A generalized machine-learning aided method for targeted identification of industrial enzymes from metagenome: a xylanase temperature dependence case study

Abstract

Growing industrial utilization of enzymes, and the increasing availability of metagenomic data highlights the demand for effective methods of targeted identification and verification of novel enzymes from various environmental microbiota. Xylanases are a class of enzymes with numerous industrial applications and are involved in the degradation of xylose, a component of lignocellulose. Optimum temperature of enzymes are essential factors to be considered when choosing appropriate biocatalysts for a particular purpose. Therefore, in-silico prediction of this attribute is a significant cost and time-effective step in the effort to characterize novel enzymes. The objective of this study was to develop a computational method to predict the thermal dependence of xylanases. This tool was then implemented for targeted screening of putative xylanases with specific thermal dependencies from metagenomic data and resulted in identification of three novel xylanases from sheep and cow rumen microbiota. Here we present TAXyl (Thermal Activity Prediction for Xylanase), a new sequence-based machine learning method that has been trained using a selected combination of various protein features. This random forest classifier discriminates non-thermophilic, thermophilic, and hyper-thermophilic xylanases. Models performance was evaluated through multiple iterations of six-fold cross-validations, and it exhibited a mean accuracy of [~]0.79. TAXyl is freely accessible as a web-service.