rewirebio.iobenchmarks
Source

A Phylogenetic Approach to Genomic Language Modeling

2025 · preprint version in PMC · Preprint

Original source

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.

Model or configurationMetricValueDatasetEvaluation
AUGUSTUSMCC (BEND Gene Finding, task-specific expert model trained end to end)0.80 unitlessGENCODE (BEND split)Augustus on BEND Gene Finding
BASSETAUROC (BEND Chromatin Accessibility, task-specific expert model trained end to end)0.85 unitlessENCODE chromatin accessibility (BEND split)Basset on BEND Chromatin Accessibility
BASSETAUROC (BEND CpG Methylation, task-specific expert model trained end to end)0.93 unitlessENCODE CpG methylation (BEND split)Basset on BEND CpG Methylation
BASSETAUROC (BEND Histone Modification, task-specific expert model trained end to end)0.74 unitlessENCODE histone modification (BEND split)Basset on BEND Histone Modification
Caduceus, largest reverse-complement-equivariant model, frozen embeddingsAUROC (BEND Chromatin Accessibility, two-layer CNN trained on frozen embeddings)0.79 unitlessENCODE chromatin accessibility (BEND split)Caduceus on BEND Chromatin Accessibility
Caduceus, largest reverse-complement-equivariant model, frozen embeddingsAUROC (BEND CpG Methylation, two-layer CNN trained on frozen embeddings)0.91 unitlessENCODE CpG methylation (BEND split)Caduceus on BEND CpG Methylation
Caduceus, largest reverse-complement-equivariant model, frozen embeddingsAUROC (BEND Disease VEP, cosine distance between the embeddings of the reference and alternative sequences)0.54 unitlessClinVar disease variants (BEND split)Caduceus on BEND Disease VEP
Caduceus, largest reverse-complement-equivariant model, frozen embeddingsAUPRC (BEND Enhancer Annotation, two-layer CNN trained on frozen embeddings)0.03 unitlessFulco 2019, Gasperini 2019 and Enformer enhancer set (BEND split)Caduceus on BEND Enhancer Annotation
Caduceus, largest reverse-complement-equivariant model, frozen embeddingsAUROC (BEND Expression VEP, cosine distance between the embeddings of the reference and alternative sequences)0.53 unitlessDeepSEA expression variants (BEND split)Caduceus on BEND Expression VEP
Caduceus, largest reverse-complement-equivariant model, frozen embeddingsMCC (BEND Gene Finding, two-layer CNN trained on frozen embeddings)0.54 unitlessGENCODE (BEND split)Caduceus on BEND Gene Finding
Caduceus, largest reverse-complement-equivariant model, frozen embeddingsAUROC (BEND Histone Modification, two-layer CNN trained on frozen embeddings)0.78 unitlessENCODE histone modification (BEND split)Caduceus on BEND Histone Modification
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class 3’ UTR)0.63 unitlessClinVar 3’ UTR variants, at least one review starCaduceus on ClinVar 3’ UTR variants, likelihood-ratio scoring
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class 5’ UTR)0.61 unitlessClinVar 5’ UTR variants, at least one review starCaduceus on ClinVar 5’ UTR variants, likelihood-ratio scoring
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Downstream of Transcript)0.72 unitlessClinVar Downstream of Transcript variants, at least one review starCaduceus on ClinVar Downstream of Transcript variants, likelihood-ratio scoring
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Intronic)0.64 unitlessClinVar Intronic variants, at least one review starCaduceus on ClinVar Intronic variants, likelihood-ratio scoring
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Missense)0.55 unitlessClinVar Missense variants, at least one review starCaduceus on ClinVar Missense variants, likelihood-ratio scoring
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Noncoding)0.59 unitlessClinVar Noncoding variants, at least one review starCaduceus on ClinVar Noncoding variants, likelihood-ratio scoring
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Splice Acceptor)0.61 unitlessClinVar Splice Acceptor variants, at least one review starCaduceus on ClinVar Splice Acceptor variants, likelihood-ratio scoring
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Splice Donor)0.68 unitlessClinVar Splice Donor variants, at least one review starCaduceus on ClinVar Splice Donor variants, likelihood-ratio scoring
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Start Codon)0.41 unitlessClinVar Start Codon variants, at least one review starCaduceus on ClinVar Start Codon variants, likelihood-ratio scoring
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Stop Lost)0.43 unitlessClinVar Stop Lost variants, at least one review starCaduceus on ClinVar Stop Lost variants, likelihood-ratio scoring
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Synonymous)0.55 unitlessClinVar Synonymous variants, at least one review starCaduceus on ClinVar Synonymous variants, likelihood-ratio scoring
Caduceus-PS 131k, 256 model dimensions, 16 layersAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class Upstream of Transcript)0.40 unitlessClinVar Upstream of Transcript variants, at least one review starCaduceus on ClinVar Upstream of Transcript variants, likelihood-ratio scoring
DEEPSEAAUROC (BEND Disease VEP, task-specific expert model trained end to end)0.56 unitlessClinVar disease variants (BEND split)DeepSEA on BEND Disease VEP
DEEPSEAAUROC (BEND Expression VEP, task-specific expert model trained end to end)0.70 unitlessDeepSEA expression variants (BEND split)DeepSEA on BEND Expression VEP
DNABERT, best model of the family on each BEND taskAUROC (BEND Chromatin Accessibility, two-layer CNN trained on frozen embeddings; best result among the models of this family)0.85 unitlessENCODE chromatin accessibility (BEND split)DNABERT on BEND Chromatin Accessibility
DNABERT, best model of the family on each BEND taskAUROC (BEND CpG Methylation, two-layer CNN trained on frozen embeddings; best result among the models of this family)0.91 unitlessENCODE CpG methylation (BEND split)DNABERT on BEND CpG Methylation
DNABERT, best model of the family on each BEND taskAUROC (BEND Disease VEP, cosine distance between the embeddings of the reference and alternative sequences; best result among the models of this family)0.56 unitlessClinVar disease variants (BEND split)DNABERT on BEND Disease VEP
DNABERT, best model of the family on each BEND taskAUPRC (BEND Enhancer Annotation, two-layer CNN trained on frozen embeddings; best result among the models of this family)0.03 unitlessFulco 2019, Gasperini 2019 and Enformer enhancer set (BEND split)DNABERT on BEND Enhancer Annotation
DNABERT, best model of the family on each BEND taskAUROC (BEND Expression VEP, cosine distance between the embeddings of the reference and alternative sequences; best result among the models of this family)0.60 unitlessDeepSEA expression variants (BEND split)DNABERT on BEND Expression VEP
DNABERT, best model of the family on each BEND taskMCC (BEND Gene Finding, two-layer CNN trained on frozen embeddings; best result among the models of this family)0.43 unitlessGENCODE (BEND split)DNABERT on BEND Gene Finding
DNABERT, best model of the family on each BEND taskAUROC (BEND Histone Modification, two-layer CNN trained on frozen embeddings; best result among the models of this family)0.79 unitlessENCODE histone modification (BEND split)DNABERT on BEND Histone Modification
ENFORMERAUPRC (BEND Enhancer Annotation, task-specific expert model trained end to end)0.07 unitlessFulco 2019, Gasperini 2019 and Enformer enhancer set (BEND split)Enformer on BEND Enhancer Annotation
GENA-LM, best model of the family on each BEND taskAUROC (BEND Chromatin Accessibility, two-layer CNN trained on frozen embeddings; best result among the models of this family)0.84 unitlessENCODE chromatin accessibility (BEND split)GENA-LM on BEND Chromatin Accessibility
GENA-LM, best model of the family on each BEND taskAUROC (BEND CpG Methylation, two-layer CNN trained on frozen embeddings; best result among the models of this family)0.91 unitlessENCODE CpG methylation (BEND split)GENA-LM on BEND CpG Methylation
GENA-LM, best model of the family on each BEND taskAUROC (BEND Disease VEP, cosine distance between the embeddings of the reference and alternative sequences; best result among the models of this family)0.55 unitlessClinVar disease variants (BEND split)GENA-LM on BEND Disease VEP
GENA-LM, best model of the family on each BEND taskAUPRC (BEND Enhancer Annotation, two-layer CNN trained on frozen embeddings; best result among the models of this family)0.04 unitlessFulco 2019, Gasperini 2019 and Enformer enhancer set (BEND split)GENA-LM on BEND Enhancer Annotation
GENA-LM, best model of the family on each BEND taskAUROC (BEND Expression VEP, cosine distance between the embeddings of the reference and alternative sequences; best result among the models of this family)0.49 unitlessDeepSEA expression variants (BEND split)GENA-LM on BEND Expression VEP
GENA-LM, best model of the family on each BEND taskMCC (BEND Gene Finding, two-layer CNN trained on frozen embeddings; best result among the models of this family)0.52 unitlessGENCODE (BEND split)GENA-LM on BEND Gene Finding
GENA-LM, best model of the family on each BEND taskAUROC (BEND Histone Modification, two-layer CNN trained on frozen embeddings; best result among the models of this family)0.78 unitlessENCODE histone modification (BEND split)GENA-LM on BEND Histone Modification
GPN-MSA, allele likelihood ratios on variant-effect tasksAUROC (BEND Disease VEP, log likelihood ratio between the reference and alternative alleles)0.98 unitlessClinVar disease variants (BEND split)GPN-MSA (LLR) on BEND Disease VEP
GPN-MSA, allele likelihood ratios on variant-effect tasksAUROC (BEND Expression VEP, log likelihood ratio between the reference and alternative alleles)0.56 unitlessDeepSEA expression variants (BEND split)GPN-MSA (LLR) on BEND Expression VEP
GPN-MSA, concatenated 128 bp window embeddingsAUROC (BEND CpG Methylation, two-layer CNN trained on frozen embeddings)0.96 unitlessENCODE CpG methylation (BEND split)GPN-MSA on BEND CpG Methylation
GPN-MSA, concatenated 128 bp window embeddingsAUROC (BEND Disease VEP, cosine distance between the embeddings of the reference and alternative sequences)0.33 unitlessClinVar disease variants (BEND split)GPN-MSA on BEND Disease VEP
GPN-MSA, concatenated 128 bp window embeddingsAUPRC (BEND Enhancer Annotation, two-layer CNN trained on frozen embeddings)0.03 unitlessFulco 2019, Gasperini 2019 and Enformer enhancer set (BEND split)GPN-MSA on BEND Enhancer Annotation
GPN-MSA, concatenated 128 bp window embeddingsAUROC (BEND Expression VEP, cosine distance between the embeddings of the reference and alternative sequences)0.44 unitlessDeepSEA expression variants (BEND split)GPN-MSA on BEND Expression VEP
GPN-MSA, concatenated 128 bp window embeddingsMCC (BEND Gene Finding, two-layer CNN trained on frozen embeddings)0.38 unitlessGENCODE (BEND split)GPN-MSA on BEND Gene Finding
GPN-MSA, concatenated 128 bp window embeddingsAUROC (BEND Histone Modification, two-layer CNN trained on frozen embeddings)0.80 unitlessENCODE histone modification (BEND split)GPN-MSA on BEND Histone Modification
GPN-MSA, published precomputed hg38 likelihood ratiosAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class 3’ UTR)0.96 unitlessClinVar 3’ UTR variants, at least one review starGPN-MSA on ClinVar 3’ UTR variants, likelihood-ratio scoring
GPN-MSA, published precomputed hg38 likelihood ratiosAUROC (ClinVar pathogenic or likely pathogenic versus benign or likely benign, zero-shot allele log likelihood ratio, class 5’ UTR)0.95 unitlessClinVar 5’ UTR variants, at least one review starGPN-MSA on ClinVar 5’ UTR variants, likelihood-ratio scoring

Claims

Statements this source supports, each with where in the source it was checked.

  • b2-phylogpn-2025: status: Review status superseded (Table 1, row '3’ UTR', column 'PhyloGPN')
  • ClinVar 3-prime UTR variant classification: attributes.benchmark_research.primary_sources: Benchmark research: primary sources ["phylogpn-2025"] (data/entities/sources.jsonl, records phylogpn-2025 and evidence-expansion-p2-phylogpn-2025-807f3a26cbfa, both with artifact_sha256 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224)
  • ClinVar 3-prime UTR variant classification: source_ids: Sources ["phylogpn-2025"] (data/entities/sources.jsonl, records phylogpn-2025 and evidence-expansion-p2-phylogpn-2025-807f3a26cbfa, both with artifact_sha256 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224)
  • evidence-expansion-p2-phylogpn-2025-807f3a26cbfa: status: Review status superseded (Both source records carry artifact_sha256 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224)
  • Licence of the pinned PhyloGPN preprint artifact: Licence CC BY-NC-ND 4.0 (Permissions statement of the PMC deposit of arXiv:2503.03773v1)
  • PhyloGPN access: Access Model weights at https://huggingface.co/songlab/phylogpn and the code for the likelihood-based evaluation at https://github.com/songlab-cal/gpn. Neither is pinned to a revision in the paper. (Footnotes, Code and model availability)
  • PhyloGPN architecture: Architecture Reverse-complement-equivariant dilated convolutional network adapted from CARP, itself adapted from ByteNet, with 40 residual blocks, a 481 bp receptive field and about 83M stored parameters. Reverse-complement weight tying leaves about half of the weights and biases free, plus the layer-normalisation parameters. (Methods, Architecture and Training (paragraph 1))
  • PhyloGPN embeddings: Embeddings A 960-dimensional embedding of any 481 bp DNA sequence, taken from one named layer. Embeddings from other layers were not tried. (Methods, Embeddings (paragraph 1))
  • PhyloGPN inference inputs: Inference inputs A single DNA sequence. The whole-genome alignment and the phylogeny enter the training loss only and are not required to make a prediction. (Abstract; Discussion and Conclusion (paragraph 1))
  • PhyloGPN reported limitation: Reported limitation The authors attribute PhyloGPN coming up short of GPN-MSA on coding variant pathogenicity to its training alignment holding many mammals but fewer distantly related species, and state they did not harmonise the more diverse vertebrate alignment with their mammalian one. (Discussion and Conclusion (paragraph 4))
  • PhyloGPN training compute: Training compute Eighteen epochs on four NVIDIA A100 GPUs with AdamW, a fixed learning rate of 1e-5 and no weight decay; 12 alignment blocks of about 10 kb per batch, with autosomal positions sampled four times per epoch, X chromosome positions three times and Y chromosome positions once. (Methods, Architecture and Training (paragraphs 2-3))
  • PhyloGPN training data: Training data Length-481 windows of the human reference genome GRCh38, each paired with the nucleotides aligned to its central position in a whole-genome alignment of 447 placental mammal genomes from the Zoonomia Consortium, and with the minimum spanning tree of a species-level phylogeny for the species aligned at that position. Positions outside the primary assembly were excluded. (Methods, Training Data (paragraphs 1-2); Methods, Architecture and Training (paragraph 2))
  • PhyloGPN training objective: Training objective A stable upper bound of a phylogenetic F81 likelihood for the aligned column at the central position, conditioned on the state of the human reference nucleotide so the model cannot simply copy it. (Methods, Loss Function (Eqs. 3 to 5))
  • phylogpn-2025: attributes.evidence_concerns: Evidence concerns One scoped entry naming phylogpn-20261116-result-t2-chromatin-gena-lm: Table 2's GENA-LM Chromatin Accessibility cell, printed 0.84, is above every GENA-LM value BEND prints in its main results table, so it is withheld from automatic comparison. The printed value is kept. (Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)')
  • phylogpn-2025: attributes.licence: Licence CC BY-NC-ND 4.0 (Permissions statement of the PMC deposit of arXiv:2503.03773v1, in the pinned full text XML)
  • phylogpn-2025: attributes.version_note: Version note Published as a peer-reviewed conference paper: Albors C., Li J.C., Benegas G., Ye C., Song Y.S., A Phylogenetic Approach to Genomic Language Modeling, Research in Computational Molecular Biology (RECOMB 2025), Lecture Notes in Computer Science (LNBI) volume 15647, pages 99-117, first online 25 April 2025, doi 10.1007/978-3-031-90252-9_7. The pinned artifact remains the preprint, so publication_status stays 'preprint'; the version of record is paywalled and was not compared with the preprint. (Springer chapter page citation metadata (series, volume, citation_firstpage, citation_lastpage, First Online); Crossref 10.1007/978-3-031-90252-9_7; Europe PMC core record for PMCID:PMC11908359)
  • phylogpn-2025: links: Links One link: supersedes evidence-expansion-p2-phylogpn-2025-807f3a26cbfa (Both source records carry artifact_sha256 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224 and the same Europe PMC fullTextXML artifact URL)
  • phylogpn-2025: status: Review status source_checked (Pinned full text XML re-retrieved 2026-11-16; SHA-256 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224)
  • Reported AUROC for PhyloGPN: Printed value 0.94 (Table 1, 3-prime UTR row, PhyloGPN AUROC column)
  • Version of record of the PhyloGPN paper: Version note Published as a peer-reviewed conference paper: Albors C., Li J.C., Benegas G., Ye C., Song Y.S., A Phylogenetic Approach to Genomic Language Modeling, Research in Computational Molecular Biology (RECOMB 2025), Lecture Notes in Computer Science (LNBI) volume 15647, pages 99-117, first online 25 April 2025, doi 10.1007/978-3-031-90252-9_7. The pinned artifact remains the preprint, whose publication_status is correctly 'preprint'; the version of record is paywalled and was not compared with the preprint. (Springer chapter page header and abstract; songlab-cal/gpn README model-families table and BibTeX entry albors2025phylogenetic)

Models, benchmarks and other records

Configurations (14)

Tasks (1)

Protocols (1)

Datasets (2)

Dataset subsets (12)

Evaluations (125)

Sources (2)

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.

25 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-adc15377fab2
Property and statementOriginal source and locationReview and provenance
Artifact retrieved at
2026-09-16T10:38:57.558218+00:00
Source metadata
A Phylogenetic Approach to Genomic Language Modeling

Original source ↗

No field-specific location recorded

Version: preprint version in PMC
Retrieved: 2026-09-16T10:38:57.558218+00:00

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.artifact_retrieved_at

Source artifact SHA-256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Artifact SHA-256
807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224
Source metadata
A Phylogenetic Approach to Genomic Language Modeling

Original source ↗

No field-specific location recorded

Version: preprint version in PMC
Retrieved: 2026-09-16T10:38:57.558218+00:00

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.artifact_sha256

Source artifact SHA-256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Artifact url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC11908359/fullTextXML
Source metadata
A Phylogenetic Approach to Genomic Language Modeling

Original source ↗

No field-specific location recorded

Version: preprint version in PMC
Retrieved: 2026-09-16T10:38:57.558218+00:00

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.artifact_url

Source artifact SHA-256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Missing metadata: doi: reason
unextracted
Source metadata
A Phylogenetic Approach to Genomic Language Modeling

Original source ↗

No field-specific location recorded

Version: preprint version in PMC
Retrieved: 2026-09-16T10:38:57.558218+00:00

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.missing_metadata.doi.reason

Source artifact SHA-256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Publication status
preprint
Source metadata
A Phylogenetic Approach to Genomic Language Modeling

Original source ↗

No field-specific location recorded

Version: preprint version in PMC
Retrieved: 2026-09-16T10:38:57.558218+00:00

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.publication_status

Source artifact SHA-256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Retrieved at
2026-09-15T23:33:26Z
Source metadata
A Phylogenetic Approach to Genomic Language Modeling

Original source ↗

No field-specific location recorded

Version: preprint version in PMC
Retrieved: 2026-09-16T10:38:57.558218+00:00

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.retrieved_at

Source artifact SHA-256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Review: artifact sha256
807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224
Source metadata
A Phylogenetic Approach to Genomic Language Modeling

Original source ↗

No field-specific location recorded

Version: preprint version in PMC
Retrieved: 2026-09-16T10:38:57.558218+00:00

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.review.artifact_sha256

Source artifact SHA-256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Review: date
2026-11-16
Source metadata
A Phylogenetic Approach to Genomic Language Modeling

Original source ↗

No field-specific location recorded

Version: preprint version in PMC
Retrieved: 2026-09-16T10:38:57.558218+00:00

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.review.date

Source artifact SHA-256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Review: method note
Independent review of the PhyloGPN batch. The artifact was re-retrieved from the recorded artifact_url on 2026-11-16 and its SHA-256 matched the stored value byte for byte. Its two tables were re-read cell by cell, its Methods, Results, Discussion, permissions statement and footnotes were read for the descriptive claims, and the Europe PMC core record for PMCID:PMC11908359 was read for the licence and the published-version metadata.
Source metadata
A Phylogenetic Approach to Genomic Language Modeling

Original source ↗

No field-specific location recorded

Version: preprint version in PMC
Retrieved: 2026-09-16T10:38:57.558218+00:00

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.review.method_note

Source artifact SHA-256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Review method
3 values
  • automated-source-review
  • independent-cell-check
  • source-hash-verification
Source metadata
A Phylogenetic Approach to Genomic Language Modeling

Original source ↗

No field-specific location recorded

Version: preprint version in PMC
Retrieved: 2026-09-16T10:38:57.558218+00:00

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.review.method

Source artifact SHA-256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

How to read the evidence

Sources and history

Release 2026-11-21-adc15377fab2 · Record review: source checked

Primary paper retained with its original identifier. Metadata inherited from the literature collection; individual result checks are separate.

Release history

No supporting source is linked yet.

Supersedes A Phylogenetic Approach to Genomic Language Modeling

Read original source

Download this release (gzip)
Technical metadata and extraction receipts

Stable ID: phylogpn-2025

areas
dna-genomes
url
https://pmc.ncbi.nlm.nih.gov/articles/PMC11908359/
version
preprint version in PMC
retrieved at
2026-09-15T23:33:26Z
publication status
preprint
year
2025
artifact sha256
807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224
artifact url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC11908359/fullTextXML
artifact retrieved at
2026-09-16T10:38:57.558218+00:00
scope decision
included
missing metadata
doi: reason: unextracted
licence
CC BY-NC-ND 4.0
version note
Published as a peer-reviewed conference paper: Albors C., Li J.C., Benegas G., Ye C., Song Y.S., A Phylogenetic Approach to Genomic Language Modeling, Research in Computational Molecular Biology (RECOMB 2025), Lecture Notes in Computer Science (LNBI) volume 15647, pages 99-117, first online 25 April 2025, doi 10.1007/978-3-031-90252-9_7. The pinned artifact remains the preprint, so publication_status stays 'preprint'; the version of record is paywalled and was not compared with the preprint.
review
method: automated-source-review; independent-cell-check; source-hash-verification; method note: Independent review of the PhyloGPN batch. The artifact was re-retrieved from the recorded artifact_url on 2026-11-16 and its SHA-256 matched the stored value byte for byte. Its two tables were re-read cell by cell, its Methods, Results, Discussion, permissions statement and footnotes were read for the descriptive claims, and the Europe PMC core record for PMCID:PMC11908359 was read for the licence and the published-version metadata.; reviewer: claude; reviewer note: Claude review agent (independent of the extractor); no human review claimed. Nothing was reproduced and no value was recomputed.; date: 2026-11-16; artifact sha256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC11908359/fullTextXML; note: Reviewed with data/omics/phylogpn-20261116 and recorded in docs/reviews/2026-11-16-phylogpn.md. publication_status stays 'preprint': the pinned artifact is the preprint, and the version of record is named in version_note and pinned by phylogpn-20261116-source-springer-chapter.
evidence concerns
applies to: phylogpn-20261116-result-t2-chromatin-gena-lm; artifact sha256: 807f3a26cbfa9b5ce238d92164bd523302c67d1c5794b08273c51cca1acd4224; message: Table 2's GENA-LM Chromatin Accessibility cell prints 0.84. The caption's rule is 'We report the best result among models in each family' and Section 4.2 says the row is reproduced from Marin et al. (BEND), but BEND's main results table prints 0.76 for GENA-LM BERT and 0.82 for GENA-LM BigBird in both the ICLR 2024 proceedings PDF pinned as evidence-expansion-bend-final-f709b6be and the arXiv rendition arXiv:2311.12570 retrieved on 2026-11-16. No subset of the GENA-LM family reproduces all seven printed cells of the row, while the DNABERT, HyenaDNA and Nucleotide Transformer rows each have one that does, so the printed value is not the family best this paper says it reports and its origin is unknown. The printed value is kept as published; this entry withholds that one result from automatic comparison. The row's other six cells and the rest of the source are not covered.; review method: independent-cell-check; review date: 2026-11-16; source id: phylogpn-2025; source locator: Table 2, row 'GENA-LM', column 'Chromatin Accessibility (AUROC)'
Related records

Suggest a correction