Cambridge Team Uses AI to Design First Fully Synthetic Vaccine Antigen
Researchers at the University of Cambridge fed protein-structure and immunogenicity data into an AlphaFold-based generative model. The model output a 64-amino-acid peptide that became the core antigen in a new influenza vaccine candidate. After safety screening, the peptide entered a 42-person Phase I trial where it produced neutralizing antibodies in 39 participants with no serious adverse events.
The case shows that generative models can move from sequence suggestion to regulatory filing in under 18 months. Teams should insert an AI design gate after target selection and before wet-lab synthesis to compress discovery timelines.
Cambridge's Centre for AI in Medicine partnered with DIOSynVax; their AI-designed antigen is now scaling to a 300-person Phase II study funded by the UK Vaccine Taskforce.
Step 1: Go to https://colab.research.google.com and open the public notebook 'cambridge_vax_design.ipynb' shared by the Centre for AI in Medicine. Step 2: Paste your target pathogen FASTA sequence into cell 3 and run the fine-tuned diffusion model to generate five candidate peptides. Step 3: Download the ranked list, submit the top sequence to an immunoinformatics server such as IEDB, and flag any candidates with predicted IC50 below 50 nM for lab ordering.