Check patentability & draft patents in minutes with Patsnap Eureka AI!

Anticancer drug screening method based on multichannel neural network

A neural network and anti-cancer drug technology, applied in the field of computer science, can solve problems such as the inability of the model to play a practical role and unsatisfactory cancer cell line data, and achieve accurate anti-cancer drug screening, strong practical application capabilities, and maintain predictive performance Effect

Pending Publication Date: 2022-05-13
HUNAN UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Cancer cell line data in practical application scenarios are often not ideal, which may cause the model to be ineffective

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
  • Anticancer drug screening method based on multichannel neural network
  • Anticancer drug screening method based on multichannel neural network
  • Anticancer drug screening method based on multichannel neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0030] Refer to attached figure 1 , a method for screening anticancer drugs based on a multi-channel neural network proposed by the present invention is specifically implemented through the following steps:

[0031] Step 1, convert the SMILES sequence representing the global structural information of the drug into a Graph form, and use GCN to extract its features.

[0032] In this example, the SMILES sequence of a given drug is converted into a molecular graph (Graph) through RDKit, and stored in the form of a feature matrix X and an adjacency matrix A, where X is a matrix of size n×f, where n is the compound The number of atomic nodes, each node is represented by an f-dimensional vector, A is a matrix of n×n size, representing the edges between nodes; use three graph convolution layers Feature extraction is performed on the drug m...

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 belongs to the field of computer science, and discloses an anti-cancer drug screening method based on a multichannel neural network. According to the method, drug molecule graph features of a graph structure are extracted through a graph convolution network, drug molecule fingerprints and cell line miRNA features in a conventional vector format are extracted through one-dimensional convolution, gene copy number features of ultrahigh dimensions are extracted through an auto-encoder, and feature information of different data structures and dimensions can be fused. According to the method, the problems of different structures and high data complexity of different input feature data can be solved, so that global and local structural information of the drug and cell line features from different omics data are effectively fused, the accuracy of drug sensitivity prediction is improved, and the efficiency of anti-cancer drug screening is improved. Meanwhile, the robustness of the model is improved through fusion of multiple information sources, so that the model can still keep stable performance when data labels are insufficient.

Description

technical field [0001] The invention belongs to the field of computer science, relates to the application of artificial intelligence technology in biomedical problems, and specifically relates to a method for screening anticancer drugs based on a multi-channel neural network. Background technique [0002] Due to the particularity of cancer treatment, precision medicine has become a difficult problem that scientists all over the world want to overcome. It is of great significance for precision medicine to predict the response of cancer cell lines to specific drugs, and then to screen out anti-cancer drugs with research significance. Some classic machine learning algorithms benefited from their strong ability in data and model integration, and made preliminary explorations for drug response prediction. However, due to the high dimensionality and few labels of anticancer drug response data, these methods are overwhelmed. Deep learning is a more advanced branch of machine lear...

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): G16H70/40G16B20/10G16B40/00G06N3/04G06N3/08
CPCG16H70/40G16B20/10G16B40/00G06N3/08G06N3/045
Inventor 彭绍亮程孝孝刘文娟王小奇王红
Owner HUNAN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com