Ganesan Pugalenthi

Prediction of Apoptosis Protein Locations with Genetic Algorithms and Support Vector Machines Through a New Mode of Pseudo Amino Acid Composition

Apoptosis is an essential process for controlling tissue homeostasis by regulating a physiological balance between cell proliferation and cell death. The subcellular locations of proteins performing the cell death are determined by mostly independent cellular mechanisms. The regular bioinformatics tools to predict the subcellular locations of such apoptotic proteins do often fail. This work proposes a model for the sorting of proteins that are involved in apoptosis, allowing us to both the prediction of their subcellular locations as well as the molecular properties that contributed to it. We report a novel hybrid Genetic Algorithm (GA)/Support Vector Machine (SVM) approach to predict apoptotic protein sequences using 119 sequence derived properties like frequency of amino acid groups, secondary structure, and physicochemical properties. GA is used for selecting a near-optimal subset of informative features that is most relevant for the classification. Jackknife cross-validation is applied to test the predictive capability of the proposed method on 317 apoptosis proteins. Our method achieved 85.80% accuracy using all 119 features and 89.91% accuracy for 25 features selected by GA. Our models were examined by a test dataset of 98 apoptosis proteins and obtained an overall accuracy of 90.34%. The results show that the proposed approach is promising; it is able to select small subsets of features and still improves the classification accuracy. Our model can contribute to the understanding of programmed cell death and drug discovery. The software and dataset are available at http://www.inb.uni-luebeck.de/tools-demos/apoptosis/GASVM.

DNA-Prot: identification of DNA binding proteins from protein sequence information using random forest.

Abstract DNA-binding proteins (DNABPs) are important for various cellular processes, such as transcriptional regulation, recombination, replication, repair, and DNA modification. So far various bioinformatics and machine learning techniques have been applied for identification of DNA-binding proteins from protein structure. Only few methods are available for the identification of DNA binding proteins from protein sequence. In this work, we report a random forest method, DNA-Prot, to identify DNA binding proteins from protein sequence. Training was performed on the dataset containing 146 DNA-binding proteins and 250 non DNA-binding proteins. The algorithm was tested on the dataset containing 92 DNA-binding proteins and 100 non DNA-binding proteins. We obtained 80.31% accuracy from training and 84.37% accuracy from testing. Benchmarking analysis on the independent of 823 DNA-binding proteins and 823 non DNA-binding proteins shows that our approach can distinguish DNA-binding proteins from non DNA-binding proteins with more than 80% accuracy. We also compared our method with DNAbinder method on test dataset and two independent datasets. Comparable performance was observed from both methods on test dataset. In the benchmark dataset containing 823 DNA-binding proteins and 823 non DNA-binding proteins, we obtained significantly better performance from DNA-Prot with 81.83% accuracy whereas DNAbinder achieved only 61.42% accuracy using amino acid composition and 63.5% using PSSM profile. Similarly, DNA-Prot achived better performance rate from the benchmark dataset containing 88 DNA-binding proteins and 233 non DNA-binding proteins. This result shows DNA-Prot can be efficiently used to identify DNA binding proteins from sequence information. The dataset and standalone version of DNA-Prot software can be obtained from http://www3.ntu.edu.sg/home/EPNSugan/index_files/dnaprot.htm.

Predicting protein structural class by SVM with class-wise optimized features and decision probabilities

Determination of protein structural class solely from sequence information is a challenging task. Several attempts to solve this problem using various methods can be found in literature. We present support vector machine (SVM) approach where probability-based decision is used along with class-wise optimized feature sets. This approach has two distinguishing characteristics from earlier attempts: (1) it uses class-wise optimized features and (2) decisions of different SVM classifiers are coupled with probability estimates to make the final prediction. The algorithm was tested on three datasets, containing 498 domains, 1092 domains and 5261 domains. Ten-fold external cross-validation was performed to assess the performance of the algorithm. Significantly high accuracy of 92.89% was obtained for the 498-dataset. We achieved 54.67% accuracy for the dataset with 1092 domains, which is better than the previously reported best accuracy of 53.8%. We obtained 59.43% prediction accuracy for the larger and less redundant 5261-dataset. We also investigated the advantage of using class-wise features over union of these features (conventional approach) in one-vs.-all SVM framework. Our results clearly show the advantage of using class-wise optimized features. Brief analysis of the selected class-wise features indicates their biological significance.

An approach for classification of highly imbalanced data using weighting and undersampling

Real-world datasets commonly have issues with data imbalance. There are several approaches such as weighting, sub-sampling, and data modeling for handling these data. Learning in the presence of data imbalances presents a great challenge to machine learning. Techniques such as support-vector machines have excellent performance for balanced data, but may fail when applied to imbalanced datasets. In this paper, we propose a new undersampling technique for selecting instances from the majority class. The performance of this approach was evaluated in the context of several real biological imbalanced data. The ratios of negative to positive samples vary from ~9:1 to ~100:1. Useful classifiers have high sensitivity and specificity. Our results demonstrate that the proposed selection technique improves the sensitivity compared to weighted support-vector machine and available results in the literature for the same datasets.

RSARF: Prediction of Residue Solvent Accessibility from Protein Sequence Using Random Forest Method

Prediction of protein structure from its amino acid sequence is still a challenging problem. The complete physicochemical understanding of protein folding is essential for the accurate structure prediction. Knowledge of residue solvent accessibility gives useful insights into protein structure prediction and function prediction. In this work, we propose a random forest method, RSARF, to predict residue accessible surface area from protein sequence information. The training and testing was performed using 120 proteins containing 22006 residues. For each residue, buried and exposed state was computed using five thresholds (0%, 5%, 10%, 25%, and 50%). The prediction accuracy for 0%, 5%, 10%, 25%, and 50% thresholds are 72.9%, 78.25%, 78.12%, 77.57% and 72.07% respectively. Further, comparison of RSARF with other methods using a benchmark dataset containing 20 proteins shows that our approach is useful for prediction of residue solvent accessibility from protein sequence without using structural information. The RSARF program, datasets and supplementary data are available at http://caps.ncbs.res.in/download/pugal/RSARF/.

Identification of catalytic residues from protein structure using support vector machine with sequence and structural features

Identification of catalytic residues can provide valuable insights into protein function. With the increasing number of protein 3D structures having been solved by X-ray crystallography and NMR techniques, it is highly desirable to develop an efficient method to identify their catalytic sites. In this paper, we present an SVM method for the identification of catalytic residues using sequence and structural features. The algorithm was applied to the 2096 catalytic residues derived from Catalytic Site Atlas database. We obtained overall prediction accuracy of 88.6% from 10-fold cross validation and 95.76% from resubstitution test. Testing on the 254 catalytic residues shows our method can correctly predict all 254 residues. This result suggests the usefulness of our approach for facilitating the identification of catalytic residues from protein structures.

BLProt: prediction of bioluminescent proteins based on support vector machine and relieff feature selection

BackgroundBioluminescence is a process in which light is emitted by a living organism. Most creatures that emit light are sea creatures, but some insects, plants, fungi etc, also emit light. The biotechnological application of bioluminescence has become routine and is considered essential for many medical and general technological advances. Identification of bioluminescent proteins is more challenging due to their poor similarity in sequence. So far, no specific method has been reported to identify bioluminescent proteins from primary sequence.ResultsIn this paper, we propose a novel predictive method that uses a Support Vector Machine (SVM) and physicochemical properties to predict bioluminescent proteins. BLProt was trained using a dataset consisting of 300 bioluminescent proteins and 300 non-bioluminescent proteins, and evaluated by an independent set of 141 bioluminescent proteins and 18202 non-bioluminescent proteins. To identify the most prominent features, we carried out feature selection with three different filter approaches, ReliefF, infogain, and mRMR. We selected five different feature subsets by decreasing the number of features, and the performance of each feature subset was evaluated.ConclusionBLProt achieves 80% accuracy from training (5 fold cross-validations) and 80.06% accuracy from testing. The performance of BLProt was compared with BLAST and HMM. High prediction accuracy and successful prediction of hypothetical proteins suggests that BLProt can be a useful approach to identify bioluminescent proteins from sequence information, irrespective of their sequence similarity. The BLProt software is available at http://www.inb.uni-luebeck.de/tools-demos/bioluminescent%20protein/BLProt

A machine learning approach for the identification of odorant binding proteins from sequence-derived properties

BackgroundOdorant binding proteins (OBPs) are believed to shuttle odorants from the environment to the underlying odorant receptors, for which they could potentially serve as odorant presenters. Although several sequence based search methods have been exploited for protein family prediction, less effort has been devoted to the prediction of OBPs from sequence data and this area is more challenging due to poor sequence identity between these proteins.ResultsIn this paper, we propose a new algorithm that uses Regularized Least Squares Classifier (RLSC) in conjunction with multiple physicochemical properties of amino acids to predict odorant-binding proteins. The algorithm was applied to the dataset derived from Pfam and GenDiS database and we obtained overall prediction accuracy of 97.7% (94.5% and 98.4% for positive and negative classes respectively).ConclusionOur study suggests that RLSC is potentially useful for predicting the odorant binding proteins from sequence-derived properties irrespective of sequence similarity. Our method predicts 92.8% of 56 odorant binding proteins non-homologous to any protein in the swissprot database and 97.1% of the 414 independent dataset proteins, suggesting the usefulness of RLSC method for facilitating the prediction of odorant binding proteins from sequence information.

3DSwap: curated knowledgebase of proteins involved in 3D domain swapping

Three-dimensional domain swapping is a unique protein structural phenomenon where two or more protein chains in a protein oligomer share a common structural segment between individual chains. This phenomenon is observed in an array of protein structures in oligomeric conformation. Protein structures in swapped conformations perform diverse functional roles and are also associated with deposition diseases in humans. We have performed in-depth literature curation and structural bioinformatics analyses to develop an integrated knowledgebase of proteins involved in 3D domain swapping. The hallmark of 3D domain swapping is the presence of distinct structural segments such as the hinge and swapped regions. We have curated the literature to delineate the boundaries of these regions. In addition, we have defined several new concepts like ‘secondary major interface’ to represent the interface properties arising as a result of 3D domain swapping, and a new quantitative measure for the ‘extent of swapping’ in structures. The catalog of proteins reported in 3DSwap knowledgebase has been generated using an integrated structural bioinformatics workflow of database searches, literature curation, by structure visualization and sequence–structure–function analyses. The current version of the 3DSwap knowledgebase reports 293 protein structures, the analysis of such a compendium of protein structures will further the understanding molecular factors driving 3D domain swapping. Database URL: http://caps.ncbs.res.in/3dswap

Identification and Analysis of Red Sea Mangrove (Avicennia marina) microRNAs by High-Throughput Sequencing and Their Association with Stress Responses

Although RNA silencing has been studied primarily in model plants, advances in high-throughput sequencing technologies have enabled profiling of the small RNA components of many more plant species, providing insights into the ubiquity and conservatism of some miRNA-based regulatory mechanisms. Small RNAs of 20 to 24 nucleotides (nt) are important regulators of gene transcript levels by either transcriptional or by posttranscriptional gene silencing, contributing to genome maintenance and controlling a variety of developmental and physiological processes. Here, we used deep sequencing and molecular methods to create an inventory of the small RNAs in the mangrove species, Avicennia marina. We identified 26 novel mangrove miRNAs and 193 conserved miRNAs belonging to 36 families. We determined that 2 of the novel miRNAs were produced from known miRNA precursors and 4 were likely to be species-specific by the criterion that we found no homologs in other plant species. We used qRT-PCR to analyze the expression of miRNAs and their target genes in different tissue sets and some demonstrated tissue-specific expression. Furthermore, we predicted potential targets of these putative miRNAs based on a sequence homology and experimentally validated through endonucleolytic cleavage assays. Our results suggested that expression profiles of miRNAs and their predicted targets could be useful in exploring the significance of the conservation patterns of plants, particularly in response to abiotic stress. Because of their well-developed abilities in this regard, mangroves and other extremophiles are excellent models for such exploration.