TERRA: A Tissue World Model Trained on 112M Cells
mo_lotfollahi · x · 2026-08-11
Researchers introduced TERRA, a foundation model designed to create universal representations for human tissues, akin to ViT for images or ESM for proteins.
- Data Scale: Pretrained on 112 million cells, utilizing spatial transcriptomics (mostly Xenium 5000-plex) and public data.
- Scope: Built on one of the largest human spatial transcriptomics corpora to date, spanning 20 tissues across development, health, and 26 disease conditions, with two-thirds newly generated in-house.
- Capabilities: Aims to map tissue biology, predict perturbations, and uncover disease mechanisms across organs.
Related event: TERRA: A Human Tissue Foundation Model Trained on 112M Cells(2 posts)→
More from Research
- AI will be superhuman at science regardless, and Europe can't opt out — teortaxesTex · 2026-10-16
- SERO augments long-horizon agentic RL with executable oracle continuations — Shanghai-AI-Laboratory · 2026-10-16
- Tsinghua and Amap propose OmniVerifier-C1, a graded verifier beating binary judges — Bowei Liu · 2026-10-16
- Alibaba open-sources MAI-Gym, an all-in-one GUI agent eval and RL training platform — Tongyi-MAI · 2026-10-16
- Peking University's SimForcing distills simulation motion priors into robot world models — PekingUniversity · 2026-10-16
- CoWorld Reasoner uses an evolving video world model as a visual reasoning engine — ModalityDance · 2026-10-16