Scientific Literature Lookup Assistant system for PubMed
LiBLA is a tool designed to assist users find articles of interest more objectively by analyzing commonalities in the abstracts of registered articles.
LiBLA objectively replaces the need for you to manually review papers, find commonalities, and perform repeated PubMed searches, generating weekly recommendations.
System configuration and processing pipeline
LiBLA is composed of a section for creating keywords, a section for suggesting recommended papers every week, a section for improving the accuracy of the recommended papers, and a section for managing papers.
Creating keywords using strong ontology databases
To create keywords, LiBLA uses an ontology database consisting of representatives and synonyms and its own text mining technology.
The ontology database consists of seven categories and consists of 1.3 million genes and approximately 220,000 diseases, phenotypes, tissues, biological species, functions, compounds, and their synonyms, and is optimized for analyzing papers on basic research such as genomes, microorganisms, viruses, and drug discovery.
The combination of text mining and ontology database is the strongest
Text mining techniques using ontology and synonym terms achieve accurate keyword selection and are tuned to select navigation keywords with high commonality.
LiBLA is a fully white-box in-house AI model
based on TF-IDF.
LiBLA allows users to create folders by theme and register papers of interest.
It then automatically extracts characteristic terms with importance scores (TF-IDF) from the collection of documents in each folder, and uses a proprietary document similarity algorithm based on Euclidean distance to recommend new papers similar to those in the folder.
As a result, it reduces the difficulty of formulating search queries, helps users avoid missing important papers, and facilitates the discovery of unexpected but relevant literature.
LiBRA can improve accuracy
In order to accumulate registered papers and improve accuracy, LiBLA has a function that allows users to "like" recommended papers. Papers that are "liked" are added to the papers used to generate keywords, further improving the accuracy of the keywords.
Independent management for each folder
In the paper management section, folders are created for each topic to manage papers and keywords. Adding comments to registered and recommended papers makes it easier to organize papers.
