Prediction of catalytic residues using Support Vector Machine with selected protein sequence and structural properties

Background  

The number of protein sequences deriving from genome sequencing projects is outpacing our knowledge about the function of these proteins. With the gap between experimentally characterized and uncharacterized proteins continuing to widen, it is necessary to develop new computational methods and tools for functional prediction. Knowledge of catalytic sites provides a valuable insight into protein function. Although many computational methods have been developed to predict catalytic residues and active sites, their accuracy remains low, with a significant number of false positives. In this paper, we present a novel method for the prediction of catalytic sites, using a carefully selected, supervised machine learning algorithm coupled with an optimal discriminative set of protein sequence conservation and structural properties.     

A discriminative method for protein remote homology detection and fold recognition combining Top-<Emphasis Type="Italic">n</Emphasis>-grams and latent semantic analysis

Background  

Protein remote homology detection and fold recognition are central problems in bioinformatics. Currently, discriminative methods based on support vector machine (SVM) are the most effective and accurate methods for solving these problems. A key step to improve the performance of the SVM-based methods is to find a suitable representation of protein sequences.     

Physicochemical property distributions for accurate and rapid pairwise protein homology detection

Background  

The challenge of remote homology detection is that many evolutionarily related sequences have very little similarity at the amino acid level. Kernel-based discriminative methods, such as support vector machines (SVMs), that use vector representations of sequences derived from sequence properties have been shown to have superior accuracy when compared to traditional approaches for the task of remote homology detection.     

Combining classifiers for improved classification of proteins from sequence or structure

Background  

Predicting a protein's structural or functional class from its amino acid sequence or structure is a fundamental problem in computational biology. Recently, there has been considerable interest in using discriminative learning algorithms, in particular support vector machines (SVMs), for classification of proteins. However, because sufficiently many positive examples are required to train such classifiers, all SVM-based methods are hampered by limited coverage.     

Impact of RNA structure on the prediction of donor and acceptor splice sites

Background  

gene identification in genomic DNA sequences by computational methods has become an important task in bioinformatics and computational gene prediction tools are now essential components of every genome sequencing project. Prediction of splice sites is a key step of all gene structural prediction algorithms.     

Motif kernel generated by genetic programming improves remote homology and fold detection

Background  

Protein remote homology detection is a central problem in computational biology. Most recent methods train support vector machines to discriminate between related and unrelated sequences and these studies have introduced several types of kernels. One successful approach is to base a kernel on shared occurrences of discrete sequence motifs. Still, many protein sequences fail to be classified correctly for a lack of a suitable set of motifs for these sequences.     

Towards the high-resolution protein structure prediction. Fast refinement of reduced models with all-atom force field

Background  

Although experimental methods for determining protein structure are providing high resolution structures, they cannot keep the pace at which amino acid sequences are resolved on the scale of entire genomes. For a considerable fraction of proteins whose structures will not be determined experimentally, computational methods can provide valuable information. The value of structural models in biological research depends critically on their quality. Development of high-accuracy computational methods that reliably generate near-experimental quality structural models is an important, unsolved problem in the protein structure modeling.     

Detection of non-coding RNAs on the basis of predicted secondary structure formation free energy change

Background  

Non-coding RNAs (ncRNAs) have a multitude of roles in the cell, many of which remain to be discovered. However, it is difficult to detect novel ncRNAs in biochemical screens. To advance biological knowledge, computational methods that can accurately detect ncRNAs in sequenced genomes are therefore desirable. The increasing number of genomic sequences provides a rich dataset for computational comparative sequence analysis and detection of novel ncRNAs.     

Determination of B-Cell Epitopes in Patients with Celiac Disease: Peptide Microarrays

Background

Most antibodies recognize conformational or discontinuous epitopes that have a specific 3-dimensional shape; however, determination of discontinuous B-cell epitopes is a major challenge in bioscience. Moreover, the current methods for identifying peptide epitopes often involve laborious, high-cost peptide screening programs. Here, we present a novel microarray method for identifying discontinuous B-cell epitopes in celiac disease (CD) by using a silicon-based peptide array and computational methods.

Methods

Using a novel silicon-based microarray platform with a multi-pillar chip, overlapping 12-mer peptide sequences of all native and deamidated gliadins, which are known to trigger CD, were synthesized in situ and used to identify peptide epitopes.

Results

Using a computational algorithm that considered disease specificity of peptide sequences, 2 distinct epitope sets were identified. Further, by combining the most discriminative 3-mer gliadin sequences with randomly interpolated3- or 6-mer peptide sequences, novel discontinuous epitopes were identified and further optimized to maximize disease discrimination. The final discontinuous epitope sets were tested in a confirmatory cohort of CD patients and controls, yielding 99% sensitivity and 100% specificity.

Conclusions

These novel sets of epitopes derived from gliadin have a high degree of accuracy in differentiating CD from controls, compared with standard serologic tests. The method of ultra-high-density peptide microarray described here would be broadly useful to develop high-fidelity diagnostic tests and explore pathogenesis.     

Prediction of transmembrane helix orientation in polytopic membrane proteins

Background  

Membrane proteins compose up to 30% of coding sequences within genomes. However, their structure determination is lagging behind compared with soluble proteins due to the experimental difficulties. Therefore, it is important to develop reliable computational methods to predict structures of membrane proteins.     

K-OPLS package: Kernel-based orthogonal projections to latent structures for prediction and interpretation in feature space

Background  

Kernel-based classification and regression methods have been successfully applied to modelling a wide variety of biological data. The Kernel-based Orthogonal Projections to Latent Structures (K-OPLS) method offers unique properties facilitating separate modelling of predictive variation and structured noise in the feature space. While providing prediction results similar to other kernel-based methods, K-OPLS features enhanced interpretational capabilities; allowing detection of unanticipated systematic variation in the data such as instrumental drift, batch variability or unexpected biological variation.     

CRYSTALP2: sequence-based protein crystallization propensity prediction

Background  

Current protocols yield crystals for <30% of known proteins, indicating that automatically identifying crystallizable proteins may improve high-throughput structural genomics efforts. We introduce CRYSTALP2, a kernel-based method that predicts the propensity of a given protein sequence to produce diffraction-quality crystals. This method utilizes the composition and collocation of amino acids, isoelectric point, and hydrophobicity, as estimated from the primary sequence, to generate predictions. CRYSTALP2 extends its predecessor, CRYSTALP, by enabling predictions for sequences of unrestricted size and provides improved prediction quality.     

pplacer: linear time maximum-likelihood and Bayesian phylogenetic placement of sequences onto a fixed reference tree

Background  

Likelihood-based phylogenetic inference is generally considered to be the most reliable classification method for unknown sequences. However, traditional likelihood-based phylogenetic methods cannot be applied to large volumes of short reads from next-generation sequencing due to computational complexity issues and lack of phylogenetic signal. "Phylogenetic placement," where a reference tree is fixed and the unknown query sequences are placed onto the tree via a reference alignment, is a way to bring the inferential power offered by likelihood-based approaches to large data sets.     

Identification of discriminative characteristics for clusters from biologic data with InforBIO software

Background  

There are a number of different methods for generation of trees and algorithms for phylogenetic analysis in the study of bacterial taxonomy. Genotypic information, such as SSU rRNA gene sequences, now plays a more prominent role in microbial systematics than does phenotypic information. However, the integration of genotypic and phenotypic information for polyphasic studies is necessary for the classification and identification of microbes. Thus, we devised an algorithm that objectively identifies discriminative characteristics for focused clusters on generated trees from a dataset composed of coded data, such as phenotypic information. Moreover, this algorithm has been integrated into the polyphasic analysis software, InforBIO.     

Phylogenetic distribution of large-scale genome patchiness

Background  

The phylogenetic distribution of large-scale genome structure (i.e. mosaic compositional patchiness) has been explored mainly by analytical ultracentrifugation of bulk DNA. However, with the availability of large, good-quality chromosome sequences, and the recently developed computational methods to directly analyze patchiness on the genome sequence, an evolutionary comparative analysis can be carried out at the sequence level.     

Predicting domain-domain interaction based on domain profiles with feature selection and support vector machines

Background  

Protein-protein interaction (PPI) plays essential roles in cellular functions. The cost, time and other limitations associated with the current experimental methods have motivated the development of computational methods for predicting PPIs. As protein interactions generally occur via domains instead of the whole molecules, predicting domain-domain interaction (DDI) is an important step toward PPI prediction. Computational methods developed so far have utilized information from various sources at different levels, from primary sequences, to molecular structures, to evolutionary profiles.     

Glycosylation site prediction using ensembles of Support Vector Machine classifiers

Background  

Glycosylation is one of the most complex post-translational modifications (PTMs) of proteins in eukaryotic cells. Glycosylation plays an important role in biological processes ranging from protein folding and subcellular localization, to ligand recognition and cell-cell interactions. Experimental identification of glycosylation sites is expensive and laborious. Hence, there is significant interest in the development of computational methods for reliable prediction of glycosylation sites from amino acid sequences.