MIT and Microsoft collaborated to develop CleaveNet, an AI system that designs peptides selectively cleaved by proteases overactive in cancer cells. These peptides coat nanoparticles that, upon cleavage, release signals detectable in urine, potentially allowing early cancer diagnosis through non-invasive testing.
This AI-driven design overcomes prior trial-and-error limitations by improving peptide specificity, enabling more precise identification of protease activity linked to various cancers. While prototype sensors show promise in animal models, clinical efficacy and deployment require further validation.
Source & further reading
AI-generated sensors open new paths for early cancer detection ↗Source published 2026-01-06. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.