It is of great importance to further the study of human health by interpreting molecular intricacies and variations at multiple levels, such as genome, epigenome, proteome, and metabolome. The data gathered at these levels is called as “multi-omics” data, which unravels the intricate working of systems biology. Machine learning methods offer novel techniques to integrate the various omics data for the discovery of new biomarkers, which have the potential to help in accurate disease prediction and delivery of precision medicine. The study of different integrative machine learning methods for multi-omics data provides an in-depth understanding of biological systems during normal physiological functioning and in the presence of a disease, and further supports insights and recommendations for interdisciplinary professionals.

After obtaining the full combination of high-throughput data obtained from different molecular layers, we need to handle the pending issues in the multi-omics data analysis field. The challenges include the heterogeneity across omics technologies, the treatment of missing values, the interpretation of multilayered system models, and the problems pertaining to data annotation, storage, and computational resources. To further the research on the multi-omics data, novel machine learning methods are urgently required.

Due to the urgency of the novel machine learning methods for multi-omics data analysis, the Special Issue aims to cover the comprehensive and latest collection of recent works in machine learning methods. We welcome original research and review articles.

Potential topics include but are not limited to the following:

• The mechanisms for class imbalance
• The algorithm to overcome overfitting
• The visualization of multi-omics data
• The design of novel feature selection methods
• The design of novel feature extraction methods
• The design of novel deep learning methods
• Effective multiclass classification models
• Clustering-based data exploration schemes
• The interpretable machine learning methods