Cross-modal representation alignment of molecular structure and perturbation-induced transcriptional profiles

TL;DR

This paper introduces a novel cross-modal retrieval task linking molecular structures with transcriptional profiles, using a deep learning approach to improve understanding of molecule-gene expression relationships for drug discovery.

Contribution

It proposes a new multi-view alignment task and a deep learning method to jointly learn chemical and transcriptional representations, highlighting the impact of cell line variability.

Findings

Cell line variability significantly affects model performance.

The proposed approach establishes the feasibility of cross-modal molecular-transcriptional alignment.

Benchmark results compare favorably against baseline models.

Abstract

Modeling the relationship between chemical structure and molecular activity is a key goal in drug development. Many benchmark tasks have been proposed for molecular property prediction, but these tasks are generally aimed at specific, isolated biomedical properties. In this work, we propose a new cross-modal small molecule retrieval task, designed to force a model to learn to associate the structure of a small molecule with the transcriptional change it induces. We develop this task formally as multi-view alignment problem, and present a coordinated deep learning approach that jointly optimizes representations of both chemical structure and perturbational gene expression profiles. We benchmark our results against oracle models and principled baselines, and find that cell line variability markedly influences performance in this domain. Our work establishes the feasibility of this new task, elucidates the limitations of current data and systems, and may serve to catalyze future research in small molecule representation learning.