CloneOT predicts cell clone responses to drug treatment accurately
CloneOT: predicting clone-specific perturbation responses with lineage-supervised neural inverse optimal transport
Machine Learning
Summary
Predicting how individual groups of cells respond to treatments is hard when we only have measurements before and after the drug, but not direct matches between cells. The authors propose CloneOT, which uses lineage information (barcodes tracking cell families) to learn how cells change specifically within each clone after treatment. Their method improves predictions by learning the best way to connect cells before and after the perturbation, unlike older methods using fixed distance measures. CloneOT helps reveal how certain cell groups survive drugs and predicts their future behavior.
What this means in practice
- •For cancer research teams: Identify how specific cancer cell clones respond to drug treatments to improve therapy design using measured pre- and post-treatment data.
- •For pharmaceutical data scientists: Improve modeling of drug effects on cell populations by integrating lineage barcodes with perturbation data for more precise predictions.
Authors
Yanshuo Chen, Wei Chen, Heng Huang
Abstract
Predicting single-cell perturbation responses requires mapping between two unpaired populations of cells measured before and after the perturbation. Optimal transport (OT) provides a principled framework for constructing such mappings by minimizing the transport cost, and neural OT methods (\textit{e.g.}, CellOT) have been employed for this prediction task. However, these methods rely on a fixed transport cost, typically the squared Euclidean distance. This cost may connect cells with the wrong responses. Lineage tracing provides the information needed to learn the cost, as heritable barcodes link the cells of the same clone before and after the perturbation. Here, we propose \CloneOT, a neural inverse OT method that learns both the transport cost and the transport map from partially lineage-traced single-cell datasets. \CloneOT\ represents the cost as a neural network. It learns the cost by minimizing the extra cost that the lineage adds to the optimal transport, so that the cheapest transport keeps the cells of each clone together. Our experiments demonstrate that \CloneOT\ recovers the correct transport on 2D datasets, while the squared Euclidean cost fails. Moreover, \CloneOT\ outperforms five baselines on 14 lineage-tracing perturbation scenarios of cancer cells, for both seen and unseen clones. Furthermore, we show that \CloneOT\ reveals the clone-specific transcriptional programs of drug-tolerant persister cells and forecasts the fate of each clone from its cells before treatment. Our implementation is available at https://github.com/poseidonchan/CloneOT.