SVM-PB-Pred: SVM Based Protein Block Prediction Method Using Sequence Profiles and Secondary Structures

Abstract

We developed a support vector machine based web server called SVM-PB-Pred, to predict the Protein Block for any given amino acid sequence. The input features of SVM-PB-Pred include i) sequence profiles (PSSM) and ii) actual secondary structures (SS) from DSSP method or predicted secondary structures from NPS@ and GOR4 methods. There were three combined input features PSSM+SS(DSSP), PSSM+SS(NPS@) and PSSM+SS(GOR4) used to test and train the SVM models. Similarly, four datasets RS90, DB433, LI1264 and SP1577 were used to develop the SVM models. These four SVM models developed were tested using three different benchmarking tests namely; (i) self consistency, (ii) seven fold cross validation test and (iii) independent case test. The maximum possible prediction accuracy of ~70% was observed in self consistency test for the SVM models of both LI1264 and SP1577 datasets, where PSSM+SS(DSSP) input features was used to test. The prediction accuracies were reduced to ~53% for PSSM+SS(NPS@) and ~43% for PSSM+SS(GOR4) in independent case test, for the SVM models of above two same datasets. Using our method, it is possible to predict the protein block letters for any query protein sequence with ~53% accuracy, when the SP1577 dataset and predicted secondary structure from NPS@ server were used. The SVM-PB-Pred server can be freely accessed through http://bioinfo.bdu.ac.in/~svmpbpred.

RPI-Pred: predicting ncRNA-protein interaction using sequence and structural information

“…Since many proteins and RNAs have not been experimentally solved, we must use theoretical approaches to predict their structures. Many research groups have proposed PB prediction methods ( 42 , 54 ). In this work, we used the PB-kPRED method ( 55 ) to predict the PB structures for proteins included in all the test data sets.…”

PB-kPRED: knowledge-based prediction of protein backbone conformation using a structural alphabet

“…For example, allowing only pentapeptides in PENTAdb from non-homologues to be accessible by the prediction algorithm emulates a scenario of attempting to predict the local structure of a protein with no homologue of known structure used. On the other hand, as in the case of other local structure prediction methods 12,[20][21][22]26 , it can be advantageous to have the ability to privilege information from homologous structures when these are available to predict the local structure of a query protein.…”

Peer Review #1 of "PBxplore: a tool to analyze local protein structure and deformability with Protein Blocks (v0.1)"

“…By reducing the complexity of protein structure, PBs have been shown to be efficient and relevant in a wide spectrum of applications. To name a few, PBs have been used to analyze protein contacts (Faure et al, 2008), to propose a structural model of a transmembrane protein (de Brevern, 2005), to reconstruct globular protein structures (Dong et al, 2007), to design peptides (Thomas et al, 2006), to define binding site signatures (Dudev and Lim, 2007), to perform local protein conformation predictions (Li et al, 2009;Rangwala et al, 2009;Suresh et al, 2013;Suresh and Parthasarathy, 2014;Zimmermann and Hansmann, 2008), to predict β -turns (Nguyen et al, 2014) and to understand local conformational changes due to mutations of the αIIbβ 3 human integrin (Jallu et al, 2012(Jallu et al, , 2013(Jallu et al, , 2014.…”