Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional Responses

Hui Liu, Shikai JinAAAI 2025 · DOI

Introduction

Predicting how individual cells respond to chemical or genetic perturbations is a cornerstone of modern drug discovery. While single-cell RNA sequencing (scRNA-seq) provides high-resolution insights into these responses, the sheer number of possible drug-cell combinations makes exhaustive laboratory testing impossible. Existing computational models often struggle to generalize across different cell types or to entirely new drugs. The primary challenge lies in disentanglement—effectively separating a cell's inherent basal state from the specific effect of a perturbation so they can be recombined to predict new outcomes.

The XTransferCDR Framework

To address these challenges, we present XTransferCDR, a generative framework designed to learn highly transferable representations of drug effects. The model utilizes a cross-domain autoencoder architecture that decouples cellular identity from perturbation effects.

The XTransferCDR architecture featuring dual encoders, a cross-transfer module, and a shared decoder.

The workflow is built upon four pillars:

  1. Dual Encoders: Separate encoders ($E_s$ and $E_p$) extract the cell's basal state (identity) and the perturbation embedding (drug effect), respectively.
  2. Feature Decoupling: An orthogonality constraint ensures that the drug-specific vector remains mathematically independent of the cell-identity vector.
  3. Cross-Transfer Module: This core innovation involves "swapping" perturbation embeddings between different samples during training. By adding the effect of Drug A to the basal state of a cell treated with Drug B, the model is forced to learn universal, context-independent representations.
  4. Shared Decoder: A single decoder ($D$) reconstructs the final gene expression profile from these combined latent vectors, assuming linear additivity in the latent space.

Experimental Results

XTransferCDR was rigorously evaluated on large-scale benchmarks, including the sci-Plex3 and sci-Plex4 datasets, as well as CRISPR-based single and combinatorial genetic perturbation data.

The model consistently outperformed state-of-the-art methods such as CPA and ChemCPA. On the sci-Plex3 dataset, it achieved a mean $R^2$ of 0.81 for all genes and 0.62 for differentially expressed genes (DEGs). Notably, the model demonstrated exceptional generalization capabilities; on the sci-Plex4 "unseen drug" test, it maintained a high Pearson Correlation Coefficient (PCC) of 0.932, showing it can accurately predict the effects of drugs it has never encountered during training.

Scatter plot comparing predicted versus actual gene expression values across multiple drugs and cell lines.

For combinatorial genetic perturbations, the model reached an $R^2$ of 0.964, indicating that its learned single-gene representations are accurate enough to be combined to predict complex genetic interactions.

Discussion and Future Directions

The success of XTransferCDR highlights several key insights. First, the "cross-transfer" training strategy effectively strips away cell-specific noise, leading to more robust drug representations. Second, the results reinforce the utility of latent linearity, suggesting that complex biological responses can be modeled as simple vector additions in a well-defined latent space. Finally, the model's strong performance on DEGs confirms its ability to capture the true biological signal of a perturbation rather than just background noise.

Future work will focus on relaxing the requirement for paired samples in training and exploring higher-order drug combinations. Additionally, integrating biological priors, such as signaling pathway information or protein-protein interaction networks, could further enhance the interpretability and accuracy of the learned latent space.

Summary updated

BibTeX
@inproceedings{liu2025learning,
  author = {Hui Liu and Shikai Jin},
  title = {{Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional Responses}},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2025},
  doi = {10.1609/aaai.v39i18.34073},
}
Figure