Gene detection knowledge base construction method and system

Abstract

The invention relates to a gene detection knowledge base construction method and system. The method comprises the steps of constructing a database entity table, an associative table of public databases and an associative table of text mining; constructing an associative table scoring system; and constructing a matched database management system. According to the method and the system, a knowledge base is constructed in a semi-automatic and semi-artificial manner; not only deviation and omission of artificial construction but also credibility difference of the public databases are considered; a text mining algorithm and public database information collection software are integrated in an automatic collection step; a core library and candidate libraries are designed; entries with fuzzy scores are artificially checked through a check library; database contents are managed in an automatic updating manner; and a matched knowledge base management system is designed, so that the databases can be subjected to content query, check, modification and version management conveniently.

Description

technical field [0001] The invention relates to the field of biological information databases, in particular to a method and system for constructing a gene detection knowledge base. Background technique [0002] The development of next-generation sequencing technology has made it more and more convenient for human beings to obtain the most basic genome sequence and understand their own genetic information. Many scientific studies have shown that many human diseases, phenotypes and responses to drugs are due to differences in individual genetic backgrounds, that is, differences in the DNA sequence of each person. Since the Human Genome Project in 2000, more and more human genomes have been deciphered, which constitute the reference sequence of the human genome. The direct purpose of genetic testing is to sequence the individual's genome (or sequence a part of the region) to obtain the sequence difference between it and the reference genomic DNA level, and then compare it wit...

AI Technical Summary

Problems solved by technology

[0012] Based on a series of algorithms such as text mining, the knowledge base is automatically built. However, the false positive rate and false negative rate of the knowledge base completely relying on the algorithm are very high, which has a great impact on the follow-up disease risk analysis of genetic testing.

[0013] After many knowledge bases are built, some existing related items also need to be automatically updated according to new scientific research results, but due to the solidified structure design of these databases, automatic updates are difficult to achieve

[0014] Many knowledge bases use some public database management software, which is inconvenient for researchers with a biological background

Images