A spurt of progress in Next-Generation Sequencing (NGS) and Third-Generation Sequencing (TGS) has caused a dramatic change in biological research. Single-cell sequencing represents a new technology for high-throughput sequencing of the genome, transcriptome, and epigenome at the individual cell level. It could reveal the gene structure and gene expression of individual cells, reflecting the heterogeneity among cells. Besides, it is a major player in such fields as tumor, developmental biology, microbiology, and neuroscience, emerging as the focus of life science. Additionally, it manages to make up for the defects of common high-throughput sequencing, allowing for more reliable conclusions. Machine learning (ML), an important subfield of artificial intelligence, has been maturely employed in model construction of disease diagnosis, risk prediction, etc., and enjoys great potential in biomarker screening. These biomarkers allow for accurate disease prediction, patient stratification, and precise treatment. Big data in healthcare, including patient-related information, from clinical parameters (e.g., gender, age, pathology and physiological history) to histological data (e.g., genetics, proteomics and metabolomics), has now become widespread.

Recently, these data have been used in precision medicine (also known as personalized medicine or stratified medicine) to provide personalized healthcare services, i.e., customized treatments for individuals. With the support of ML algorithms and data mining tools, unprecedented developments in precision medicine have occurred. These technologies are also helpers to discover new histological biological markers that can identify the molecular causes of disease. Although still in its infancy, multi-omics ML analysis has been widely used in brain diseases, cancer, cardiovascular diseases, medical imaging, human single-cell analysis and plant science.

The Special Issue will focus on articles involving ML combined with multi-omics techniques to explore the relevance of cell populations, thus discovering disease-related markers that could provide informative value for disease prevention, occurrence and development. Original research and review articles are welcome.

Potential topics include but are not limited to the following:

• Review of methods and prospective analysis of ML in multi-omics such as single-cell sequencing
• Screening of disease biomarkers in multi-omics technologies using novel ML algorithms
• Construction of ML algorithms with multi-omics technologies
• Potential connections between genomics, metabolomics, transcriptomics using ML algorithms
• Combination of the latest ensemble learning algorithms, such as XGboost, with multi-omics technologies to precisely study the correlation of cell populations, thus discovering disease-related biomarkers