Bocconi Institute on Data Science and Analytics (BIDSA)
Via Guglielmo Röntgen 1
20136 Milan, Italy
Computational Biology and Bioinformatics continuously give rise to new and complex biological and computational questions, which can be effectively tackled by relying on Artificial Intelligence (AI) strategies. As a matter of fact, the application of cutting-edge computational approaches, involving Machine Learning (ML) and Computational Intelligence (CI) techniques, has gradually increased in the last few years. As an example, the advent of single-cell sequencing technologies, widely used in molecular biology research, has enabled the possibility of a better understanding of the molecular processes at the basis of both normal cell development and the onset of several pathologies. However, the analysis of such data is a challenging task, which requires the application of AI strategies. AI techniques can be efficiently exploited to combine and analyze heterogeneous sources of information, allowing also for multi-omics data integration, representing a significant step towards personalized and precision medicine. For instance, in the last few years, Deep Learning (DL) approaches have been successfully used to solve Bioinformatics tasks, thanks to their abilities in dealing with high-dimensional and sparse data. The application of ML and DL techniques can facilitate the identification of latent representations, which are fundamental for a better understanding of existing patterns on the omics data. In addition, ML and DL approaches can be applied to solve the clustering and classification challenges, which always arise when single-omic and multi-omics data are analyzed. Finally, ML- and CI-based strategies can be also used to tackle other well-known problems in Bioinformatics and Computational Systems Biology (e.g., alignments, dimensionality reduction, and parameter estimation). Thus, the development of effective AI techniques and mathematical models can allow for a better understanding of the complexity behind diseases, as well as for achieving personalized and precision medicine.
This Research Topic aims at publishing Original Research papers, which cover the application of state-of-the-art and novel AI-based algorithms, for the analysis and integration of omics data.
Topics of interest include but are not limited to:
Machine Learning and Computational Intelligence techniques for multi-omics data integration and analysis.
Machine Learning and Computational Intelligence techniques for combinatorial problems in Bioinformatics.
Machine Learning and Deep Learning strategies for classification tasks in single-cell data analysis.
Clustering approaches for single-cell data analysis.
Generative models for single-cell data analysis.
Application of graph theory to multi-omics data.
Computational Intelligence methods for the optimization of biomedical data analysis tasks.
Keywords: Machine Learning, Deep Learning, Computational Intelligence, Bioinformatics, Computational Biology, Single-cell data analysis and integration, Multi-omics data integration
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.