Knowledge-driven Multimodal Drug Response Predictor
Abstract
This study proposes a knowledge distillation-based multimodal drug response prediction framework (KMDRP). Its student model, utilizing only single-modal RNA data, achieves predictive performance surpassing that of models trained on complete multi-omics data, and demonstrates promising potential in guiding patient survival prognosis and individualized treatment in clinical validation.
Fields of Study & Subjects
Computational Drug Discovery Methods
Machine Learning in Healthcare
Bioinformatics and Genomic Networks
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 29 January 2026
- Document type
- Dataset