A method for predicting new indications of old drugs based on matrix factorization based on gene space fusion
A matrix decomposition and space fusion technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of time-consuming and energy-consuming, and achieve the effect of reliable data and eliminating the calculation process.
Active Publication Date: 2017-04-05
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
These studies have achieved certain results, but they all require clear attribute data for drugs and diseases to be calculated before the research, which will consume a certain amount of time and energy
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0061] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.
[0062] The present invention is based on the analysis of drug-disease association, drug-gene association, disease-gene association and gene association. The joint space is constructed through the gene interaction network in the gene space, and then the feature vectors of drugs and diseases are obtained from the joint space. In this way, the topological features of gene space are integrated into the feature space of drugs and diseases. Then, under the supervision of drug-disease association data, the eigenvectors of drugs and diseases are updated and adjusted by matrix factorization model. Finally, the drug and disease-adjusted feature space is used to screen potential drug-disease associations to predict new indications ...
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 method for predicting a novel adaptation disease of an older medicine based on gene space fusion matrix decomposition. The method comprises the following steps: collecting correlation data of the medicine and the disease, preparing data of a gene space, extracting a gene tightness matrix from the gene space, establishing a correlated space according to the gene tightness matrix, calculating a characteristic space of the medicine and the disease according to the correlated space, initializing a matrix decomposition model by using the characteristic space of the medicine and the disease, preparing a training sample, training the matrix decomposition model, performing correlation degree prediction on a medicine-disease combination rather than the training sample, repeating the steps of sample preparing, model training and prediction for multiple times, predicting the correlation degrees of all possible medicine-disease combinations according to an average value, sequencing the correlation prediction degrees, setting a degree threshold, and screening potential medicine-disease correlation, thereby predicting the adaptation disease of the medicine. By adopting the method, the potential medicine-disease correlation can be relatively accurately screened.
Description
technical field [0001] The invention relates to the application of computer technology in medical research, in particular to a method for predicting new indications (reuse of old drugs) of old drugs based on matrix decomposition of gene space fusion. Background technique [0002] Due to the large investment, long cycle and high risk of new drug research and development, the number of new drugs on the market has decreased significantly. The development cycle of a new chemical entity drug is often more than 10 years, and the cost is more than 1 billion US dollars. From drug candidate to approval for production, the success rate is only 10%. In recent years, drug developers have paid more and more attention to new applications of old drugs. New use of old drugs refers to finding new indications for existing drugs in clinical practice. The research and development process of new use of old drugs can avoid the existing toxicology and pharmacokinetic evaluation, which greatly r...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F19/00G06K9/66
Inventor 刘西代文高一波卢朋
Owner INST OF AUTOMATION CHINESE ACAD OF SCI