Computational research - Computational prioritization of neoantigen candidates
Building a computational pipeline to prioritize personalized neoantigen candidates. Computational research.
- Client
- ComfyBloom
- Year
- Service
- Biomedical research, Computational pipelines, R&D
- Engagement
- Computational research
The Challenge
Personalized tumor research needs a way to narrow a large mutation-derived candidate set before experimental validation.
The Approach
The research pipeline compares tumor and patient data, analyzes mutations, generates peptide candidates and applies predictive recognition and healthy-tissue filtering before proposed experimental validation.
Capabilities
- Tumor/patient genomic comparison
- Mutation analysis
- Peptide candidate generation
- Immune-recognition prediction
- Healthy-tissue filtering
- Candidate prioritization
- Proposed wet-lab validation
Workflow
- Gather genomic data
- Analyze mutations
- Generate peptides
- Predict recognition
- Filter healthy-tissue risks
- Prioritize candidates
- Plan experimental validation
- Computational genomics
- Neoantigen prediction pipeline
- Public cancer data
Outcome
The research proposal reports 75 prioritized candidates from 2,878 in one computational example. Wet-lab validation and clinical efficacy were not established.