Entity relationship mining method based on biomedical literature

Abstract

The invention discloses an entity relationship mining method based on biomedical literature, which comprises the following steps: (1) querying disease-related biomedical literature in a public database, and obtaining biomedical text data after data preprocessing; (2) performing biomedical named entity recognition on the obtained biomedical text data in combination with a regular matching templateand a deep learning model; and (3) based on the entity recognition result, mining the entity relationship by adopting transfer learning and reinforcement learning methods. The biomedical nouns entities in the literature can be effectively identified by acquiring the biomedical literature related to the disease from the network, extracting the abstract and the title and carrying out entity recognition and relationship mining, and the hidden relationship among various entities can be mined.

Description

technical field [0001] The invention belongs to the technical field of text data mining, in particular to an entity relationship mining method based on biomedical literature. Background technique [0002] With the rapid development of biomedical technology, the amount of biomedical literature is currently exploding at an unprecedented rate. Biomedical researchers are faced with massive literature databases, and effective information acquisition has become an arduous task. Non-coding RNA and protein-coding genes are important objects in disease research. The potential relationship between genes, non-coding RNAs, proteins and diseases revealed in the research results can help biologists more effectively explore the mysteries of life generation, health maintenance and disease treatment. Most of the current databases mined from biomedical literature are manually compiled by domain experts. However, in the face of the exponentially increasing number of documents, there are gre...

AI Technical Summary

Problems solved by technology

[0005] In recent years, deep learning models have achieved relatively good results in biomedical text mining tasks, but deep learning methods require huge training data sets

Due to the high cost of building a large biomedical text training set, the development of deep learning for biomedical text mining is limited.

Therefore, the current disease-related databases are generally collected manually and based on templates. They fail to make full use of deep learning models to mine entity relationships, and rely heavily on complex feature engineering of machine learning.

Images