PLAN2L

PLAN2L performs literature mining and information extraction to retrieve and organize Arabidopsis thaliana biological data relevant to genetic, cellular, and molecular research.

Key Features:

• Integration of Text Mining and Information Extraction: Uses text mining and information extraction to extract biological information from literature and complement existing annotation databases and bioinformatics-generated data.
• Comprehensive Biological Topic Coverage: Retrieves information on protein interactions, gene regulation, sub-cellular localization, and processes including the cell cycle, flowering, root, leaf, and seed development in Arabidopsis thaliana.
• Entity Pair Queries: Accepts predefined pairs of entities and returns literature-derived relationships together with supporting textual evidence.

Scientific Applications:

• Hypothesis Generation: Exposes literature-derived relationships among genes, proteins, and processes in Arabidopsis thaliana to support formulation of hypotheses.
• Experimental Design: Provides extracted evidence on gene regulation, interactions, and sub-cellular localization to inform experimental planning.
• Model Validation and Network Analysis: Facilitates validation of biological models and analysis of gene regulatory and interaction networks using curated literature evidence.

Methodology:

Applies text mining to scan published research and information extraction to identify and organize relationships and contextual textual evidence related to Arabidopsis thaliana.