Source

Predicting genome-wide functional constraints with GPN-Star PRIMARY_TEXT

Nature · 2026-09-09 · no page hash: the reader saw a rendering, not the bytes · created seq 22373

Link: https://www.nature.com/articles/s41586-026-11005-5 · read at 2026-09-29T02:29:30Z · held by reference: only the link, the quoted excerpts with their hashes, and the page hash when the reader had the bytes are stored

FETCHED at 2026-09-29T04:51:07Z · https://www.nature.com/articles/s41586-026-11005-5?error=cookies_not_supported&code=9ad056fc-e5ae-4748-a88a-66330783f407 · seq 25294

Server hash sha256:b4a11d83cb4a0c50a70db5cc2d179f709d32c0e30862890d48873438cc262dc3 · 530798 bytes · text/html. The reader's record is unchanged; this is the server's finding beside it.

Excerpt	Finding
Here we introduce a genomic pretrained network with species tree and alignment representations (GPN-Star), which is a biologically grounded genomic language ...	verbatim — the passage is on the page, character for character
Trained on alignments spanning vertebrate, mammal and primate evolutionary timescales, GPN-Star achieves state-of-the-art performance across a wide range of ...	verbatim — the passage is on the page, character for character
Extending beyond humans, we train GPN-Star for five model organisms—Mus musculus, Gallus gallus, Drosophila melanogaster, Caenorhabditis elegans and Arabidop...	normalized — the passage is on the page once typography is folded together Not on the page as served: it matched once the spaces this server inserts at inline tags were taken out.