KB-Rank

KB-Rank ranks protein structures by relevance to user-provided text queries to identify and functionally annotate proteins in biological contexts such as diseases and drug interactions.

Key Features:

• Text-Based Query System: Accepts textual queries including disease names, drug identifiers, or functional descriptors to retrieve matching protein structures.
• Relevance Ranking Algorithm: Identifies matches between the query text and associated textual fields of protein entries and orders proteins by the prevalence of annotations across retrieved structures.
• Functional Annotation Categories: Provides functional annotation categories for each retrieved protein structure to contextualize biological roles and significance.

Scientific Applications:

• Disease Research: Explore proteins implicated in specific diseases to aid understanding of pathogenic mechanisms and potential therapeutic targets.
• Drug Discovery: Identify protein targets associated with particular drugs to support drug development and repurposing efforts.
• Functional Genomics: Provide insights into protein functions to support studies of gene function and interaction networks.

Methodology:

Retrieve matches between the query text and textual fields of protein structures, then rank proteins by the relative content of annotations prevalent across the retrieved structures.