InspirThe 23andMe bankruptcy left 15 million patients' genomic data in limbo, highlighting a critical gap: patients generate valuable biodata
but lack tools to leverage it for their own health outcomes. Meanwhile, BioNTech and Moderna have pioneered personalized mRNA cancer
vaccines that design neoantigens from tumor sequencing data—but this technology remains locked behind expensive clinical trials and
specialized bioinformatics pipelines.
We asked: What if any patient with their VCF file could explore potential neoantigen candidates for personalized immunotherapy?
What it does
The mRNA Personal Vaccine Neoantigens Calculator allows patients to:
- Upload genomic data (VCF, OpenCRAVAT SQLite, or Caris tumor profiling PDFs)
- Input their HLA typing (the immune system's "lock" that neoantigens must fit)
- Automatically identify coding missense variants from their tumor/exome data
- Predict MHC-I binding affinity for 8-11mer peptides spanning each mutation
- Rank neoantigen candidates by binding strength, clonality (VAF), and immunogenicity
- Generate mRNA vaccine constructs with optimized linkers, UTRs, and codon sequences
- Download clinical reports in JSON, FASTA, and HTML formats
The Caris report parser is HIPAA-compliant, automatically anonymizing all PHI (patient names, DOB, MRN) before processing.
How we built it
We used Prompt-Driven Development (PDD)—a methodology where .prompt files serve as the source of truth and code is a generated artifact.ation
What it does
How we built it
Challenges we ran into
Accomplishments that we're proud of
What we learned
What's next for mRNA Personal Vaccine Antigenes Calculator
Built With
- claude
- javascript
- pdd
- python
Log in or sign up for Devpost to join the conversation.