Transcriptional regulation is an important mechanism that has been involved in many biological processes. Experimental methods have provided a massive amount of data in public databases. However, carefully curating and deep analysis of these data is still expected to reveal knowledge in the transcriptional regulations. Particularly, deep machine learning has been widely applied in analyzing transcriptomics data in various forms, including RNA sequences, RNA secondary structures, RNA tertiary structure, RNA modifications, miRNA-mRNA interactions, lncRNA-protein interactions, miRNA-lncRNA interactions, and many others. Many aspects of transcriptional regulation are related to the molecular functions of both coding and non-coding genes, including molecular functions, cellular processes, and cellular localization.
Modern deep machine learning technology, along with traditional machined learning technology and quantitative statistical inference technology, serves as the methodology basis of modern computational genomics. Particularly, sequence feature embedding technologies, like dna2vec, node2vec, and prot2vec, are providing very efficient information representation to the raw genomic data, which facilitates the studies of this kind. We encourage to use of all these technologies to address questions related to transcriptional regulations in all levels.
In this Research Topic, we focus on, but are not limited to the following topics:
• Databases and well-curated data resources related to transcriptional regulations
• Statistical methods for analyzing transcriptomic data, both large and small sparse datasets
• Recognition and functional determination of genomic elements using computational methods.
• DNA and RNA modifications recognition and analysis of their biological functions
• Spatial transcriptomics
• Non-coding RNA regulation function analysis
• Innovative introduction or application of deep machine learning algorithms in computational analysis of transcriptional regulations.
Transcriptional regulation is an important mechanism that has been involved in many biological processes. Experimental methods have provided a massive amount of data in public databases. However, carefully curating and deep analysis of these data is still expected to reveal knowledge in the transcriptional regulations. Particularly, deep machine learning has been widely applied in analyzing transcriptomics data in various forms, including RNA sequences, RNA secondary structures, RNA tertiary structure, RNA modifications, miRNA-mRNA interactions, lncRNA-protein interactions, miRNA-lncRNA interactions, and many others. Many aspects of transcriptional regulation are related to the molecular functions of both coding and non-coding genes, including molecular functions, cellular processes, and cellular localization.
Modern deep machine learning technology, along with traditional machined learning technology and quantitative statistical inference technology, serves as the methodology basis of modern computational genomics. Particularly, sequence feature embedding technologies, like dna2vec, node2vec, and prot2vec, are providing very efficient information representation to the raw genomic data, which facilitates the studies of this kind. We encourage to use of all these technologies to address questions related to transcriptional regulations in all levels.
In this Research Topic, we focus on, but are not limited to the following topics:
• Databases and well-curated data resources related to transcriptional regulations
• Statistical methods for analyzing transcriptomic data, both large and small sparse datasets
• Recognition and functional determination of genomic elements using computational methods.
• DNA and RNA modifications recognition and analysis of their biological functions
• Spatial transcriptomics
• Non-coding RNA regulation function analysis
• Innovative introduction or application of deep machine learning algorithms in computational analysis of transcriptional regulations.
