| Comparison: adaptation Supervised logistic regression probe, class weight inversely proportional to frequency, L2 strength chosen by cross-validation (scikit-learn) Context-only references | DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) Original source ↗ No field-specific location recorded Version: PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914 Retrieved: 2026-11-16T00:29:00Z | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.adaptation Source artifact SHA-256: 8ff2184c07f5e6807af0b9d5103d669e1920e735ab5a4b1ea856c070077ae1e0 Hash scope: Hash scope not separately documented; inspect source record Format: JATS XML |
|---|
| Comparison: aggregation Per class; the paper quotes only the highest and the lowest Context-only references | DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) Original source ↗ No field-specific location recorded Version: PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914 Retrieved: 2026-11-16T00:29:00Z | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.aggregation Source artifact SHA-256: 8ff2184c07f5e6807af0b9d5103d669e1920e735ab5a4b1ea856c070077ae1e0 Hash scope: Hash scope not separately documented; inspect source record Format: JATS XML |
|---|
| Comparison: budget Not reported Context-only references | DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) Original source ↗ No field-specific location recorded Version: PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914 Retrieved: 2026-11-16T00:29:00Z | missing or unspecified No individual claim review recorded author reported Audit detailsField: attributes.comparison.budget Source artifact SHA-256: 8ff2184c07f5e6807af0b9d5103d669e1920e735ab5a4b1ea856c070077ae1e0 Hash scope: Hash scope not separately documented; inspect source record Format: JATS XML |
|---|
| Comparison: dataset version TAIR10.1 (GCF_000001735.4), EnsemblPlants gene annotation Context-only references | DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) Original source ↗ No field-specific location recorded Version: PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914 Retrieved: 2026-11-16T00:29:00Z | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.dataset_version Source artifact SHA-256: 8ff2184c07f5e6807af0b9d5103d669e1920e735ab5a4b1ea856c070077ae1e0 Hash scope: Hash scope not separately documented; inspect source record Format: JATS XML |
|---|
| Comparison: inputs GPN embeddings averaged over each 100 bp window, averaged between strands and standardised Context-only references | DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) Original source ↗ No field-specific location recorded Version: PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914 Retrieved: 2026-11-16T00:29:00Z | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.inputs Source artifact SHA-256: 8ff2184c07f5e6807af0b9d5103d669e1920e735ab5a4b1ea856c070077ae1e0 Hash scope: Hash scope not separately documented; inspect source record Format: JATS XML |
|---|
| Comparison: metric implementation Not reported Context-only references | DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) Original source ↗ No field-specific location recorded Version: PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914 Retrieved: 2026-11-16T00:29:00Z | missing or unspecified No individual claim review recorded author reported Audit detailsField: attributes.comparison.metric_implementation Source artifact SHA-256: 8ff2184c07f5e6807af0b9d5103d669e1920e735ab5a4b1ea856c070077ae1e0 Hash scope: Hash scope not separately documented; inspect source record Format: JATS XML |
|---|
| Comparison: population Non-overlapping 100 bp windows with unambiguous gene region annotation Context-only references | DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) Original source ↗ No field-specific location recorded Version: PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914 Retrieved: 2026-11-16T00:29:00Z | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.population Source artifact SHA-256: 8ff2184c07f5e6807af0b9d5103d669e1920e735ab5a4b1ea856c070077ae1e0 Hash scope: Hash scope not separately documented; inspect source record Format: JATS XML |
|---|
| Comparison: protocol id gpn-paper-20261116-protocol-gene-region-classification Context-only references | DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) Original source ↗ No field-specific location recorded Version: PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914 Retrieved: 2026-11-16T00:29:00Z | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.protocol_id Source artifact SHA-256: 8ff2184c07f5e6807af0b9d5103d669e1920e735ab5a4b1ea856c070077ae1e0 Hash scope: Hash scope not separately documented; inspect source record Format: JATS XML |
|---|
| Comparison: split Leave one chromosome out: each chromosome predicted by a model trained on the remaining chromosomes Context-only references | DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) Original source ↗ No field-specific location recorded Version: PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914 Retrieved: 2026-11-16T00:29:00Z | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.comparison.split Source artifact SHA-256: 8ff2184c07f5e6807af0b9d5103d669e1920e735ab5a4b1ea856c070077ae1e0 Hash scope: Hash scope not separately documented; inspect source record Format: JATS XML |
|---|
Limitations2 values- Reported by the authors of the model, on an evaluation they designed and ran.
- Only two of the per-class accuracies are printed. The confusion matrix of Figure 2B holds the rest and prints no values.
Context-only references | DNA language models are powerful predictors of genome-wide variant effects (PNAS 2023) Original source ↗ No field-specific location recorded Version: PNAS 120(44) e2311219120, published 26 October 2023; Europe PMC full text JATS XML of PMC10622914 Retrieved: 2026-11-16T00:29:00Z | not individually reviewed No individual claim review recorded author reported Audit detailsField: attributes.limitations Source artifact SHA-256: 8ff2184c07f5e6807af0b9d5103d669e1920e735ab5a4b1ea856c070077ae1e0 Hash scope: Hash scope not separately documented; inspect source record Format: JATS XML |
|---|