Unmodified Synthetic mRNA Control Training Data

Provided here are the data files for parsing the unmodified synthetic training data for subsequent training of a machine learning classifier that calls reads discriminates reads with a pseudouridine modification versus uridine at a particular site. This includes the aligned bam files, aligned raw ionic current signal, and the summary file that is used to map the signal to the correct mRNA read.

本文提供了用于解析未修饰合成训练数据的数据文件，以供后续训练一款机器学习分类器，该分类器可区分特定位点上带有假尿苷（pseudouridine）修饰的读段与尿苷（uridine）修饰的读段。此类数据文件包含比对后的BAM文件、经过比对的原始离子电流信号，以及用于将信号映射至正确mRNA读段的汇总文件。