Support vector machine-based method for subcellular localization of human proteins using amino acid compositions, their order, and similarity search

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.     

A machine learning based method for the prediction of secretory proteins using amino acid composition, their order and similarity-search

Most of the prediction methods for secretory proteins require the presence of a correct N-terminal end of the preprotein for correct classification. As large scale genome sequencing projects sometimes assign the 5'-end of genes incorrectly, many proteins are encoded without the correct N-terminus leading to incorrect prediction. In this study, a systematic attempt has been made to predict secretory proteins irrespective of presence or absence of N-terminal signal peptides (also known as classical and non-classical secreted proteins respectively), using machine-learning techniques; artificial neural network (ANN) and support vector machine (SVM). We trained and tested our methods on a dataset of 3321 secretory and 3654 non-secretory mammalian proteins using five-fold cross-validation technique. First, ANN-based modules have been developed for predicting secretory proteins using 33 physico-chemical properties, amino acid composition and dipeptide composition and achieved accuracies of 73.1%, 76.1% and 77.1%, respectively. Similarly, SVM-based modules using 33 physico-chemical properties, amino acid, and dipeptide composition have been able to achieve accuracies of 77.4%, 79.4% and 79.9%, respectively. In addition, BLAST and PSI-BLAST modules designed for predicting secretory proteins based on similarity search achieved 23.4% and 26.9% accuracy, respectively. Finally, we developed a hybrid-approach by integrating amino acid and dipeptide composition based SVM modules and PSI-BLAST module that increased the accuracy to 83.2%, which is significantly better than individual modules. We also achieved high sensitivity of 60.4% with low value of 5% false positive predictions using hybrid module. A web server SRTpred has been developed based on above study for predicting classical and non-classical secreted proteins from whole sequence of mammalian proteins, which is available from http://www.imtech.res.in/raghava/srtpred/.     

Oxypred: prediction and classification of oxygen-binding proteins

This study describes a method for predicting and classifying oxygen-binding proteins. Firstly, support vector machine (SVM) modules were developed using amino acid composition and dipeptide composition for predicting oxygen-binding proteins, and achieved maximum accuracy of 85.5% and 87.8%, respectively. Secondly, an SVM module was developed based on amino acid composition, classifying the predicted oxygen-binding proteins into six classes with accuracy of 95.8%, 97.5%, 97.5%, 96.9%, 99.4%, and 96.0% for erythrocruorin, hemerythrin, hemocyanin, hemoglobin, leghemoglobin, and myoglobin proteins, respectively. Finally, an SVM module was developed using dipeptide composition for classifying the oxygen-binding proteins, and achieved maximum accuracy of 96.1%, 98.7%, 98.7%, 85.6%, 99.6%, and 93.3% for the above six classes, respectively. All modules were trained and tested by five-fold cross validation. Based on the above approach, a web server Oxypred was developed for predicting and classifying oxygen-binding proteins (available from http://www.imtech.res.in/raghava/oxypred/).     

BTXpred: prediction of bacterial toxins

This paper describes a method developed for predicting bacterial toxins from their amino acid sequences. All the modules, developed in this study, were trained and tested on a non-redundant dataset of 150 bacterial toxins that included 77 exotoxins and 73 endotoxins. Firstly, support vector machines (SVM) based modules were developed for predicting the bacterial toxins using amino acids and dipeptides composition and achieved an accuracy of 96.07% and 92.50%, respectively. Secondly, SVM based modules were developed for discriminating entotoxins and exotoxins, using amino acids and dipeptides composition and achieved an accuracy of 95.71% and 92.86%, respectively. In addition, modules have been developed for classifying the exotoxins (e.g. activate adenylate cyclase, activate guanylate cyclase, neurotoxins) using hidden Markov models (HMM), PSI-BLAST and a combination of the two and achieved overall accuracy of 95.75%, 97.87% and 100%, respectively. Based on the above study, a web server called 'BTXpred' has been developed, which is available at http://www.imtech.res.in/raghava/btxpred/. Supplementary information is available at http://www.imtech.res.in/raghava/btxpred/supplementary.html.     

Oxypred: Prediction and Classification of Oxygen-Binding Proteins

This study describes a method for predicting and classifying oxygen-binding pro- teins. Firstly, support vector machine (SVM) modules were developed using amino acid composition and dipeptide composition for predicting oxygen-binding pro- teins, and achieved maximum accuracy of 85.5% and 87.8%, respectively. Sec- ondly, an SVM module was developed based on amino acid composition, classify- ing the predicted oxygen-binding proteins into six classes with accuracy of 95.8%, 97.5%, 97.5%, 96.9%, 99.4%, and 96.0% for erythrocruorin, hemerythrin, hemo- cyanin, hemoglobin, leghemoglobin, and myoglobin proteins, respectively. Finally, an SVM module was developed using dipeptide composition for classifying the oxygen-binding proteins, and achieved maximum accuracy of 96.1%, 98.7%, 98.7%, 85.6%, 99.6%, and 93.3% for the above six classes, respectively. All modules were trained and tested by five-fold cross validation. Based on the above approach, a web server Oxypred was developed for predicting and classifying oxygen-binding proteins(available from http://www.imtech.res.in/raghava/oxypred/).     

Oxypred： Prediction and Classification of Oxygen-Binding Proteins

This study describes a method for predicting and classifying oxygen-binding pro- teins. Firstly, support vector machine (SVM) modules were developed using amino acid composition and dipeptide composition for predicting oxygen-binding pro- teins, and achieved maximum accuracy of 85.5% and 87.8%, respectively. Sec- ondly, an SVM module was developed based on amino acid composition, classify- ing the predicted oxygen-binding proteins into six classes with accuracy of 95.8%, 97.5%, 97.5%, 96.9%, 99.4%, and 96.0% for erythrocruorin, hemerythrin, hemo- cyanin, hemoglobin, leghemoglobin, and myoglobin proteins, respectively. Finally, an SVM module was developed using dipeptide composition for classifying the oxygen-binding proteins, and achieved maximum accuracy of 96.1%, 98.7%, 98.7%, 85.6%, 99.6%, and 93.3% for the above six classes, respectively. All modules were trained and tested by five-fold cross validation. Based on the above approach, a web server Oxypred was developed for predicting and classifying oxygen-binding proteins(available from http://www.imtech.res.in/raghava/oxypred/).     

VGIchan： Prediction and Classification of Voltage-Gated Ion Channels

This study describes methods for predicting and classifying voltage-gated ion channels. Firstly, a standard support vector machine （SVM） method was developed for predicting ion channels by using amino acid composition and dipeptide composition, with an accuracy of 82.89% and 85.56%, respectively. The accuracy of this SVM method was improved from 85.56% to 89.11% when combined with PSIBLAST similarity search. Then we developed an SVM method for classifying ion channels （potassium, sodium, calcium, and chloride） by using dipeptide composition and achieved an overall accuracy of 96.89%. We further achieved a classification accuracy of 97.78% by using a hybrid method that combines dipeptidebased SVM and hidden Markov model methods. A web server VGIchan has been developed for predicting and classifying voltage-gated ion channels using the above approaches. VGIchan is freely available at www.imtech.res.in/raghava/vgichan/.     

RSLpred: an integrative system for predicting subcellular localization of rice proteins combining compositional and evolutionary information

The attainment of complete map‐based sequence for rice (Oryza sativa) is clearly a major milestone for the research community. Identifying the localization of encoded proteins is the key to understanding their functional characteristics and facilitating their purification. Our proposed method, RSLpred, is an effort in this direction for genome‐scale subcellular prediction of encoded rice proteins. First, the support vector machine (SVM)‐based modules have been developed using traditional amino acid‐, dipeptide‐ (i+1) and four parts‐amino acid composition and achieved an overall accuracy of 81.43, 80.88 and 81.10%, respectively. Secondly, a similarity search‐based module has been developed using position‐specific iterated‐basic local alignment search tool and achieved 68.35% accuracy. Another module developed using evolutionary information of a protein sequence extracted from position‐specific scoring matrix achieved an accuracy of 87.10%. In this study, a large number of modules have been developed using various encoding schemes like higher‐order dipeptide composition, N‐ and C‐terminal, splitted amino acid composition and the hybrid information. In order to benchmark RSLpred, it was tested on an independent set of rice proteins where it outperformed widely used prediction methods such as TargetP, Wolf‐PSORT, PA‐SUB, Plant‐Ploc and ESLpred. To assist the plant research community, an online web tool ‘RSLpred’ has been developed for subcellular prediction of query rice proteins, which is freely accessible at http://www.imtech.res.in/raghava/rslpred.     

SSPred: A prediction server based on SVM for the identification and classification of proteins involved in bacterial secretion systems

Protein secretion systems used by almost all bacteria are highly significant for the normal existence and interaction of bacteria with their host. The accumulation of genome sequence data in past few years has provided great insights into the distribution and function of these secretion systems. In this study, a support vector machine (SVM)- based method, SSPred was developed for the automated functional annotation of proteins involved in secretion systems further classifying them into five major sub-types (Type-I, Type-II, Type-III, Type-IV and Sec systems). The dataset used in this study for training and testing was obtained from KEGG and SwissProt database and was curated in order to avoid redundancy. To overcome the problem of imbalance in positive and negative dataset, an ensemble of SVM modules, each trained on a balanced subset of the training data were used. Firstly, protein sequence features like amino-acid composition (AAC), dipeptide composition (DPC) and physico-chemical composition (PCC) were used to develop the SVM-based modules that achieved an average accuracy of 84%, 85.17% and 82.59%, respectively. Secondly, a hybrid module (hybrid-I) integrating all the previously used features was developed that achieved an average accuracy of 86.12%. Another hybrid module (hybrid-II) developed using evolutionary information of a protein sequence extracted from position-specific scoring matrix and amino-acid composition achieved a maximum average accuracy of 89.73%. On unbiased evaluation using an independent data set, SSPred showed good prediction performance in identification and classification of secretion systems. SSPred is a freely available World Wide Web server at http//www.bioinformatics.org/sspred.     

Predicting sub-cellular localization of tRNA synthetases from their primary structures

Since endo-symbiotic events occur, all genes of mitochondrial aminoacyl tRNA synthetase (AARS) were lost or transferred from ancestral mitochondrial genome into the nucleus. The canonical pattern is that both cytosolic and mitochondrial AARSs coexist in the nuclear genome. In the present scenario all mitochondrial AARSs are nucleus-encoded, synthesized on cytosolic ribosomes and post-translationally imported from the cytosol into the mitochondria in eukaryotic cell. The site-based discrimination between similar types of enzymes is very challenging because they have almost same physico-chemical properties. It is very important to predict the sub-cellular location of AARSs, to understand the mitochondrial protein synthesis. We have analyzed and optimized the distinguishable patterns between cytosolic and mitochondrial AARSs. Firstly, support vector machines (SVM)-based modules have been developed using amino acid and dipeptide compositions and achieved Mathews correlation coefficient (MCC) of 0.82 and 0.73, respectively. Secondly, we have developed SVM modules using position-specific scoring matrix and achieved the maximum MCC of 0.78. Thirdly, we developed SVM modules using N-terminal, intermediate residues, C-terminal and split amino acid composition (SAAC) and achieved MCC of 0.82, 0.70, 0.39 and 0.86, respectively. Finally, a SVM module was developed using selected attributes of split amino acid composition (SA-SAAC) approach and achieved MCC of 0.92 with an accuracy of 96.00%. All modules were trained and tested on a non-redundant data set and evaluated using fivefold cross-validation technique. On the independent data sets, SA-SAAC based prediction model achieved MCC of 0.95 with an accuracy of 97.77%. The web-server 'MARSpred' based on above study is available at http://www.imtech.res.in/raghava/marspred/.     

Support vector machine based prediction of glutathione S-transferase proteins

Glutathione S-transferase (GST) proteins play vital role in living organism that includes detoxification of exogenous and endogenous chemicals, survivability during stress condition. This paper describes a method developed for predicting GST proteins. We have used a dataset of 107 GST and 107 non-GST proteins for training and the performance of the method was evaluated with five-fold cross-validation technique. First a SVM based method has been developed using amino acid and dipeptide composition and achieved the maximum accuracy of 91.59% and 95.79% respectively. In addition we developed a SVM based method using tripeptide composition and achieved maximum accuracy 97.66% which is better than accuracy achieved by HMM based searching (96.26%). Based on above study a web-server GSTPred has been developed (http://www.imtech.res.in/raghava/gstpred/).     

PSLpred: prediction of subcellular localization of bacterial proteins

SUMMARY: We developed a web server PSLpred for predicting subcellular localization of gram-negative bacterial proteins with an overall accuracy of 91.2%. PSLpred is a hybrid approach-based method that integrates PSI-BLAST and three SVM modules based on compositions of residues, dipeptides and physico-chemical properties. The prediction accuracies of 90.7, 86.8, 90.3, 95.2 and 90.6% were attained for cytoplasmic, extracellular, inner-membrane, outer-membrane and periplasmic proteins, respectively. Furthermore, PSLpred was able to predict approximately 74% of sequences with an average prediction accuracy of 98% at RI = 5. AVAILABILITY: PSLpred is available at http://www.imtech.res.in/raghava/pslpred/     

Prediction of transmembrane regions of beta-barrel proteins using ANN- and SVM-based methods

This article describes a method developed for predicting transmembrane beta-barrel regions in membrane proteins using machine learning techniques: artificial neural network (ANN) and support vector machine (SVM). The ANN used in this study is a feed-forward neural network with a standard back-propagation training algorithm. The accuracy of the ANN-based method improved significantly, from 70.4% to 80.5%, when evolutionary information was added to a single sequence as a multiple sequence alignment obtained from PSI-BLAST. We have also developed an SVM-based method using a primary sequence as input and achieved an accuracy of 77.4%. The SVM model was modified by adding 36 physicochemical parameters to the amino acid sequence information. Finally, ANN- and SVM-based methods were combined to utilize the full potential of both techniques. The accuracy and Matthews correlation coefficient (MCC) value of SVM, ANN, and combined method are 78.5%, 80.5%, and 81.8%, and 0.55, 0.63, and 0.64, respectively. These methods were trained and tested on a nonredundant data set of 16 proteins, and performance was evaluated using "leave one out cross-validation" (LOOCV). Based on this study, we have developed a Web server, TBBPred, for predicting transmembrane beta-barrel regions in proteins (available at http://www.imtech.res.in/raghava/tbbpred).     

LIPOPREDICT: bacterial lipoprotein prediction server

Bacterial lipoproteins have many important functions owing to their essential nature and roles in pathogenesis and represent a class of possible vaccine candidates. The prediction of bacterial lipoproteins from sequence is thus an important task for computational vaccinology. A Support Vector Machines (SVM) based module for predicting bacterial lipoproteins, LIPOPREDICT, has been developed. The best performing sequence model were generated using selected dipeptide composition, which gave 97% accuracy of prediction. The results obtained were compared very well with those of previously developed methods.     

DPROT: prediction of disordered proteins using evolutionary information

The association of structurally disordered proteins with a number of diseases has engendered enormous interest and therefore demands a prediction method that would facilitate their expeditious study at molecular level. The present study describes the development of a computational method for predicting disordered proteins using sequence and profile compositions as input features for the training of SVM models. First, we developed the amino acid and dipeptide compositions based SVM modules which yielded sensitivities of 75.6 and 73.2% along with Matthew’s Correlation Coefficient (MCC) values of 0.75 and 0.60, respectively. In addition, the use of predicted secondary structure content (coil, sheet and helices) in the form of composition values attained a sensitivity of 76.8% and MCC value of 0.77. Finally, the training of SVM models using evolutionary information hidden in the multiple sequence alignment profile improved the prediction performance by achieving a sensitivity value of 78% and MCC of 0.78. Furthermore, when evaluated on an independent dataset of partially disordered proteins, the same SVM module provided a correct prediction rate of 86.6%. Based on the above study, a web server (“DPROT”) was developed for the prediction of disordered proteins, which is available at .     

GNBSL: a new integrative system to predict the subcellular location for Gram-negative bacteria proteins

This paper proposes a new integrative system (GNBSL--Gram-negative bacteria subcellular localization) for subcellular localization specifized on the Gram-negative bacteria proteins. First, the system generates a position-specific frequency matrix (PSFM) and a position-specific scoring matrix (PSSM) for each protein sequence by searching the Swiss-Prot database. Then different features are extracted by four modules from the PSFM and the PSSM. The features include whole-sequence amino acid composition, N- and C-terminus amino acid composition, dipeptide composition, and segment composition. Four probabilistic neural network (PNN) classifiers are used to classify these modules. To further improve the performance, two modules trained by support vector machine (SVM) are added in this system. One module extracts the residue-couple distribution from the amino acid sequence and the other module applies a pairwise profile alignment kernel to measure the local similarity between every two sequences. Finally, an additional SVM is used to fuse the outputs from the six modules. Test on a benchmark dataset shows that the overall success rate of GNBSL is higher than those of PSORT-B, CELLO, and PSLpred. A web server GNBSL can be visited from http://166.111.24.5/webtools/GNBSL/index.htm.     

Prediction of methylated CpGs in DNA sequences using a support vector machine

DNA methylation plays a key role in the regulation of gene expression. The most common type of DNA modification consists of the methylation of cytosine in the CpG dinucleotide. At the present time, there is no method available for the prediction of DNA methylation sites. Therefore, in this study we have developed a support vector machine (SVM)-based method for the prediction of cytosine methylation in CpG dinucleotides. Initially a SVM module was developed from human data for the prediction of human-specific methylation sites. This module achieved a MCC and AUC of 0.501 and 0.814, respectively, when evaluated using a 5-fold cross-validation. The performance of this SVM-based module was better than the classifiers built using alternative machine learning and statistical algorithms including artificial neural networks, Bayesian statistics, and decision trees. Additional SVM modules were also developed based on mammalian- and vertebrate-specific methylation patterns. The SVM module based on human methylation patterns was used for genome-wide analysis of methylation sites. This analysis demonstrated that the percentage of methylated CpGs is higher in UTRs as compared to exonic and intronic regions of human genes. This method is available on line for public use under the name of Methylator at http://bio.dfci.harvard.edu/Methylator/.     

A neural network method for prediction of beta-turn types in proteins using evolutionary information

MOTIVATION: The prediction of beta-turns is an important element of protein secondary structure prediction. Recently, a highly accurate neural network based method Betatpred2 has been developed for predicting beta-turns in proteins using position-specific scoring matrices (PSSM) generated by PSI-BLAST and secondary structure information predicted by PSIPRED. However, the major limitation of Betatpred2 is that it predicts only beta-turn and non-beta-turn residues and does not provide any information of different beta-turn types. Thus, there is a need to predict beta-turn types using an approach based on multiple sequence alignment, which will be useful in overall tertiary structure prediction. RESULTS: In the present work, a method has been developed for the prediction of beta-turn types I, II, IV and VIII. For each turn type, two consecutive feed-forward back-propagation networks with a single hidden layer have been used where the first sequence-to-structure network has been trained on single sequences as well as on PSI-BLAST PSSM. The output from the first network along with PSIPRED predicted secondary structure has been used as input for the second-level structure-to-structure network. The networks have been trained and tested on a non-homologous dataset of 426 proteins chains by 7-fold cross-validation. It has been observed that the prediction performance for each turn type is improved significantly by using multiple sequence alignment. The performance has been further improved by using a second level structure-to-structure network and PSIPRED predicted secondary structure information. It has been observed that Type I and II beta-turns have better prediction performance than Type IV and VIII beta-turns. The final network yields an overall accuracy of 74.5, 93.5, 67.9 and 96.5% with MCC values of 0.29, 0.29, 0.23 and 0.02 for Type I, II, IV and VIII beta-turns, respectively, and is better than random prediction. AVAILABILITY: A web server for prediction of beta-turn types I, II, IV and VIII based on above approach is available at http://www.imtech.res.in/raghava/betaturns/ and http://bioinformatics.uams.edu/mirror/betaturns/ (mirror site).