Current Issue : October - December Volume : 2014 Issue Number : 4 Articles : 6 Articles
Background: Pulmonary acoustic parameters extracted from recorded respiratory sounds provide valuable information\nfor the detection of respiratory pathologies. The automated analysis of pulmonary acoustic signals can serve as a\ndifferential diagnosis tool for medical professionals, a learning tool for medical students, and a self-management tool for\npatients. In this context, we intend to evaluate and compare the performance of the support vector machine (SVM) and\nK-nearest neighbour (K-nn) classifiers in diagnosis respiratory pathologies using respiratory sounds from R.A.L.E database.\nResults: The pulmonary acoustic signals used in this study were obtained from the R.A.L.E lung sound database. The\npulmonary acoustic signals were manually categorised into three different groups, namely normal, airway obstruction\npathology, and parenchymal pathology. The mel-frequency cepstral coefficient (MFCC) features were extracted from the\npre-processed pulmonary acoustic signals. The MFCC features were analysed by one-way ANOVA and then fed separately\ninto the SVM and K-nn classifiers. The performances of the classifiers were analysed using the confusion matrix technique.\nThe statistical analysis of the MFCC features using one-way ANOVA showed that the extracted MFCC features are\nsignificantly different (p < 0.001). The classification accuracies of the SVM and K-nn classifiers were found to be 92.19%\nand 98.26%, respectively.\nConclusion: Although the data used to train and test the classifiers are limited, the classification accuracies found are\nsatisfactory. The K-nn classifier was better than the SVM classifier for the discrimination of pulmonary acoustic signals\nfrom pathological and normal subjects obtained from the RALE database....
Background: Flux Balance Analysis (FBA) is a genome-scale computational technique for modeling the steady-state\nfluxes of an organism�s reaction network. When the organism�s reaction network needs to be completed to obtain\ngrowth using FBA, without relying on the genome, the completion process is called reaction gap-filling. Currently,\ncomputational techniques used to gap-fill a reaction network compute the minimum set of reactions using\nMixed-Integer Linear Programming (MILP). Depending on the number of candidate reactions used to complete the\nmodel, MILP can be computationally demanding.\nResults: We present a computational technique, called FastGapFilling, that efficiently completes a reaction network\nby using only Linear Programming, not MILP. FastGapFilling creates a linear program with all candidate reactions, an\nobjective function based on their weighted fluxes, and a variable weight on the biomass reaction: no integer variable\nis used. A binary search is performed by modifying the weight applied to the flux of the biomass reaction, and solving\neach corresponding linear program, to try reducing the number of candidate reactions to add to the network to\ngenerate a working model. We show that this method has proved effective on a series of incomplete E. coli and yeast\nmodels with, in some cases, a three orders of magnitude execution speedup compared with MILP. We have\nimplemented FastGapFilling in MetaFlux as part of Pathway Tools (version 17.5), which is freely available to academic\nusers, and for a fee to commercial users. Download from: biocyc.org/download.shtml.\nConclusions: The computational technique presented is very efficient allowing interactive completion of reaction\nnetworks of FBA models. Computational techniques based on MILP cannot offer such fast and interactive completion....
Background: Knockdown or overexpression of genes is widely used to identify genes that play important roles in many\naspects of cellular functions and phenotypes. Because next-generation sequencing generates high-throughput data that\nallow us to detect genes, it is important to identify genes that drive functional and phenotypic changes of cells. However,\nconventional methods rely heavily on the assumption of normality and they often give incorrect results when the\nassumption is not true. To relax the Gaussian assumption in causal inference, we introduce the non-paranormal method\nto test conditional independence in the PC-algorithm. Then, we present the non-paranormal intervention-calculus when\nthe directed acyclic graph (DAG) is absent (NPN-IDA), which incorporates the cumulative nature of effects through a\ncascaded pathway via causal inference for ranking causal genes against a phenotype with the non-paranormal method\nfor estimating DAGs.\nResults: We demonstrate that causal inference with the non-paranormal method significantly improves the performance\nin estimating DAGs on synthetic data in comparison with the original PC-algorithm. Moreover, we show that NPN-IDA\noutperforms the conventional methods in exploring regulators of the flowering time in Arabidopsis thaliana and\nregulators that control the browning of white adipocytes in mice. Our results show that performance improvement in\nestimating DAGs contributes to an accurate estimation of causal effects.\nConclusions: Although the simplest alternative procedure was used, our proposed method enables us to design efficient\nintervention experiments and can be applied to a wide range of research purposes, including drug discovery, because of\nits generality....
Background: Although the costs of next generation sequencing technology have decreased over the past years,\nthere is still a lack of simple-to-use applications, for a comprehensive analysis of RNA sequencing data. There is\nno one-stop shop for transcriptomic genomics. We have developed MAP-RSeq, a comprehensive computational\nworkflow that can be used for obtaining genomic features from transcriptomic sequencing data, for any\ngenome.\nResults: For optimization of tools and parameters, MAP-RSeq was validated using both simulated and real\ndatasets. MAP-RSeq workflow consists of six major modules such as alignment of reads, quality assessment of\nreads, gene expression assessment and exon read counting, identification of expressed single nucleotide\nvariants (SNVs), detection of fusion transcripts, summarization of transcriptomics data and final report. This\nworkflow is available for Human transcriptome analysis and can be easily adapted and used for other genomes.\nSeveral clinical and research projects at the Mayo Clinic have applied the MAP-RSeq workflow for RNA-Seq studies. The\nresults from MAP-RSeq have thus far enabled clinicians and researchers to understand the transcriptomic landscape of\ndiseases for better diagnosis and treatment of patients.\nConclusions: Our software provides gene counts, exon counts, fusion candidates, expressed single nucleotide variants,\nmapping statistics, visualizations, and a detailed research data report for RNA-Seq. The workflow can be executed\non a standalone virtual machine or on a parallel Sun Grid Engine cluster. The software can be downloaded from\nhttp://bioinformaticstools.mayo.edu/research/maprseq/....
Background: Meta-analysis has become increasingly popular in recent years, especially in genomic data analysis, due\nto the fast growth of available data and studies that target the same questions. Many methods have been developed,\nincluding classical ones such as Fisherââ?¬â?¢s combined probability test and Stoufferââ?¬â?¢s Z-test. However, not all meta-analyses\nhave the same goal in mind. Some aim at combining information to find signals in at least one of the studies, while\nothers hope to find more consistent signals across the studies. While many classical meta-analysis methods are\ndeveloped with the former goal in mind, the latter goal has much more practicality for genomic data analysis.\nResults: In this paper, we propose a class of meta-analysis methods based on summaries of weighted ordered\np-values (WOP) that aim at detecting significance in a majority of studies. We consider weighted versions of classical\nprocedures such as Fisherââ?¬â?¢s method and Stoufferââ?¬â?¢s method where the weight for each p-value is based on its order\namong the studies. In particular, we consider weights based on the binomial distribution, where the median of the\np-values are weighted highest and the outlying p-values are down-weighted. We investigate the properties of our\nmethods and demonstrate their strengths through simulations studies, comparing to existing procedures. In addition,\nwe illustrate application of the proposed methodology by several meta-analysis of gene expression data.\nConclusions: Our proposed weighted ordered p-value (WOP) methods displayed better performance compared to\nexisting methods for testing the hypothesis that there is signal in the majority of studies. They also appeared to be\nmuch more robust in applications compared to the rth ordered p-value (rOP) method (Song and Tseng, Ann. Appl.\nStat. 2014, 8(2):777ââ?¬â??800). With the flexibility of incorporating different p-value combination methods and different\nweighting schemes, the weighted ordered p-values (WOP) methods have great potential in detecting consistent\nsignal in meta-analysis with heterogeneity....
Background: Locating the protein-coding genes in novel genomes is essential to understanding and exploiting\nthe genomic information but it is still difficult to accurately predict all the genes. The recent availability of detailed\ninformation about transcript structure from high-throughput sequencing of messenger RNA (RNA-Seq) delineates\nmany expressed genes and promises increased accuracy in gene prediction. Computational gene predictors have\nbeen intensively developed for and tested in well-studied animal genomes. Hundreds of fungal genomes are now\nor will soon be sequenced. The differences of fungal genomes from animal genomes and the phylogenetic sparsity\nof well-studied fungi call for gene-prediction tools tailored to them.\nResults: SnowyOwl is a new gene prediction pipeline that uses RNA-Seq data to train and provide hints for the\ngeneration of Hidden Markov Model (HMM)-based gene predictions and to evaluate the resulting models. The\npipeline has been developed and streamlined by comparing its predictions to manually curated gene models in\nthree fungal genomes and validated against the high-quality gene annotation of Neurospora crassa; SnowyOwl\npredicted N. crassa genes with 83% sensitivity and 65% specificity. SnowyOwl gains sensitivity by repeatedly running\nthe HMM gene predictor Augustus with varied input parameters and selectivity by choosing the models with best\nhomology to known proteins and best agreement with the RNA-Seq data.\nConclusions: SnowyOwl efficiently uses RNA-Seq data to produce accurate gene models in both well-studied and\nnovel fungal genomes. The source code for the SnowyOwl pipeline (in Python) and a web interface (in PHP) is\nfreely available from http://sourceforge.net/projects/snowyowl/....
Loading....