This Research Topic is part of the Machine Learning-Based Methods for RNA Data Analysis series:
Previous volumes can be found here:
Volume 1: https://www.frontiersin.org/research-topics/16969/machine-learning-based-methods-for-rna-data-analysis
Volume 2: https://www.frontiersin.org/research-topics/20934/machine-learning-based-methods-for-rna-data-analysis---volume-ii
RNA is an extremely important biological macromolecule, which plays a key role in all aspects of life activities and biological processes through its interactions with other biological entities. Thus, it is critical to identify the complex biological associations between RNA and other biological entities and traits. However, experimental methods are usually time-consuming and resource demanding and this provides a need for computational models, especially those involving the fast developing next generation sequencing techniques. Based on the assumption of “guilt-by-association” and other machine learning theories, accumulated computational methods have been developed to perform association predictions. However, the performance of most methods are unsatisfying due to data complexity and heterogeneity. More importantly, RNA is a kind of genetic material in RNA viruses. Many viruses can replicate their genomes by encoding an RNA-dependent RNA polymerase. Host factors provided by the host cells are involved in RNA modification and the formation of RNA replication complexes, which plays important roles in remodelling a few kind of interactions including RNA-RNA associations and RNA-protein associations during virus RNA replication. Finally, single-cell RNA sequencing technologies has been proven to be helpful in probing cell states, finding complex and rare cell types, identifying gene regulatory associations, describing cell lineages, and revealing cell-to-cell variabilities within diseases in a transcriptomic perspective. Comparing with bulk tumor transcriptome data analysis, single-cell RNA sequencing analysis can monitor RNA changes of each cell, which will have many potential clinical applications especially in the era of precision medicine.
Thus, we think it is a good time to comprehensively discuss the topics about RNA data analysis. This Research Topic can involve various kinds of machine learning methods to identify associations between biological entities, find the clues of treatment for the infectious diseases caused by RNA viruses, and analyze single cell RNA data. We welcome researchers to contribute Original Research and Review articles on machine learning-based methods and its applications on these three topics. Topics of interest include but are not limited to the following:
- Inferring RNA-disease associations, for example, miRNA-disease associations, long noncoding RNA-disease associations, circular RNA-disease associations, Piwi-interacting RNA-disease associations, and so on.
- Inferring RNA-protein interactions, for example, long noncoding RNA-protein interactions, microRNA-target interactions, circular RNA-protein interactions, and so on.
- Inferring RNA-RNA interactions, for example, the associations among microRNA, ribosomal RNA, transfer RNA, small nucleolar RNA, and so on.
- Inferring drug-like small molecule-noncoding RNA interactions, for example, small molecule-miRNAs, small molecule-long noncoding RNAs, small molecule-repetitive RNAs, small molecule-intronic RNAs, and so on.
- Inferring the interactions between small molecules and RNA-binding proteins, for example, microRNA-binding proteins, single-stranded RNA-binding toll-like receptors, and so on.
- Inferring biomarkers associated with RNAs in cancer, for example, circulating miRNAs, messenger RNA, long noncoding RNAs, competing endogenous RNAs, and so on.
- Performing the analysis of single cell RNA sequence data, for example, dropout, imputation, dimensionality reduction, clustering, and so on.
- Inferring clues of treatment for the infectious diseases caused by single-stranded RNA viruses.
- Inferring RNA-binding proteins in the infectious diseases caused by single-stranded RNA viruses.
- Wet-lab experimental validation and clinical applications of the above mentioned associations.
Topic Editor Dr Jialiang Yang is Vice President of Geneis (Beijing) Co. Ltd. The other Topic Editors declare no conflict of interest with the Research Topic theme
This Research Topic is part of the Machine Learning-Based Methods for RNA Data Analysis series:
Previous volumes can be found here:
Volume 1: https://www.frontiersin.org/research-topics/16969/machine-learning-based-methods-for-rna-data-analysis
Volume 2: https://www.frontiersin.org/research-topics/20934/machine-learning-based-methods-for-rna-data-analysis---volume-ii
RNA is an extremely important biological macromolecule, which plays a key role in all aspects of life activities and biological processes through its interactions with other biological entities. Thus, it is critical to identify the complex biological associations between RNA and other biological entities and traits. However, experimental methods are usually time-consuming and resource demanding and this provides a need for computational models, especially those involving the fast developing next generation sequencing techniques. Based on the assumption of “guilt-by-association” and other machine learning theories, accumulated computational methods have been developed to perform association predictions. However, the performance of most methods are unsatisfying due to data complexity and heterogeneity. More importantly, RNA is a kind of genetic material in RNA viruses. Many viruses can replicate their genomes by encoding an RNA-dependent RNA polymerase. Host factors provided by the host cells are involved in RNA modification and the formation of RNA replication complexes, which plays important roles in remodelling a few kind of interactions including RNA-RNA associations and RNA-protein associations during virus RNA replication. Finally, single-cell RNA sequencing technologies has been proven to be helpful in probing cell states, finding complex and rare cell types, identifying gene regulatory associations, describing cell lineages, and revealing cell-to-cell variabilities within diseases in a transcriptomic perspective. Comparing with bulk tumor transcriptome data analysis, single-cell RNA sequencing analysis can monitor RNA changes of each cell, which will have many potential clinical applications especially in the era of precision medicine.
Thus, we think it is a good time to comprehensively discuss the topics about RNA data analysis. This Research Topic can involve various kinds of machine learning methods to identify associations between biological entities, find the clues of treatment for the infectious diseases caused by RNA viruses, and analyze single cell RNA data. We welcome researchers to contribute Original Research and Review articles on machine learning-based methods and its applications on these three topics. Topics of interest include but are not limited to the following:
- Inferring RNA-disease associations, for example, miRNA-disease associations, long noncoding RNA-disease associations, circular RNA-disease associations, Piwi-interacting RNA-disease associations, and so on.
- Inferring RNA-protein interactions, for example, long noncoding RNA-protein interactions, microRNA-target interactions, circular RNA-protein interactions, and so on.
- Inferring RNA-RNA interactions, for example, the associations among microRNA, ribosomal RNA, transfer RNA, small nucleolar RNA, and so on.
- Inferring drug-like small molecule-noncoding RNA interactions, for example, small molecule-miRNAs, small molecule-long noncoding RNAs, small molecule-repetitive RNAs, small molecule-intronic RNAs, and so on.
- Inferring the interactions between small molecules and RNA-binding proteins, for example, microRNA-binding proteins, single-stranded RNA-binding toll-like receptors, and so on.
- Inferring biomarkers associated with RNAs in cancer, for example, circulating miRNAs, messenger RNA, long noncoding RNAs, competing endogenous RNAs, and so on.
- Performing the analysis of single cell RNA sequence data, for example, dropout, imputation, dimensionality reduction, clustering, and so on.
- Inferring clues of treatment for the infectious diseases caused by single-stranded RNA viruses.
- Inferring RNA-binding proteins in the infectious diseases caused by single-stranded RNA viruses.
- Wet-lab experimental validation and clinical applications of the above mentioned associations.
Topic Editor Dr Jialiang Yang is Vice President of Geneis (Beijing) Co. Ltd. The other Topic Editors declare no conflict of interest with the Research Topic theme