Detect inosine using nanopore sequencing

Adenosine to Inosine (A-to-I) editing is one of the most prevalent post-transcriptional RNA modifications. It plays numerous crucial roles in determining a cell's fate. Until now, there is no direct approach to detect Inosine in RNA yet. Here, we introduce a method to detect Inosine using Nanop...

全面介紹

Saved in:
書目詳細資料
主要作者: Nguyen, Tram Anh
其他作者: Tan Meng How
格式: Final Year Project
語言:English
出版: Nanyang Technological University 2021
主題:
在線閱讀:https://hdl.handle.net/10356/151918
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
機構: Nanyang Technological University
語言: English
實物特徵
總結:Adenosine to Inosine (A-to-I) editing is one of the most prevalent post-transcriptional RNA modifications. It plays numerous crucial roles in determining a cell's fate. Until now, there is no direct approach to detect Inosine in RNA yet. Here, we introduce a method to detect Inosine using Nanopore direct RNA sequencing with high overall accuracy and area under the curve (AUC) of receiver operating characteristic (ROC) and precision-recall (PR) around 90%. Our method is based on the differences in current signal, as well as base-calling and alignment errors from Inosine. We also explored that the sequence context goes beyond the widely used 5-mer in Nanopore. A series of convolutional neural networks (CNN) was built to detect Inosine from not only Adenosine but also single nucleotide polymorphism (SNP). We then show that our method can be generalized to identify edit sites from unseen organisms. Our result will shed light on the future of investigating more about RNA modifications and their roles in the cells.