Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2015 Nov 1;22(11):1005–1024. doi: 10.1089/cmb.2015.0051

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2015; Published by Mary Ann Liebert, Inc.

This Open Access article is distributed under the terms of the Creative Commons Attribution Noncommercial License (http://creativecommons.org/licenses/by-nc/4.0/) which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and the source are credited.

PMC Copyright notice

FIG. 12. — Histograms of dependency measures computed for various sets of tuples. Panel (a) shows distribution of mutual information values computed on all possible pairs of the entire set of genes (5,905 genes). Similarly, panel (b) shows values computed on all possible triplets of the set of genes involved in pairs with high MI (1051 genes involved in pairs that are above 20 standard deviations threshold). Selecting 279 variables from high triplets (above 1,000 st. dev.) and computing on all possible quads results in a distribution shown in panel (c). Finally, computing on all possible 5-variable tuples of 118 variables involved in high quads (above 55 st. dev.) results in a distribution shown in panel (d). Each panel is composed of three subpanels showing the original distribution, its magnified tail, and the distribution in the log-scale (from top down). The red vertical lines show the minimal and maximal values of each distribution, the green lines show three st. dev. from the mean, and the pink lines show the thresholds used for selecting the informative tuples at each step.

Inline graphic — Histograms of dependency measures computed for various sets of tuples. Panel (a) shows distribution of mutual information values computed on all possible pairs of the entire set of genes (5,905 genes). Similarly, panel (b) shows values computed on all possible triplets of the set of genes involved in pairs with high MI (1051 genes involved in pairs that are above 20 standard deviations threshold). Selecting 279 variables from high triplets (above 1,000 st. dev.) and computing on all possible quads results in a distribution shown in panel (c). Finally, computing on all possible 5-variable tuples of 118 variables involved in high quads (above 55 st. dev.) results in a distribution shown in panel (d). Each panel is composed of three subpanels showing the original distribution, its magnified tail, and the distribution in the log-scale (from top down). The red vertical lines show the minimal and maximal values of each distribution, the green lines show three st. dev. from the mean, and the pink lines show the thresholds used for selecting the informative tuples at each step.