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

Drug-target protein affinity prediction method and system

A prediction method and target protein technology, applied in proteomics, biostatistics, bioinformatics, etc., can solve problems such as task inequality, improve accuracy, solve cold start problems, and improve task adaptability Effect

Active Publication Date: 2021-12-21
NANKAI UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a method for effectively mining the correlation between different subtasks, alleviating the task inequality between different subtasks, improving the accuracy of drug-target protein affinity prediction, and effectively solving the problem of drug-target protein affinity prediction. Drug-target protein affinity prediction method and system based on task-adaptive meta-learning neural network for the cold start problem

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
  • Drug-target protein affinity prediction method and system
  • Drug-target protein affinity prediction method and system
  • Drug-target protein affinity prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Embodiment 1 provides a drug-target protein affinity prediction system, which includes:

[0055] The extraction module is used to encode the medicinal chemical molecule and the target protein molecule in the drug-target protein pair to be detected, respectively, to obtain the drug input representation and the target protein input representation;

[0056] The prediction module is used to use the drug-target protein affinity prediction model to process the drug input representation and the target protein input representation to obtain a drug-target protein affinity prediction value; wherein, the drug-target protein affinity prediction model utilizes a training set After training, the training set includes a plurality of drug-target protein pairs and a label marking the true value of the affinity between the drug and the target protein in each drug-target protein pair.

[0057] In Example 1, a drug-target protein affinity prediction method was implemented using the above-m...

Embodiment 2

[0077] Meta-learning, also known as learning how to learn, includes metric-based learning methods, model-based methods, and optimization-based methods. Meta-learning aims to mine the similarities between different tasks, and its significant advantage is that it can be quickly transferred to new tasks. Therefore, meta-learning provides a new way to solve the cold-start problem in drug-target protein affinity prediction.

[0078] Based on this, in this embodiment 2, a drug-target protein affinity prediction method based on task-adaptive meta-learning neural network is proposed. Task inequality, thereby improving the ability of the model's task adaptability and generalization. The problem of drug cold start, target protein cold start, and drug-target protein cold start can be solved simultaneously in the same model, and the accuracy of drug-target protein affinity prediction can be improved.

[0079] like figure 1 As shown, the drug-target protein affinity prediction method ba...

Embodiment 3

[0150] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium. The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the drug- A method for predicting target protein affinity, the method comprising:

[0151] The medicinal chemical molecule and the target protein molecule in the drug-target protein pair to be detected are respectively coded to obtain the drug input representation and the target protein input representation;

[0152] The drug-target protein affinity prediction model is used to process the drug input representation and the target protein input representation to obtain a drug-target protein affinity prediction value; wherein, the drug-target protein affinity prediction model is trained using a training set, and the The training set includes multiple drug-target protein pairs and a label annotating the true value of the affinit...

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 provides a drug-target protein affinity prediction method and system, and belongs to the technical field of biological information processing based on artificial intelligence. The method comprises the following steps: respectively coding a drug chemical molecule and a target protein molecule in a drug-target protein pair to be detected to obtain a drug input representation and a target protein input representation ; and processing the drug input representation and the target protein input representation by using a drug-target protein affinity prediction model to obtain a drug-target protein affinity prediction value. A meta-learning algorithm is utilized to effectively mine the correlation between different subtasks; and the task unevenness between different subtasks is relieved by using the regularization item, the task adaptability of the drug-target protein affinity prediction model is improved, the drug-target protein affinity prediction model with generalization performance is obtained, the accuracy of unknown drug-target protein pair affinity prediction is improved, and the cold start problem in the aspect of drug-target protein affinity prediction is effectively solved.

Description

technical field [0001] The invention relates to the technical field of biological information processing based on artificial intelligence, in particular to a drug-target protein affinity prediction method and system based on a task-adaptive meta-learning neural network. Background technique [0002] Drug-target protein affinity, also known as drug-target protein interaction, reflects the binding strength between a drug molecule and a specific target protein, and its prediction results play an important role in new drug discovery, drug repositioning and drug side effect prediction. [0003] Traditional laboratory-based methods for drug-target protein affinity prediction are costly and inefficient, and are not suitable for dealing with a large number of medicinal chemical molecules and target protein molecules. In recent years, machine learning-based methods have accelerated the progress of drug-target protein affinity prediction, and have received more and more attention in b...

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): G16B15/30G16B20/00G16B40/00
CPCG16B15/30G16B20/00G16B40/00Y02A90/10
Inventor 汲化李梅徐思涵蔡祥睿
Owner NANKAI 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com