Using Functional Domain Composition and Support Vector Machines for Prediction of Protein Subcellular Location*

By Kuo-Chen Chou, Yu-Dong Cai. Journal of Biological Chemistry, 2002

482 citations recorded by the source corpus.

Proteins are generally classified into the following 12 subcellular locations: 1) chloroplast, 2) cytoplasm, 3) cytoskeleton, 4) endoplasmic reticulum, 5) extracellular, 6) Golgi apparatus, 7) lysosome, 8) mitochondria, 9) nucleus, 10) peroxisome, 11) plasma membrane, and 12) vacuole. Because the function of a protein is closely correlated with its subcellular location, with the rapid increase in new protein sequences entering into databanks, it is vitally important for both basic research and pharmaceutical industry to establish a high throughput tool for predicting protein subcellular location. In this paper, a new concept, the so-called “functional domain composition” is introduced. Based on the novel concept, the representation for a protein can be defined as a vector in a high-dimensional space, where each of the clustered functional domains derived from the protein universe serves as a vector base. With such a novel representation for a protein, the support vector machine (SVM) algorithm is introduced for predicting protein subcellular location. High success rates are obtained by the self-consistency test, jackknife test, and independent dataset test, respectively. The current approach not only can play an important complementary role to the powerful covariant discriminant algorithm based on the pseudo amino acid composition representation (Chou, K. C. (2001)Proteins Struct. Funct. Genet. 43, 246–255; Correction (2001) Proteins Struct. Funct. Genet. 44, 60), but also may greatly stimulate the development of this area.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/a4016425c8a037aece8f7768a41ac41846a9abdb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Prediction of protein subcellular localization (2006, background): “8 proteins in 12 subcellular locations[30]; and the third set including 1443 protein sequences in five localization sites[9].”
Better prediction of sub‐cellular localization by combining evolutionary and structural information (2003, methodology): “using similar data sets with unspecified sequence similarity between testing and training.(77,78) Given the accuracy”
Some remarks on protein attribute prediction and pseudo amino acid composition (2010, methodology): “Using the FunD information to formulate protein samples was originally proposed in Cai et al. (2003) and Chou and Cai (2002) based on the 2005 FunDs in the SBASE-A database (Murvai et al., 2001).”
Recent progress in protein subcellular location prediction. (2007, background): “[ 21 ,68] based on the rationale that the function of a protein usually is correlated with its subcellular location.”
YLoc—an interpretable web server for predicting subcellular localization (2010, methodology): “More advanced methods incorporate annotation information such as functional domains and motifs (10,11), homologous proteins (12,13), Gene Ontology (GO) terms (14) and textual information (15,16).”
Classification of Nuclear Receptors Based on Amino Acid Composition and Dipeptide Composition* (2004, unknown): “In the past, the amino acid composition has been used to predict the domains structural class and subcellular localization of proteins (9-11).”
Predicting subcellular localization of proteins for Gram‐negative bacteria by support vector machines based on n‐peptide compositions (2004, background): “On the other hand, a number of studies (Cedano et al. 1997; Andrade et al. 1998; Reinhardt and Hubbard 1998; Yuan 1999; Chou 2001; Hua and Sun 2001; Chou and Cai 2002) have shown that amino acid compositions are useful in discriminating protein subcellular localization sites.”
iLoc-Euk: A Multi-Label Classifier for Predicting the Subcellular Localization of Singleplex and Multiplex Eukaryotic Proteins (2011, methodology): “One is to extract more useful information from protein sequences via different approaches or models, such as from the model of targeting or leader sequences [11], to the amino acid composition [13,27], to the amino acid pair composition [28], to the various modes [21,29,30,31, 32,33,34,35,36] of pse”
Multitask Learning for Protein Subcellular Location Prediction (2011, methodology): “We adapt and compare two specializations of the multitask learning algorithms on 20 different organisms.”
Plant-mPLoc: A Top-Down Strategy to Augment the Power for Predicting Plant Protein Subcellular Localization (2010, methodology): “Using FunD to formulate protein samples was originally proposed in [32,33] based on the 2005 FunDs in the SBASE-A database [34].”
Pseudo Amino Acid Composition and its Applications in Bioinformatics, Proteomics and System Biology (2009, background): “The concept of PseAAC was expanded to incorporate the functional domain information for predicting protein subcellular localization [49,175], membrane protein types [176,177], enzyme functional classes [53], protein structural class [68], protease types [178, 179], and protein quaternary structural ”
iPro54-PseKNC: a sequence-based predictor for identifying sigma-54 promoters in prokaryote with pseudo k-tuple nucleotide composition (2014, unknown): “A brief introduction about the formulation of SVM was given in (66,68).”
Update of PROFEAT: a web server for computing structural and physicochemical features of proteins and peptides from amino acid sequence (2006, methodology): “Amino acid and dipeptide composition are simplistic descriptors of protein sequence features (15), which have been used for predicting protein fold and structural classes (19,20), functional classes (16) and subcellular locations (17, 18 ) at accuracy levels of 72–95%, 83–97% and 79–91%, respectivel”
REVIEW : Recent advances in developing web-servers for predicting protein attributes (2009, methodology): “…the PseAA (pseudo amino acid) composition [18,53] or PseAAC approach, a complement to the GO approach in Cell-PLoc , can take into account some partial sequence order effects, the original PseAAC [18] missed the functional domain (FunD) [23] and sequential evolution (SeqE) information [54,55].”
MultiLoc2: integrating phylogeny and Gene Ontology terms improves subcellular protein localization prediction (2009, unknown): “Annotation-based predictors search the sequence for functional domains and motifs [24,25] or use textual information like Swiss-Prot keywords [26,27], Gene Ontology (GO) terms [28,29] or PubMed abstracts [30,31].”
Cell-PLoc: a package of Web servers for predicting subcellular localization of proteins in various organisms (2008, methodology): “23, a protein entry can be deﬁned as a high-dimensional vector in the FunD space according to the following procedure: search the FunD database for the protein sequence; if a hit is found, then the corresponding vector component is assigned 1, otherwise 0.”