A melanoma patient walks into a lab. Doctors extract a sample of the tumor, feed its genetic profile through an AI algorithm, and weeks later a vaccine arrives — built from scratch to target up to 34 unique mutations in that specific patient's cancer. Not a theoretical framework. Not a PowerPoint from a fundraising gala. A real drug, in a real Phase 3 trial, with 1,137 real patients enrolled.

The five-year data says it's working.

The drug is called intismeran autogene — branded mRNA-4157 — and it's a joint effort between Moderna and Merck. Phase 2b trial results, drawn from 157 patients with Stage III and Stage IV melanoma, showed a 49% reduction in the risk of cancer recurrence or death. The risk of the cancer spreading to distant parts of the body or killing the patient dropped 59%. That's five years of follow-up data, not a press release projection.

The vaccine works alongside Merck's Keytruda — the PD-1 checkpoint inhibitor pembrolizumab — which is already one of the most widely used cancer drugs in the world. What intismeran autogene does is teach the immune system to recognize the specific neoantigens on a patient's tumor. Not cancer in general. That patient's cancer, specifically.

Stéphane Bancel, Moderna's CEO, put it plainly: "For many years, the idea of creating an mRNA treatment designed specifically for an individual patient's cancer was aspirational. We are now helping turn that vision into a reality."

Here's what makes it possible. AI-powered algorithms analyze the tumor biopsy and identify which of the cancer's mutations are most likely to provoke an immune response. The vaccine is then manufactured to target up to 34 of those neoantigens. Dr. Murad Alam, Chief of Dermatology at Northwestern Medicine in Chicago, explained why this wasn't feasible before: "These things are difficult, and historically took a lot of time, and it just wouldn't be feasible to do this for every individual patient without the power of AI."

The manufacturing timeline is still measured in months, not days. That's a real constraint. But the Phase 3 trial — enrolling 1,137 patients with Stage IIB through Stage IV melanoma — is designed to confirm whether those Phase 2b numbers hold at scale. Moderna and Merck are also running trials in non-small cell lung cancer, bladder cancer, and kidney cancer. If the melanoma data holds, this platform isn't a one-disease story.

FDA approval could come as early as 2027. That timeline depends on the Phase 3 results, which are still being collected. But the trajectory is clear: a drug that cuts melanoma recurrence in half over five years, built individually for every patient who takes it, using AI to do in weeks what used to take years of lab work.

That's the kind of innovation that happens when the private sector is solving problems instead of lobbying for subsidies.