NT 500M Randomly Initialized, trained from scratch (NT benchmark)
NT 500M Randomly Initialized, trained from scratch, a configuration of Nucleotide Transformer: trained from scratch.
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluations and results
19 evaluations · 19 results. Different protocols are not a single leaderboard.
Sorted by MCC (median over 10 cross-validation folds) (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.
All 19 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark Enhancer, fine-tuning (PEFT) Dataset: NT benchmark Enhancer | 0.251 (± 0.012) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.012 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark Enhancer (fine-tuning) lit-genomics-20261011-ntbench-protocol-enhancer-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'Enhancer' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark Enhancer types, fine-tuning (PEFT) Dataset: NT benchmark Enhancer types | 0.215 (± 0.022) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.022 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark Enhancer types (fine-tuning) lit-genomics-20261011-ntbench-protocol-enhancer-types-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'Enhancer types' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark H2AFZ, fine-tuning (PEFT) Dataset: NT benchmark H2AFZ | 0.281 (± 0.017) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.017 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark H2AFZ (fine-tuning) lit-genomics-20261011-ntbench-protocol-h2afz-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'H2AFZ' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark H3K27ac, fine-tuning (PEFT) Dataset: NT benchmark H3K27ac | 0.233 (± 0.015) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.015 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark H3K27ac (fine-tuning) lit-genomics-20261011-ntbench-protocol-h3k27ac-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'H3K27ac' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark H3K27me3, fine-tuning (PEFT) Dataset: NT benchmark H3K27me3 | 0.364 (± 0.021) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.021 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark H3K27me3 (fine-tuning) lit-genomics-20261011-ntbench-protocol-h3k27me3-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'H3K27me3' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark H3K36me3, fine-tuning (PEFT) Dataset: NT benchmark H3K36me3 | 0.305 (± 0.004) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.004 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark H3K36me3 (fine-tuning) lit-genomics-20261011-ntbench-protocol-h3k36me3-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'H3K36me3' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark H3K4me1, fine-tuning (PEFT) Dataset: NT benchmark H3K4me1 | 0.228 (± 0.018) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.018 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark H3K4me1 (fine-tuning) lit-genomics-20261011-ntbench-protocol-h3k4me1-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'H3K4me1' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark H3K4me2, fine-tuning (PEFT) Dataset: NT benchmark H3K4me2 | 0.317 (± 0.021) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.021 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark H3K4me2 (fine-tuning) lit-genomics-20261011-ntbench-protocol-h3k4me2-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'H3K4me2' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark H3K4me3, fine-tuning (PEFT) Dataset: NT benchmark H3K4me3 | 0.452 (± 0.031) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.031 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark H3K4me3 (fine-tuning) lit-genomics-20261011-ntbench-protocol-h3k4me3-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'H3K4me3' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark H3K9ac, fine-tuning (PEFT) Dataset: NT benchmark H3K9ac | 0.329 (± 0.035) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.035 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark H3K9ac (fine-tuning) lit-genomics-20261011-ntbench-protocol-h3k9ac-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'H3K9ac' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark H3K9me3, fine-tuning (PEFT) Dataset: NT benchmark H3K9me3 | 0.088 (± 0.015) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.015 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark H3K9me3 (fine-tuning) lit-genomics-20261011-ntbench-protocol-h3k9me3-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'H3K9me3' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark H4K20me1, fine-tuning (PEFT) Dataset: NT benchmark H4K20me1 | 0.431 (± 0.012) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.012 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark H4K20me1 (fine-tuning) lit-genomics-20261011-ntbench-protocol-h4k20me1-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'H4K20me1' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark Promoter all, fine-tuning (PEFT) Dataset: NT benchmark Promoter all | 0.575 (± 0.01) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.01 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark Promoter all (fine-tuning) lit-genomics-20261011-ntbench-protocol-promoter-all-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'Promoter all' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark Promoter non-TATA, fine-tuning (PEFT) Dataset: NT benchmark Promoter non-TATA | 0.581 (± 0.025) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.025 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark Promoter non-TATA (fine-tuning) lit-genomics-20261011-ntbench-protocol-promoter-non-tata-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'Promoter non-TATA' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark Promoter TATA, fine-tuning (PEFT) Dataset: NT benchmark Promoter TATA | 0.39 (± 0.044) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.044 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark Promoter TATA (fine-tuning) lit-genomics-20261011-ntbench-protocol-promoter-tata-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'Promoter TATA' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark Splice acceptor, fine-tuning (PEFT) Dataset: NT benchmark Splice acceptor | 0.207 (± 0.031) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.031 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark Splice acceptor (fine-tuning) lit-genomics-20261011-ntbench-protocol-splice-acceptor-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'Splice acceptor' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark Splice donor, fine-tuning (PEFT) Dataset: NT benchmark Splice donor | 0.596 (± 0.057) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.057 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark Splice donor (fine-tuning) lit-genomics-20261011-ntbench-protocol-splice-donor-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'Splice donor' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark Splice site all, fine-tuning (PEFT) Dataset: NT benchmark Splice site all | 0.363 (± 0.038) MCC (median over 10 cross-validation folds) unitless · higher Uncertainty: SD 0.038 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized on NT benchmark Splice site all (fine-tuning) lit-genomics-20261011-ntbench-protocol-splice-site-all-fine-tuning Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 7, row 'NT 500M Randomly Initialized', column 'Splice site all' |
| Configuration: NT 500M Randomly Initialized, trained from scratch (NT benchmark) | Protocol: NT benchmark normalised summed performance (Supplementary Table 9) Dataset: NT benchmark, all 18 tasks | 0.355 MCC (mean over three task categories of median cross-validation MCC) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT 500M Randomly Initialized (Training from scratch) NT benchmark normalised summed performance lit-genomics-20261011-ntbench-protocol-normalised-summed-performance Aggregation: Not reported Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Supplementary Table 9, row 'NT 500M Randomly Initialized', approach 'Training from scratch', column 'Average performance' |
Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.
Use this configuration
How it works, versions and access
Strengths, limitations and unresolved questions
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.
0 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
1 source record and release history
- Nucleotide Transformer: Supplementary Information (Supplementary Tables 1-12) · Original source · Nature Methods 22, 287-297 (published online 2024-11-28); Supplementary Information PDF (MOESM1, 25 pages)
Technical metadata and extraction receipts
Stable ID: lit-genomics-20261011-ntbench-config-nt-500m-randomly-initialized-trained-from-scratch
- areas
- dna-genomes
- contexts
- research
- method types
- supervised_machine_learning
- reported name
- NT 500M Randomly Initialized
- foundation model eligible
- false
- parameters
- trained from scratch; hyperparameters in Supplementary Tables 1 and 8
- access reuse
- Not stated in the tables
- source locator
- Supplementary Tables 6, 7 and 9 row labels
- model identity note
- Randomly initialised NT architecture trained from scratch; a control, not a pretrained checkpoint
- missing metadata
- version: reason: unreported; note: Row label gives training data and parameter count only
- provenance note
- NT 500M Randomly Initialized as evaluated in the NT benchmark, trained from scratch.
Related records
- configuration of: Nucleotide Transformer
- system: NT 500M Randomly Initialized on NT benchmark Enhancer (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark Enhancer types (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark H2AFZ (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark H3K27ac (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark H3K27me3 (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark H3K36me3 (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark H3K4me1 (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark H3K4me2 (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark H3K4me3 (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark H3K9ac (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark H3K9me3 (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark H4K20me1 (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark Promoter all (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark Promoter non-TATA (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark Promoter TATA (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark Splice acceptor (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark Splice donor (fine-tuning)
- system: NT 500M Randomly Initialized on NT benchmark Splice site all (fine-tuning)
- system: NT 500M Randomly Initialized (Training from scratch) NT benchmark normalised summed performance