Method and device for detecting protein complexes based on supervised learning
A protein complex and supervised learning technology, applied in the field of protein complex detection, can solve the problem of not being able to effectively learn the topological characteristics of known protein complexes, and achieve significant biological significance and strong adaptability
Active Publication Date: 2022-03-29
UNIV OF SCI & TECH BEIJING
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The above-mentioned detection methods based on unsupervised learning have some common shortcomings such as: (1) the accuracy of the detection method depends heavily on the reliability of the protein interaction network; (2) it can only detect protein complexes with a single topology; (3) ) cannot efficiently learn topological features of known protein complexes
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
[0078] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will describe in detail with reference to the drawings and specific embodiments.
[0079] like figure 1 As shown, the embodiment of the present invention provides a method for detecting protein complexes based on supervised learning, which is implemented by electronic devices. like figure 1 The shown flow chart of a method for detecting protein complexes based on supervised learning, the processing flow of the method may include the following steps:
[0080] S11. Construct a protein interaction network with weights based on the graph embedding method, topological attributes and biological information; wherein the biological information includes gene expression data, gene ontology, and subcellular localization.
[0081] S12. Detecting the nucleus of the protein complex in the protein interaction network with weights.
[0082] S13. Ac...
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 and device for detecting protein complexes based on supervised learning, and relates to the technical field of protein complex detection. Including: constructing a protein interaction network with weights; detecting the nucleus of protein complexes in the protein interaction network with weights; according to the protein complex model training method with supervised learning, training the protein complex detection model; based on local search Strategies and constructed protein complex detection models, extending the core of protein complexes to form protein complexes; scoring protein complexes according to the protein complex detection model and filtering out low-scoring and highly overlapping protein complexes to be mined out of protein complexes. The invention can further improve the precision of the protein complex detection method; extract effective topological features to describe the protein complex; train and obtain a protein complex model based on supervised learning with strong robustness.
Description
technical field [0001] The invention relates to the technical field of protein complex detection, in particular to a method and device for detecting protein complexes based on supervised learning. Background technique [0002] The methods for detecting protein complexes based on protein interaction networks are mainly divided into three categories: the first type of methods is based on the screening and expansion of seed nodes to search dense subgraphs in protein interaction networks to detect protein complexes, but its time complexity is very high. high and low accuracy. The second class of methods detects protein complexes based on core-attachment structures, such as the COACH algorithm of Wu et al. The algorithm is divided into two steps. First, the core of the protein complex is mined based on concepts such as density, and then the core of the mined protein complex is combined with the accessory proteins to form the final detected protein complex. The third category of...
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): G16B40/20G16B15/00G16B20/00G06N20/10
CPCG16B40/20G16B15/00G16B20/00G06N20/10
Inventor 王荣全赵贺马惠敏储华珍
Owner UNIV OF SCI & TECH BEIJING