Cancer is one of the leading causes of death globally, and the number of cancer patients is increasing worldwide. Unfortunately, current treatments for cancer are still not entirely effective due to the heterogeneity of the disease. Up to now, the exact molecular mechanism of cancer initiation and progression has still not fully been clarified. An in-depth understanding of the molecular basis of cancer is urgently needed.

Recent technological developments provide the opportunity to perform large-scale measurements of cancer at various levels. Some cancer research can be conducted using machine learning tasks, including cancer classification, diagnosis, prognosis, biomarker identification, etc. However, current low-throughput biological experimental methods-based “trial and error” strategies are more accurate, which are also time-consuming and resource demanding. High-throughput multi-omics techniques have facilitated the research of cancer initiation, progression, and drug sensitivity. We are now able to characterize multi-omics data including genomics, transcriptomics, proteomics, metabolomics, etc. However, we still lack full understanding of these mass multi-omics data which are often publicly and freely available. The design of methodologies to analyze and integrate these data, especially machine learning-based methods, would promote clinical diagnosis and precision medicine for cancer.

The aim of this Special Issue is to promote the application of machine learning-based methods for multi-omics data analysis in cancer by collecting original research and review articles in this field.

Potential topics include but are not limited to the following:

• Coding/noncoding RNA-cancer associations, including mRNA-cancer, miRNA-cancer, lncRNA-cancer, circRNA-cancer, etc.
• RNA and/or protein interactions in cancer, including ceRNA-ceRNA, lncRNA-mRNA, circRNA-mRNA, RNA-protein, protein-protein, etc.
• The prediction of drug sensitivity/resistance of cancer using multi-omics data
• The application of multi-omics data in cancer chemotherapy and immunotherapy
• Bioinformatic tools for multi-omics data analysis and visualization
• Methods for integration of multi-omics data about cancer
• Application of multi-omic data for diagnostic and prognostic biomarker
• Identification of molecular biomarkers related to tumor progression
• Wet-lab experimental validation and clinical applications of the above-mentioned sections