Gajendra P. S. Raghava

Prediction of continuous B-cell epitopes in an antigen using recurrent neural network

B‐cell epitopes play a vital role in the development of peptide vaccines, in diagnosis of diseases, and also for allergy research. Experimental methods used for characterizing epitopes are time consuming and demand large resources. The availability of epitope prediction method(s) can rapidly aid experimenters in simplifying this problem. The standard feed‐forward (FNN) and recurrent neural network (RNN) have been used in this study for predicting B‐cell epitopes in an antigenic sequence. The networks have been trained and tested on a clean data set, which consists of 700 non‐redundant B‐cell epitopes obtained from Bcipep database and equal number of non‐epitopes obtained randomly from Swiss‐Prot database. The networks have been trained and tested at different input window length and hidden units. Maximum accuracy has been obtained using recurrent neural network (Jordan network) with a single hidden layer of 35 hidden units for window length of 16. The final network yields an overall prediction accuracy of 65.93% when tested by fivefold cross‐validation. The corresponding sensitivity, specificity, and positive prediction values are 67.14, 64.71, and 65.61%, respectively. It has been observed that RNN (JE) was more successful than FNN in the prediction of B‐cell epitopes. The length of the peptide is also important in the prediction of B‐cell epitopes from antigenic sequences. The webserver ABCpred is freely available at www.imtech.res.in/raghava/abcpred/. Proteins 2006.

ESLpred: SVM-based method for subcellular localization of eukaryotic proteins using dipeptide composition and PSI-BLAST

Automated prediction of subcellular localization of proteins is an important step in the functional annotation of genomes. The existing subcellular localization prediction methods are based on either amino acid composition or N-terminal characteristics of the proteins. In this paper, support vector machine (SVM) has been used to predict the subcellular location of eukaryotic proteins from their different features such as amino acid composition, dipeptide composition and physico-chemical properties. The SVM module based on dipeptide composition performed better than the SVM modules based on amino acid composition or physico-chemical properties. In addition, PSI-BLAST was also used to search the query sequence against the dataset of proteins (experimentally annotated proteins) to predict its subcellular location. In order to improve the prediction accuracy, we developed a hybrid module using all features of a protein, which consisted of an input vector of 458 dimensions (400 dipeptide compositions, 33 properties, 20 amino acid compositions of the protein and 5 from PSI-BLAST output). Using this hybrid approach, the prediction accuracies of nuclear, cytoplasmic, mitochondrial and extracellular proteins reached 95.3, 85.2, 68.2 and 88.9%, respectively. The overall prediction accuracy of SVM modules based on amino acid composition, physico-chemical properties, dipeptide composition and the hybrid approach was 78.1, 77.8, 82.9 and 88.0%, respectively. The accuracy of all the modules was evaluated using a 5-fold cross-validation technique. Assigning a reliability index (reliability index > or =3), 73.5% of prediction can be made with an accuracy of 96.4%. Based on the above approach, an online web server ESLpred was developed, which is available at http://www.imtech.res.in/raghava/eslpred/.

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.

CPPsite: a curated database of cell penetrating peptides

Delivering drug molecules into the cell is one of the major challenges in the process of drug development. In past, cell penetrating peptides have been successfully used for delivering a wide variety of therapeutic molecules into various types of cells for the treatment of multiple diseases. These peptides have unique ability to gain access to the interior of almost any type of cell. Due to the huge therapeutic applications of CPPs, we have built a comprehensive database ‘CPPsite’, of cell penetrating peptides, where information is compiled from the literature and patents. CPPsite is a manually curated database of experimentally validated 843 CPPs. Each entry provides information of a peptide that includes ID, PubMed ID, peptide name, peptide sequence, chirality, origin, nature of peptide, sub-cellular localization, uptake efficiency, uptake mechanism, hydrophobicity, amino acid frequency and composition, etc. A wide range of user-friendly tools have been incorporated in this database like searching, browsing, analyzing, mapping tools. In addition, we have derived various types of information from these peptide sequences that include secondary/tertiary structure, amino acid composition and physicochemical properties of peptides. This database will be very useful for developing models for predicting effective cell penetrating peptides. Database URL: http://crdd.osdd.net/raghava/cppsite/.

AlgPred: prediction of allergenic proteins and mapping of IgE epitopes

In this study a systematic attempt has been made to integrate various approaches in order to predict allergenic proteins with high accuracy. The dataset used for testing and training consists of 578 allergens and 700 non-allergens obtained from A. K. Bjorklund, D. Soeria-Atmadja, A. Zorzet, U. Hammerling and M. G. Gustafsson (2005) Bioinformatics, 21, 39–50. First, we developed methods based on support vector machine using amino acid and dipeptide composition and achieved an accuracy of 85.02 and 84.00%, respectively. Second, a motif-based method has been developed using MEME/MAST software that achieved sensitivity of 93.94 with 33.34% specificity. Third, a database of known IgE epitopes was searched and this predicted allergenic proteins with 17.47% sensitivity at specificity of 98.14%. Fourth, we predicted allergenic proteins by performing BLAST search against allergen representative peptides. Finally hybrid approaches have been developed, which combine two or more than two approaches. The performance of all these algorithms has been evaluated on an independent dataset of 323 allergens and on 101 725 non-allergens obtained from Swiss-Prot. A web server AlgPred has been developed for the predicting allergenic proteins and for mapping IgE epitopes on allergenic proteins (). AlgPred is available at .

Prediction of RNA binding sites in a protein using SVM and PSSM profile

RNA‐binding proteins (RBPs) play key roles in post‐transcriptional control of gene expression, which, along with transcriptional regulation, is a major way to regulate patterns of gene expression during development. Thus, the identification and prediction of RNA binding sites is an important step in comprehensive understanding of how RBPs control organism development. Combining evolutionary information and support vector machine (SVM), we have developed an improved method for predicting RNA binding sites or RNA interacting residues in a protein sequence. The prediction models developed in this study have been trained and tested on 86 RNA binding protein chains and evaluated using fivefold cross validation technique. First, a SVM model was developed that achieved a maximum Matthews correlation coefficient (MCC) of 0.31. The performance of this SVM model further improved the MCC from 0.31 to 0.45, when multiple sequence alignment in the form of PSSM profiles was used as input to the SVM, which is far better than the maximum MCC achieved by previous methods (0.41) on the same dataset. In addition, SVM models were also developed on an alternative dataset that contained 107 RBP chains. Utilizing PSSM as input information to the SVM, the training/testing on this alternate dataset achieved a maximum MCC of 0.32. Conclusively, the prediction performance of SVM models developed in this study is better than the existing methods on the same datasets. A web server ‘Pprint’ was also developed for predicting RNA binding residues in a protein sequence which is freely available at http://www.imtech.res.in/raghava/pprint/. Proteins 2008.

BcePred: Prediction of Continuous B-Cell Epitopes in Antigenic Sequences Using Physico-chemical Properties

A crucial step in designing of peptide vaccines involves the identification of B-cell epitopes. In past, numerous methods have been developed for predicting continuous B-cell epitopes, most of these methods are based on physico-chemical properties of amino acids. Presently, its difficult to say which residue property or method is better than the others because there is no independent evaluation or benchmarking of existing methods. In this study the performance of various residue properties commonly used in B-cell epitope prediction has been evaluated on a clean dataset. The dataset used in this study consists of 1029 non-redundant B cell epitopes obtained from Bcipep database and equally number of non-epitopes obtained randomly from SWISS-PROT database. The performance of each residue property used in existing methods has been computed at various thresholds on above dataset. The accuracy of prediction based on properties varies between 52.92% and 57.53%. We have also evaluated the combination of two or more properties as combination of parameters enhance the accuracy of prediction. Based on our analysis we have developed a method for predicting B cell epitopes, which combines four residue properties. The accuracy of this method is 58.70%, which is slightly better than any single residue property. A web server has been developed to predict B cell epitopes in an antigen sequence. The server is accessible from http://www.imtech.res.in/raghava/bcepred/.

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/

GPCRpred: an SVM-based method for prediction of families and subfamilies of G-protein coupled receptors

G-protein coupled receptors (GPCRs) belong to one of the largest superfamilies of membrane proteins and are important targets for drug design. In this study, a support vector machine (SVM)-based method, GPCRpred, has been developed for predicting families and subfamilies of GPCRs from the dipeptide composition of proteins. The dataset used in this study for training and testing was obtained from http://www.soe.ucsc.edu/research/compbio/gpcr/. The method classified GPCRs and non-GPCRs with an accuracy of 99.5% when evaluated using 5-fold cross-validation. The method is further able to predict five major classes or families of GPCRs with an overall Matthews correlation coefficient (MCC) and accuracy of 0.81 and 97.5% respectively. In recognizing the subfamilies of the rhodopsin-like family, the method achieved an average MCC and accuracy of 0.97 and 97.3% respectively. The method achieved overall accuracy of 91.3% and 96.4% at family and subfamily level respectively when evaluated on an independent/blind dataset of 650 GPCRs. A server for recognition and classification of GPCRs based on multiclass SVMs has been set up at http://www.imtech.res.in/raghava/gpcrpred/. We have also suggested subfamilies for 42 sequences which were previously identified as unclassified ClassA GPCRs. The supplementary information is available at http://www.imtech.res.in/raghava/gpcrpred/info.html.

Identification of DNA-binding proteins using support vector machines and evolutionary profiles

BackgroundIdentification of DNA-binding proteins is one of the major challenges in the field of genome annotation, as these proteins play a crucial role in gene-regulation. In this paper, we developed various SVM modules for predicting DNA-binding domains and proteins. All models were trained and tested on multiple datasets of non-redundant proteins.ResultsSVM models have been developed on DNAaset, which consists of 1153 DNA-binding and equal number of non DNA-binding proteins, and achieved the maximum accuracy of 72.42% and 71.59% using amino acid and dipeptide compositions, respectively. The performance of SVM model improved from 72.42% to 74.22%, when evolutionary information in form of PSSM profiles was used as input instead of amino acid composition. In addition, SVM models have been developed on DNAset, which consists of 146 DNA-binding and 250 non-binding chains/domains, and achieved the maximum accuracy of 79.80% and 86.62% using amino acid composition and PSSM profiles. The SVM models developed in this study perform better than existing methods on a blind dataset.ConclusionA highly accurate method has been developed for predicting DNA-binding proteins using SVM and PSSM profiles. This is the first study in which evolutionary information in form of PSSM profiles has been used successfully for predicting DNA-binding proteins. A web-server DNAbinder has been developed for identifying DNA-binding proteins and domains from query amino acid sequences http://www.imtech.res.in/raghava/dnabinder/.