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

FM-N-DNN-based drug and target interaction prediction method

A prediction method and target technology, applied in the field of bioinformatics, can solve problems such as cost reduction and efficiency

Inactive Publication Date: 2018-09-07
SUN YAT SEN UNIV
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the FM pre-training strategy has two limitations: one is that the embedding parameters may exceed the influence of FM; the other is that the overhead introduced in the pre-training stage reduces the efficiency
In addition, FNN only captures high-order feature interactions

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
  • FM-N-DNN-based drug and target interaction prediction method
  • FM-N-DNN-based drug and target interaction prediction method
  • FM-N-DNN-based drug and target interaction prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] The prediction method provided by the present invention includes the following steps:

[0032] 1. Data acquisition

[0033] In this example, 10731 pairs of real drug-target interaction pairs were obtained from the DrugBank database, and these were marked as positive samples. For negative samples, since the number of uncertain data is much larger than known interactions, in order to alleviate the problem of unbalanced data, random downsampling is used to generate negative samples. First, drug-target pairs are divided into different drugs and targets to form independent drug groups and target groups. The numbers of drugs and targets were 4292 and 2311, respectively. Next, drugs and targets are randomly selected to construct new drug-target pairs. Then, drug-target pairs already in the positive set are replaced with other non-redundant pairs. Finally, these drug-target pairs are labeled as negative samples. This results in a dataset of 22,719 negative samples, about t...

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 relates to an FM-N-DNN-based drug and target interaction prediction method. The method comprises the following steps of: S1, obtaining drug and target interaction pairs from a DrugBank database and marking the drug and target interaction pairs as a positive samples; S2, dividing the drug and target interaction pairs into different drugs and targets and then forming an independent drug group and an independent target group; randomly selecting drugs and targets from the drug group and the target group to construct new drug and target interaction pairs, and marking samples which arenot positive samples in the newly constructed drug and target interaction pairs as negative samples; S3, extracting feature vectors of the positive samples and the negative samples by utilizing an open source python software package PyDPI; S4, preprocessing the feature vectors extracted in the step S3; S5, constructing an FM-N-DNN model and training the FM-N-FNN model by utilizing the feature vectors of the positive samples and the negative samples; and S6, predicting a drug and target interaction by utilizing the trained FM-N-DNN model.

Description

technical field [0001] The present invention relates to the technical field of bioinformatics, and more specifically, to a method for predicting drug-target interaction based on FM-N-DNN. Background technique [0002] Drug-target interaction refers to identifying whether there is an interaction between a pair of drugs and a target. The identification of drug-target interactions helps researchers find new targets for existing drugs or discover new drug candidates that act on known targets. The identification of interactions between drugs and targets is also one of the key areas of drug repositioning. Drug repositioning refers to the possibility that a drug already on the market may be repurposed for a new disease treatment that is different from its original purpose. Since experimental prediction of drug-target interactions is expensive and time-consuming, in silico methods for drug-target interaction prediction have become increasingly popular in recent years. At the same...

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): G06F19/16G06F19/24G06F19/28
CPCG16B15/00G16B40/00G16B50/00
Inventor 王昊常会友
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

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