BIOSMILE

BIOSMILE extracts relational information about protein-protein interactions from PubMed abstracts using text mining and natural language processing to identify biomedical verbs and their arguments.

Key Features:

• NCBI-PubMed integration: Retrieves relevant abstracts from the NCBI PubMed database based on user-provided keywords.
• Biomedical verb analysis: Identifies selected biomedical verbs and extracts relational arguments such as subject, object, location, manner, and time.
• Relevance ranking: Orders retrieved abstracts by their relevance to protein-protein interactions.
• Markup of biomedical relations: Highlights and annotates detected biomedical relationships within the abstract text.
• Flexible output formats: Presents analysis results inline in the abstract text or organized into tables.

Scientific Applications:

• Protein–protein interaction discovery: Automates extraction of interaction statements from the literature to support mapping of interaction networks relevant to cellular processes and disease mechanisms.

Methodology:

Text mining of PubMed abstracts to identify key biomedical verbs and their associated relational data, using natural language processing (NLP) algorithms to discern complex relationships within the text.