http://precedings.nature.com/tags/protein%20function%20prediction Recently posted documents tagged with 'protein function prediction' Nature Publishing Group en Nature Precedings http://precedings.nature.com/images/header_logo.gif http://precedings.nature.com http://dx.doi.org/10.1038/npre.2008.2239.1 One of the most important tasks of modern bioinformatics is the development of computational tools that can be used to understand and treat human disease. To date, a variety of methods have been explored and algorithms for predicting whether a protein is involved in disease are gaining in their utility. Here, we describe an algorithm for detecting protein-disease associations based on the human protein-protein interaction network, known gene-disease associations, protein sequence, and protein functional information at the molecular level. Our method, PhenoPred (www.phenopred.org), is supervised: first, we map each protein onto the spaces of disease and functional terms based on distance to all annotated proteins in the protein interaction network. We also encode sequence, function, physicochemical, and predicted structural properties, such as secondary structure and flexibility. We then train support vector machines to detect a protein’s disease function for a number of terms in Disease Ontology (DO). We provided evidence that, despite the noise/incompleteness of experimental data and unfinished ontology of diseases, identification of candidate genes and proteins can be successful even when a large number of candidate disease terms are predicted on simultaneously. http://dx.doi.org/10.1038/npre.2008.2239.1 Fri, 29 Aug 2008 12:44:48 UTC Predicting Protein-Disease Relationships Using Sequence, Physicochemical Properties, and Molecular Function Information doi:10.1038/npre.2008.2239.1 2008-08-29 Predrag Radivojac Nature Precedings 2008-08-29T12:44:48Z Manuscript Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://precedings.nature.com/documents/2223/version/1 The emergence of “Systems Biology” in recent years highlights the systematic viewpoint of bio-system modeling. Building on such a background, Dual Descriptor Method, a generic methodology for biological sequence analysis is proposed. From a systematic perspective, Dual Descriptor is defined as a two element set of Composition Weight Map and Position Weight Function which aim at reflecting the composition and permutation information of a sequence. An alternate training algorithm is provided to get an optimum description of the building patterns of the sequences. In this paper, dual descriptor method has been applied to the analysis of two typical problems of molecular biology: gene identification and the prediction of protein function. Satisfactory and insightful results are achieved. Owing to the generality of this methodology, dual descriptor method has wide application perspective for many problems of pattern recognition, especially those involved in “Systems Biology”. http://precedings.nature.com/documents/2223/version/1 Tue, 26 Aug 2008 14:24:54 UTC Building Block and Building Rule: Dual Descriptor Method for Biological Sequence Analysis hdl:10101/npre.2008.2223.1 2008-08-26 Bin-Guang Ma Nature Precedings 2008-08-26T14:24:54Z Manuscript Biotechnology Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://dx.doi.org/10.1038/npre.2008.2199.1 There is an increasing number of proteins with known structure but unknown function. Determining their function would have a significant impact on understanding diseases and designing new therapeutics. Computational methods can facilitate function determination by identifying proteins that have high structural and chemical similarity. Below, we will briefly describe LabelHash, a new method for partial structure comparison. In partial structure comparison, the goal is to find the best geometric and chemical similarity between a set of 3D points called a motif and a subset of a set of 3D points called the target. Both the motif and targets are represented as sets of labeled 3D points. A motif is ideally composed of the functionally most-relevant residues in a binding site. The labels denote the type of residue. Motif points can have multiple labels to denote that substitutions are allowed. Any subset of the target that has labels that are compatible with the motif’s labels is called a match. The aim is to find statistically significant matches to a structural motif. Our method preprocesses a background database of targets such as a non-redundant subset of the Protein Data Bank in such a way that we can look up in constant time partial matches to a motif. Using a variant of the previously described match augmentation algorithm (1), we obtain complete matches to our motif. The nonparametric statistical model developed by (2,3) corrects for any bias introduced by our algorithm. This bias is introduced by excluding matches that do not satisfy certain geometric constraints for efficiency reasons. http://dx.doi.org/10.1038/npre.2008.2199.1 Fri, 15 Aug 2008 16:25:57 UTC LabelHash: A Flexible and Extensible Method for Matching Structural Motifs doi:10.1038/npre.2008.2199.1 2008-08-15 Mark Moll Nature Precedings 2008-08-15T16:25:57Z Manuscript Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://dx.doi.org/10.1038/npre.2008.2193.1 We present here the Extended Similarity Group (ESG) method, which annotates query sequences with Gene Ontology (GO) terms by assigning probability to each annotation computed based on iterative PSI-BLAST searches. Conventionally sequence homology based function annotation methods, such as BLAST, retrieve function information from top hits with a significant score (E-values). In contrast, the PFP method, which we have presented previously, goes one step ahead in utilizing a PSI-BLAST result by considering very weak hits even an E-value of up to 100 and also by incorporating the functional association between GO terms (FAM matrix) computed using term co-occurrence frequencies in the UniProt database. PFP is very successful which is evidenced by the top rank in the function prediction category in CASP7 competition. Our new approach, ESG method, further improves the accuracy of PFP by essentially employing PFP in an iterative fashion. An advantage of ESG is that it is built in a rigorous statistical framework: Unlike PFP method that assigns a weighted score to each GO term, ESG assigns a probability based on weights computed using the E-value of each hit sequence on the path between the original query sequence and the current hit sequence. http://dx.doi.org/10.1038/npre.2008.2193.1 Fri, 15 Aug 2008 16:17:50 UTC ESG: Extended Similarity Group method for automated protein function prediction doi:10.1038/npre.2008.2193.1 2008-08-15 Daisuke Kihara Nature Precedings 2008-08-15T16:17:50Z Manuscript Biotechnology Ecology Bioinformatics http://creativecommons.org/licenses/by/3.0/