COVID-19 Knowledge Graph

COVID-19 Knowledge Graph encodes cause-and-effect relationships from scientific literature about SARS-CoV-2 pathophysiology into a computable knowledge graph for computational reasoning and hypothesis generation.

Key Features:

• Multi-modal Knowledge Representation: Integrates diverse data types and sources to capture complex interactions within COVID-19 pathophysiology.
• Cause-and-Effect Network: Focuses on causal relationships to represent how biological processes and factors contribute to disease progression and outcomes.
• Computable Format: Provides a structured, machine-readable graph representation that enables computational analysis and large-scale hypothesis testing.

Scientific Applications:

• Research Facilitation: Centralizes formalized knowledge to support individual and collaborative research on COVID-19 pathophysiology.
• Data Exploration and Analysis: Enables large-scale computational exploration and analysis to identify novel connections and generate hypotheses about SARS-CoV-2 impacts.

Methodology:

Extracted knowledge from scientific publications and formalized it into a structured network of cause-and-effect relationships, then encoded the graph in multiple standard formats.