Inspiration
I decided to combine my background in genetics with my passion for machine learning to research the genetic basis of prostate cancer.
What it does
An AI-powered knowledge graph platform integrating Neo4j and Modus API for prostate cancer research
How we built it
This project provides an interactive web-based platform for analyzing prostate cancer gene data using Neo4j for knowledge graph representation, PyVis for visualization, and Modus API for machine learning analysis I used Streamlit UI to display machine learning results and provide a Neo4j query interface for visualizing relationships. I used Modus API to integrate external machine learning analysis for enhanced performance. Neo4j Integration inserts and queries data for graph-based visualizations. GraphQL interaction provides a seamless way to query and visualize graph data.
Challenges we ran into
I had difficulty signing up on Hypermods Modus API and obtaining the API key for the project. I also encountered difficulties fine tuning the model.
Accomplishments that we're proud of
Completing the project in a timely manner and introducing the decision tree fallback.
What we learned
The importance of resilience and persistence in the face of challenges. The importance of GraphQL in genetic interaction visualization.
What's next for Prostate Cancer Gene Analysis
Integration of gene-drug interaction data. Linking with clinical trial databases. Scalability to support multi-disease or multi-tissue analysis.
Log in or sign up for Devpost to join the conversation.