Hasan Oğul

A discriminative method for remote homology detection based on n-peptide compositions with reduced amino acid alphabets

In this study, n-peptide compositions are utilized for protein vectorization over a discriminative remote homology detection framework based on support vector machines (SVMs). The size of amino acid alphabet is gradually reduced for increasing values of n to make the method to conform with the memory resources in conventional workstations. A hash structure is implemented for accelerated search of n-peptides. The method is tested to see its ability to classify proteins into families on a subset of SCOP family database and compared against many of the existing homology detection methods including the most popular generative methods; SAM-98 and PSI-BLAST and the recent SVM methods; SVM-Fisher, SVM-BLAST and SVM-Pairwise. The results have demonstrated that the new method significantly outperforms SVM-Fisher, SVM-BLAST, SAM-98 and PSI-BLAST, while achieving a comparable accuracy with SVM-Pairwise. In terms of efficiency, it performs much better than SVM-Pairwise. It is shown that the information of n-peptide compositions with reduced amino acid alphabets provides an accurate and efficient means of protein vectorization for SVM-based sequence classification.

Subcellular Localization Prediction with New Protein Encoding Schemes

Subcellular localization is one of the key properties in functional annotation of proteins. Support vector machines (SVMs) have been widely used for automated prediction of subcellular localizations. Existing methods differ in the protein encoding schemes used. In this study, we present two methods for protein encoding to be used for SVM-based subcellular localization prediction: n-peptide compositions with reduced amino acid alphabets for larger values of n and pairwise sequence similarity scores based on whole sequence and N-terminal sequence. We tested the methods on a common benchmarking data set that consists of 2,427 eukaryotic proteins with four localization sites. As a result of 5-fold cross-validation tests, the encoding with n-peptide compositions provided the accuracies of 84.5, 88.9, 66.3, and 94.3 percent for cytoplasmic, extracellular, mitochondrial, and nuclear proteins, where the overall accuracy was 87.1 percent. The second method provided 83.6, 87.7, 87.9, and 90.5 percent accuracies for individual locations and 87.8 percent overall accuracy. A hybrid system, which we called PredLOC, makes a final decision based on the results of the two presented methods which achieved an overall accuracy of 91.3 percent, which is better than the achievements of many of the existing methods. The new system also outperformed the recent methods in the experiments conducted on a new-unique SWISSPROT test set

SVM-based detection of distant protein structural relationships using pairwise probabilistic suffix trees

A new method based on probabilistic suffix trees (PSTs) is defined for pairwise comparison of distantly related protein sequences. The new definition is adopted in a discriminative framework for protein classification using pairwise sequence similarity scores in feature encoding. The framework uses support vector machines (SVMs) to separate structurally similar and dissimilar examples. The new discriminative system, which we call as SVM-PST, has been tested for SCOP family classification task, and compared with existing discriminative methods SVM-BLAST and SVM-Pairwise, which use BLAST similarity scores and dynamic-programming-based alignment scores, respectively. Results have shown that SVM-PST is more accurate than SVM-BLAST and competitive with SVM-Pairwise. In terms of computational efficiency, PST-based comparison is much better than dynamic-programming-based alignment. We also compared our results with the original family-based PST approach from which we were inspired. The present method provides a significantly better solution for protein classification in comparison with the family-based PST model.

Variable context Markov chains for HIV protease cleavage site prediction.

Deciphering the knowledge of HIV protease specificity and developing computational tools for detecting its cleavage sites in protein polypeptide chain are very desirable for designing efficient and specific chemical inhibitors to prevent acquired immunodeficiency syndrome. In this study, we developed a generative model based on a generalization of variable order Markov chains (VOMC) for peptide sequences and adapted the model for prediction of their cleavability by certain proteases. The new method, called variable context Markov chains (VCMC), attempts to identify the context equivalence based on the evolutionary similarities between individual amino acids. It was applied for HIV-1 protease cleavage site prediction problem and shown to outperform existing methods in terms of prediction accuracy on a common dataset. In general, the method is a promising tool for prediction of cleavage sites of all proteases and encouraged to be used for any kind of peptide classification problem as well.

miSEA: microRNA set enrichment analysis

UNLABELLED We introduce a novel web-based tool, miSEA, for evaluating the enrichment of relevant microRNA sets from microarray and miRNA-Seq experiments on paired samples, e.g. control vs. TREATMENT In addition to a group of previously annotated microRNA sets embedded in the system, this tool enables users to import new microRNA sets obtained from their own research. miSEA allows users to select from a large variety of microRNA grouping categories, such as family classification, disease association, common regulation, and genome coordinates, based on their requirements. miSEA therefore provides a knowledge-driven representation scheme for microRNA experiments. The usability of this platform was discerned with a cancer type-classification task performed on a set of real microRNA expression profiling experiments. The miSEA web server is available at http://www.baskent.edu.tr/∼hogul/misea.

A probabilistic approach to microRNA-target binding

Elucidation of microRNA activity is a crucial step in understanding gene regulation. One key problem in this effort is how to model the pairwise interactions of microRNAs with their targets. As this interaction is strongly mediated by their sequences, it is desired to set-up a probabilistic model to explain the binding preferences between a microRNA sequence and the sequence of a putative target. To this end, we introduce a new model of microRNA-target binding, which transforms an aligned duplex to a new sequence and defines the likelihood of this sequence using a Variable Length Markov Chain. It offers a complementary representation of microRNA-mRNA pairs for microRNA target prediction tools or other probabilistic frameworks of integrative gene regulation analysis. The performance of present model is evaluated by its ability to predict microRNA-target mRNA interaction given a mature microRNA sequence and a putative mRNA binding site. In regard to classification accuracy, it outperforms two recent methods based on thermodynamic stability and sequence complementarity. The experiments can also unveil the effects of base pairing types and non-seed region in duplex formation.

Integrating Features for Accelerometer-based Activity Recognition

Activity recognition is the problem of predicting the current action of a person through the motion sensors worn on the body. The problem is usually approached as a supervised classification task where a discriminative model is learned from known samples and a new query is assigned to a known activity label using learned model. The challenging issue here is how to feed this classifier with a fixed number of features where the real input is a raw signal of varying length. In this study, we consider three possible feature sets, namely time-domain, frequency domain and wavelet-domain statistics, and their combinations to represent motion signal obtained from accelerometer reads worn in chest through a mobile phone. In addition to a systematic comparison of these feature sets, we also provide a comprehensive evaluation of some preprocessing steps such as filtering and feature selection. The results determine that feeding a random forest classifier with an ensemble selection of most relevant time-domain and frequency-domain features extracted from raw data can provide the highest accuracy in a real dataset.

Content-Based Search on Time-Series Microarray Databases

We study, for the first time, the problem of content-based searching of time-series microarray experiments in large-scale gene expression databases. The problem is approached as an information retrieval task where an entire ex-periment is taken as the query and searched through a collection of previous experiments. The relevant experiments are required to be retrieved based on the content similarity rather than their meta-data descriptions. A comparison of different fingerprinting and distance computation schemes is presented over a retrieval framework based on the differential expression of genes in varying time points.

TriClust: A Tool for Cross-Species Analysis of Gene Regulation

We present a software tool, called TriClust, for multi‐way analysis of gene expression data from paired conditions of multiple organisms. The analysis is based on a new concept called triclustering, which is an extension of biclustering over a third dimension that represents the organism where the microarray experiment is performed. TriClust provides a comprehensive analysis of co‐regulated genes under a subset of experimental conditions over multiple organisms. The results are visualized using heat‐maps and the Gene Ontology (GO) term enrichment statistics. The experimental results indicate that TriClust can successfully identify biologically significant triclusters and promote a useful tool for cross species analysis of gene regulation from microarray expression data. The statistical results suggest that, when available, triclustering on multi‐organism data can result in better gene clusters in comparison to biclustering on single‐organism data. The TriClust software is publicly available as a standalone program.

Eliminating rib shadows in chest radiographic images providing diagnostic assistance

A major difficulty with chest radiographic analysis is the invisibility of abnormalities caused by the superimposition of normal anatomical structures, such as ribs, over the main tissue to be examined. Suppressing the ribs with no information loss about the original tissue would therefore be helpful during manual identification or computer-aided detection of nodules on a chest radiographic image. In this study, we introduce a two-step algorithm for eliminating rib shadows in chest radiographic images. The algorithm first delineates the ribs using a novel hybrid self-template approach and then suppresses these delineated ribs using an unsupervised regression model that takes into account the change in proximal thickness (depth) of bone in the vertical axis. The performance of the system is evaluated using a benchmark set of real chest radiographic images. The experimental results determine that proposed method for rib delineation can provide higher accuracy than existing methods. The knowledge of rib delineation can remarkably improve the nodule detection performance of a current computer-aided diagnosis (CAD) system. It is also shown that the rib suppression algorithm can increase the nodule visibility by eliminating rib shadows while mostly preserving the nodule intensity.