rewirebio.iobenchmarks
Result

R² (linear head per drug on frozen genome embeddings predicting log(1+MIC), random 70/10/20 split, mean over 56 antibiotics, printed as a percentage) of Nucleotide Transformer (frozen embeddings with a trained linear head) on Antibiotic resistance MIC regression subset, 56 antibiotics

27.74 ± 17.80 R² (linear head per drug on frozen genome embeddings predicting log(1+MIC), random 70/10/20 split, mean over 56 antibiotics, printed as a percentage)

Methods

Tested configuration
Nucleotide Transformer (frozen embeddings with a trained linear head)
Protocol
BacBench antibiotic resistance, MIC regression R squared
Dataset subset
Antibiotic resistance MIC regression subset, 56 antibiotics
Procedure
One linear model per drug on mean-pooled whole-genome embeddings: a single layer preceded by dropout of 0.1 and layer normalisation, binary cross-entropy for the resistant or susceptible setting and mean squared error for the log(1+MIC) regression, at most 100 epochs, early stopping patience 10 on validation AUROC or validation R squared, a learning-rate sweep per model across seeds and drugs, Adam with weight decay 0.01, and three random splits.
Evaluation
Nucleotide Transformer on BacBench antibiotic resistance, MIC regression R squared
Coverage
Not reported scored / Not reported eligible
Uncertainty
SD 17.80. The caption says the spread is across antibiotics; the Methods state 37 antibiotics in the binary setting and 56 in the regression setting.
Evidence
Author-reported evaluation · source checkedBacformer preprint, bioRxiv 2025.07.20.665723 version 3 · Table S18, row 'Nucleotide Transformer', column 'Regression R2'

A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.

Reproduction

Split
Random 70/10/20 split per antibiotic and seed; deliberately not phylogeny-aware.
Adaptation
Linear head trained on frozen embeddings
Scoring implementation
linear head per drug on frozen genome embeddings predicting log(1+MIC), random 70/10/20 split, mean over 56 antibiotics, printed as a percentage

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Reported result
27.74 ± 17.80
Individual claims
Bacformer preprint, bioRxiv 2025.07.20.665723 version 3

Original source ↗

Table S18, row 'Nucleotide Transformer', column 'Regression R2'

Version: Version 3, posted 17 August 2026 according to the page banner; the bioRxiv API lists version 3 with date 2026-08-19
Retrieved: 2026-11-15T22:55:00Z

source checked

["independent-cell-check","deterministic-table-parse","pdf-text-parse","source-hash-verification","ai-assisted-source-review"] · 2026-11-15T23:55:00Z

author reported

Audit details

Antibiotic resistance, Table S18. The denominators are the Methods' own counts, 37 antibiotics in the binary setting and 56 in the regression setting; Table S17 prints 37 drug rows for the binary setting. The caption's wording 'Performance (percent, higher is better)' describes the printed scale and does not make these metrics proportions. The unit concept was changed from percent to unitless in this review, with unit_detail 'printed x100'. data/vocab/unit.ttl says so in the scope note of unitless, and percent would assert that an AUROC, an R squared or a Pearson correlation is a proportion of items. The printed value, the numeric value and the spread are unchanged.

Field: attributes.printed_value

Source artifact SHA-256: d86de3315063e038ec8d5bed60b7b1a916c137ee60973e55d9d5c82f078d8dfd

Hash scope: The hash is of one download. bioRxiv regenerates this PDF on request, so the container bytes differ between downloads: a second download minutes later gave 08fcc83af256845d942345fc6b63c64911878733acd028edab5e9307d63319db. The pdftotext -layout text layer of both downloads is byte-identical (SHA-256 86636e89b167d7304b3a83ee7f159cad0a9bdbe97019588ce836087b8fe3b0b2), and that text layer, archived gzipped in artifacts/ with SHA-256 0afdefd78a410d036d1c4f17e33bdf481e8d76241ee02f4c84c7c4be91ee72aa, is what every extracted value was read from.

Extraction artifact SHA-256: 86636e89b167d7304b3a83ee7f159cad0a9bdbe97019588ce836087b8fe3b0b2

Extraction artifact

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: bacformer-20261115-result-amr-nucleotide-transformer-regression-r2

metric
coefficient-of-determination
metric direction
higher
metric qualifier
linear head per drug on frozen genome embeddings predicting log(1+MIC), random 70/10/20 split, mean over 56 antibiotics, printed as a percentage
numeric value
27.74
printed value
27.74 ± 17.80
review
artifact sha256: 86636e89b167d7304b3a83ee7f159cad0a9bdbe97019588ce836087b8fe3b0b2; method: independent-cell-check; deterministic-table-parse; pdf-text-parse; source-hash-verification; ai-assisted-source-review; method note: Independent review pass. Every cell of the six benchmark tables was re-read by review/recheck_cells.py, written for this pass, which uses neither of the extractor's scripts and does not read the pdftotext -layout text layer they read. It takes the word bounding boxes pdftotext -bbox-layout emits for a freshly downloaded version 3 PDF, groups words into printed lines by their y coordinate, derives each table's column boundaries from the x extent of that table's own printed header words, and assigns every number to a column by where it sits on the page, so a value printed under one header cannot be read as a value of another. It asserts the printed row order, that every column of every row is filled, that each cell holds exactly a mean and a spread, that each cell prints its own plus-minus sign, and for Tables S13 and S18 that the group header sits geometrically over the two columns this review names after it. All 186 cells agreed on the printed value, the mean, the spread, the spread's printed string and its source column, with no disagreement, and the six tables print no cell the batch leaves unrecorded. Three negative controls (two cells of one row exchanged, one cell taking its neighbour's value, every Table S18 locator moved one column right) were all rejected, and the unmutated batch accepted; the log is review/negative-controls.txt. npm run batch -- check-values reproduced the extractor's figures exactly, 36 in_cell and 150 in_row with nothing else, against a text layer regenerated from a fresh download. A manual sample of 47 cells was then read by eye against the printed table bodies: 24 drawn with random.sample over all 186 at seed 20261115, all 18 cells of Table S12, and the eight Evo and Evo-2 cells of Tables S1 and S14, where the printed row order differs from the other tables. All matched, column assignment included.; note: Antibiotic resistance, Table S18. The denominators are the Methods' own counts, 37 antibiotics in the binary setting and 56 in the regression setting; Table S17 prints 37 drug rows for the binary setting. The caption's wording 'Performance (percent, higher is better)' describes the printed scale and does not make these metrics proportions. The unit concept was changed from percent to unitless in this review, with unit_detail 'printed x100'. data/vocab/unit.ttl says so in the scope note of unitless, and percent would assert that an AUROC, an R squared or a Pearson correlation is a proportion of items. The printed value, the numeric value and the spread are unchanged.; retrieval url: https://www.biorxiv.org/content/10.1101/2025.07.20.665723v3.full.pdf; reviewed at: 2026-11-15T23:55:00Z; reviewer: claude; reviewer note: Claude (Opus 5) review agent, independent of the agent that extracted this batch; no human review claimed. Transcription was checked against the pinned sources. Nothing was reproduced and no value was recomputed.
source locator
Table S18, row 'Nucleotide Transformer', column 'Regression R2'
source table
S18
uncertainty
n: 56; note: The caption says the spread is across antibiotics; the Methods state 37 antibiotics in the binary setting and 56 in the regression setting.; printed: 27.74 ± 17.80; scope: across antibiotics; source column: Regression R2; type: standard_deviation; unit: unitless; value: 17.80
unit
unitless
unit detail
printed x100
Related records

Suggest a correction