Evolution and applications of plant pathway resources and databases

Prediction of plant secondary metabolic pathways using deep transfer learning

BACKGROUND

Plant secondary metabolites are highly valued for their applications in pharmaceuticals, nutrition, flavors, and aesthetics. It is of great importance to elucidate plant secondary metabolic pathways due to their crucial roles in biological processes during plant growth and development. However, understanding plant biosynthesis and degradation pathways remains a challenge due to the lack of sufficient information in current databases. To address this issue, we proposed a transfer learning approach using a pre-trained hybrid deep learning architecture that combines Graph Transformer and convolutional neural network (GTC) to predict plant metabolic pathways.

RESULTS

GTC provides comprehensive molecular representation by extracting both structural features from the molecular graph and textual information from the SMILES string. GTC is pre-trained on the KEGG datasets to acquire general features, followed by fine-tuning on plant-derived datasets. Four metrics were chosen for model performance evaluation. The results show that GTC outperforms six other models, including three previously reported machine learning models, on the KEGG dataset. GTC yields an accuracy of 96.75%, precision of 85.14%, recall of 83.03%, and F1_score of 84.06%. Furthermore, an ablation study confirms the indispensability of all the components of the hybrid GTC model. Transfer learning is then employed to leverage the shared knowledge acquired from the KEGG metabolic pathways. As a result, the transferred GTC exhibits outstanding accuracy in predicting plant secondary metabolic pathways with an average accuracy of 98.30% in fivefold cross-validation and 97.82% on the final test. In addition, GTC is employed to classify natural products. It achieves a perfect accuracy score of 100.00% for alkaloids, while the lowest accuracy score of 98.42% for shikimates and phenylpropanoids.

CONCLUSIONS

The proposed GTC effectively captures molecular features, and achieves high performance in classifying KEGG metabolic pathways and predicting plant secondary metabolic pathways via transfer learning. Furthermore, GTC demonstrates its generalization ability by accurately classifying natural products. A user-friendly executable program has been developed, which only requires the input of the SMILES string of the query compound in a graphical interface.

Agrigenomics for microalgal biofuel production: an overview of various bioinformatics resources and recent studies to link OMICS to bioenergy and bioeconomy

Microalgal biofuels offer great promise in contributing to the growing global demand for alternative sources of renewable energy. However, to make algae-based fuels cost competitive with petroleum, lipid production capabilities of microalgae need to improve substantially. Recent progress in algal genomics, in conjunction with other "omic" approaches, has accelerated the ability to identify metabolic pathways and genes that are potential targets in the development of genetically engineered microalgal strains with optimum lipid content. In this review, we summarize the current bioeconomic status of global biofuel feedstocks with particular reference to the role of "omics" in optimizing sustainable biofuel production. We also provide an overview of the various databases and bioinformatics resources available to gain a more complete understanding of lipid metabolism across algal species, along with the recent contributions of "omic" approaches in the metabolic pathway studies for microalgal biofuel production.

STIFDB2: an updated version of plant stress-responsive transcription factor database with additional stress signals, stress-responsive transcription factor binding sites and stress-responsive genes in Arabidopsis and rice

Understanding the principles of abiotic and biotic stress responses, tolerance and adaptation remains important in plant physiology research to develop better varieties of crop plants. Better understanding of plant stress response mechanisms and application of knowledge derived from integrated experimental and bioinformatics approaches are gaining importance. Earlier, we showed that compiling a database of stress-responsive transcription factors and their corresponding target binding sites in the form of Hidden Markov models at promoter, untranslated and upstream regions of stress-up-regulated genes from expression analysis can help in elucidating various aspects of the stress response in Arabidopsis. In addition to the extensive content in the first version, STIFDB2 is now updated with 15 stress signals, 31 transcription factors and 5,984 stress-responsive genes from three species (Arabidopsis thaliana, Oryza sativa subsp. japonica and Oryza sativa subsp. indica). We have employed an integrated biocuration and genomic data mining approach to characterize the data set of transcription factors and consensus binding sites from literature mining and stress-responsive genes from the Gene Expression Omnibus. STIFDB2 currently has 38,798 associations of stress signals, stress-responsive genes and transcription factor binding sites predicted using the Stress-responsive Transcription Factor (STIF) algorithm, along with various functional annotation data. As a unique plant stress regulatory genomics data platform, STIFDB2 can be utilized for targeted as well as high-throughput experimental and computational studies to unravel principles of the stress regulome in dicots and gramineae. STIFDB2 is available from the URL: http://caps.ncbs.res.in/stifdb2.

MetNet Online: a novel integrated resource for plant systems biology

BACKGROUND

Plants are important as foods, pharmaceuticals, biorenewable chemicals, fuel resources, bioremediation tools and general tools for recombinant technology. The study of plant biological pathways is advanced by easy access to integrated data sources. Today, various plant data sources are scattered throughout the web, making it increasingly complicated to build comprehensive datasets.

RESULTS

MetNet Online is a web-based portal that provides access to a regulatory and metabolic plant pathway database. The database and portal integrate Arabidopsis, soybean (Glycine max) and grapevine (Vitis vinifera) data. Pathways are enriched with known or predicted information on sub cellular location. MetNet Online enables pathways, interactions and entities to be browsed or searched by multiple categories such as sub cellular compartment, pathway ontology, and GO term. In addition to this, the "My MetNet" feature allows registered users to bookmark content and track, import and export customized lists of entities. Users can also construct custom networks using existing pathways and/or interactions as building blocks.

CONCLUSION

The site can be reached at http://www.metnetonline.org. Extensive video tutorials on how to use the site are available through http://www.metnetonline.org/tutorial/.

CORNET 2.0: integrating plant coexpression, protein-protein interactions, regulatory interactions, gene associations and functional annotations

To enable easy access and interpretation of heterogeneous and scattered data, we have developed a user-friendly tool for data mining and integration in Arabidopsis, named CORNET. This tool allows the browsing of microarray data, the construction of coexpression and protein-protein interaction (PPI) networks and the exploration of diverse functional annotations. Here, we present the new functionalities of CORNET 2.0 for data integration in plants. First of all, CORNET allows the integration of regulatory interaction datasets accessible through the new transcription factor (TF) tool that can be used in combination with the coexpression tool or the PPI tool. In addition, we have extended the PPI tool to enable the analysis of gene-gene associations from AraNet as well as newly identified PPIs. Different search options are implemented to enable the construction of networks centered around multiple input genes or proteins. New functional annotation resources are included to retrieve relevant literature, phenotypes, plant ontology and biological pathways. We have also extended CORNET to attain the construction of coexpression and PPI networks in the crop species maize. Networks and associated evidence of the majority of currently available data types are visualized in Cytoscape. CORNET is available at https://bioinformatics.psb.ugent.be/cornet.