Unlock instant, AI-driven research and patent intelligence for your innovation.
Drug-drug interaction prediction method and system based on non-negative tensor decomposition
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A non-negative tensor decomposition and prediction method technology, applied in the field of computer-aided drug research, can solve problems such as unpredictability, costing a lot of money and time, and unexplainable reasons for drug interactions, achieving good stability and robustness , The process is fast, simple and convenient, and the effect of predicting the effect is good
Inactive Publication Date: 2021-08-13
重庆亿创西北工业技术研究院有限公司
View PDF0 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0003] However, traditional DDI identification methods rely on clinical identification, which usually consumes a lot of money and time
Although, existing computational methods can predict potential DDI on a large scale using drug properties (eg, chemical structure, etc.); however, existing computational methods can only predict "with or without" DDI, so there are at least the following shortcomings: its First, DDI including pharmacological types (PK type and PD type) cannot be predicted, and pharmacological DDI occurs at the pharmacokinetic and / or pharmacodynamic level; second, the reason for the interaction between the two drugs cannot be explained; other 3. Failure to predict DDI for newly developed drugs
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0036] Refer to attached figure 1 , this embodiment provides a drug-drug interaction prediction method based on non-negative tensor decomposition, comprising the following steps:
[0037] S01. Obtain the network data, drug characteristics and new drug characteristics of pharmacological type drug-drug interaction (DDI); specifically, the network data of pharmacological type DDI is a self-loop undirected network, denoted as G, G=(V , E, l); where V={v 1 , v 2 ,...,v m} is a collection of nodes in the network, each node represents a drug; E={e 1 , e 2 ,...,e c} is the set of edges between nodes, each edge represents a DDI, l={PK, PD} is the attribute of the set of edges. The adjacency matrix of the DDI network data is a single-type third-order tensor, denoted as Y (generalized adjacency matrix), which can be regarded as a stack of two adjacent matrices interacting with PK and PD types. If the drug d i with drugs d j If there is an interaction and the pharmacological type...
Embodiment 2
[0068] Refer to attached Figure 5 , this embodiment provides a system for realizing the non-negative tensor decomposition-based drug-drug interaction prediction method provided in the above embodiment 1, which includes: an acquisition module, a dimensionality reduction module, a training module, a prediction module and Evaluation module.
[0069] Among them, the obtaining module is used to obtain network data, drug characteristics and new drug characteristics of pharmacological types of drug-drug interactions.
[0070] The dimensionality reduction module is used to reduce the dimensionality of drug features and new drug features using the principal component analysis method based on kernel functions.
[0071] The training module is used to construct a training model through the non-negative tensor decomposition method according to the network data of pharmacological type drug-drug interaction and the drug feature after dimensionality reduction, so as to obtain the latent spa...
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
Login to View More
Abstract
The invention discloses a drug-drug interaction prediction method and system based on non-negative tensor decomposition, and belongs to the technical field of computer-aided drug research. The prediction method includes the following steps: obtaining network data of pharmacological type drug-drug interaction, drug features and new drug features; using kernel function-based principal component analysis method to reduce the dimensionality of drug features and new drug features; Quantity decomposition method is used to construct the training model to obtain the potential space characteristics of the drug; according to the new drug characteristics after dimensionality reduction and the potential space characteristics of the drug, the potential space characteristics of the new drug are obtained, and the prediction model is constructed by the non-negative tensor decomposition method to obtain Prediction score of potential pharmacological type drug‑drug interactions for new drugs. The whole process of the prediction method provided by the present invention is fast, simple and convenient, and it can achieve good prediction effect in less time, and can be applied to social networks and biological information networks of different scales.
Description
technical field [0001] The invention relates to the technical field of computer-aided drug research, in particular to a drug-drug interaction prediction method and system based on non-negative tensor decomposition. Background technique [0002] In the case of simultaneous use of multiple drugs, the pharmacodynamic effects of each drug may not be independent of each other, and the pharmacokinetic (PK) or pharmacodynamic (Pharmadynamic, PD) behavior of different drugs This effect is called drug-drug interaction (Drug-Drug Interaction, DDI). Drug-drug interactions may lead to adverse drug reactions, which in turn lead to treatment failure in complex diseases. Therefore, it is of great significance to identify DDI before prescribing compounded drugs. [0003] However, traditional DDI identification methods rely on clinical identification, which usually consumes a lot of money and time. Although, existing computational methods can predict potential DDI on a large scale using d...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More