Cross-modal representation alignment of molecular structure and perturbation-induced transcriptional profiles
This work addresses a key challenge in drug development by enabling better modeling of molecular activity, though it is incremental as it builds on existing representation learning methods.
The paper tackled the problem of associating chemical structures with transcriptional changes by proposing a cross-modal small molecule retrieval task, finding that cell line variability significantly affects performance.
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.