Unlock instant, AI-driven research and patent intelligence for your innovation.

End-to-end ncRNA family identification method based on deep learning

A technology of deep learning and identification methods, applied in neural learning methods, informatics, biostatistics, etc., can solve problems such as unsuitable ncRNA family identification problems, and achieve the effect of improving receiving sensitivity and processing speed

Inactive Publication Date: 2019-12-20
JILIN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The purpose of the present invention is to provide an end-to-end ncRNA family recognition method based on deep learning in order to solve the problem that many existing methods are not suitable for solving a large number of ncRNA family recognition problems

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • End-to-end ncRNA family identification method based on deep learning
  • End-to-end ncRNA family identification method based on deep learning
  • End-to-end ncRNA family identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] see Figure 1 to Figure 3 Shown:

[0036] In an embodiment of the present invention, a general-purpose PC computer is usually used as the upper computer 01, which can be connected to an ncRNA family identification device of an ARM9 microprocessor connected to a graphics card through an RS-232 serial port, and works together to Complete identification of ncRNA families.

[0037] 1) Collect some ncRNA detection data on the Rfam website as test data.

[0038] 2) Input the collected ncRNA sequence through the input unit of the host computer. And transmit it to the internal storage unit of the ncRNA family identification device through the RS-232 serial port, and further read the data into the cache unit.

[0039] 3) The preprocessing unit reads the ncRNA information from the cache unit, first truncates the data with a length greater than 400 to a sequence with a length of 400, and fills the sequence with a length less than 400 with N to a length of 400 and stores it in the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an end-to-end ncRNA family identification method based on deep learning. The method is composed of three parts including model design, model training and device design, and model testing, and comprises a first step of model design, a second step of model training and device design, and a third step of model testing. The end-to-end ncRNA family identification method based ondeep learning is characterized by extracting ncRNA sequence features by directly using deep learning to identify the ncRNA family, without the need for a secondary structural feature based on a ncRNAsecondary structure prediction tool. Unlike other methods, the method avoids the negative impact on accurately identifying the ncRNA family caused by the low accuracy of the ncRNA secondary structureprediction tool. Therefore, the method not only simplifies the operation steps and makes the identification of the ncRNA family easier, but also improves the identification accuracy.

Description

technical field [0001] The invention relates to an ncRNA family identification method, in particular to an end-to-end deep learning-based ncRNA family identification method. Background technique [0002] At present, there is enough evidence to prove that ncRNA plays an important role in cell life activities and disease pathogenesis. High-throughput technologies have generated a large number of ncRNAs with unknown functions. Accurate identification of ncRNA families is helpful to study their functions, so it is necessary and urgent to identify each ncRNA family. [0003] In this era of high-throughput technology, a large number of unknown ncRNAs have been discovered, and the functional studies of these ncRNAs have brought great challenges to researchers. Since different ncRNA families have different functions, accurate identification of ncRNA families is beneficial to the study of ncRNA functions, which in turn has important theoretical and practical significance for drug r...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G16B30/10G16B40/00G06N3/04G06N3/08
CPCG16B30/10G16B40/00G06N3/08G06N3/045
Inventor 刘元宁王林宇钟晓丹刘海明张浩郑少阁
Owner JILIN UNIV