Polypeptide classification method based on complex network
A complex network and classification model technology, applied in the field of computer-aided drug design, can solve problems such as limited scope of application, inaccurate classification of peptide classification methods, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0042] This embodiment provides a method for classifying polypeptides based on a complex network, the method comprising:
[0043] Step1 Extract the primary structure and tertiary structure of the polypeptide to be classified, and analyze the tertiary structure to obtain the secondary structure and network structure;
[0044] Step2 Obtain the degree, proximity centrality and betweenness centrality of the amino acids Phe, Trp, Lys, Arg, Ile, Leu, Val, Tyr of the polypeptide to be classified according to the network structure as network features;
[0045] Step3 takes the network characteristics of the polypeptide to be classified as input, and uses the trained classification model obtained by training the network characteristics to classify the polypeptide to be classified, and obtains the first judgment result of the category of the polypeptide to be classified; the trained classification model includes Classification model based on three algorithms of support vector machine, K ...
Embodiment 2
[0052] This embodiment provides a polypeptide classification method based on a complex network. This embodiment takes anticancer polypeptides and antihypertensive polypeptides as research objects, uses the topological attribute values in the complex network to represent the characteristics of polypeptides, and combines the first-level , secondary and tertiary structure information, three classification models of support vector machine, K nearest neighbor and random forest were constructed, and then the support vector machine algorithm based on the recursive feature elimination method removed redundant features, and anti-cancer drugs were screened from each structural level. Key features of peptides and antihypertensive peptides. The added network features can describe peptide drugs more comprehensively, thus providing a theoretical basis for the analysis and design of new peptide drugs.
[0053] Specifically, the following steps are included:
[0054] S1: Extract the primar...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More