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

Drug recommendation method based on twin neural network and deep factorization machine

A technique of deep factoring and factorization, applied in the field of biological information

Pending Publication Date: 2022-01-04
TIANJIN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, methods for drug sensitivity prediction are not optimal for clinical situations

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 recommendation method based on twin neural network and deep factorization machine
  • Drug recommendation method based on twin neural network and deep factorization machine
  • Drug recommendation method based on twin neural network and deep factorization machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0059] The invention discloses a drug recommendation method based on a twin neural network and a deep factorization machine, including: data preprocessing, sample pair generation, model construction of the twin neural network and a deep factorization machine, model training, and evaluation index display. The present invention applies the twin neural network and deep factorization machine model to the problem of drug recommendation for the first time, combined with cell line gene expression data and drug structure data, and achieved good results on the CCLE data set. At the same time, the present invention introduces an embedded Response unit to generate gene features to better mine the correlation between drugs and genes, so that the algorithm can better capture the characteristics of combined features.

[0060] Such...

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 drug recommendation method based on a twin depth factorization machine. The drug recommendation method comprises the steps of data preprocessing, training set and verification set division through three-fold cross validation, construction of a network model based on a depth factorization machine, model training and evaluation. According to the method, a deep factorization machine model is applied to the drug recommendation problem for the first time, the model is constructed in combination with cell line gene expression data and drug structure data, and good results are obtained on three verification sets. Meanwhile, the mechanism of a Response unit is introduced, the correlation between a drug and a gene can be better mined, and the algorithm can learn more combination characteristics.

Description

technical field [0001] The invention relates to the technical field of biological information, in particular to a neural network-based drug recommendation method. Background technique [0002] In most studies, drug sensitivity is used as an index to judge whether the drug is sensitive to the patient, which is divided into the half inhibitory concentration (IC50) of the drug on the cell line and the active area (ActArea) of the drug on the cell line. If a sensitive feature is shown, it proves that the drug is useful for the patient. At present, a large number of machine learning methods have been applied to the field of drug sensitivity prediction. For example, popular regression models include elastic nets (EN), support vector machines (SVM), and deep neural network-based methods. However, in actual clinical practice, patients prefer to know the most suitable drug for their condition, rather than knowing the exact value of drug sensitivity. Therefore, methods for drug sen...

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): G16H20/10G16B25/00G16C20/00G06N3/08G06N3/04G06K9/62
CPCG16H20/10G16B25/00G16C20/00G06N3/08G06N3/045G06F18/214
Inventor 苏苒黄译萱
Owner TIANJIN 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