Sequence-based prediction of protein domains.

TitleSequence-based prediction of protein domains.
Publication TypeJournal Article
Year of Publication2004
AuthorsLiu, J, Rost, B
JournalNucleic Acids Res
Date Published2004
KeywordsComputational Biology, Genomics, Neural Networks (Computer), Protein Structure, Tertiary, Reproducibility of Results, Sequence Analysis, Protein

Guessing the boundaries of structural domains has been an important and challenging problem in experimental and computational structural biology. Predictions were based on intuition, biochemical properties, statistics, sequence homology and other aspects of predicted protein structure. Here, we introduced CHOPnet, a de novo method that predicts structural domains in the absence of homology to known domains. Our method was based on neural networks and relied exclusively on information available for all proteins. Evaluating sustained performance through rigorous cross-validation on proteins of known structure, we correctly predicted the number of domains in 69% of all proteins. For 50% of the two-domain proteins the centre of the predicted boundary was closer than 20 residues to the boundary assigned from three-dimensional (3D) structures; this was about eight percentage points better than predictions by 'equal split'. Our results appeared to compare favourably with those from previously published methods. CHOPnet may be useful to restrict the experimental testing of different fragments for structure determination in the context of structural genomics.

Alternate JournalNucleic Acids Res.
PubMed ID15240828
PubMed Central IDPMC484172
Grant List1-P50-GM62413-01 / GM / NIGMS NIH HHS / United States
R01-GM63029-01 / GM / NIGMS NIH HHS / United States
R01-GM64633-01 / GM / NIGMS NIH HHS / United States
R01-LM07329-01 / LM / NLM NIH HHS / United States