Abstract
MOTIVATION: Predicting the response of cell lines to characteristic drugs based on multi-omics gene information has become the core problem of precision oncology. At present, drug response prediction using multi-omics gene data faces the following three main challenges: first, how to design a gene probe feature extraction model with biological interpretation and high performance; second, how to develop multi-omics weighting modules for reasonably fusing genetic data of different lengths and noise conditions; third, how to construct deep learning models that can handle small sample sizes while minimizing the risk of possible overfitting. RESULTS: We propose an innovative drug response prediction model (NMDP). First, the NMDP model introduces an interpretable semi-supervised weighted SPCA module to solve the feature extraction problem in multi-omics gene data. Next, we construct a multi-omics data fusion framework based on sample similarity networks, bimodal tests, and variance information, which solves the data fusion problem and enables the NMDP model to focus on more relevant genomic data. Finally, we combine a one-dimensional convolution method and Kolmogorov-Arnold networks (KANs) to predict the drug response. We conduct five sets of real data experiments and compare NMDP against seven advanced drug response prediction methods. The results show that NMDP achieves the best performance, with sensitivity and specificity reaching 0.92 and 0.93, respectively-an improvement of 11%-57% compared to other models. Bio-enrichment experiments strongly support the biological interpretation of the NMDP model and its ability to identify potential targets for drug activity prediction.