rewirebio.iobenchmarks
Evaluation

DeepMicrobes on the BERTax final model dataset

Published taxonomic-classification comparison; transcribed, not reproduced.

Evaluation results

1 evaluation · 3 results. Different protocols are not a single leaderboard.

Protocol: BERTax Final model dataset: taxonomic classification at superkingdom and phylum, and genus (Mock et al. 2022) · Dataset: BERTax Final model dataset (Mock et al. 2022)

Sorted by Macro average precision (genus rank; macro average over classes; unclassified samples treated as random guesses) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configurationMacro average precision (genus rank; macro average over classes; unclassified samples treated as random guesses)Macro average precision (phylum rank; macro average over classes; unclassified samples treated as random guesses)Macro average precision (superkingdom rank; macro average over classes; unclassified samples treated as random guesses)
DeepMicrobes (Final model dataset, Mock et al. 2022)Evaluation66.4%92.1%98.1%
All 3 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: DeepMicrobes (Final model dataset, Mock et al. 2022)Protocol: BERTax Final model dataset: taxonomic classification at superkingdom and phylum, and genus (Mock et al. 2022)
Dataset: BERTax Final model dataset (Mock et al. 2022)
66.4% Macro average precision (genus rank; macro average over classes; unclassified samples treated as random guesses)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

DeepMicrobes on the BERTax final model dataset

dna-pathogen-20261012-bertax-protocol-final

Aggregation: Not reported

Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks (PNAS PDF) · Table 1, row "DeepMicrobes", column group "Final", column "Genus" (PNAS PDF page 4)
Configuration: DeepMicrobes (Final model dataset, Mock et al. 2022)Protocol: BERTax Final model dataset: taxonomic classification at superkingdom and phylum, and genus (Mock et al. 2022)
Dataset: BERTax Final model dataset (Mock et al. 2022)
92.1% Macro average precision (phylum rank; macro average over classes; unclassified samples treated as random guesses)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

DeepMicrobes on the BERTax final model dataset

dna-pathogen-20261012-bertax-protocol-final

Aggregation: Not reported

Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks (PNAS PDF) · Table 1, row "DeepMicrobes", column group "Final", column "Phyl." (PNAS PDF page 4)
Configuration: DeepMicrobes (Final model dataset, Mock et al. 2022)Protocol: BERTax Final model dataset: taxonomic classification at superkingdom and phylum, and genus (Mock et al. 2022)
Dataset: BERTax Final model dataset (Mock et al. 2022)
98.1% Macro average precision (superkingdom rank; macro average over classes; unclassified samples treated as random guesses)
percent · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

DeepMicrobes on the BERTax final model dataset

dna-pathogen-20261012-bertax-protocol-final

Aggregation: Not reported

Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks (PNAS PDF) · Table 1, row "DeepMicrobes", column group "Final", column "Supk." (PNAS PDF page 4)

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-10-22-1b7cf027e4f6 · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified
  • Sample annotations are recorded: not yet verified
  • Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • A pinned run recipe exists: not yet verified
  • Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Independent validation data exist: not yet verified
  • Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Evaluation procedure

BERTax Final model dataset: taxonomic classification at superkingdom and phylum, and genus (Mock et al. 2022)

Configuration
DeepMicrobes (Final model dataset, Mock et al. 2022)
Protocol
BERTax Final model dataset: taxonomic classification at superkingdom and phylum, and genus (Mock et al. 2022)
Dataset
BERTax Final model dataset (Mock et al. 2022)
origin
Author-reported evaluation
configuration
Primary source as retrieved 2026-10-12
protocol id
dna-pathogen-20261012-bertax-protocol-final
dataset version
BERTax final model dataset (Mock et al. 2022)
split
Closely related selection on an expanded fragment set (additional 2 million eukaryotic and bacterial fragments); classes with fewer than 10,000 fragments are pooled into an 'unknown' class at each rank.
population
5 superkingdom, 44 phylum and 156 genus classes, including 'unknown'
inputs
1,500-nt genome fragments
adaptation
Reference or training data restricted to the dataset's training partition
metric implementation
Top prediction only; unclassified samples treated as random guesses for AveP
aggregation
Macro average over classes for AveP
budget
Not reported

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split
Closely related selection on an expanded fragment set (additional 2 million eukaryotic and bacterial fragments); classes with fewer than 10,000 fragments are pooled into an 'unknown' class at each rank.
Adaptation
Reference or training data restricted to the dataset's training partition
Scoring implementation
Top prediction only; unclassified samples treated as random guesses for AveP

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

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.

57 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statementOriginal source and locationReview and provenance
Comparison: adaptation
Reference or training data restricted to the dataset's training partition
Context-only references
Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks

Original source ↗

Table 1 (PNAS PDF page 4)

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: PNAS 119(35):e2122636119, published 2022-08-26; PMC9436379 full-text XML
Retrieved: 2026-10-12T20:51:54Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: c0bb2f1bba8680b300076292389b39346ae58bea4bdf28647dd9462333b3bcd7

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

Inspected artifact

Comparison: adaptation
Reference or training data restricted to the dataset's training partition
Context-only references
Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks (PNAS PDF)

Original source ↗

Table 1 (PNAS PDF page 4)

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: PNAS 119(35):e2122636119 version-of-record PDF (10 pages)
Retrieved: 2026-10-12T20:56:37Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: 7977424613ab5e5f4986745b527a270fd2c0427dbab40471813903eda85dcaec

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

Inspected artifact

Comparison: adaptation
Reference or training data restricted to the dataset's training partition
Context-only references
BERTax SI Appendix (pnas.2122636119.sapp.pdf)

Original source ↗

Table 1 (PNAS PDF page 4)

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: SI Appendix as distributed with PMC9436379 (member pnas.2122636119.sapp.pdf of the Europe PMC supplementaryFiles ZIP)
Retrieved: 2026-10-12T20:55:54Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: 89a2f86f66cbb2ff17886d413cd89577285086fedd1009e1d9daf87b29fbc1c0

Hash scope: SHA-256 of the PDF member, not of the ZIP (the ZIP is rebuilt per request)

Inspected artifact

Comparison: aggregation
Macro average over classes for AveP
Context-only references
Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks

Original source ↗

Table 1 (PNAS PDF page 4)

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: PNAS 119(35):e2122636119, published 2022-08-26; PMC9436379 full-text XML
Retrieved: 2026-10-12T20:51:54Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: c0bb2f1bba8680b300076292389b39346ae58bea4bdf28647dd9462333b3bcd7

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

Inspected artifact

Comparison: aggregation
Macro average over classes for AveP
Context-only references
Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks (PNAS PDF)

Original source ↗

Table 1 (PNAS PDF page 4)

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: PNAS 119(35):e2122636119 version-of-record PDF (10 pages)
Retrieved: 2026-10-12T20:56:37Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: 7977424613ab5e5f4986745b527a270fd2c0427dbab40471813903eda85dcaec

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

Inspected artifact

Comparison: aggregation
Macro average over classes for AveP
Context-only references
BERTax SI Appendix (pnas.2122636119.sapp.pdf)

Original source ↗

Table 1 (PNAS PDF page 4)

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: SI Appendix as distributed with PMC9436379 (member pnas.2122636119.sapp.pdf of the Europe PMC supplementaryFiles ZIP)
Retrieved: 2026-10-12T20:55:54Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: 89a2f86f66cbb2ff17886d413cd89577285086fedd1009e1d9daf87b29fbc1c0

Hash scope: SHA-256 of the PDF member, not of the ZIP (the ZIP is rebuilt per request)

Inspected artifact

Comparison: budget
Not reported
Context-only references
Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks

Original source ↗

Table 1 (PNAS PDF page 4)

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: PNAS 119(35):e2122636119, published 2022-08-26; PMC9436379 full-text XML
Retrieved: 2026-10-12T20:51:54Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: c0bb2f1bba8680b300076292389b39346ae58bea4bdf28647dd9462333b3bcd7

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

Inspected artifact

Comparison: budget
Not reported
Context-only references
Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks (PNAS PDF)

Original source ↗

Table 1 (PNAS PDF page 4)

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: PNAS 119(35):e2122636119 version-of-record PDF (10 pages)
Retrieved: 2026-10-12T20:56:37Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: 7977424613ab5e5f4986745b527a270fd2c0427dbab40471813903eda85dcaec

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

Inspected artifact

Comparison: budget
Not reported
Context-only references
BERTax SI Appendix (pnas.2122636119.sapp.pdf)

Original source ↗

Table 1 (PNAS PDF page 4)

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: SI Appendix as distributed with PMC9436379 (member pnas.2122636119.sapp.pdf of the Europe PMC supplementaryFiles ZIP)
Retrieved: 2026-10-12T20:55:54Z

missing or unspecified

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: 89a2f86f66cbb2ff17886d413cd89577285086fedd1009e1d9daf87b29fbc1c0

Hash scope: SHA-256 of the PDF member, not of the ZIP (the ZIP is rebuilt per request)

Inspected artifact

Comparison: dataset version
BERTax final model dataset (Mock et al. 2022)
Context-only references
Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks

Original source ↗

Table 1 (PNAS PDF page 4)

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: PNAS 119(35):e2122636119, published 2022-08-26; PMC9436379 full-text XML
Retrieved: 2026-10-12T20:51:54Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: c0bb2f1bba8680b300076292389b39346ae58bea4bdf28647dd9462333b3bcd7

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

Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

3 source records and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: dna-pathogen-20261012-bertax-eval-deepmicrobes-final

areas
microbes-communities
contexts
research
origin
author_reported
protocol
dna-pathogen-20261012-bertax-protocol-final
version
Primary source as retrieved 2026-10-12
comparison
protocol id: dna-pathogen-20261012-bertax-protocol-final; dataset version: BERTax final model dataset (Mock et al. 2022); split: Closely related selection on an expanded fragment set (additional 2 million eukaryotic and bacterial fragments); classes with fewer than 10,000 fragments are pooled into an 'unknown' class at each rank.; population: 5 superkingdom, 44 phylum and 156 genus classes, including 'unknown'; inputs: 1,500-nt genome fragments; adaptation: Reference or training data restricted to the dataset's training partition; metric implementation: Top prediction only; unclassified samples treated as random guesses for AveP; aggregation: Macro average over classes for AveP; budget: Not reported
source locator
Table 1 (PNAS PDF page 4)
limitations
All tools were run by the BERTax authors, who developed BERTax; the evaluations are author_reported.; Database tools were restricted to the training partition as reference; whole reference genomes were excluded to avoid duplicate samples between training and test data.
review
method: source-hash-verification; scope-review; reviewer: claude; reviewer note: Separate Claude review agent (rev-mlvb), independent of the extracting agent; no human review claimed; date: 2026-10-12; artifact sha256: c0bb2f1bba8680b300076292389b39346ae58bea4bdf28647dd9462333b3bcd7; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC9436379/fullTextXML; note: Checked against the re-downloaded article XML (SHA-256 matches) and SI.
Related records

Suggest a correction