervised domain adaptation, multi-task learning used for limited labeled data

DruID improves patient response prediction in pan-cancer and site-specific datasets

Biocomputational method; Genomic analysis; Pharmacoinformatics; Cancer; Machine learning