About this Research Topic
The widespread adoption of computational technologies has made it possible to analyse big biological datasets, such as whole genome sequencing, using Artificial Intelligence (AI). In particular, Deep Neural Networks (DNNs) have shown great promise in Systems Biology. In recent years, DNN techniques have been applied to a wide range of biological problems, from predicting gene expression and regulatory interactions to designing and optimizing nucleic acid sequences for both therapeutic and research purposes. By leveraging the power of DNNs and machine learning, researchers can more accurately model and simulate complex genetic systems, facilitating the discovery of novel biological mechanisms and potential drug targets.
While a powerful tool, the lack of interpretability of DNNs without an initial hypothesis-based question remains a major challenge further complicated by the time and computational power needed to analyse these datasets. As such, finding ways to reduce computation time and power, while maintaining high performance is a crucial objective for researchers within the field.
The goal of this Research Topic is to gather original research and reviews on the application of AI-based methods, especially DNNs, in handling and interpreting large-scale genetic data in systems biology. Authors are encouraged to present methods and pipelines for reducing computation time and to explore new models for handling complex genetic/genomic datasets. Additionally, research addressing the interpretability of AI-based methods within systems biology will be highly valued. This Research Topic invites contributions covering the following areas, but not limited to:
- DNN approaches for predicting gene function and regulatory interactions.
- DNN approaches for designing nucleic acid sequences applied in gene therapy and diagnostics.
- DNN analysis of single-cell data applied to systems level understanding of behaviour and gene expression patterns of cells.
- Studies that discuss the interpretability of methods using DNN-based approaches
- Novel methods and techniques for reducing computation time and power.
- Development of new models for interpreting complex genetic systems
While a powerful tool, the lack of interpretability of DNNs without an initial hypothesis-based question remains a major challenge further complicated by the time and computational power needed to analyse these datasets. As such, finding ways to reduce computation time and power, while maintaining high performance is a crucial objective for researchers within the field.
The goal of this Research Topic is to gather original research and reviews on the application of AI-based methods, especially DNNs, in handling and interpreting large-scale genetic data in systems biology. Authors are encouraged to present methods and pipelines for reducing computation time and to explore new models for handling complex genetic/genomic datasets. Additionally, research addressing the interpretability of AI-based methods within systems biology will be highly valued. This Research Topic invites contributions covering the following areas, but not limited to:
- DNN approaches for predicting gene function and regulatory interactions.
- DNN approaches for designing nucleic acid sequences applied in gene therapy and diagnostics.
- DNN analysis of single-cell data applied to systems level understanding of behaviour and gene expression patterns of cells.
- Studies that discuss the interpretability of methods using DNN-based approaches
- Novel methods and techniques for reducing computation time and power.
- Development of new models for interpreting complex genetic systems
Keywords: deep neural networks, systems biology, genetics, neural network
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.
