Ye et al. 2026, Predicting genome-wide functional constraints with GPN-Star (Nature)
Nature · 2026 · Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09 · Peer-reviewed
What this source contributed
Records in this release that cite this source. A record can cite several sources.
Results
Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.
Claims
Statements this source supports, each with where in the source it was checked.
- access: GPN-Star: Access Pretrained models, training datasets and benchmark datasets are on the Hugging Face collection songlab/gpn-star-68c0c055acc2ee51d5c4f129. Precomputed GPN-Star predictions for all possible single nucleotide variants in the human genome and in the five model organisms are on Hugging Face at doi:10.57967/hf/9849. (Data availability (PDF page 10))
- GPN-Star: source_ids: Sources ["vep-uc-20261014-source-gpn-star", "gpn-star-20261116-source-nature-2026"] (data/entities/sources.jsonl, record gpn-star-20261116-source-nature-2026, the version of record doi:10.1038/s41586-026-11005-5; data/entities/sources.jsonl, record vep-uc-20261014-source-gpn-star and its companion_of link)
- licence: GPN-Star: Licence The paper states a licence for the code (MIT) but none for the released model weights. The article itself is open access under CC BY 4.0. (Reporting Summary, Software and code, 'Data analysis' (PDF page 23); Open Access statement (PDF page 10))
- mutation_rate_calibration: GPN-Star: Mutation rate calibration GPN-Star raw scores are calibrated to remove the effect of local mutation rate variation. The paper reports that the calibration substantially reduced correlations with Roulette mutation rate estimates while improving performance on most downstream benchmarks, and that the uncalibrated raw scores were used only for the head-to-head comparison with GPN-MSA in Supplementary Fig. 20. (Results, genome-wide evolutionary constraints (PDF page 7); Supplementary Information, Mutation Rate Calibration (PDF page 10) and Supplementary Fig. 20 caption)
- printed_values_scope: gpn-star-20261116-benchmark-gpn-star-vep: Printed values scope Of this paper's evaluations, four print numbers: Supplementary Table 3 (ablation studies), the bar labels of Fig. 4b, the bar labels of Fig. 5a for five non-human species, and the rare variant association gene counts in the Results. The model comparisons in Figs. 2 and 3, Fig. 4a,c,d, Fig. 5b-d, Extended Data Figs. 1-10 and Supplementary Figs. 1-27 are plots whose values are not printed, so the paper's headline comparisons against CADD, GPN-MSA, Evo 2, Nucleotide Transformer, ESM-1b, Enformer, Borzoi, AlphaGenome, AlphaMissense, PrimateAI-3D, PromoterAI, SpeciesLM, GPN-Promoter, PhyloP and PhastCons cannot be extracted as values from this source. One statistic inside a panel is an exception to this and was missed at extraction: Fig. 3e prints r = 0.47 and P = 0.0072 for the correlation between trait polygenicity and the enrichment difference between GPN-Star (P) and (M). It is a property of the models' relationship to each other rather than a score against a ground truth, so no result is recorded for it. (Figs. 2-5 and their captions; Extended Data Figs. 1-10; Supplementary Information, Supplementary Figs. 1-27)
- prioritized_variant_consequences: GPN-Star: Prioritized variant consequences Among the top 0.1% most constrained common variants by GPN-Star (P), missense variants are the largest class at 33% and 170-fold enriched, followed by variants in distal enhancer-like regions at 26% and 2.4-fold enriched and their flanks at 8% and 0.35-fold depleted. Compared with GPN-Star (M), GPN-Star (P) is enriched 1.14-fold in missense variants; compared with GPN-Star (V) it is enriched 1.52-fold in missense and 3.89-fold in synonymous variants and depleted in non-exonic classes such as intergenic. (Results, relevant evolutionary timescales (PDF page 5); Supplementary Information, relevant evolutionary timescales (PDF page 3) with Supplementary Tables 5-8 (PDF pages 24-26))
- timescale_guidance: GPN-Star: Timescale guidance The authors report that coding variants and lower-frequency variants with larger effect sizes are better predicted by models trained on deeper evolutionary timescales, while non-coding variants and higher-frequency variants with smaller effect sizes are better predicted by models trained on shallower timescales, and that GPN-Star predictions quantify evolutionary constraint at a timescale rather than general variant pathogenicity. (Results, relevant evolutionary timescales (PDF page 5); Discussion (PDF pages 9-10))
- version: GPN-Star: Version The paper names no model release version. Its code is the gpn package at v0.8 (github.com/songlab-cal/gpn), archived at doi:10.5281/zenodo.21501177 and available under the MIT licence. Model checkpoints are named by assembly, alignment and parameter count (Supplementary Table 1); the three human models are called GPN-Star (V), (M) and (P) for the vertebrate, mammal and primate timescales. (Reporting Summary, Software and code, 'Data analysis' (PDF page 23); Code availability (PDF page 10); Results (PDF page 3); Supplementary Information, Supplementary Table 1 (PDF page 21))
Models, benchmarks and other records
Models (1)
Methods (2)
Configurations (12)
- CADD (GPN-Star Fig. 4b)
- GPN-MSA (GPN-Star Fig. 4b)
- GPN-Star (M) (GPN-Star Fig. 4b)
- GPN-Star (P) (GPN-Star Fig. 4b)
- GPN-Star (V) (GPN-Star Fig. 4b)
- PhastCons (M) (GPN-Star Fig. 4b)
- PhastCons (P) (GPN-Star Fig. 4b)
- PhastCons (V) (GPN-Star Fig. 4b)
- PhyloP (M) (GPN-Star Fig. 4b)
- PhyloP (P) (GPN-Star Fig. 4b)
- PhyloP (V) (GPN-Star Fig. 4b)
- Roulette mutation rate (GPN-Star Fig. 4b)
Benchmarks (1)
Protocols (3)
Datasets (2)
Evaluations (16)
- CADD on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
- DeepRVAT with GPN-Star annotations, discovered genes (GPN-Star Fig. 2j)
- DeepRVAT with GPN-Star annotations, replicated genes (GPN-Star Fig. 2j)
- DeepRVAT, discovered genes (GPN-Star Fig. 2j)
- DeepRVAT, replicated genes (GPN-Star Fig. 2j)
- GPN-MSA on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
- GPN-Star (M) on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
- GPN-Star (P) on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
- GPN-Star (V) on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
- PhastCons (M) on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
- PhastCons (P) on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
- PhastCons (V) on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
- PhyloP (M) on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
- PhyloP (P) on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
- PhyloP (V) on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
- Roulette mutation rate on gnomAD rare versus common enrichment (GPN-Star Fig. 4b)
Sources (4)
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
30 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Artifact SHA-256 d7dfe801bad2a0a23478753147af2320bc31c8b37ee50d66f1a1af8385e9005d Source metadata | Ye et al. 2026, Predicting genome-wide functional constraints with GPN-Star (Nature) No field-specific location recorded Version: Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte. |
| Artifact url https://www.nature.com/articles/s41586-026-11005-5.pdf Source metadata | Ye et al. 2026, Predicting genome-wide functional constraints with GPN-Star (Nature) No field-specific location recorded Version: Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte. |
| Doi 10.1038/s41586-026-11005-5 Source metadata | Ye et al. 2026, Predicting genome-wide functional constraints with GPN-Star (Nature) No field-specific location recorded Version: Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte. |
| Hash scope SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte. Source metadata | Ye et al. 2026, Predicting genome-wide functional constraints with GPN-Star (Nature) No field-specific location recorded Version: Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte. |
| Licence CC BY 4.0 (Open Access) Source metadata | Ye et al. 2026, Predicting genome-wide functional constraints with GPN-Star (Nature) No field-specific location recorded Version: Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte. |
Limitations2 values
| Ye et al. 2026, Predicting genome-wide functional constraints with GPN-Star (Nature) No field-specific location recorded Version: Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte. |
| Media type application/pdf Source metadata | Ye et al. 2026, Predicting genome-wide functional constraints with GPN-Star (Nature) No field-specific location recorded Version: Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte. |
| Publication status peer_reviewed Source metadata | Ye et al. 2026, Predicting genome-wide functional constraints with GPN-Star (Nature) No field-specific location recorded Version: Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte. |
| Retrieved at 2026-11-16T00:11:46Z Source metadata | Ye et al. 2026, Predicting genome-wide functional constraints with GPN-Star (Nature) No field-specific location recorded Version: Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte. |
| Review: artifact sha256 d7dfe801bad2a0a23478753147af2320bc31c8b37ee50d66f1a1af8385e9005d Source metadata | Ye et al. 2026, Predicting genome-wide functional constraints with GPN-Star (Nature) No field-specific location recorded Version: Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09 | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte. |
Sources and history
Release 2026-11-21-adc15377fab2 · Record review: source checked
Peer-reviewed version of record of the GPN-Star paper, retrieved as the publisher PDF.
Technical metadata and extraction receipts
Stable ID: gpn-star-20261116-source-nature-2026
- areas
- dna-genomes
- contexts
- research; clinical_research
- artifact sha256
- d7dfe801bad2a0a23478753147af2320bc31c8b37ee50d66f1a1af8385e9005d
- artifact url
- https://www.nature.com/articles/s41586-026-11005-5.pdf
- doi
- 10.1038/s41586-026-11005-5
- hash scope
- SHA-256 of the 26-page publisher PDF as downloaded. A second download in the same session reproduced the hash byte for byte.
- licence
- CC BY 4.0 (Open Access)
- limitations
- Figs. 2 and 3, Fig. 4a,c,d, Fig. 5b-d and Extended Data Figs. 1-10 print no performance values for the compared models. One statistic is printed inside a panel and was missed at extraction: Fig. 3e prints 'r = 0.47, P = 0.0072' for the Pearson correlation between log effective polygenicity and the difference in heritability enrichment between GPN-Star (P) and (M) across 27 traits, restated in the Supplementary Notes. It characterises the model rather than scoring it against a ground truth and is not extracted as a result; the Supplementary Notes also give a range, Spearman's rho 0.31-0.34, for the raw scores against Roulette mutation rate estimates on chromosome 22. Fig. 4b and Fig. 5a carry printed value labels; only Fig. 4b is extracted here, because Fig. 5a's labels can be assigned to a species and a score only by grouping them by position and taking the bar order from the legend.; The store already holds vep-uc-20261014-source-gpn-star for the same article URL, pinned on 2026-10-14 to the accelerated article preview PDF (97f61ec05d4ace41692549290db3faf019ce869459459d2c5694bf54e16d0996). That URL now serves this final version of record, whose bytes differ. Checked at review: the Internet Archive's capture of the article page on 2026-10-21 carries citation_firstpage 1 and citation_lastpage 10 with no volume, which is the preview state, while this PDF is paginated 141-150 in volume 659; the stored hash is therefore a correct pin of a different artifact and nothing stored is wrong. The two records are linked with companion_of from the preview to this version of record, placed on the stored record by npm run records -- change, rather than with supersedes.
- media type
- application/pdf
- publication status
- peer_reviewed
- retrieved at
- 2026-11-16T00:11:46Z
- review
- artifact sha256: d7dfe801bad2a0a23478753147af2320bc31c8b37ee50d66f1a1af8385e9005d; method: source-hash-verification; method note: Independent review pass of 2026-11-16. All four pinned artifacts were re-retrieved. The Nature article PDF, the Supplementary Information PDF and the Hugging Face collection API JSON each hashed to the value on their source record. The bioRxiv PDF did not and cannot: two downloads minutes apart gave b3e4d729d3363c16fb6b6cb99e4e18ffadb01b48614dba910480fb96f42b3d73 and 47f87f72baf93793177d3e40f70f43f03ac5d3050bbc5244f655e92041c7db4a, differing from each other in 34 bytes, all of them download-time stamps (XMP ModifyDate and MetadataDate, the xmpMM DocumentID and InstanceID, the document /ModDate and the second element of the trailer /ID); the page count, the CreationDate of 2025-09-21 and the pdftotext -layout text layer are identical across downloads. No value in this batch comes from the preprint. npm run batch -- check-values reproduced the extractor's figures exactly: 12 in_cell, 44 in_row, 16 locator_not_parsed, no not_in_row, no wrong_column and no overclaimed_in_row (value-check.tsv). All 72 results were then re-read by review/check_values_independent.py, written for this pass and importing nothing from extract/build.py. Supplementary Table 3 is printed rotated, so that script reads the page's word bounding boxes rather than a text dump: it recovers the seven column bands from the header words' y extents, pairing each 'Finemapped' header with whichever of 'coding' and 'non-coding' overlaps it, clusters the body words into eight row bands by x centre, and places every numeric token in the cell whose column centre is nearest, rejecting any token that is more than 45 per cent of a column pitch from its nearest column or less than 25 per cent of a pitch clear of the runner-up. Column order is therefore a measured property of the page and not an assumption, which is the check extract/build.py could not make: it asserted the column order positionally. Results are matched to cells through each source_locator's text, not through record IDs. Fig. 4b's 12 bar labels were required to be the first number printed after their series label on the same line, and the four rare variant counts were matched against the two sentences that print them, with the capture position fixing which count belongs to DeepRVAT with GPN-Star annotations and which to the original method. Result: 68 in cell, 4 in sentence, 0 failures (review/value-check-independent.tsv). Two negative controls confirm the checker is a cell check and not a row check: exchanging two ClinVar values between rows and moving a Fig. 4b label onto another series both fail (review/control-swap.tsv), and shifting a value into a neighbouring column of its own row fails and names the column that actually holds it, including across the Finemapped coding / OMIM and Finemapped coding / Finemapped non-coding boundaries (review/control-shift.tsv). Independently of both scripts, all 56 cells of Supplementary Table 3 and all 12 Fig. 4b labels were transcribed by hand from the pages rendered at 190 dpi with pdftoppm, into review/manual-transcription.tsv, and compared by review/cmp_manual.py: 68 values, 0 problems. That hand pass is what settles the column assignment the repository checker could only place at row level. The 12 descriptive claims were read against the pinned PDFs and the collection JSON.; note: Re-downloaded 2026-11-16 and matched the pinned hash byte for byte. Confirmed to be the version of record: the running footer reads 'Nature | Vol 659 | 5 November 2026' on every article page and the pagination is 141-150, with no accelerated article preview banner.; retrieval url: https://www.nature.com/articles/s41586-026-11005-5.pdf; reviewed at: 2026-11-16T01:30:00Z; reviewer: claude; reviewer note: Claude review agent (independent of the extractor); no human review claimed. Values were checked against the pinned artifacts; nothing was reproduced and no value was recomputed.
- source locator
- Results (PDF pages 3-6); Fig. 4 (PDF page 7); Data availability and Code availability (PDF page 10); Reporting Summary (PDF page 23)
- url
- https://www.nature.com/articles/s41586-026-11005-5
- venue
- Nature
- version
- Version of record: Nature 659, 141-150 (5 November 2026); received 2025-09-10, accepted 2026-08-07, published online 2026-09-09
- year
- 2026
Related records
- companion of: Ye et al. 2025, Predicting functional constraints across evolutionary timescales with phylogeny-informed genomic language models (bioRxiv v1)
- companion of: songlab/gpn-star Hugging Face collection (API response)
- companion of: Ye et al. 2026 GPN-Star, Nature Supplementary Information
- companion of: Ye et al. 2026, Nature (publisher PDF)