Integrating Single-Cell Foundation Models with Graph Neural Networks for Drug Response Prediction
This work addresses the challenge of accurate drug response prediction for personalized cancer treatment, but it is incremental as it builds on an existing framework.
The study tackled drug response prediction in cancer by integrating the pretrained foundation model scGPT with the DeepCDR framework to enhance cell representations, resulting in improved performance and greater training stability compared to existing methods.
AI-driven drug response prediction holds great promise for advancing personalized cancer treatment. However, the inherent heterogenity of cancer and high cost of data generation make accurate prediction challenging. In this study, we investigate whether incorporating the pretrained foundation model scGPT can enhance the performance of existing drug response prediction frameworks. Our approach builds on the DeepCDR framework, which encodes drug representations from graph structures and cell representations from multi-omics profiles. We adapt this framework by leveraging scGPT to generate enriched cell representations using its pretrained knowledge to compensate for limited amount of data. We evaluate our modified framework using IC$_{50}$ values on Pearson correlation coefficient (PCC) and a leave-one-drug out validation strategy, comparing it against the original DeepCDR framework and a prior scFoundation-based approach. scGPT not only outperforms previous approaches but also exhibits greater training stability, highlighting the value of leveraging scGPT-derived knowledge in this domain.