AI-designed neoantigen vaccines just hit a Phase 3 milestone —

AI-designed neoantigen vaccines have reached a Phase 3 milestone, with the pipeline from tumor sequencing to mRNA construct increasingly driven by machine learning tools such as NetMHCpan, MHCflurry, and pVACseq. The author outlines a reproducible end-to-end stack for GPU clusters, noting that prediction accuracy is no longer the bottleneck—NetMHCpan-4.1 achieves AUC 0.92—but manufacturing turnaround remains slow, with Moderna quoting 6-8 weeks from biopsy to vial and academic cores taking 12-16 weeks.

AI-designed neoantigen vaccines just hit a Phase 3 milestone — work at scale. The pipeline — tumor sequencing → mutation calling → HLA binding prediction → epitope ranking → mRNA construct — is where ML has been eating the workflow for years. Most of the heavy lifting NetMHCpan, MHCflurry, pVACseq is already open. What's missing is a clean, reproducible end-to-end stack you can run on your own GPU cluster without pharma-grade infra. I've been stitching together a minimal viable version for a side project. Rough outline if anyone wants to replicate: 1. Somatic variant calling tumor/normal pair → filtered VCF gatk Mutect2 \ -R hg38.fa \ -I tumor.bam \ -I normal.bam \ -tumor TUMOR \ -normal NORMAL \ -O somatic.vcf.gz 2. HLA typing from RNA-seq or WES optitype --rna -i tumor rna.fastq.gz -o hla typing.tsv 3. Neoantigen prediction + ranking pVACseq wrapper — handles NetMHCpan binding, expression filter, clonal fraction pvacseq run \ somatic.vcf.gz \ hla typing.tsv \ sample id \ output dir \ -e 8,9,10,11 \ --allele-specific-binding-threshold 0.5 \ --top-score-metric lowest 4. Construct design Feed top 20-30 epitopes into your mRNA backbone 5' UTR, CDS optimization, poly-A tail . I'm using a custom codon optimizer + UTR selector trained on ribosome profiling data — happy to share the notebook if there's interest. 5. In silico immunogenicity sanity check Run the final construct through MHCflurry 2.0 presentation score + TCRdist similarity to known immunogenic epitopes. Filters out ~40% of candidates that look good on binding alone. The bottleneck isn't prediction accuracy anymore — NetMHCpan-4.1 hits AUC 0.92 on presented ligands. It's manufacturing turnaround . Moderna quotes 6-8 weeks from biopsy to vial. Academic cores run 12-16. If you're building in this space, the lever is automating the QC/release pipeline residual DNA, dsRNA, integrity not the ML. Anyone running a similar stack? Curious what HLA typing method you trust — OptiType, HLA-LA, or something newer. Next Seven Claude AI levels that actually matter for real work → /en/threads/6959/