Project description:MotivationIn cluster analysis, the validity of specific solutions, algorithms, and procedures present significant challenges because there is no null hypothesis to test and no 'right answer'. It has been noted that a replicable classification is not necessarily a useful one, but a useful one that characterizes some aspect of the population must be replicable. By replicable we mean reproducible across multiple samplings from the same population. Methodologists have suggested that the validity of clustering methods should be based on classifications that yield reproducible findings beyond chance levels. We used this approach to determine the performance of commonly used clustering algorithms and the degree of replicability achieved using several microarray datasets.MethodsWe considered four commonly used iterative partitioning algorithms (Self Organizing Maps (SOM), K-means, Clutsering LARge Applications (CLARA), and Fuzzy C-means) and evaluated their performances on 37 microarray datasets, with sample sizes ranging from 12 to 172. We assessed reproducibility of the clustering algorithm by measuring the strength of relationship between clustering outputs of subsamples of 37 datasets. Cluster stability was quantified using Cramer's v2 from a kXk table. Cramer's v2 is equivalent to the squared canonical correlation coefficient between two sets of nominal variables. Potential scores range from 0 to 1, with 1 denoting perfect reproducibility.ResultsAll four clustering routines show increased stability with larger sample sizes. K-means and SOM showed a gradual increase in stability with increasing sample size. CLARA and Fuzzy C-means, however, yielded low stability scores until sample sizes approached 30 and then gradually increased thereafter. Average stability never exceeded 0.55 for the four clustering routines, even at a sample size of 50. These findings suggest several plausible scenarios: (1) microarray datasets lack natural clustering structure thereby producing low stability scores on all four methods; (2) the algorithms studied do not produce reliable results and/or (3) sample sizes typically used in microarray research may be too small to support derivation of reliable clustering results. Further research should be directed towards evaluating stability performances of more clustering algorithms on more datasets specially having larger sample sizes with larger numbers of clusters considered.

Project description:The foundational concept of habitat lies at the very root of the entire science of ecology, but inaccurate use of the term compromises scientific rigor and communication among scientists and nonscientists. In 1997, Hall, Krausman & Morrison showed that 'habitat' was used correctly in only 55% of articles. We ask whether use of the term has been more accurate since their plea for standardization and whether use varies across the broader range of journals and taxa in the contemporary literature (1998-2012). We searched contemporary literature for 'habitat' and habitat-related terms, ranking usage as either correct or incorrect, following a simplified version of Hall et al.'s definitions. We used generalized linear models to compare use of the term in contemporary literature with the papers reviewed by Hall et al. and to test the effects of taxa, journal impact in the contemporary articles and effects due to authors that cited Hall et al. Use of the term 'habitat' has not improved; it was still only used correctly about 55% of the time in the contemporary data. Proportionately more correct uses occurred in articles that focused on animals compared to ones that included plants, and papers that cited Hall et al. did use the term correctly more often. However, journal impact had no effect. Some habitat terms are more likely to be misused than others, notably 'habitat type', usually used to refer to vegetation type, and 'suitable habitat' or 'unsuitable habitat', which are either redundant or nonsensical by definition. Inaccurate and inconsistent use of the term can lead to (1) misinterpretation of scientific findings; (2) inefficient use of conservation resources; (3) ineffective identification and prioritization of protected areas; (4) limited comparability among studies; and (5) miscommunication of science-based findings. Correct usage would improve communication with scientists and nonscientists, thereby benefiting conservation efforts, and ecology as a science.

Dataset Information

Whither the Bicarbonate Era.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets