About this Research Topic
Cancer remains a top threat to human health and society. Novel large-scale approaches based on the electronic health record (EHR), medical imaging, and genomic, transcriptomic, epigenomic, proteomic, and metagenomics (omics techniques) have allowed the expansion of our current knowledge regarding the etiology of cancer, general or specific to different cancer types. With large omics data that have been generated at individual omics, the plea for multi-omics integrative analysis is also urgent to permit a more complete understanding of the interplay of the genes, microorganisms, and metabolites as well as other risk factors (from EHR, imaging, and different omics) on cancer. However, these modern high throughput techniques are associated with significant limitations such as the high-dimensional data size relative to the available sample size. Most of these methods are not applicable to non-linear and multi-view datasets.
Markedly, the number of genes and genomic variants can be more than tens of thousands, while the sample size in cancer studies is mostly in the hundreds or less. Statistical methods appropriate for high-dimensional data have been widely studied, for example, the penalized regression. Recently, the breakthrough of machine-learning methods featured by the deep learning leads to a new direction for high-dimensional data analysis, as well as cancer research. The incorporation of various statistical machine learning approaches into genomic analyses is a rather recent area of study. Since large-scale microarray data presents significant challenges for statistical data analysis, in addition to the classical approaches, there is a need for an advanced method.
In this second volume, we aim to build on the knowledge acquired in the first one, focusing on the development and application of novel statistical and machine-learning methods, such as the kernel-based methods, for high-dimensional clinical and (multi-)omics data in cancer-related research.
We welcome the submission of Original Research, Reviews, Mini-Reviews, Perspectives, and Opinions covering, but not limited to, the following topics:
• Integrative analysis of clinical, imaging, and (multi-)omics cancer data;
• Prediction in cancer diagnosis, survival/progression, and drug responses using multiple datasets;
• Incorporation of statistical, kernel-based, and deep learning methods into high-dimensional data analysis.
Topic editor Dr. Shaolong Cao is employed by Biogen IDEC. All other Topic Editors declare no competing interests with regard to the Research Topic subject.
Markedly, the number of genes and genomic variants can be more than tens of thousands, while the sample size in cancer studies is mostly in the hundreds or less. Statistical methods appropriate for high-dimensional data have been widely studied, for example, the penalized regression. Recently, the breakthrough of machine-learning methods featured by the deep learning leads to a new direction for high-dimensional data analysis, as well as cancer research. The incorporation of various statistical machine learning approaches into genomic analyses is a rather recent area of study. Since large-scale microarray data presents significant challenges for statistical data analysis, in addition to the classical approaches, there is a need for an advanced method.
In this second volume, we aim to build on the knowledge acquired in the first one, focusing on the development and application of novel statistical and machine-learning methods, such as the kernel-based methods, for high-dimensional clinical and (multi-)omics data in cancer-related research.
We welcome the submission of Original Research, Reviews, Mini-Reviews, Perspectives, and Opinions covering, but not limited to, the following topics:
• Integrative analysis of clinical, imaging, and (multi-)omics cancer data;
• Prediction in cancer diagnosis, survival/progression, and drug responses using multiple datasets;
• Incorporation of statistical, kernel-based, and deep learning methods into high-dimensional data analysis.
Topic editor Dr. Shaolong Cao is employed by Biogen IDEC. All other Topic Editors declare no competing interests with regard to the Research Topic subject.
Keywords: high-dimensional data, integrative analysis, big-data, cancer genomics, machine-learning
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.
