Predicting Single-cell Drug Sensitivity by Adaptive Weighted Feature for Adversarial Multi-source Domain Adaptation

Author:

Wei Duan, Hui Liu

Keyword:

Computer Science, Artificial Intelligence, Artificial Intelligence (cs.AI)

journal:

date:

2024-03-08 00:00:00

Abstract

The development of single-cell sequencing technology had promoted the generation of a large amount of single-cell transcriptional profiles, providing valuable opportunities to explore drug-resistant cell subpopulations in a tumor. However, the drug sensitivity data in single-cell level is still scarce to date, pressing an urgent and highly challenging task for computational prediction of the drug sensitivity to individual cells. This paper proposed scAdaDrug, a multi-source adaptive weighting model to predict single-cell drug sensitivity. We used an autoencoder to extract domain-invariant features related to drug sensitivity from multiple source domains by exploiting adversarial domain adaptation. Especially, we introduced an adaptive weight generator to produce importance-aware and mutual independent weights, which could adaptively modulate the embedding of each sample in dimension-level for both source and target domains. Extensive experimental results showed that our model achieved state-of-the-art performance in predicting drug sensitivity on sinle-cell datasets, as well as on cell line and patient datasets.

PDF: Predicting Single-cell Drug Sensitivity by Adaptive Weighted Feature for Adversarial Multi-source Domain Adaptation.pdf