<p>Clustering of top-ranked features and their relative importance. The nodes sizes represent the feature importance as calculated by CRISTA. Edges transparencies represent correlation such that strongly correlated features are connected by darker edges. Yellow and blue edges represent positively and negatively correlated features respectively. Abbreviations: YY- mismatches of type pyrimidine-pyrimidine; RR–mismatches of type purine-purine; MGW–minor groove width; ‘#’ represents counts (for further explanations of the features, see <a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1005807#pcbi.1005807.s016" target="_blank">S3 Table</a>). The graph was produced with Cytoscape [<a href="http://www.ploscompbiol.org/art...
<p>CD: Correlation dimension. SampEn: Sample entropy. LF<sub>peak</sub>: peak frequency of LF band. ...
<p>Each vertex is a metabolite and its size is proportional to its corresponding metabolite’s indivi...
<p>Left: Clustering score in dependence on the index of the used feature vectors. The colors indicat...
(A) Feature importance. The feature importance (horizontal axis) is defined as the reduction in accu...
<p>(A) Important features identified by PLS-DA and VIP scores. The colored boxes on the right indica...
<p>Ranking given according to features importance computed in the course of training. The decrease i...
A. Sorted feature importance scores showing a small minority of contacts contribute to predicting th...
Visualisation of the feature importance for the HC-RNN with two clusters found using FCM, cluster 1 ...
Visualisation of the feature importance for the HC-CNN with two clusters found using FCM, cluster 1 ...
<p>X-axis contains the 4 clusters. Y-axis contains the peak intensity, scaled from 0 (minimum detect...
<p>(A) Pearson correlation and (B) Euclidean distance as distance measure. Each line represents a ge...
<p>X-axis represents peak ranks. Y-axis represents the percentage of reported peaks containing at le...
<p>The definitions of V14, V34 and V84 are listed in <a href="http://www.plosone.org/article/info:do...
<p>(A) GO pie charts show PANTHER classifications made according to the associated Molecular functio...
<p>The species are ordered according to their phylogenetic relationships as shown on the left. For e...
<p>CD: Correlation dimension. SampEn: Sample entropy. LF<sub>peak</sub>: peak frequency of LF band. ...
<p>Each vertex is a metabolite and its size is proportional to its corresponding metabolite’s indivi...
<p>Left: Clustering score in dependence on the index of the used feature vectors. The colors indicat...
(A) Feature importance. The feature importance (horizontal axis) is defined as the reduction in accu...
<p>(A) Important features identified by PLS-DA and VIP scores. The colored boxes on the right indica...
<p>Ranking given according to features importance computed in the course of training. The decrease i...
A. Sorted feature importance scores showing a small minority of contacts contribute to predicting th...
Visualisation of the feature importance for the HC-RNN with two clusters found using FCM, cluster 1 ...
Visualisation of the feature importance for the HC-CNN with two clusters found using FCM, cluster 1 ...
<p>X-axis contains the 4 clusters. Y-axis contains the peak intensity, scaled from 0 (minimum detect...
<p>(A) Pearson correlation and (B) Euclidean distance as distance measure. Each line represents a ge...
<p>X-axis represents peak ranks. Y-axis represents the percentage of reported peaks containing at le...
<p>The definitions of V14, V34 and V84 are listed in <a href="http://www.plosone.org/article/info:do...
<p>(A) GO pie charts show PANTHER classifications made according to the associated Molecular functio...
<p>The species are ordered according to their phylogenetic relationships as shown on the left. For e...
<p>CD: Correlation dimension. SampEn: Sample entropy. LF<sub>peak</sub>: peak frequency of LF band. ...
<p>Each vertex is a metabolite and its size is proportional to its corresponding metabolite’s indivi...
<p>Left: Clustering score in dependence on the index of the used feature vectors. The colors indicat...