Harnessing biomedical foundation models for genomic feature engineering to investigate patient drug response

Utilising pre-trained biomedical foundation models (BMFMs) for inference on multi-omic data from small cohorts, represents a promising and practical route to demonstrate advantage of this technology in real-world drug discovery tasks. Here, we show this via an innovative and unique BMFM inference workflow, where BMFMs provide discernible advantage for predicting patient drug response from omics data. We utilise open-source, pre-trained, fine-tuned, multi-omics BMFMs for inference to enable feature selection and engineering. Firstly, predicting drug- target binding affinity (BA) prediction, enabling ranking and prioritisation of gene targets and associated SNPs, and secondly, using patient SNPs to mutate reference proteins and assess their impact on prednisolone BA. BMFM-derived features were composed and used alongside non-BMFM features to predict patient-specific prednisolone response using an explainable machine learning approach. We demon- strate superior predictive power of BMFM-derived feature sets, and downstream explainability distinguished SNPs that were most influential for personalised drug response prediction.