-
Categories
-
Pharmaceutical Intermediates
-
Active Pharmaceutical Ingredients
-
Food Additives
- Industrial Coatings
- Agrochemicals
- Dyes and Pigments
- Surfactant
- Flavors and Fragrances
- Chemical Reagents
- Catalyst and Auxiliary
- Natural Products
- Inorganic Chemistry
-
Organic Chemistry
-
Biochemical Engineering
- Analytical Chemistry
-
Cosmetic Ingredient
- Water Treatment Chemical
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
On January 17, 2022, Li Xuan's research group, Wang Jiawei's research group, and Hao Pei's research group of Shanghai Pasteur Institute, Chinese Academy of Sciences cooperated to publish an online publication in the international academic journal Genome Biology entitled " DENA: training an authentic neural network model using Nanopore sequencing data of Arabidopsis transcripts for detection and quantification of N 6 -methyladenosine on RNA”
.
In this study, a deep learning neural network approach was used to train and construct a quantitative model DENA (Deeplearning Explore Nanopore m 6 A) for the identification of RNA methylation (m 6 A) modifications in the transcriptome, and to study RNA appearance for direct sequencing from the transcriptome.
RNA post-transcriptional modification is a new hotspot in recent years to study the apparent function of RNA
.
The N-6 methylation (m 6 A) modification of RNA, as the most common modification mechanism of RNA, is involved in a series of important molecular processes such as mRNA splicing, transport, translation, localization, and degradation
Nanopore sequencing is currently the only technology that can directly determine RNA sequences, providing a breakthrough possibility for the direct and accurate detection of various apparent modifications of RNA
.
The Nanopore direct sequencing process of RNA, when the RNA bases pass through the nanopore, the modified structure on it will generate a specific current signal
Aiming at the most common N-6 methylation (m 6 A) modification structure of RNA, the research group used a deep learning neural network method to establish a quantitative model for identifying RNA methylation (m 6 A) modification in the transcriptome
.
The research group used Arabidopsis materials, including wild-type and m 6 A modified mutants, to compare the Nanopore direct sequencing data of its mRNA, and obtained m 6 A high modification (wild type) and low modification (m 6 A ) at the same sequence site.
(1) For the first time, the m 6 A-modified signal featuresof natural RNA were isolated from the RNA direct sequencing data of biological samples , avoiding the problem of signal noise in the sequencing data of artificially synthesized RNA
.
The neural network model training is based on millions of sequencing data features extracted from more than 3,000 m 6 A modification sites, which solves the difficulty of training complex neural network models caused by insufficient synthetic RNA data sites
(2) DENA is the first neural network model to obtain RNA m 6
A modification signal recognition .
For different test site data, the obtained model evaluation index (AUC) was between 0.
(3) DENA not only has high accuracy in the prediction of m 6 A modification sitesin Arabidopsis mRNA sequencing data, but also obtained excellent results in the detection and quantification of known m 6 A modification sites in human mRNA (using SCARLET).
result verification)
.
It proves the better robustness of DENA, which is not only applicable to Arabidopsis, but also can be used for RNA modification research of other biological species
(4) Using DENA to analyze the sequencing data of wild-type and three m 6 A-deficient Arabidopsis mutants, the m 6 A modification of Arabidopsis mRNA at the whole transcriptome level and single-base precision was established for the first time.
Atlas
.
This research result not only provides an important tool for the study of m 6 A modification of Arabidopsis thaliana and other biological mRNAs, but also provides research ideas and identification model templates for deep learning neural networks for the identification and analysis of other epigenetic modifications of RNA.
.
DENA is open and freely available on Github (https://github.
Qin Hang, a doctoral student at the Center for Excellence in Molecular Plant Science, Chinese Academy of Sciences, and Ou Liang, a doctoral student at the Pasteur Institute, Chinese Academy of Sciences, are the co-first authors of this article
.
Researcher Li Xuan and Wang Jiawei of the Center for Excellence in Molecular Plant Science, Chinese Academy of Sciences, and Hao Pei, researcher of the Pasteur Institute, Chinese Academy of Sciences are the co-corresponding authors
.
The research work was supported by the National Key R&D Program, the National Natural Science Foundation of China, and the Pilot Project of the Chinese Academy of Sciences
.
Paper link: https://genomebiology.
biomedcentral.
com/articles/10.
1186/s13059-021-02598-3
Transcriptome-wide, single-base precision mapping of m 6 A modification of Arabidopsis mRNA
