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

. 2014 Oct 23;10(10):e1003908. doi: 10.1371/journal.pcbi.1003908

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

© 2014 Li et al

This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.

PMC Copyright notice

Boxplot of Spearman rank correlation between the predicted and the actual held-out genes in 10-fold cross-validation (CV). The full RACER model (red, left most) using all of the input variables was compared with the reduced model using all except for one type of the input variables “RACER, all excluding X”, where × is one of the following factors: CNV (copy number variation), miRNA (miRNA expression number of conserved target sites), DM (DNA methylation), TF (TF binding scores from ENCODE). RANDOM represents predictions from the complete RACER model on the same data but with gene labels randomly shuffled. The 10-fold CV was performed for each sample, and the average was taken over the 10 correlations. Each boxplot displays the distribution of the averaged correlation across the 173 AML samples. The higher the reduction relative to the full RACER model, the more power provided by the excluded variables in terms of explaining the underlying mRNA expression level.

Inline graphic — Boxplot of Spearman rank correlation between the predicted and the actual held-out genes in 10-fold cross-validation (CV). The full RACER model (red, left most) using all of the input variables was compared with the reduced model using all except for one type of the input variables “RACER, all excluding X”, where × is one of the following factors: CNV (copy number variation), miRNA (miRNA expression number of conserved target sites), DM (DNA methylation), TF (TF binding scores from ENCODE). RANDOM represents predictions from the complete RACER model on the same data but with gene labels randomly shuffled. The 10-fold CV was performed for each sample, and the average was taken over the 10 correlations. Each boxplot displays the distribution of the averaged correlation across the 173 AML samples. The higher the reduction relative to the full RACER model, the more power provided by the excluded variables in terms of explaining the underlying mRNA expression level.