LipidFun

LipidFun curates lipid function information from biomedical literature using natural language processing and manual curation to connect lipids to phenotypes and biological functions with sentence-level evidence.

Key Features:

• Named Entity Recognition: LipidFun constructs classification systems for lipids, biological functions, and phenotypes to support named entity recognition.
• Sentence-Level Evidence Extraction: Sentence-level evidence is extracted to highlight connections to lipid-associated biological processes and diseases.
• Association Visualization: Integration of classification systems and sentence-level evidence provides an overview of lipid-phenotype and lipid-biological function associations through concise visualizations.

Scientific Applications:

• Lipid Function Discovery: LipidFun unravels relationships between lipids and biological mechanisms, underscoring their overarching influence on physiological processes.
• Disease Association Research: The database enables investigation of lipid-related phenotypes and diseases through curated literature evidence.

Methodology:

Potential lipid functions are extracted from biomedical literature using natural language processing techniques, with accuracy and reliability ensured through manual curation by four domain experts.