Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Protein function prediction method combining multi-task learning and self-attention mechanism

A protein function and multi-task learning technology, which is applied in the field of protein function prediction combining multi-task learning and self-attention mechanism, can solve the problems of lack of multi-task learning methods and difficult protein function prediction

Active Publication Date: 2021-03-26
SUN YAT SEN UNIV
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the lack of use of multi-task learning methods in the prior art and the difficulty in accurately predicting protein functions, the present invention provides a protein function prediction method combining multi-task learning and self-attention mechanism

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
  • Protein function prediction method combining multi-task learning and self-attention mechanism
  • Protein function prediction method combining multi-task learning and self-attention mechanism
  • Protein function prediction method combining multi-task learning and self-attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] like figure 1 As shown, a protein function prediction method combining multi-task learning and self-attention mechanism, including the following steps:

[0058] S1: According to the molecular function category MF prediction task, the biological process category BP prediction task and the cell component category CC prediction task, construct a protein function prediction system model based on multi-task learning and self-attention mechanism;

[0059] S2: Obtain the sample data set, extract the feature information of the protein sequence in the sample data set, and build a training set and a test set;

[0060] S3: Preprocess the training set and input it into the protein function prediction system model, and train the protein function prediction system model;

[0061] S4: Preprocess the test set and input it into the trained protein function prediction system model to perform protein function prediction.

[0062] Further, the step S1 is specifically:

[0063] S101: Con...

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 a protein function prediction method combining multi-task learning and a self-attention mechanism, and the method comprises the following steps: predicting a task according toa molecular function type MF, a biological process type BP, and a cell module type CC; constructing a protein function prediction system model based on multi-task learning and a self-attention mechanism; obtaining a sample data set, extracting feature information of protein sequences in the sample data set, and establishing a training set and a test set; preprocessing the training set, inputting the preprocessed training set into a protein function prediction system model, and training the protein function prediction system model; and preprocessing the test set, inputting the preprocessed testset into the trained protein function prediction system model, and carrying out protein function prediction. According to the method, prediction of three ontology theories is regarded as three prediction tasks, prediction is performed by establishing a protein function prediction system model based on multi-task learning and a self-attention mechanism, and the accuracy of protein function prediction is improved.

Description

technical field [0001] The invention relates to the field of protein function prediction, and more specifically, relates to a protein function prediction method combining multi-task learning and self-attention mechanism. Background technique [0002] Protein function prediction is a very important task in the field of biology, and plays a key role in the development of new drugs and pathological understanding. In the early days, the functional annotation of proteins was mainly carried out through in vivo or in vitro experiments, but its time-consuming and expensive characteristics could not adapt to the development speed of current high-throughput sequencing technology. Therefore, calculation-based methods have gradually become the focus due to their low cost and fast speed. research direction. [0003] Protein function can be annotated by Gene Ontology (Gene Ontology), which contains more than 40,000 functional items, which can be divided into three categories: molecular f...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G16B20/00G16B40/00G16B50/30
CPCG16B20/00G16B40/00G16B50/30Y02A90/10
Inventor 杨跃东黄伟林赵慧英卢宇彤
Owner SUN YAT SEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products