Support Vector Machine-based Method for Subcellular Localization of Human Proteins Using Amino Acid Compositions, Their Order, and Similarity Search
Journal of Biological ChemistryPublished 13 January 2005Open access
Aarti Garg, Manoj Bhasin, Gajendra P. S. Raghava
Citations232
SJR quartileQ1
SJR score1.71
SNIP1.00
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A systematic approach for predicting subcellular localization (cytoplasm, mitochondrial, nuclear, and plasma membrane) of human proteins by developing SVM modules based on amino acid composition, dipeptide composition, and similarity information and achieving overall accuracy of 84.4%.
Abstract
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.
Keywords
Biochemistry, Genetics and Molecular Biology
Journal of Molecular BiologyBasic local alignment search tool
94,539 Citations1990Stephen F. Altschul, Warren Gish +3 more
A new approach to rapid sequence comparison, basic local alignment search tool (BLAST), directly approximates alignments that optimize a measure of local similarity, the maximal segment pair (MSP) score.
The Annals of StatisticsMultivariate Adaptive Regression Splines
8,084 Citations1991Jerome H. Friedman
A new method is presented for flexible regression modeling of high dimensional data that takes the form of an expansion in product spline basis functions, where the number of basis functions as well as the parameters associated with each one are automatically determined by the data.
Molecular Cell Biology
5,646 Citations1986Harvey F. Lodish
Journal of Molecular BiologyPredicting Subcellular Localization of Proteins Based on their N-terminal Amino Acid Sequence
4,347 Citations2000Olof Emanuelsson, Henrik Nielsen +2 more
A neural network-based tool, TargetP, for large-scale subcellular location prediction of newly identified proteins has been developed and it is estimated that 10% of all plant proteins are mitochondrial and 14% chloroplastic, and that the abundance of secretory proteins, in both Arabidopsis and Homo, is around 10%.
Nucleic Acids ResearchThe SWISS-PROT protein sequence database and its supplement TrEMBL in 2000
3,133 Citations2000Amos Bairoch
The Human Proteomics Initiative (HPI), a major project to annotate all known human sequences according to the quality standards of SWISS-PROT, is described.
Proceedings of the National Academy of SciencesKnowledge-based analysis of microarray gene expression data by using support vector machines
2,315 Citations2000Michael P. Brown, William Noble Grundy +6 more
A method of functionally classifying genes by using gene expression data from DNA microarray hybridization experiments, based on the theory of support vector machines (SVMs), to predict functional roles for uncharacterized yeast ORFs based on their expression data is introduced.
IEEE Transactions on ComputersA Projection Pursuit Algorithm for Exploratory Data Analysis
1,635 Citations1974Jerome H. Friedman, John W. Tukey
GenomicsA knowledge base for predicting protein localization sites in eukaryotic cells
1,508 Citations1992Kenta Nakai, Minoru Kanehisa
An expert system is reported for predicting localization sites of proteins only from the information on the amino acid sequence and the source origin, which is powerful and flexible enough to be used in genome analyses.
Nucleic Acids ResearchComplete Sequence Analysis of the Genome of the Bacterium Mycoplasma Pneumoniae
1,162 Citations1996Ralf Himmelreich, H. Hilbert +4 more
The entire genome of the bacterium Mycoplasma pneumoniae M129 has been sequenced and a functional classification to a large number of ORFs is tentatively assigned and the biochemical and physiological properties of this bacterium are deduced.
BioinformaticsSupport vector machine approach for protein subcellular localization prediction
858 Citations2001Sujun Hua, Zhirong Sun
Support Vector Machine has been introduced to predict the subcellular localization of proteins from their amino acid compositions and can be a complementary method to other existing methods based on sorting signals.
Proteins Structure Function and BioinformaticsExpert system for predicting protein localization sites in gram‐negative bacteria
755 Citations1991Kenta Nakai, Minoru Kanehisa
BioinformaticsExtensive feature detection of N-terminal protein sorting signals
732 Citations2002Hideo Bannai, Yoshinori Tamada +3 more
This work has succeeded in finding rules whose prediction accuracies come close to that of TargetP, while still retaining a very simple and interpretable form.
Nucleic Acids ResearchUsing neural networks for prediction of the subcellular location of proteins
589 Citations1998Anita Reinhardt
With the subcellular location restricting a protein's possible function, this method should be a useful tool for the systematic analysis of genome data and is available via a server on the world wide web.
Journal of Biological ChemistryUsing Functional Domain Composition and Support Vector Machines for Prediction of Protein Subcellular Location
487 Citations2002Kuo‐Chen Chou, Yu‐Dong Cai
With such a novel representation for a protein, the support vector machine (SVM) algorithm is introduced for predicting protein subcellular location and high success rates are obtained by the self-consistency test, jackknife test, and independent dataset test.
Proteins Structure Function and BioinformaticsA novel approach to predicting protein structural classes in a (20–1)‐D amino acid composition space
431 Citations1995Kuo‐Chen Chou
A method has been developed that makes allowance for taking into account the coupling effect among different amino acid components of a protein by a covariance matrix and a theorem is presented and proved in Appendix A that is instructive for understanding the novel method at a deeper level.
Nucleic Acids ResearchPSORT-B: improving protein subcellular localization prediction for Gram-negative bacteria
426 Citations2003Jennifer L. Gardy
PSORT-B, an updated version of PSORT for Gram-negative bacteria, is presented, designed to favor high precision over high recall (sensitivity), and attained an overall precision of 97% and recall of 75% in 5-fold cross-validation tests, using a dataset the authors developed of 1443 proteins of experimentally known localization.
Protein Engineering Design and SelectionProtein subcellular location prediction
375 Citations1999Kuo‐Chen Chou, David W. Elrod
It is anticipated that the classification scheme and concept and also the prediction algorithm can expedite the functionality determination of new proteins, which can also be of use in the prioritization of genes and proteins identified by genomic efforts as potential molecular targets for drug design.
BMC BioinformaticsPrediction of MHC class I binding peptides, using SVMHC
332 Citations2002Pierre Dönnes, Arne Elofsson
This work presents a novel approach, SVMHC, based on support vector machines to predict the binding of peptides to MHC class I molecules, which seems to perform slightly better than two profile based methods, SYFPEITHI and HLA_BIND.
FEBS LettersPrediction of protein subcellular locations using Markov chain models
197 Citations1999Zheng Yuan
A novel method was introduced to predict protein subcellular locations from sequences using sequence data, and this method achieved a prediction accuracy higher than previous methods based on the amino acid composition.
Nucleic Acids ResearchThe major 5' determinant in stop codon read-through involves two adjacent adenines
93 Citations2004Sanaa Tork
It is proposed that the mRNA structure, depending on the nucleotides in the P site, is the main 5' determinant of read-through efficiency in Saccharomyces cerevisiae.
Nucleic Acids ResearchLOC3D: annotate sub-cellular localization for protein structures
41 Citations2003Rajesh Nair
The LOC3D database and web server can be used to predict sub-cellular localization for proteins for which only a predicted structure is available from threading servers, which makes the resource of particular interest to structural genomics initiatives.
Mathematical and Computer ModellingPROSET—a fast procedure to create non-redundant sets of protein sequences
32 Citations1992Volker Brendel
The PROSET computer program described efficiently eliminates redundant entries from a set of proteins and derives a block identity score between any two sequences that share at least one sufficiently long exact repeat, and discards the shorter of the two sequences if the score exceeds a user-defined threshold.
PubMedPrediction of subcellular localizations using amino acid composition and order.
26 Citations2001Yukiko Fujiwara, Minoru Asogawa
SortPred, a method using the amino acid composition and order for the prediction of subcellular localizations, achieved slightly higher prediction accuracy, 86% for plant and 91% for non-plant.