| Comparison: adaptation Linear head trained on frozen embeddings Context-only references | Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 Original source ↗ Table S18, row 'ESM-2', column 'Regression Pearson' 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 | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.adaptation 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. |
|---|
| Comparison: aggregation Mean and standard deviation across antibiotics Context-only references | Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 Original source ↗ Table S18, row 'ESM-2', column 'Regression Pearson' 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 | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.aggregation 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. |
|---|
| Comparison: budget About 50 hours on one NVIDIA H100 with 96 GB of memory and 72 CPU cores, including tuning, training and testing for all models across seeds, excluding the cost of embedding the genomes Context-only references | Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 Original source ↗ Table S18, row 'ESM-2', column 'Regression Pearson' 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 | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.budget 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. |
|---|
| Comparison: dataset version As described in version 3 of the preprint and published on Hugging Face Context-only references | Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 Original source ↗ Table S18, row 'ESM-2', column 'Regression Pearson' 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 | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.dataset_version 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. |
|---|
| Comparison: inputs Single protein sequence. Each protein embedded on its own, last-layer hidden states mean-pooled over amino acids Context-only references | Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 Original source ↗ Table S18, row 'ESM-2', column 'Regression Pearson' 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 | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.inputs 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. |
|---|
| Comparison: metric 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 Context-only references | Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 Original source ↗ Table S18, row 'ESM-2', column 'Regression Pearson' 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 | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.metric_implementation 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. |
|---|
| Comparison: population 56 antibiotics with quoted minimum inhibitory concentrations, log(1+x) transformed; drawn from 26,052 unique genomes with matched resistance labels Context-only references | Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 Original source ↗ Table S18, row 'ESM-2', column 'Regression Pearson' 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 | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.population 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. |
|---|
| Comparison: protocol id bacformer-20261115-protocol-amr-regression-pearson Context-only references | Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 Original source ↗ Table S18, row 'ESM-2', column 'Regression Pearson' 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 | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.protocol_id 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. |
|---|
| Comparison: split Random 70/10/20 split per antibiotic and seed; deliberately not phylogeny-aware. Context-only references | Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 Original source ↗ Table S18, row 'ESM-2', column 'Regression Pearson' 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 | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.split 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. |
|---|
Limitations2 values- Reported by the authors of Bacformer, who also built BacBench and ran every benchmarked model on it.
- Not reproduced by Rewire; the exact splits, seeds and BacBench commit behind the runs are not published.
Context-only references | Bacformer preprint, bioRxiv 2025.07.20.665723 version 3 Original source ↗ Table S18, row 'ESM-2', column 'Regression Pearson' 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 | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.limitations 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. |
|---|