GenomeRx

🌟 Inspiration

With the rise of personalized medicine and genomic technology, I wanted to create a tool that empowers individuals to understand their genetic makeup and receive tailored health recommendations. The goal was to bridge the gap between raw genetic data and actionable insights for everyday wellness and preventive care.

🔍 What it does

GenomeRx takes raw DNA data (e.g., from 23andMe or Ancestry) and analyzes it for traits, disease markers, drug responses, and nutritional insights. Users receive:

• A trait summary (e.g., lactose intolerance, caffeine sensitivity)
  
• Risk profiles for conditions with genetic predisposition
  
• Pharmacogenomic guidance (e.g., how one might respond to certain medications)
  
• Lifestyle and wellness suggestions based on genetic predisposition
  

🛠️ How I built it

• Frontend: Flutter for cross-platform app support
  
• Backend: Flask and MongoDB for API and data storage
  
• DNA Parsing: Used Python libraries like Biopython and Pandas
  
• Data Sources: Integrated public genomics databases like SNPedia and PharmGKB
  
• Security: Data anonymization and local-only processing options
  

🧗 Challenges I ran into

• Interpreting SNP data accurately from raw genome files
  
• Managing sensitive health data securely while maintaining performance
  
• Ensuring scientific accuracy when mapping SNPs to traits and medical conditions
  
• Creating clear, user-friendly visualizations of complex genetic insights
  

🏆 Accomplishments that I'm proud of

• Successfully parsed and matched over 500 SNPs to meaningful traits
  
• Built a modular analysis engine that can expand to future datasets
  
• Designed a clean, intuitive UI that presents genomics in an engaging way
  
• Integrated FinBERT sentiment analysis for interpreting research trends in genomic studies
  

📚 What I learned

• Deepened my understanding of human genomics and bioinformatics pipelines
  
• Improved skills in Flask routing, MongoDB structuring, and modular back-end logic
  
• Gained insight into the challenges of health tech applications—especially privacy and data interpretation
  
• Applied NLP to biomedical content using FinBERT, enhancing insight extraction
  

🚀 What's next for GenomeRx

• Add support for polygenic risk scoring using recent GWAS data
  
• Implement secure cloud sync with user-controlled encryption
  
• Expand to support real-time integration with wearable health data
  
• Launch a beta program for early feedback and validation with real users
  

Built With

• css
• html5
• javascript
• machine-learning
• python
• react