armored-cart-design-agent
Design armored CAR-T cells with cytokine payloads and resistance mechanisms.
Maintainer FreedomIntelligence · Last updated April 1, 2026
Identify tumor neoantigens from somatic mutations using pVACtools for personalized cancer immunotherapy. Predict mutant peptides that bind patient HLA and may elicit T-cell responses. Use when identifying vaccine targets or checkpoint inhibitor response biomarkers from tumor sequencing data.
Original source
https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/bio-immunoinformatics-neoantigen-prediction
Skill Snapshot
Source Doc
Goal: Install pVACtools and its IEDB prediction engine dependencies.
Approach: Install via pip (optionally in a dedicated conda environment) and download IEDB tools for binding prediction.
## Download IEDB tools
pvactools download_iedb_tools
Goal: Run the full pVACseq neoantigen prediction pipeline on a VEP-annotated VCF.
Approach: Provide annotated VCF with patient HLA alleles and select binding prediction algorithms; pVACseq generates mutant peptides and predicts MHC binding.
Related skills
Design armored CAR-T cells with cytokine payloads and resistance mechanisms.
Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.
Autonomous oncology research agent: literature mining, trial matching, biomarker analysis, and treatment hypothesis generation.
Preprocesses cell-free DNA sequencing data including adapter trimming, alignment optimized for short fragments, and UMI-aware duplicate remo…