Detecting microRNA binding and siRNA off-target effects from expression data

Abstract

Sylamer is a method for detecting microRNA target and small interfering RNA off-target signals in 3' untranslated regions from a ranked gene list, sorted from upregulated to downregulated, after a microRNA perturbation or RNA interference experiment. The output is a landscape plot that tracks occurrence biases using hypergeometric P-values for all words across the gene ranking. We demonstrated the utility, speed and accuracy of this approach on several datasets.

Figure 1. Mouse miR-155 knockout experiment

Sylamer enrichment landscape plots for a) 6nt, (b) 7nt and (c) 8nt words. In each case, the x-axis represents the sorted genelist from most upregulated (left) to most downregulated (right). The y-axis shows the hypergeometric significance for each word at each leading bin. Positive values indicate enrichment (−log₁₀ (P-value)) and negative values, depletion (log₁₀(P-value)). The horizontal line represents an E-value threshold (Bonferroni corrected) of 0.01. Vertical lines indicate significance peaks across bins for a given word with the number of sequences indicated and (in parentheses) the number possessing the appropriate match. Grey lines show the profiles of words unrelated to the seed region of miR-155, while colored lines represent words complementary to the seed-region. Some grey lines appear to pass the E-value threshold, these 7nt and 8nt words contain the core 6nt seed flanked by mismatches. The position of a previously validated target (c-Myc) within the genelist is indicated by a green triangle.

Figure 2. Human RNAi off-target analysis

Sylamer enrichment plots for: (a) Enrichment profile for a successful RNAi probe which does not appear to exhibit any off-target effects according to sorted expression data, (b) RNAi probe showing off-target effects as evidenced by strong enrichment of words matching its seed region for the 2,500 most downregulated transcripts, (c) an RNAi probe exhibiting a very strong off-target effect involving more than 3,000 transcripts. Dotted lines represent an E-value threshold (Bonferroni corrected) of 0.01. Each possible word matching the siRNA is shown in colour.