Users thanked the team behind the Universal Cell Embedding Paper published in Nature for sharing their research openly.
Based on 1 visible X reactions from 1 accounts; directional sample.
Ask a question below.
Published answers will appear here.
Paper: https://www.nature.com/articles/s41586-026-10689-z?utm_source=rct_congratemailt&utm_medium=email&utm_campaign=oa_20260708&utm_content=10.1038/s41586-026-10689-z Code: https://github.com/snap-stanford/UCE Thanks so much to the team @YanayRosen @yusufroohani @StephenQuake!
Excited to share that our Universal Cell Embedding (UCE) paper is published in @Nature! Single-cell RNA sequencing data gives us an unprecedented look into the diversity of cell biology, but analysis has often been limited to the specific dataset or atlas that was collected. https://www.nature.com/articles/s41586-026-10689-z?utm_source=rct_congratemailt&utm_medium=email&utm_campaign=oa_20260708&utm_content=10.1038/s41586-026-10689-z
UCE connects molecular and cellular scales of biology. Genes are more than just columns in an expression matrix: in UCE, they are encoded according to the proteins they produce, using ESM, embedding novel species not seen during training, across 100Ms of years of evolution.
We designed and trained the UCE foundation model so that any new data, from any disease, tissue or species, could be mapped into the same universal representation space, without fine tuning or retraining.
Paper: https://www.nature.com/articles/s41586-026-10689-z?utm_source=rct_congratemailt&utm_medium=email&utm_campaign=oa_20260708&utm_content=10.1038/s41586-026-10689-z Code: https://github.com/snap-stanford/UCE Thanks so much to the team @YanayRosen @yusufroohani @StephenQuake!
Excited to share that our Universal Cell Embedding (UCE) paper is published in @Nature! Single-cell RNA sequencing data gives us an unprecedented look into the diversity of cell biology, but analysis has often been limited to the specific dataset or atlas that was collected. https://www.nature.com/articles/s41586-026-10689-z?utm_source=rct_congratemailt&utm_medium=email&utm_campaign=oa_20260708&utm_content=10.1038/s41586-026-10689-z
UCE connects molecular and cellular scales of biology. Genes are more than just columns in an expression matrix: in UCE, they are encoded according to the proteins they produce, using ESM, embedding novel species not seen during training, across 100Ms of years of evolution.
We designed and trained the UCE foundation model so that any new data, from any disease, tissue or species, could be mapped into the same universal representation space, without fine tuning or retraining.
Users thanked the team behind the Universal Cell Embedding Paper published in Nature for sharing their research openly.
Based on 1 visible X reactions from 1 accounts; directional sample.
Ask a question below.
Published answers will appear here.