The reality of pervasive transcription

Abstract

Despite recent controversies, the evidence that the majority of the human genome is transcribed into RNA remains strong.

Figure 1. Precision recall curves for the overlap of transcribed regions (transfrags) detected in different experiments and annotated exons (from GENCODE version 4 and the UCSC known genes track from the UCSC Genome Browser).

The Clark et al. transfrags are based on data generated as part of the ENCODE transcriptome project from K562 cell polyA+ RNA. The transfrags are generated from 5-bp two-color tiling arrays (MinRun  = 40 bp, MaxGap  = 40 bp). The seqfrags are based on 200 million paired-end 76 bp reads generated on the Illumina sequencing platform. Any detected region that overlaps an annotated exon is scored positive, all others negative. Fewer exons are detected overall (compared to van Bakel et al. [2]), likely reflecting the difference between a relatively homogeneous cell line and complex tissue like brain.

Figure 2. Poor coverage of single intron transcriptional units (TUs) by van Bakel et al. .

The figure shows the abundance of sequence reads mapped to the HAR1A locus (green) and the TU created from these tags by van Bakel et al. using TopHat (red) . In contrast, the Clark et al. TU created by reanalysis of sequence reads using Cufflinks includes the extended 5′ and 3′ exonic sequences (dark blue).