Modeling Cell-Cycle-Aware Single-Cell Drug Perturbation Responses

2026-06-28

AI Summary

Existing single-cell drug perturbation models struggle to accurately predict the effects of drugs on cell cycle phase transitions, as they typically treat the cell cycle as a nuisance factor rather than explicitly modeling it. This work proposes scCycleMol, a novel framework that infers cell cycle supervision signals from post-treatment gene expression profiles in the SciPlex3 dataset. By reframing cell cycle state as a learnable output target instead of an input covariate, scCycleMol establishes a closed-loop supervision mechanism. Integrating molecular representations, pretraining strategies, circular modeling of G1/S/G2M phases, and a conditional perturbation architecture, the method achieves state-of-the-art performance across over 600,000 cells, yielding an R² of 0.9093 for all genes, 0.6843 for differentially expressed genes, and a phase classification accuracy of 0.9609—significantly outperforming baselines such as ChemCPA.

Abstract

Single-cell drug perturbation models should predict not only transcriptional response magnitude, but also whether a treatment alters the proliferative state of a cell. This is challenging because cell-cycle variation is often treated as nuisance variation, and benchmark pipelines rarely treat drug-induced phase changes as a primary prediction target. We introduce scCycleMol, a cell-cycle-aware perturbation prediction framework built on a curated 24-hour SciPlex3 benchmark with standardized molecule identities, dose and cell-line metadata, and gene expression with cell-cycle supervision derived from treated states. Instead of using cell-cycle state as an input covariate, scCycleMol derives supervision from predicted treated expression and propagates it through a learnable full-expression cell-cycle head with circular G1/S/G2M phase targets. We evaluate marker-based supervision, molecular representations, and pretraining strategies to isolate sources of improvement. Across a SciPlex3 benchmark with over 600k cells, 186 perturbation conditions, multiple cancer cell lines, and thousands of genes, scCycleMol improves out-of-distribution expression prediction compared with conditional perturbation baselines. The best LINCS-pretrained circular model achieves 0.9093 expected all-gene r squared and 0.6843 expected differentially expressed gene r squared, compared with 0.6800 and 0.5400 for LINCS-pretrained ChemCPA. Closed-loop cell-cycle supervision improves phase accuracy by about 0.5 to 0.6 points while maintaining nearly unchanged expression prediction. A Tahoe-pretrained variant reaches 0.9609 phase accuracy, highlighting the benefit of explicit cell-cycle-aware supervision in perturbation modeling.

Problem

• single-cell drug perturbation
• cell-cycle state
• proliferative state
• transcriptional response
• phase prediction

Innovation

• cell-cycle-aware modeling
• single-cell perturbation prediction
• closed-loop cell-cycle supervision
• circular phase representation
• out-of-distribution generalization