A biological-response compound representation allows chemical perturbation prediction across cell lines
- 1Universite de Montreal
Abstract
Accurately predicting cellular responses to drugs remains a challenge with the potential to reduce experimental screening costs and accelerate drug discovery. Current computational approaches represent compounds through chemical structures, which carry little information regarding their activity within biological systems. We show that gene expression responses, measured in a reference cell line, can instead serve as transferable representations of chemical perturbations. The proposed framework, BioPert, uses biological representations with a small neural network to predict transcriptional delta responses in cell lines of different lineages. Across the Tahoe-100M and LINCS L1000 datasets, BioPert outperforms molecular fingerprints and embeddings learned from chemical structure, which provide limited improvements over random controls. BioPert's prediction correlations reach 0.79 on Tahoe-100M, corresponding to an improvement of 0.34 over the next-best representation. On LINCS, performance varies with the experimental reproducibility of the test conditions, highlighting the impact of batch effects. Notably, BioPert considerably surpasses predictions obtained by copying the reference response, demonstrating that it captures context-dependent effects. Further analysis of a C32-cobimetinib case shows pathway-level accuracy of the predictions, including when the reference and target responses differ. These results open a new path for chemical perturbation prediction and could ultimately reduce the burden of phenotypic screening.
Related
- The recoverable resolution of cellular perturbation-response prediction
- scDisentangle: sequential disentanglement for single-cell perturbation response prediction
- Generalizable single-cell perturbation response prediction using energy-guided flow matching
- Response representation shapes AlphaGenome enhancer-gene prediction in human astrocytes
- SHERLOCK: Structured representation learning and causal inference of downstream perturbation effects
BibTeX
@misc{breton2026biologicalresponse,
title = {{A biological-response compound representation allows chemical perturbation prediction across cell lines}},
author = {L. Le Breton and L. Kaufmann and E. Carraz-Billat and Q. Fournier and S. Lemieux},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.28.755146},
url = {https://www.biorxiv.org/content/10.64898/2026.09.28.755146v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - A biological-response compound representation allows chemical perturbation prediction across cell lines
AU - L. Le Breton
AU - L. Kaufmann
AU - E. Carraz-Billat
AU - Q. Fournier
AU - S. Lemieux
PY - 2026
DA - 2026/09/28
PB - bioRxiv
DO - 10.64898/2026.09.28.755146
UR - https://www.biorxiv.org/content/10.64898/2026.09.28.755146v1
AB - Accurately predicting cellular responses to drugs remains a challenge with the potential to reduce experimental screening costs and accelerate drug discovery. Current computational approaches represent compounds through chemical structures, which carry little information regarding their activity within biological systems. We show that gene expression responses, measured in a reference cell line, can instead serve as transferable representations of chemical perturbations. The proposed framework, BioPert, uses biological representations with a small neural network to predict transcriptional delta responses in cell lines of different lineages. Across the Tahoe-100M and LINCS L1000 datasets, BioPert outperforms molecular fingerprints and embeddings learned from chemical structure, which provide limited improvements over random controls. BioPert's prediction correlations reach 0.79 on Tahoe-100M, corresponding to an improvement of 0.34 over the next-best representation. On LINCS, performance varies with the experimental reproducibility of the test conditions, highlighting the impact of batch effects. Notably, BioPert considerably surpasses predictions obtained by copying the reference response, demonstrating that it captures context-dependent effects. Further analysis of a C32-cobimetinib case shows pathway-level accuracy of the predictions, including when the reference and target responses differ. These results open a new path for chemical perturbation prediction and could ultimately reduce the burden of phenotypic screening.
ER -