Darling

Darling employs literature mining to detect disease-related biomedical entity associations from biomedical literature in disease-centric databases.

Key Features:

• Biomedical entity co-occurrence detection: Darling detects sentence-based cooccurrences of genes, proteins, chemicals, functions, tissues, diseases, environments, and phenotypes.
• Named entity recognition: Darling utilizes Name Entity Recognition to identify human-related biomedical terms in PubMed articles mentioned in OMIM, DisGeNET and Human Phenotype Ontology (HPO) disease records.
• Extended query options: Users can search with PubMed identifiers, disease records, entity names, titles, single nucleotide polymorphisms, or the Entrez syntax.
• Free text mining: After applying named entity recognition, users can retrieve and mine relevant literature from recognized terms for a free input text.
• Network visualization: Term associations are captured in customizable networks visualized in 2D as weighted graphs or in 3D as multi-layered networks, with filtering by term or co-occurrence frequency.
• Searchable output organization: Fetched terms are organized in searchable tables and clustered annotated documents.
• Functional enrichment analysis: Reported genes can be analyzed for functional enrichment using external applications called from within Darling.
• Specialized query channels: Additional query channels focus on COVID-19, GWAS studies, cardiovascular, neurodegenerative, and cancer diseases.

Scientific Applications:

• Disease-biomedical entity association discovery: Finding, exploring and filtering frequent sentence-based associations between a disease and a biomedical entity co-mentioned in disease-related PubMed literature.
• Interactive biomedical entity association network generation: Generating networks with nodes representing genes, proteins, chemicals, functions, tissues, diseases, environments and phenotypes.
• Literature exploration: Users can explore relevant abstracts in an annotated format.

Methodology:

Darling applies named entity recognition to identify human-related biomedical terms in PubMed articles from disease records in OMIM, DisGeNET and Human Phenotype Ontology (HPO), then detects sentence-based cooccurrences of biomedical entities from biomedical literature found in six disease-centric databases.