A new era in plant functional genomics

In the last few years, research in plant sciences has seen an unprecedented growth of high dimensional omics data sets and its application in functional genomics studies. These studies have used the individual or integrative omics analysis approach for establishing a network of relationships between biomolecules within a system. The expansion of knowledge base–derived and the generated omics data sets offer a unique opportunity to use deep learning approaches to derive plant metabolic models. The deep learning algorithms require large data sets to identify important associations that regulate a biological process and to achieve high accuracy against expected outcomes. Legacy omics data sets could serve as input for such deep learning algorithms, while knowledge base serves as its expected outcome around which the algorithm attempts to achieve high prediction accuracy. Therefore, structured metadata submission associated with omics data sets and knowledge derived from it is valuable to derive next-generation toolsets for functional genomics in plant sciences. Here, we have reviewed recent advances in the functional genomics knowledge base driven by results from genomics, transcriptomics, metabolomics analysis, and their integration. We have particularly focused on studies that have generated large-scale omics data sets that will be suitable for deriving the plant metabolic models. We conclude our review with a brief discussion on requirements for legacy data to derive metabolic models by using machine learning and deep learning approaches.