High dimensionality of microarray data sets may lead to low efficiency and overfitting. In this paper, a multiphase cooperative game theoretic feature selection approach is proposed for microarray data classification. In the first phase, due to high dimension of microarray data sets, the features are reduced using one of the two filter-based feature selection methods, namely, mutual information and Fisher ratio. In the second phase, Shapley index is used to evaluate the power of each feature. The main innovation of the proposed approach is to employ Qualitative Mutual Information (QMI) for this purpose. The idea of Qualitative Mutual Information causes the selected features to have more stability and this stability helps to deal with the problem of data imbalance and scarcity. In the third phase, a forward selection scheme is applied which uses a scoring function to weight each feature. The performance of the proposed method is compared with other popular feature selection algorithms such as Fisher ratio, minimum redundancy maximum relevance, and previous works on cooperative game based feature selection. The average classification accuracy on eleven microarray data sets shows that the proposed method improves both average accuracy and average stability compared to other approaches.

Atiyeh Mortazavi

Mohammad Hossein Moattar

Robust Feature Selection from Microarray Data Based on Cooperative Game Theory and Qualitative Mutual Information

Bevacizumab and trastuzumab are two antibody based antiangiogenic drugs that are in clinical practice for the treatment of different cancers. Presently applications of these drugs are based on the empirical choice of clinical experts that follow towards population based clinical trials and, hence, their molecular efficacies in terms of quantitative estimates are not being explored. Moreover, different clinical trials with these drugs showed different toxicity symptoms in patients. Here, using molecular docking study, we made an attempt to reveal the molecular rationale regarding their efficacy and off-target toxicity. Though our study reinforces their antiangiogenic potentiality and, among the two, trastuzumab has much higher efficacy; however, this study also reveals that compared to bevacizumab, trastuzumab has higher toxicity effect, specially on the cardiovascular system. This study also reveals the molecular rationale of ocular dysfunction by antiangiogenic drugs. The molecular rationale of toxicity as revealed in this study may help in the judicious choice as well as therapeutic scheduling of these drugs in different cancers.

Sayan Mukherjee

Gopa Chatterjee

Moumita Ghosh

Bishwajit Das

Durjoy Majumder

Efficacy and Toxicity Assessment of Different Antibody Based Antiangiogenic Drugs by Computational Docking Method

The human Argonaute2 protein (Ago2) is a key player in RNA interference pathway and small RNA recognition by Ago2 is the crucial step in siRNA mediated gene silencing mechanism. The present study highlights the structural and functional dynamics of human Ago2 and the interaction mechanism of Ago2 with a set of seven siRNAs for the first time. The human Ago2 protein adopts two conformations such as &#x201c;open&#x201d; and &#x201c;close&#x201d; during the simulation of 25 ns. One of the domains named as PAZ, which is responsible for anchoring the 3&#x2032;-end of siRNA guide strand, is observed as a highly flexible region. The interaction between Ago2 and siRNA, analyzed using a set of siRNAs (targeting at positions 128, 251, 341, 383, 537, 1113, and 1115 of mRNA) designed to target tdp43 mutants causing Amyotrophic Lateral Sclerosis (ALS) disease, revealed the stable and strong recognition of siRNA by the Ago2 protein during dynamics. Among the studied siRNAs, the siRNA341 is identified as a potent siRNA to recognize Ago2 and hence could be used further as a possible siRNA candidate to target the mutant tdp43 protein for the treatment of ALS patients.

Vishwambhar Bhandare

Amutha Ramaswamy

Structural Dynamics of Human Argonaute2 and Its Interaction with siRNAs Designed to Target Mutant tdp43

Identifying sets of metastable conformations is a major research topic in RNA energy landscape analysis, and recently several methods have been proposed for finding local minima in landscapes spawned by RNA secondary structures. An important and time-critical component of such methods is steepest, or gradient, descent in attraction basins of local minima. We analyse the speed-up achievable by randomised descent in attraction basins in the context of large sample sets where the size has an order of magnitude in the region of &#x7e;106. While the gain for each individual sample might be marginal, the overall run-time improvement can be significant. Moreover, for the two nongradient methods we analysed for partial energy landscapes induced by ten different RNA sequences, we obtained that the number of observed local minima is on average larger by 7.3&#x25; and 3.5&#x25;, respectively. The run-time improvement is approximately 16.6&#x25; and 6.8&#x25; on average over the ten partial energy landscapes. For the large sample size we selected for descent procedures, the coverage of local minima is very high up to energy values of the region where the samples were randomly selected from the partial energy landscapes; that is, the difference to the total set of local minima is mainly due to the upper area of the energy landscapes.

Luke Day

Ouala Abdelhadi Ep Souki

Andreas A. Albrecht

Kathleen Steinh&#xf6;fel

Random versus Deterministic Descent in RNA Energy Landscape Analysis

The recent upsurge in microbial genome data has revealed that hemoglobin-like (HbL) proteins may be widely distributed among bacteria and that some organisms may carry more than one HbL encoding gene. However, the discovery of HbL proteins has been limited to a small number of bacteria only. This study describes the prediction of HbL proteins and their domain classification using a machine learning approach. Support vector machine (SVM) models were developed for predicting HbL proteins based upon amino acid composition (AC), dipeptide composition (DC), hybrid method (AC + DC), and position specific scoring matrix (PSSM). In addition, we introduce for the first time a new prediction method based on max to min amino acid residue (MM) profiles. The average accuracy, standard deviation (SD), false positive rate (FPR), confusion matrix, and receiver operating characteristic (ROC) were analyzed. We also compared the performance of our proposed models in homology detection databases. The performance of the different approaches was estimated using fivefold cross-validation techniques. Prediction accuracy was further investigated through confusion matrix and ROC curve analysis. All experimental results indicate that the proposed BacHbpred can be a perspective predictor for determination of HbL related proteins. BacHbpred, a web tool, has been developed for HbL prediction.

MuthuKrishnan Selvaraj

Munish Puri

Kanak L. Dikshit

Christophe Lefevre

BacHbpred: Support Vector Machine Methods for the Prediction of Bacterial Hemoglobin-Like Proteins

With the incidence rate of oral carcinogenesis increasing in the Southeast-Asian countries, due to increase in the consumption of tobacco and betel quid as well as infection from human papillomavirus, specifically type 16, it becomes crucial to predict the transition of premalignant lesion to cancerous tissue at an initial stage in order to control the process of oncogenesis. DEPDC1B, downregulated in the presence of E2 protein, was recently found to be overexpressed in oral cancer, which can possibly be explained by the disruption of the E2 open reading frame upon the integration of viral genome into the host genome. DEPDC1B mediates its effect by directly interacting with Rac1 protein, which is known to regulate important cell signaling pathways. Therefore, DEPDC1B can be a potential biomarker as well as a therapeutic target for diagnosing and curing the disease. However, the lack of 3D model of the structure makes the utilization of DEPDC1B as a therapeutic target difficult. The present study focuses on the prediction of a suitable 3D model of the protein as well as the analysis of protein-protein interaction between DEPDC1B and Rac1 protein using PatchDock web server along with the identification of allosteric or regulatory sites of DEPDC1B.

Palak Ahuja

Kailash Singh

In Silico Approach for SAR Analysis of the Predicted Model of DEPDC1B: A Novel Target for Oral Cancer

The accurate prediction of genetic networks using computational tools is one of the greatest challenges in the postgenomic era. Recurrent Neural Network is one of the most popular but simple approaches to model the network dynamics from time-series microarray data. To date, it has been successfully applied to computationally derive small-scale artificial and real-world genetic networks with high accuracy. However, they underperformed for large-scale genetic networks. Here, a new methodology has been proposed where a hybrid Cuckoo Search-Flower Pollination Algorithm has been implemented with Recurrent Neural Network. Cuckoo Search is used to search the best combination of regulators. Moreover, Flower Pollination Algorithm is applied to optimize the model parameters of the Recurrent Neural Network formalism. Initially, the proposed method is tested on a benchmark large-scale artificial network for both noiseless and noisy data. The results obtained show that the proposed methodology is capable of increasing the inference of correct regulations and decreasing false regulations to a high degree. Secondly, the proposed methodology has been validated against the real-world dataset of the DNA SOS repair network of Escherichia coli. However, the proposed method sacrifices computational time complexity in both cases due to the hybrid optimization process.

Sudip Mandal

Abhinandan Khan

Goutam Saha

Rajat K. Pal

Large-Scale Recurrent Neural Network Based Modelling of Gene Regulatory Network Using Cuckoo Search-Flower Pollination Algorithm

The increasing resistance to anti-tb drugs has enforced strategies for finding new drug targets against Mycobacterium tuberculosis (Mtb). In recent years enzymes associated with the rhamnose pathway in Mtb have attracted attention as drug targets. The present work is on &#x3b1;-D-glucose-1-phosphate thymidylyltransferase (RmlA), the first enzyme involved in the biosynthesis of L-rhamnose, of Mtb cell wall. This study aims to derive a 3D structure of RmlA by using a comparative modeling approach. Structural refinement and energy minimization of the built model have been done with molecular dynamics. The reliability assessment of the built model was carried out with various protein checking tools such as Procheck, Whatif, ProsA, Errat, and Verify 3D. The obtained model investigates the relation between the structure and function. Molecular docking interactions of Mtb-RmlA with modified EMB (ethambutol) ligands and natural substrate have revealed specific key residues Arg13, Lys23, Asn109, and Thr223 which play an important role in ligand binding and selection. Compared to all EMB ligands, EMB-1 has shown better interaction with Mtb-RmlA model. The information thus discussed above will be useful for the rational design of safe and effective inhibitors specific to RmlA enzyme pertaining to the treatment of tuberculosis.

N. Harathi

Madhusudana Pulaganti

C. M. Anuradha

Suresh Kumar Chitta

Inhibition of Mycobacterium-RmlA by Molecular Modeling, Dynamics Simulation, and Docking

2-Haloalkanoic acid dehalogenase enzymes have broad range of applications, starting from bioremediation to chemical synthesis of useful compounds that are widely distributed in fungi and bacteria. In the present study, a total of 81 full-length protein sequences of 2-haloalkanoic acid dehalogenase from bacteria and fungi were retrieved from NCBI database. Sequence analysis such as multiple sequence alignment (MSA), conserved motif identification, computation of amino acid composition, and phylogenetic tree construction were performed on these primary sequences. From MSA analysis, it was observed that the sequences share conserved lysine (K) and aspartate (D) residues in them. Also, phylogenetic tree indicated a subcluster comprised of both fungal and bacterial species. Due to nonavailability of experimental 3D structure for fungal 2-haloalkanoic acid dehalogenase in the PDB, molecular modelling study was performed for both fungal and bacterial sources of enzymes present in the subcluster. Further structural analysis revealed a common evolutionary topology shared between both fungal and bacterial enzymes. Studies on the buried amino acids showed highly conserved Leu and Ser in the core, despite variation in their amino acid percentage. Additionally, a surface exposed tryptophan was conserved in all of these selected models.

Raghunath Satpathy

V. B. Konkimalla

Jagnyeswar Ratha

In Silico Phylogenetic Analysis and Molecular Modelling Study of 2-Haloalkanoic Acid Dehalogenase Enzymes from Bacterial and Fungal Origin

About this journal

Advances in Bioinformatics publishes original research articles and review articles focusing on computational and statistical methods to address biological problems.

Journal profile

Meet the editorial board

Advances in Bioinformatics maintains an Editorial Board of practicing researchers from around the world, to ensure manuscripts are handled by editors who are experts in the field of study.

Editor spotlight

Submit your proposal

Do you think there is an emerging area of research that really needs to be highlighted? Or an existing research area that has been overlooked or would benefit from deeper investigation? Raise the profile of a research area by leading a Special Issue.

Special Issues

Author guidelines

Editorial board

Databases and indexing

Advances in Bioinformatics - Table of contents 2016

title

Advances in Bioinformatics ceased publication in 2019 and is no longer accepting submissions.

description

Advances in Bioinformatics publishes original research articles and review articles focusing on computational and statistical methods to address biological problems.

Advances in Bioinformatics