About this Research Topic
The development of high throughput omics technologies have enabled accurate measurement of multiple modalities simultaneously in individual studies or multi-omics integration from different studies, and rapid data accumulation in multimodal omics, including genomics, transcriptomics, protteomics, metabolomics, phenomics, radiomics and the cutting-edge 3D spatial omics, single-cell omics. These provide an unparalleled opportunity for knowledge discovery in intractable diseases, such as discovery of biomarkers, functional modules, causal pathways and regulatory networks etc., which have great potential to bolster the therapeutic pipelines.
Traditional statistical methods have been successfully applied to incorporate multi-omic datasets, such as the genome-wide association studies (GWAS), molecular quantitative trait loci (QTL) analysis and summarized Mendelian Randomization. However, limited pre-defined modalities have restricted the flexibility of available omics data, and the ability to incorporate different types of features of existing methods is still insufficient, which both decrease the power in knowledge discovery. Considering these aspects, advanced data mining, statistical and machine learning methods are urgently needed to perform cross-modal data integration and modeling. The aim of this Research Topic is to showcase the advanced data mining and statistical approaches helpful to discover disease-related knowledges and illuminate molecular mechanisms of complex diseases. Topics of interest include but are not limited to:
(1) Statistical methods and applications for integrating multimodal omics data.
(2) Machine learning methods of feature representation for multimodal omics.
(3) Graph-based deep learning methods for disease-related node/linkage prediction.
(4) Identification of molecular biomarkers for complex diseases.
(5) Disease-related module identification and validation through integrating multimodal omics data.
(6) Database and web-tools for depositing and visualizing disease-related knowledges discovered based on multimodal omics.
Traditional statistical methods have been successfully applied to incorporate multi-omic datasets, such as the genome-wide association studies (GWAS), molecular quantitative trait loci (QTL) analysis and summarized Mendelian Randomization. However, limited pre-defined modalities have restricted the flexibility of available omics data, and the ability to incorporate different types of features of existing methods is still insufficient, which both decrease the power in knowledge discovery. Considering these aspects, advanced data mining, statistical and machine learning methods are urgently needed to perform cross-modal data integration and modeling. The aim of this Research Topic is to showcase the advanced data mining and statistical approaches helpful to discover disease-related knowledges and illuminate molecular mechanisms of complex diseases. Topics of interest include but are not limited to:
(1) Statistical methods and applications for integrating multimodal omics data.
(2) Machine learning methods of feature representation for multimodal omics.
(3) Graph-based deep learning methods for disease-related node/linkage prediction.
(4) Identification of molecular biomarkers for complex diseases.
(5) Disease-related module identification and validation through integrating multimodal omics data.
(6) Database and web-tools for depositing and visualizing disease-related knowledges discovered based on multimodal omics.
Keywords: Knowledge discovery, Diseases, Multimodal omics, Data mining methods, Statistical methods
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
