RNA profile diversity across arthropoda: guidelines, methodological artifacts, and expected outcomes

Abstract

High-quality RNA is an important precursor for high-throughput RNA sequencing (RNAseq) and subsequent analyses. However, the primary metric used to assess RNA quality, the RNA Integrity Number (RIN), was developed based on model bacterial and vertebrate organisms. Though the phenomenon is not widely recognized, invertebrate 28S ribosomal RNA (rRNA) is highly prone to a form of denaturation known as gap deletion, in which the subunit collapses into two smaller fragments. In many nonmodel invertebrates, this collapse of the 28S subunit appears as a single band similar in size to the 18S rRNA subunit. This phenomenon is hypothesized to be commonplace among arthropods and is often misinterpreted as a "degraded" rRNA profile. The limited characterization of gap deletion in arthropods, a highly diverse group, as well as other nonmodel invertebrates, often biases RNA quality assessments. To test whether the collapse of 28S is a general pattern or a methodological artifact, we sampled more than half of the major lineages within Arthropoda. We found that the 28S collapse is present in ∼90% of the species sampled. Nevertheless, RNA profiles exhibit considerable diversity with a range of banding patterns. High-throughput RNAseq and subsequent assembly of high-quality transcriptomes from select arthropod species exhibiting collapsed 28S subunits further illustrates the limitations of current RIN proxies in accurately characterizing RNA quality in nonmodel organisms. Furthermore, we show that this form of 28S denaturation, which is often mistaken for true "degradation," can occur at relatively low temperatures.

Keywords: RNAseq; crustaceans; denaturation; gap deletion; genomics; insects; invertebrates; nucleic acids; transcriptomics.

Figure 1:

Bioanalyzer electropherograms of total RNA for a diverse array of Arthropod lineages. Sample information including taxonomic classifications are given in Table 1. Samples in Panels a–f are randomized (nontaxonomic order) but corresponding lane information is in Table 1. Ladders correspond to the picochip RNA size standard. Red (or highlighted) cells above a lane indicate that the RIN could not be calculated.

Figure 2:

Temperature gradient (denaturing treatment) for three representative taxa and a positive control (See Table 1): Escherichia coli (Qubit Standard 2), Millipede (HBG5053), Centipede (HBG5058), and Blue crab (HBG5273). (a) 20–30°C, (b) 40–50°C, (c) 60–70°C, and (d) 80–90°C. Ladder corresponds to the picochip RNA size standard. These samples match those used in Supplementary Fig. S1.

Figure 3:

De novo transcriptome assembly statistics for the isopod Asellus aquaticus (a) and amphipod Niphargus hrabei (b), each exhibiting denatured RNA profiles indicative of 28S rRNA subunit collapse (left). Raw data were generated on an Illumina HiSeq4000 (BioProject PRJNA476149) using methods described in [37]. Transcriptomes were assembled using Trinity and assessed for quality and completeness using Transrate and BUSCO. Metrics include: total number of assembled transcripts, longest generated transcript (bp), mean length of all transcripts (bp), number of transcripts with an open reading frame (ORF), mean ORF percent, N50 statistic and overall GC content (see [37] for additional details).