Mixed-Weight Neural Bagging for Detecting $m^6A$ Modifications in SARS-CoV-2 RNA Sequencing
Ruhan Liu, Liang Ou, Bin Sheng, Pei Hao, Ping Li, Xiaokang Yang, Guangtao Xue, Lei Zhu, Yuyang Luo, Ping Zhang, Po Yang, Huating Li, David Dagan Feng
Abstract
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Objective:</i> The m6A modification is the most common ribonucleic acid (RNA) modification, playing a role in prompting the virus's gene mutation and protein structure changes in the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). Nanopore single-molecule direct RNA sequencing (DRS) provides data support for RNA modification detection, which can preserve the potential <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m^6A$</tex-math></inline-formula> signature compared to second-generation sequencing. However, due to insufficient DRS data, there is a lack of methods to find m6A RNA modifications in DRS. Our purpose is to identify <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m^6A$</tex-math></inline-formula> modifications in DRS precisely. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Methods:</i> We present a methodology for identifying <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m^6A$</tex-math></inline-formula> modifications that incorporated mapping and extracted features from DRS data. To detect <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m^6A$</tex-math></inline-formula> modifications, we introduce an ensemble method called mixed-weight neural bagging (MWNB), trained with 5-base RNA synthetic DRS containing modified and unmodified <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m^6A$</tex-math></inline-formula> . <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Results:</i> Our MWNB model achieved the highest classification accuracy of 97.85% and AUC of 0.9968. Additionally, we applied the MWNB model to the COVID-19 dataset; the experiment results reveal a strong association with biomedical experiments. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Conclusion:</i> Our strategy enables the prediction of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m^6A$</tex-math></inline-formula> modifications using DRS data and completes the identification of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m^6A$</tex-math></inline-formula> modifications on the SARS-CoV-2. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Significance:</i> The Corona Virus Disease 2019 (COVID-19) outbreak has significantly influence, caused by the SARS-CoV-2. An RNA modification called <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m^6A$</tex-math></inline-formula> is connected with viral infections. The appearance of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m^6A$</tex-math></inline-formula> modifications related to several essential proteins affects proteins’ structure and function. Therefore, finding the location and number of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m^6A$</tex-math></inline-formula> RNA modifications is crucial for subsequent analysis of the protein expression profile.