Analysing extremely small sized ratio datasets

Q4 Health Professions

International Journal of Bioinformatics Research and Applications Pub Date : 2015-05-01 DOI:10.1504/IJBRA.2015.069225

Piero Ricchiuto, J. Sng, W. Goh

引用次数: 1

Abstract

The naïve use of expression ratios in high-throughput biological studies can greatly limit analytical outcome especially when sample size is small. In the worst-case scenario, with only one reference and one test state each (often due to the severe lack of study material); such limitations make it difficult to perform statistically meaningful analysis. Workarounds include the single sample Z-test or through network inference. Here, we describe a complementary plot-based approach for analysing such extremely small sized ratio (ESSR) data - a generalisation of the Bland-Altman plot, which we shall refer to as the Dodeca-Panels. Included in this paper is an R implementation of the Dodeca-Panels method.

查看原文本刊更多论文

分析极小的比率数据集

naïve在高通量生物学研究中使用表达比会极大地限制分析结果，特别是在样本量小的情况下。在最坏的情况下，每个人只有一个参考和一个测试状态(通常是由于严重缺乏学习材料);这些限制使得很难进行统计上有意义的分析。变通方法包括单样本z检验或通过网络推理。在这里，我们描述了一种互补的基于图的方法来分析这种极小尺寸的比率(ESSR)数据——Bland-Altman图的概括，我们将其称为十二面板。本文中包含了Dodeca-Panels方法的R实现。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Bioinformatics Research and Applications Health Professions-Health Information Management

CiteScore

0.60

自引率

0.00%

发文量

期刊介绍： Bioinformatics is an interdisciplinary research field that combines biology, computer science, mathematics and statistics into a broad-based field that will have profound impacts on all fields of biology. The emphasis of IJBRA is on basic bioinformatics research methods, tool development, performance evaluation and their applications in biology. IJBRA addresses the most innovative developments, research issues and solutions in bioinformatics and computational biology and their applications. Topics covered include Databases, bio-grid, system biology Biomedical image processing, modelling and simulation Bio-ontology and data mining, DNA assembly, clustering, mapping Computational genomics/proteomics Silico technology: computational intelligence, high performance computing E-health, telemedicine Gene expression, microarrays, identification, annotation Genetic algorithms, fuzzy logic, neural networks, data visualisation Hidden Markov models, machine learning, support vector machines Molecular evolution, phylogeny, modelling, simulation, sequence analysis Parallel algorithms/architectures, computational structural biology Phylogeny reconstruction algorithms, physiome, protein structure prediction Sequence assembly, search, alignment Signalling/computational biomedical data engineering Simulated annealing, statistical analysis, stochastic grammars.