Not Yet AI Curing Cancer But Validating Gains Can Be Made

The Moderna Neoantigen selection. A tumor carries thousands of mutations. Only a handful produce peptides that get presented on MHC and recognized by T cells. Moderna’s pipeline takes next-generation sequencing data from tumor and blood samples, reviews the genetic mutations, and predicts up to 34 neoantigens most likely to elicit an immune response. That’s the Machine Learning core — an MHC-binding/immunogenicity ranking problem. Notably, the algorithm had to be locked down before Phase 2 began, freezing its parameters so it wouldn’t change mid-trial — so INTerpath-001 validates a frozen 2021-era model, not a continuously learning one.

Clearly, there should be improved algorithms for neoantigen selection since 2021.

Without high-performance compute and machine learning for mutation analysis, immunogenicity prediction, sequence optimization, and logistics, true personalization at scale would not be practical. Moderna is expanding the same approach to other tumors (lung, bladder, kidney, etc.).

Manufacturing orchestration the treatment. One batch per patient. Moderna built Maestro. it is an end-to-end digital system giving cross-functional views of manufacturing activities for every patient. Current turnaround is roughly 4–8 weeks from biopsy to patient, for both Moderna’s mRNA-4157 and BioNTech’s iNeST. Compressing that is a logistics-and-scheduling problem more than a model-capability problem, and it’s the main thing standing between this and a commercial product at scale.

This was AI-assisted target selection. It is not AI-designed drug in the Isomorphic sense. The mRNA scaffold and the LNP are platform technology. The AI picks which 34 mutations to encode.

KEYNOTE-942 at five years showed a 49% reduction in risk of recurrence or death (HR 0.51) and 59% reduction in distant metastasis or death (HR 0.411). Those are composite event endpoints in ~150 patients. Overall survival was not the endpoint. In the Phase 3, Overall Survival was not mature at the time of analysis. Curing cancer is ahead of the evidence.This is adjuvant therapy that delays recurrence in already-resected disease.

Brian Wang

Brian Wang is a Futurist Thought Leader and a popular Science blogger with 1 million readers per month. His blog Nextbigfuture.com is ranked #1 Science News Blog. It covers many disruptive technology and trends including Space, Robotics, Artificial Intelligence, Medicine, Anti-aging Biotechnology, and Nanotechnology.

Known for identifying cutting edge technologies, he is currently a Co-Founder of a startup and fundraiser for high potential early-stage companies. He is the Head of Research for Allocations for deep technology investments and an Angel Investor at Space Angels.

A frequent speaker at corporations, he has been a TEDx speaker, a Singularity University speaker and guest at numerous interviews for radio and podcasts.  He is open to public speaking and advising engagements.