Eduardo José da S. Luz, L. Merschmann, D. Menotti, G. Moreira
{"title":"Evaluating a hierarchical approach for heartbeat classification from ECG","authors":"Eduardo José da S. Luz, L. Merschmann, D. Menotti, G. Moreira","doi":"10.1504/IJBRA.2017.10003488","DOIUrl":"https://doi.org/10.1504/IJBRA.2017.10003488","url":null,"abstract":"Several types of arrhythmias that can be rare and harmless, but may result in serious cardiac issues, and several ECG analysis methods have been proposed in the literature to automatically classify the various classes of arrhythmias. Following the Association for the Advancement of Medical Instrumentation (AAMI) standard, 15 classes of heartbeats can be hierarchically grouped into five superclasses. In this work, we propose to employ the hierarchical classification paradigm to five ECG analysis methods in the literature, and compare their performance with flat classification paradigm. In our experiments, we use the MIT-BIH Arrhythmia Database and analyse the use of the hierarchical classification following AAMI standard and a well-known and established evaluation protocol using five superclasses. The experimental results showed that the hierarchical classification provided the highest gross accuracy for most of the methods used in this work and provided an improvement in classification performance of N and SVEB superclasses.","PeriodicalId":434900,"journal":{"name":"Int. J. Bioinform. Res. Appl.","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134021753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Using conditional inference forest to identify variable importance","authors":"N. Settouti, Mostafa EL HABIB DAHO, Amine Chikh","doi":"10.1504/IJBRA.2017.10003483","DOIUrl":"https://doi.org/10.1504/IJBRA.2017.10003483","url":null,"abstract":"Variable importance measure with Random Forests (RF) have received increased attention as a means of variable selection in classification tasks. The measure of variable importance in Random Forests is a smart way of variable selection in many applications, but is not reliable in situations where potential predictor variables vary in their scale of measurement or their number of categories. In this paper, we have implemented Random Forest built from Conditional Inference Trees (CIT) that is called Conditional Inference Forest (CIF). In each tree in the forest of conditional inference, the division of the nodes is based on the way to have a good associativity. The chi-square test statistics is used to measure the association. In addition to identifying variables that improve the classification accuracy, the methodology also clearly identifies the variables that are neutral to the accuracy, and also those who interfere in the right classification. In this paper, we are particularly interested in the overall algorithm Conditional Inference Forest (CIF) for the classification of large biological data. The algorithm is evaluated on its ability to select a reduced number of features while preserving a very satisfactory classification rate.","PeriodicalId":434900,"journal":{"name":"Int. J. Bioinform. Res. Appl.","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125583854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Prediction of Homo sapiens cancer cells by electrical network modelling of amino acid sequence","authors":"Tanusree Roy, S. Barman","doi":"10.1504/IJBRA.2017.10002833","DOIUrl":"https://doi.org/10.1504/IJBRA.2017.10002833","url":null,"abstract":"Amino acids are the essential primary component of every living organism, deficiency of which may lead to different types of genetic abnormalities in cells. In the present paper, electrical network modelling technique is applied on Homo sapiens genes for prediction of cancer disease. Amino acids are designed using passive electrical components i.e. resistor, inductor and capacitor. The network of amino acid sequence is used to predict the cancer genes by analysing pole-zero distribution and impedance of the network. The results show high affinity of the hydrophilic amino acids in cancer cell related genes compare to healthy genes, which validate the medical research reports. Since the present network model realisation is based on amino acid level, the concept is significantly better than other modelling approach in terms of complexity and computational load.","PeriodicalId":434900,"journal":{"name":"Int. J. Bioinform. Res. Appl.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131004055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Annotation transfer by homology among closely related genomes helps to identify protein function in Plasmodium species","authors":"Devaraj Raghul Rajan, B. Chandramohan","doi":"10.1504/IJBRA.2017.10002824","DOIUrl":"https://doi.org/10.1504/IJBRA.2017.10002824","url":null,"abstract":"Malaria is a major killer disease causing heavy loss in terms of life and medical expenditure. The genome of Plasmodium falciparum sequenced in 2002 but more than 60% of its meaning still remains unknown. We compared protein sequences from P. falciparum in the genomic sequences with P. vivax and P. knowlesi through standalone blast tool from NCBI. We found many proteins annotated in one species sharing high similarity with unannotated proteins in the other/s species. Based on the 'annotation transfer by homology' method we annotated 715 hypothetical proteins. By the latest information available as of 1st September our method annotated 343 protein sequences. Gene Ontology annotation with BLAST2GO revealed 128 proteins with Enzyme Codes among the 561 sequences mapped with GO terms. The kognitor results showed 542 proteins similar to proteins belonging to various KOG categories. More attention should be paid to these 'hypothetical' proteins as they can reveal unknown insights on the biology of organisms and have an impact in the field of drug discovery and medicine.","PeriodicalId":434900,"journal":{"name":"Int. J. Bioinform. Res. Appl.","volume":"166 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131465395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A new neural unsupervised classification approach using amended competitive Hebbian learning: PET image segmentation insights","authors":"M. Timouyas, S. Eddarouich, A. Hammouch","doi":"10.1504/IJBRA.2017.10002820","DOIUrl":"https://doi.org/10.1504/IJBRA.2017.10002820","url":null,"abstract":"This paper proposes a new classification procedure based on the competitive concept, divided into three processing stages. It begins by the estimation of the Probability Density Function (pdf), followed by a competitive training neural network with the Mahalanobis distance as an activation function. This stage allows detecting the local maxima of the pdf. Then, we use the competitive Hebbian learning to analyse the connectivity between the detected maxima of the pdf upon the Mahalanobis distance. The so detected groups of maxima are then used for the classification process. Compared to the K-means clustering or the clustering approaches based on the different competitive learning schemes, the proposed approach has proven, under a number of real (positron emission tomography image) and synthetic data samples, that it does not pass by any thresholding and does not require any prior information on the number of classes or on the structure of their distributions in the data set.","PeriodicalId":434900,"journal":{"name":"Int. J. Bioinform. Res. Appl.","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123976999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An empirical study of self-training and data balancing techniques for splice site prediction","authors":"A. Stanescu, Doina Caragea","doi":"10.1504/IJBRA.2017.10002831","DOIUrl":"https://doi.org/10.1504/IJBRA.2017.10002831","url":null,"abstract":"Thanks to Next Generation Sequencing technologies, unlabelled data is now generated easily, while the annotation process remains expensive. Semi-supervised learning represents a cost-effective alternative to supervised learning, as it can improve supervised classifiers by making use of unlabelled data. However, semi-supervised learning has not been studied much for problems with highly skewed class distributions, which are prevalent in bioinformatics. To address this limitation, we carry out a study of a semi-supervised learning algorithm, specifically self-training based on Naive Bayes, with focus on data-level approaches for handling imbalanced class distributions. Our study is conducted on the problem of predicting splice sites and it is based on datasets for which the ratio of positive to negative examples is 1-to-99. Our results show that under certain conditions semi-supervised learning algorithms are a better choice than purely supervised classification algorithms.","PeriodicalId":434900,"journal":{"name":"Int. J. Bioinform. Res. Appl.","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126235628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. M. E. Kamrani, F. Mosaffa, J. Behravan, F. Hadizadeh
{"title":"P-gp and BCRP inhibition induced by some new 1, 4-Dihydropyridine and Dihydropyrimidines","authors":"S. M. E. Kamrani, F. Mosaffa, J. Behravan, F. Hadizadeh","doi":"10.1504/IJBRA.2017.10002832","DOIUrl":"https://doi.org/10.1504/IJBRA.2017.10002832","url":null,"abstract":"Overexpression of ABC transporters leads to MDR (Multiple Drug Resistance). MDR is considered to be the major contributor to failure of chemotherapy in metastatic cancers. ABC transporters have protective role in normal cells by extruding xenobiotics of cytotoxic compounds from the cell. The development of selective inhibitors of P-gp, MRP1, MRP2, and BCRP has been a major goal of many research groups in the last few years. Previous studies have shown that 1,4-dihydropyridines could inhibit these transporters. In this study, some new 1,4-dihydropyridine and pyrimidine have been developed and their inhibitory effect on the resistant cancer cell lines was examined. In order to elucidate the binding mode of these compounds, a molecular docking and molecular dynamic simulation was performed for the protein-ligand complex. Dihydropyridines were more potent than dihydropyrimidines. However, one of the dihydropyrimidine derivatives selectively inhibited BCRP. The binding mode of these compounds showed that methoxy groups and heterocyclic rings could create hydrogen bonds with polar residues at the active sites. These regions were more stable during MD simulation.","PeriodicalId":434900,"journal":{"name":"Int. J. Bioinform. Res. Appl.","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131319127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Recent advancement in next-generation sequencing techniques and its computational analysis","authors":"Khalid Raza, Sabahuddin Ahmad","doi":"10.1504/IJBRA.2019.10022508","DOIUrl":"https://doi.org/10.1504/IJBRA.2019.10022508","url":null,"abstract":"Next Generation Sequencing (NGS), a recently evolved technology, have served a lot in the research and development sector of our society. This novel approach is a newbie and has critical advantages over the traditional Capillary Electrophoresis (CE) based Sanger Sequencing. The advancement of NGS has led to numerous important discoveries, which could have been costlier and time taking in case of traditional CE based Sanger sequencing. NGS methods are highly parallelized enabling to sequence thousands to millions of molecules simultaneously. This technology results into huge amount of data, which need to be analysed to conclude valuable information. Specific data analysis algorithms are written for specific task to be performed. The algorithms in group, act as a tool in analysing the NGS data. Analysis of NGS data unravels important clues in quest for the treatment of various life-threatening diseases; improved crop varieties and other related scientific problems related to human welfare. In this review, an effort was made to address basic background of NGS technologies, possible applications, computational approaches and tools involved in NGS data analysis, future opportunities and challenges in the area.","PeriodicalId":434900,"journal":{"name":"Int. J. Bioinform. Res. Appl.","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124125631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"In silico pathway analysis of MAPKs and computational investigation of bipyrazole analogues as novel p38alpha MAPK inhibitors","authors":"Deepak Nedunuri, Y. Adimulam, K. Reddi","doi":"10.1504/IJBRA.2016.075395","DOIUrl":"https://doi.org/10.1504/IJBRA.2016.075395","url":null,"abstract":"Mitogen-Activated Protein Kinase MAPK belongs to one of the largest super-families of proteins. The activity of most MAPKs is stimulated by a large variety of signals, including mitogens, growth factors, cytokines, T-cell antigens, pheromones, UV and ionising radiations, osmotic stress, heat shock, oxidative stress and others. The present work determines the participation of particular MAPK to one specific pathway in the MAPKinase signalling MAPK 1-14. Various computational analyses involving Clustal omega, phylogenetic tree reconstruction and ProDom have been utilised in the study. Based on evolutionary relationships, domain detections and comparison of active site residues, the specificity of MAPKs in defined pathways is emphasised. MAPKs have been shown to play a pivotal role in diverse diseases, including cancer. Majority of studies have focused on targeting p38 MAPK isoform alpha MAPK14. Hence, in this paper we elucidate a computational mechanism of inhibition by bipyrazole analogues, for the first time, as promising inhibitors of p38alpha MAPK.","PeriodicalId":434900,"journal":{"name":"Int. J. Bioinform. Res. Appl.","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116669748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Weng Howe Chan, M. S. Mohamad, S. Deris, J. Corchado, S. Omatu, Z. Ibrahim, S. Kasim
{"title":"An improved gSVM-SCADL2 with firefly algorithm for identification of informative genes and pathways","authors":"Weng Howe Chan, M. S. Mohamad, S. Deris, J. Corchado, S. Omatu, Z. Ibrahim, S. Kasim","doi":"10.1504/IJBRA.2016.075404","DOIUrl":"https://doi.org/10.1504/IJBRA.2016.075404","url":null,"abstract":"Incorporation of pathway knowledge into microarray analysis has been favoured by researchers owing to the improved biological interpretation of the analysis outcome. However, most of the pathway data are manually curated without specific biological context. Inclusion of non-informative genes in the analysis of context specific microarray data could lead to classifier with poor discriminative power. Thus, one of the main challenges is how to effectively identify informative genes from the pathway data. This paper proposes a firefly optimised penalised support vector machine with SCADL2 penalty function SVM-SCADL2-FFA in optimising tuning parameters for each pathway for efficient identification of informative genes and pathways. Experiments are done on lung cancer and gender data sets. Tenfold CV is used to evaluate the performance in terms of accuracy, specificity, sensitivity and F-score. The identified informative genes are validated through online databases. Our proposed method shows consistent improvements compared to previous works.","PeriodicalId":434900,"journal":{"name":"Int. J. Bioinform. Res. Appl.","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126866104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}