Predicting metabolic pathways of plant enzymes without using sequence similarity: Models from machine learning.

Most of the bioinformatics tools for enzyme annotation focus on enzymatic function assignments. Sequence similarity to well-characterized enzymes is often used for functional annotation and to assign metabolic pathways. However, these approaches are not feasible for all sequences leading to inaccurate annotations or lack of metabolic pathway information. Here we present the mApLe (metabolic pathway predictor of plant enzymes), a high-performance machine learning-based tool with models to label the metabolic pathway of enzymes rather than specifying enzymes' reactions. The mApLe uses molecular descriptors of the enzyme sequences to perform predictions without considering sequence similarities with reference sequences. Hence, mApLe can classify a diversity of enzymes, even the ones without any homolog or with incomplete EC numbers. This tool can be used to improve the quality of genomic annotation of plants or to narrow down the number of candidate genes for metabolic engineering researches. The mApLe tool is available online, and the GUI can be locally installed.

Review of combinations of experimental and computational techniques to identify and understand genes involved in innate immunity and effector-triggered defence.

The innate immune system includes a first layer of defence that recognises conserved pathogen-associated molecular patterns that are essential for microbial fitness. Resistance (R) gene-based recognition of pathogen effectors, which function in modulation or avoidance of host immunity, activates a second layer of plant defence. In this review, experimental and computational techniques are considered to improve understanding of the plant immune system. Biocomputation contributes to discovery of the molecular genetic basis of host resistance against pathogens. Sequenced genomes have been used to identify R genes in plants. Resistance gene enrichment sequencing based on conserved protein domains has increased the number of R genes with nucleotide-binding site and leucine-rich repeat domains. Network analysis will contribute to an improved understanding of the innate immune system and identify novel genes for partial disease resistance. Machine learning algorithms are expected to become important in defining aspects of the immune system that are less well characterised, including identification of R genes that lack conserved protein domains.