Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional Responses
This work addresses the challenge of phenotypic drug discovery by improving the ability to predict cellular responses to perturbations, though it appears incremental as it builds on existing representation learning approaches.
The paper tackled the problem of learning transferable drug perturbation representations from single-cell transcriptional responses by proposing XTransferCDR, a generative framework for feature decoupling and cross-domain representation learning, which achieved better performance than state-of-the-art methods in evaluations on multiple datasets.
Phenotypic drug discovery has attracted widespread attention because of its potential to identify bioactive molecules. Transcriptomic profiling provides a comprehensive reflection of phenotypic changes in cellular responses to external perturbations. In this paper, we propose XTransferCDR, a novel generative framework designed for feature decoupling and transferable representation learning across domains. Given a pair of perturbed expression profiles, our approach decouples the perturbation representations from basal states through domain separation encoders and then cross-transfers them in the latent space. The transferred representations are then used to reconstruct the corresponding perturbed expression profiles via a shared decoder. This cross-transfer constraint effectively promotes the learning of transferable drug perturbation representations. We conducted extensive evaluations of our model on multiple datasets, including single-cell transcriptional responses to drugs and single- and combinatorial genetic perturbations. The experimental results show that XTransferCDR achieved better performance than current state-of-the-art methods, showcasing its potential to advance phenotypic drug discovery.