Causal Cellular Context Transfer Learning (C3TL): An Efficient Architecture for Prediction of Unseen Perturbation Effects

TL;DR

This paper introduces a lightweight, efficient architecture for predicting the effects of unseen perturbations on cell states, using minimal data and computational resources, making causal learning more accessible in biomedical research.

Contribution

The authors propose a novel, resource-efficient framework that generalizes perturbation effect predictions to new contexts using structured biological information and simple data, outperforming large models in practicality.

Findings

Accurately predicts unseen perturbation effects in new contexts.

Requires smaller models and less data than state-of-the-art approaches.

Demonstrates competitive performance with reduced computational resources.

Abstract

Predicting the effects of chemical and genetic perturbations on quantitative cell states is a central challenge in computational biology, molecular medicine and drug discovery. Recent work has leveraged large-scale single-cell data and massive foundation models to address this task. However, such computational resources and extensive datasets are not always accessible in academic or clinical settings, hence limiting utility. Here we propose a lightweight framework for perturbation effect prediction that exploits the structured nature of biological interventions and specific inductive biases/invariances. Our approach leverages available information concerning perturbation effects to allow generalization to novel contexts and requires only widely-available bulk molecular data. Extensive testing, comparing predictions of context-specific perturbation effects against real, large-scale interventional experiments, demonstrates accurate prediction in new contexts. The proposed approach is competitive with SOTA foundation models but requires simpler data, much smaller model sizes and less time. Focusing on robust bulk signals and efficient architectures, we show that accurate prediction of perturbation effects is possible without proprietary hardware or very large models, hence opening up ways to leverage causal learning approaches in biomedicine generally.