Show simple item record

Files in this item


Item metadata

dc.contributor.authorDe Ferrari, Luna
dc.contributor.authorAitken, Stuart
dc.contributor.authorvan Hemert, Jano
dc.contributor.authorGoryanin, Igor
dc.identifier.citationDe Ferrari , L , Aitken , S , van Hemert , J & Goryanin , I 2012 , ' EnzML : multi-label prediction of enzyme classes using InterPro signatures ' BMC Bioinformatics , vol. 13 , 61 .
dc.identifier.otherPURE: 35085614
dc.identifier.otherPURE UUID: 2a87b079-caa1-4a01-b6df-0624708ed880
dc.identifier.otherWOS: 000308067200001
dc.identifier.otherScopus: 84860154266
dc.descriptionLDF is funded by ONDEX DTG, BBSRC TPS Grant BB/F529038/1 of the Centre for Systems Biology at Edinburgh and the University of Newcastle. SA is supported by by a Wellcome Trust Value In People award and, together with IG, the Centre for Systems Biology at Edinburgh, a centre funded by the Biotechnology and Biological Sciences Research Council and the Engineering and Physical Sciences Research Council (BB/D019621/1). JVH was funded by various BBSRC and EPSRC granten
dc.description.abstractBackground: Manual annotation of enzymatic functions cannot keep up with automatic genome sequencing. In this work we explore the capacity of InterPro sequence signatures to automatically predict enzymatic function. Results: We present EnzML, a multi-label classification method that can efficiently account also for proteins with multiple enzymatic functions: 50,000 in UniProt. EnzML was evaluated using a standard set of 300,747 proteins for which the manually curated Swiss-Prot and KEGG databases have agreeing Enzyme Commission (EC) annotations. EnzML achieved more than 98% subset accuracy (exact match of all correct Enzyme Commission classes of a protein) for the entire dataset and between 87 and 97% subset accuracy in reannotating eight entire proteomes: human, mouse, rat, mouse-ear cress, fruit fly, the S. pombe yeast, the E. coli bacterium and the M. jannaschii archaebacterium. To understand the role played by the dataset size, we compared the cross-evaluation results of smaller datasets, either constructed at random or from specific taxonomic domains such as archaea, bacteria, fungi, invertebrates, plants and vertebrates. The results were confirmed even when the redundancy in the dataset was reduced using UniRef100, UniRef90 or UniRef50 clusters. Conclusions: InterPro signatures are a compact and powerful attribute space for the prediction of enzymatic function. This representation makes multi-label machine learning feasible in reasonable time (30 minutes to train on 300,747 instances with 10,852 attributes and 2,201 class values) using the Mulan Binary Relevance Nearest Neighbours algorithm implementation (BR-kNN).
dc.relation.ispartofBMC Bioinformaticsen
dc.rights© 2012 Ferrari et al.; licensee BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.en
dc.subjectEnzymatic functionen
dc.subjectAutomatic genome sequencingen
dc.subjectInterPro signaturesen
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subjectQH301 Biologyen
dc.titleEnzML : multi-label prediction of enzyme classes using InterPro signaturesen
dc.typeJournal articleen
dc.description.versionPublisher PDFen
dc.contributor.institutionUniversity of St Andrews.School of Chemistryen
dc.description.statusPeer revieweden

This item appears in the following Collection(s)

Show simple item record