Individualized mRNA neoantigen cancer therapy (intismeran) from Moderna and Merck, tested with Keytruda in melanoma.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
mRNA-4157 (intismeran) is an individualized neoantigen therapy developed by Moderna and Merck. A patient's tumour is sequenced and compared with healthy cells to identify cancer-specific mutations. A synthetic mRNA encoding up to 34 of these mutations is then manufactured for that patient. Cells translate the mRNA into protein fragments that are presented to the immune system as antigens. It uses Moderna's mRNA platform, which was also used for its COVID-19 vaccine. Commentary on the programme says machine-learning methods are used to predict neoantigens.
In August 2026 the companies announced that a Phase 3 trial met its endpoints at a planned interim analysis. The trial enrolled 1,137 patients with resected stage IIB–IV melanoma. They were randomized 2:1 to mRNA-4157 plus Keytruda (pembrolizumab) or Keytruda alone, for about a year. The combination reportedly extended recurrence-free survival and distant metastasis-free survival, with statistical significance. Detailed figures have not been released and are expected at an upcoming medical conference. Five-year Phase 2 data showed a 49% reduction in risk of recurrence or death and a 59% reduction in risk of distant metastasis or death.
It is an investigational therapy and is not a software tool or a model. It is not yet approved, and is available only through clinical trials. Open questions include the magnitude of benefit, subgroup results, quality-of-life data and overall survival.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
mRNA melanoma vaccine succeeded in a phase 3 trial of 1,137 patients, extending time without recurrence. The creator notes its design uses AI/machine-learning algorithms to predict neoantigens.
Closest neighbours by meaning, not just by category.
Model · Nyra Labs
Controllable multilingual speech recognition with verbatim or clean output and word-level timestamps, from Nyra Labs.
Model · Alibaba Tongyi Lab
Autoregressive scientific model that tokenizes proteins, molecules, materials, antibodies and reactions into one shared grammar.
Model · Hugging Face
Open 14.8B language model from Hugging Face that reads raw DNA in chat and answers in English, built on Qwen3-14B.
Model
Multimodal biomedical foundation model for drug discovery across small molecules, proteins, antibodies and gene expression.
Model · IndexTeam
Open-weights zero-shot text-to-speech model from Bilibili's IndexTeam with voice cloning and emotion control in 5 languages.
Model · Princeton
Fully open 3B text-to-image diffusion model from Princeton with released weights, training code, and data pipeline.