Protein Sequence and Feature Data used to develop the ECemble enzyme classification methodology

This dataset relates to the development of ECemble, an approach to identifying enzymes and enzyme classes and study the human gut metabolic pathways, using an ensemble of machine-learning methods to accurately model and predict enzymes from protein sequences. ECemble has been used to predict entire complements of enzymes from ten sequenced proteomes including the human proteome, as well as predicting enzymes encoded by the human gut microbiome from gut metagenomic samples, and to study the role played by the microbe-derived enzymes in the human metabolism. This dataset includes enzyme and non-enzyme sequence data (FASTA format and Identifiers) and sequence features from Pfam, Prosite and Superfamily databases used to develop ECemble enzyme classification methodology. The files include: Enzyme Data : 64,950 sequences (Fasta File | Sequence ID File) Non-enzyme Data : 128,475 sequences (Fasta File | Sequence ID File) All Data : 193,425 sequences (Fasta File | Sequence ID File) List of Unique Features : 14,241 featuresThese files are in .txt format and can be opened by any open source or standard word processing software.