From Data to Discovery: Harnessing the Power of Knowledge Graphs in Drug Development

The integration and exploration of diverse datasets have become crucial for unlocking the complexities in the relationships between genes, diseases, and pharmaceuticals. By integrating gene data from the National Center for Biotechnology Information (NCBI), disease data from DisGeNET, and drug data from DrugCentral, in this white paper we have created a comprehensive knowledge graph to visually represent intricate relationships between these entities. Additionally, we employ spaCy's Named Entity Recognition (NER) model to identify medical entities such as diseases, genes, drugs, and symptoms. This approach aims:  

• To transform drug discovery and repurposing through structured data and knowledge graphs
• To build a method that seeks to expedite the drug discovery process, aiming to reduce costs by 50% and increase speed tenfold
• At empowering researchers to uncover complex relationships between genes, diseases, symptoms, cellular functions, mechanisms of action, and drugs, facilitating efficient and impactful decision-making