Document Detail


Support vector machine-based method for subcellular localization of human proteins using amino acid compositions, their order, and similarity search.
MedLine Citation:
PMID:  15647269     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Here we report a systematic approach for predicting subcellular localization (cytoplasm, mitochondrial, nuclear, and plasma membrane) of human proteins. First, support vector machine (SVM)-based modules for predicting subcellular localization using traditional amino acid and dipeptide (i + 1) composition achieved overall accuracy of 76.6 and 77.8%, respectively. PSI-BLAST, when carried out using a similarity-based search against a nonredundant data base of experimentally annotated proteins, yielded 73.3% accuracy. To gain further insight, a hybrid module (hybrid1) was developed based on amino acid composition, dipeptide composition, and similarity information and attained better accuracy of 84.9%. In addition, SVM modules based on a different higher order dipeptide i.e. i + 2, i + 3, and i + 4 were also constructed for the prediction of subcellular localization of human proteins, and overall accuracy of 79.7, 77.5, and 77.1% was accomplished, respectively. Furthermore, another SVM module hybrid2 was developed using traditional dipeptide (i + 1) and higher order dipeptide (i + 2, i + 3, and i + 4) compositions, which gave an overall accuracy of 81.3%. We also developed SVM module hybrid3 based on amino acid composition, traditional and higher order dipeptide compositions, and PSI-BLAST output and achieved an overall accuracy of 84.4%. A Web server HSLPred (www.imtech.res.in/raghava/hslpred/ or bioinformatics.uams.edu/raghava/hslpred/) has been designed to predict subcellular localization of human proteins using the above approaches.
Authors:
Aarti Garg; Manoj Bhasin; Gajendra P S Raghava
Related Documents :
17135159 - Fatty acid composition of some medicinally useful seeds.
21949679 - Erythrocyte and porcine intestinal glycosphingolipids recognized by f4 fimbriae of ente...
10540979 - Proximate composition and mineral content of two edible species of cnidoscolus (tree sp...
18692589 - Free amino acids in spider hemolymph.
19908899 - Genotypic and environmental effects on coffee (coffea arabica l.) bean fatty acid profi...
22685129 - Ketoglutarate transport protein kgtp is secreted through the type iii secretion system ...
2952639 - Studies on glucosyltransferase and endogenous glucosyl acceptor in bacillus cereus ahu ...
2689929 - Diversion colitis: a nutritional deficiency syndrome?
16184009 - Kinetics of fatty acid binding ability of glycated human serum albumin.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't     Date:  2005-01-12
Journal Detail:
Title:  The Journal of biological chemistry     Volume:  280     ISSN:  0021-9258     ISO Abbreviation:  J. Biol. Chem.     Publication Date:  2005 Apr 
Date Detail:
Created Date:  2005-04-11     Completed Date:  2005-06-07     Revised Date:  2006-11-15    
Medline Journal Info:
Nlm Unique ID:  2985121R     Medline TA:  J Biol Chem     Country:  United States    
Other Details:
Languages:  eng     Pagination:  14427-32     Citation Subset:  IM    
Affiliation:
Bioinformatics Centre, Institute of Microbial Technology, Sector 39A, Chandigarh, India.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Cell Nucleus / metabolism
Cytoplasm / metabolism
Databases, Protein
Genetic Vectors
Humans
Internet
Mitochondria / metabolism
Models, Theoretical
Peptides / chemistry
Proteins / chemistry*
Proteomics / methods*
Reproducibility of Results
Software
Chemical
Reg. No./Substance:
0/Peptides; 0/Proteins

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Stability of the topoisomerase II closed clamp conformation may influence DNA-stimulated ATP hydroly...
Next Document:  Activation of budding yeast replication origins and suppression of lethal DNA damage effects on orig...