Ab initio and homology based prediction of protein domains by recursive neural networks

Files in This Item:
File Description SizeFormat 
Walsh_domains_2009.pdf570.82 kBAdobe PDFDownload
Title: Ab initio and homology based prediction of protein domains by recursive neural networks
Authors: Walsh, Ian
Martin, Alberto J. M.
Mooney, Catherine
Rubagotti, Enrico
Vullo, Alessandro
Pollastri, Gianluca
Permanent link: http://hdl.handle.net/10197/3396
Date: 26-Jun-2009
Abstract: Background: Proteins, especially larger ones, are often composed of individual evolutionary units, domains, which have their own function and structural fold. Predicting domains is an important intermediate step in protein analyses, including the prediction of protein structures. Results: We describe novel systems for the prediction of protein domain boundaries powered by Recursive Neural Networks. The systems rely on a combination of primary sequence and evolutionary information, predictions of structural features such as secondary structure, solvent accessibility and residue contact maps, and structural templates, both annotated for domains (from the SCOP dataset) and unannotated (from the PDB). We gauge the contribution of contact maps, and PDB and SCOP templates independently and for different ranges of template quality. We find that accurately predicted contact maps are informative for the prediction of domain boundaries, while the same is not true for contact maps predicted ab initio. We also find that gap information from PDB templates is informative, but, not surprisingly, less than SCOP annotations. We test both systems trained on templates of all qualities, and systems trained only on templates of marginal similarity to the query (less than 25% sequence identity). While the first batch of systems produces near perfect predictions in the presence of fair to good templates, the second batch outperforms or match ab initio predictors down to essentially any level of template quality. We test all systems in 5-fold cross-validation on a large non-redundant set of multi-domain and single domain proteins. The final predictors are state-of-the-art, with a template-less prediction boundary recall of 50.8% (precision 38.7%) within ± 20 residues and a single domain recall of 80.3% (precision 78.1%). The SCOP-based predictors achieve a boundary recall of 74% (precision 77.1%) again within ± 20 residues, and classify single domain proteins as such in over 85% of cases, when we allow a mix of bad and good quality templates. If we only allow marginal templates (max 25% sequence identity to the query) the scores remain high, with boundary recall and precision of 59% and 66.3%, and 80% of all single domain proteins predicted correctly. Conclusion: The systems presented here may prove useful in large-scale annotation of protein domains in proteins of unknown structure. The methods are available as public web servers at the address: http://distill.ucd.ie/shandy/ and we plan on running them on a multi-genomic scale and make the results public in the near future.
Funding Details: Science Foundation Ireland
Health Research Board
Type of material: Journal Article
Publisher: BioMed Central
Copyright (published version): 2009 Walsh et al; licensee BioMed Central Ltd.
Keywords: RNNNeural networksProtein domain prediction
Subject LCSH: Neural networks (Computer science)
DOI: 10.1186/1471-2105-10-195
Language: en
Status of Item: Peer reviewed
Appears in Collections:Computer Science Research Collection
CASL Research Collection

Show full item record

Citations 20

Last Week
Last month
checked on Aug 17, 2018

Page view(s) 5

checked on May 25, 2018

Download(s) 20

checked on May 25, 2018

Google ScholarTM



This item is licensed under a Creative Commons License Creative Commons