About this Research Topic
Genomic, transcriptomic, proteomic, and other omics data contain the cues to unveiling underlying biological mechanisms. Due to the impracticality of manually analysing the huge amounts of the omics data, bioinformatics research based on computational analysis has become key to the understanding of this biological data. Recent developments in artificial intelligence offer a promising opportunity for bioinformatics research of omics data. Inspired by the advancing techniques in artificial intelligence, there are a great number of powerful and effective bioinformatics models erupting in omics data research.
Recent emerging intelligence models of bioinformatics are mostly constructed through the architecture of supervised learning. Despite the successes achieved by the previously published bioinformatics models in omics data research, a major drawback is that these models obligate training data with annotated labels. Since the data involved in omics analysis are massive, annotating labels for such amounts of data requires extensively manual efforts of experts, and the insufficiency of annotated labels in omics data has become the crucial bottleneck in the construction of intelligence bioinformatics models. To circumvent the issue of lacking annotations in omics data analysis, the paradigm of unsupervised learning exhibits very promising potential to analyze the unlabeled data of omics. In contrast to the supervised learning framework, establishing an unsupervised learning model for unlabeled data is likely to overcome the limiting shortage of annotated labels in omics data.
In this Research Topic, we would like to focus on the unsupervised learning models for unlabeled omics data. To urge the development of unsupervised learning model in research of genomic, transcriptomic, and proteomic data, we welcome the submission of Original Research articles, Technology Reports, and Reviews articles related to unsupervised learning model in omics analysis.
This Research Topic will cover but not be limited to the following:
1. Clustering models or applications in omics data analysis;
2. Outlier detection models or applications in omics data analysis;
3. Omics data dimension reduction models or applications;
4. Unsupervised noise filtering models or applications in omics data analysis;
5. Algorithms or applications of unsupervised feature extraction in omics data analysis;
6. Data representation learning in the analysis or applications for omics data.
7. Genomic or epigenomic discovery via unsupervised learning models;
8. Transcriptomic discovery for coding and noncoding RNA via unsupervised learning;
9. Proteomic and interactomic applications via unsupervised learning models;
10. Metabolomic and immunomic discovery via unsupervised learning models;
Keywords: unsupervised learning, unlabeled data, omics data, genome, transcriptome, proteome
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.