Evaluation of Commercial RNA Extraction Protocols for Avian Influenza Virus Using Nanopore Metagenomic Sequencing

Abstract

Avian influenza virus (AIV) is a significant threat to the poultry industry, necessitating rapid and accurate diagnosis. The current AIV diagnostic process relies on virus identification via real-time reverse transcription-polymerase chain reaction (rRT-PCR). Subsequently, the virus is further characterized using genome sequencing. This two-step diagnostic process takes days to weeks, but it can be expedited by using novel sequencing technologies. We aim to optimize and validate nucleic acid extraction as the first step to establishing Oxford Nanopore Technologies (ONT) as a rapid diagnostic tool for identifying and characterizing AIV from clinical samples. This study compared four commercially available RNA extraction protocols using AIV-known-positive clinical samples. The extracted RNA was evaluated using total RNA concentration, viral copies as measured by rRT-PCR, and purity as measured by a 260/280 absorbance ratio. After NGS testing, the number of total and influenza-specific reads and quality scores of the generated sequences were assessed. The results showed that no protocol outperformed the others on all parameters measured; however, the magnetic particle-based method was the most consistent regarding C_T value, purity, total yield, and AIV reads, and it was less error-prone. This study highlights how different RNA extraction protocols influence ONT sequencing performance.

Keywords: avian influenza; metagenomic sequencing; nanopore sequencing; nucleic acid extraction.

Figure 1

Experimental workflow. The total time (spent extracting 24 samples) was split into passive and hands-on time for each protocol.

Figure 2

The log mean concentration distribution for each extraction protocol is represented as MagMAX Pathogen RNA/DNA™ (A), QIAamp^® Viral RNA (B), TRIzol™ LS Reagent (C), and SwiftX™ Swabs (D). Statistical differences between protocols are indicated atop the boxplots using the results from a mixed-effect regression model (protocol as a fixed effect and tissue type nested within bird as a random effect). No significance “ns”; “****” indicate p-values > 0.05 and ≤0.0001, respectively. An alpha value of 0.05 was used, and p-values were adjusted using the Sidak method for 6 tests.

Figure 3

The distribution of cycle threshold values for each extraction protocol is represented as MagMAX Pathogen RNA/DNA™ (A), QIAamp^® Viral RNA (B), TRIzol™ LS Reagent (C), and SwiftX™ Swabs (D). Statistical differences between protocols are indicated atop the boxplots using the results from a mixed-effect regression model (C_T as the protocol as a fixed effect and tissue type nested within bird as a random effect). No significance “ns”, “*”, and “****” indicate p-values > 0.05, ≤0.05, and ≤0.0001, respectively. An alpha value of 0.05 was used, and p-values were adjusted using the Sidak method for 6 tests.

Figure 4

The count of positive samples by rRT-PCR by extraction protocol, represented as MagMAX Pathogen RNA/DNA™ (A), QIAamp^® Viral RNA (B), TRIzol™ LS Reagent (C), and SwiftX™ Swabs (D). The total number of evaluated extracts per protocol was 48, considering that we extracted 24 samples in two different sections, resulting in 48 individual results per protocol. An extract has a positive detection (1) when the C_T value is less than (<) 40 and a negative detection (0) when the C_T value is equal to or higher than 40.

Figure 5

The distribution of purity values for each extraction protocol is represented as MagMAX Pathogen RNA/DNA™ (A), QIAamp^® Viral RNA (B), TRIzol™ LS Reagent (C), and SwiftX™ Swabs (D). Statistical differences between protocols are indicated atop the boxplots using the results from a mixed-effect regression model (purity (pure or impure) was the response variable, the extraction protocol was the fixed effect, and tissue type nested within the bird was used as a random effect). “ns” and “*” indicate p-values > 0.05 and ≤0.05 respectively. An alpha value of 0.05 was used, and p-values were adjusted using the Sidak method for 6 tests. The red dashed lines indicate the range of absorbance ratio values between 1.9 and 2.2 within which an extract is considered pure.

Figure 6

The count (numbers within the bars) of pure and impure extracts by extraction protocol, represented as MagMAX Pathogen RNA/DNA ™ (A), QIAamp^® Viral RNA (B), TRIzol™ LS Reagent (C), and SwiftX™ Swabs (D). An extract is considered pure if the absorbance ratio values lie between 1.9 and 2.2. “NA”: purity could not be assessed due to insufficient extract volume.

Figure 7

Metagenomic nanopore sequencing results by protocol. A-D plots of the different aspects evaluated to assess the sequence performance of the extraction protocols, represented as MagMAX Pathogen RNA/DNA™ (A), QIAamp^® Viral RNA (B), TRIzol™ LS Reagent (C), and SwiftX™ Swabs (D). The boxplots represent the results from the three samples selected for mNGS. (a) Quality scores from the generated reads. (b) Log-transformed number of Influenza A reads generated. (c) Length of the generated reads expressed in bases. (d) Total yield (number of total reads) generated by protocol. Statistical differences between protocols are indicated atop the boxplots using the results from a mixed-effect regression model (read quality/log number of reads/read length, yield as the protocol as a fixed effect, and tissue type nested within bird as a random effect). “ns,” “*”, and “**”indicate p-values > 0.05, ≤0.05, and ≤0.0001 respectively. An alpha value of 0.05 was used, and p-values were adjusted using the Sidak method for six tests.