Biomedical literature records, genomic and chemical data in public repositories could be a source of knowledge for biomedical discovery if interrelations between different pieces of data are well understood. However, collecting, curating, and transforming the data into an easy-to-comprehend knowledge representation is a major challenge. We are looking to uncover and summarize important relationships between chemicals, genes, proteins, and diseases by analyzing co-occurrences of terms in biomedical literature. We utilize NLP packages, such as LeadMine from NextMove Software, to annotate PubMed records, and then use our own software along with additional information from PubChem and other public databases to perform statistical analysis and relevance-based sampling to identify the most relevant information and summarize it a compact form on PubChem compound pages. Reconciliation of different relevance factors is an intricate problem. Balancing the publication date with other relevance factors can be especially difficult, and strongly depends on the user’s needs. To enable user input, while operating with the precalculated data in the default setting to assure PubChem system efficiency, we enable selection of the preferred publication date from a limited number of options (last 2 years, 5 years, 10 years, etc.). The page view is formed and changed at the front end from the precalculated data based the user’s selection. Besides a better knowledge representation, the PubChem QA/QC is a major driving force for this project. Analyzing biomedical records using NLP software and utilizing the statistics allows us to understand the typical use, rank synonyms, correct spelling of submitter-provided names, and verify submitter-provided links. While we are currently developing a system to process PubMed records, we are considering extending the input data set by using abstracts from other public sources, as well as patents and full-text publications. In addition, we are evaluating opportunities for data-representation refinement and enrichment that could be provided to a sophisticated user through additional server requests.

From text mining to knowledge: PubChem knowledge panels provide synopsis of chemical, gene, protein and disease term co-occurrences in biomedical literature

256th National Meeting (2018)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.