Configuration

primateAI_b (Cubuk et al. 2021)

primateAI scores dichotomised at the cited threshold.

Overview

primateAI scores dichotomised at the cited threshold.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

2 evaluations · 6 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: primateAI_b (Cubuk et al. 2021)	Protocol: BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021) Dataset: BRCA1 functional truth set: 1641 missense variants classed deleterious or tolerated by HAP1 cell survival after saturation genome editing	1.2 benignity-likelihood-ratio unitless · higher Uncertainty: Sources conflict: Printed interval (.928-1.56) has the same log-scale width as this row's positive likelihood ratio interval and is not consistent with the Supplementary Table 6 counts; kept in printed_source_cell only. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source primateAI_b on the BRCA1 functional truth set (Cubuk et al. 2021) brca-20261009-protocol-cubuk2021-brca1 Aggregation: Not reported Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx) · Supplementary Table 9 (sheet 'SupTable9_Likelihood_Ratios'), G42; tool 'primateAI_b'; column 'BRCA1_negative_LR'
Configuration: primateAI_b (Cubuk et al. 2021)	Protocol: BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021) Dataset: BRCA1 functional truth set: 1641 missense variants classed deleterious or tolerated by HAP1 cell survival after saturation genome editing	283 false-negative-count count · lower Uncertainty: Not applicable: Count Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source primateAI_b on the BRCA1 functional truth set (Cubuk et al. 2021) brca-20261009-protocol-cubuk2021-brca1 Aggregation: Not reported Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx) · Supplementary Table 6 (sheet 'SupTable6_Tool_Counts'), L58; tool 'primateAI_b'; column 'BRCA1_FN'
Configuration: primateAI_b (Cubuk et al. 2021)	Protocol: BRCA1 functional truth set, binary in silico calls (Cubuk et al. 2021) Dataset: BRCA1 functional truth set: 1641 missense variants classed deleterious or tolerated by HAP1 cell survival after saturation genome editing	2.92 likelihood-ratio unitless · higher Uncertainty: CI 2.25 to 3.79. Interval level and method not printed. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source primateAI_b on the BRCA1 functional truth set (Cubuk et al. 2021) brca-20261009-protocol-cubuk2021-brca1 Aggregation: Not reported Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx) · Supplementary Table 9 (sheet 'SupTable9_Likelihood_Ratios'), F42; tool 'primateAI_b'; column 'BRCA1_positive_LR'
Configuration: primateAI_b (Cubuk et al. 2021)	Protocol: BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021) Dataset: BRCA2 functional truth set: 188 missense variants classed deleterious or tolerated by Homology-directed repair	1.23 benignity-likelihood-ratio unitless · higher Uncertainty: Sources conflict: Printed interval (.425-3.60) has the same log-scale width as this row's positive likelihood ratio interval and is not consistent with the Supplementary Table 6 counts; kept in printed_source_cell only. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source primateAI_b on the BRCA2 functional truth set (Cubuk et al. 2021) brca-20261009-protocol-cubuk2021-brca2 Aggregation: Not reported Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx) · Supplementary Table 9 (sheet 'SupTable9_Likelihood_Ratios'), I42; tool 'primateAI_b'; column 'BRCA2_negative_LR'
Configuration: primateAI_b (Cubuk et al. 2021)	Protocol: BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021) Dataset: BRCA2 functional truth set: 188 missense variants classed deleterious or tolerated by Homology-directed repair	50 false-negative-count count · lower Uncertainty: Not applicable: Count Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source primateAI_b on the BRCA2 functional truth set (Cubuk et al. 2021) brca-20261009-protocol-cubuk2021-brca2 Aggregation: Not reported Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx) · Supplementary Table 6 (sheet 'SupTable6_Tool_Counts'), U58; tool 'primateAI_b'; column 'BRCA2_FN'
Configuration: primateAI_b (Cubuk et al. 2021)	Protocol: BRCA2 functional truth set, binary in silico calls (Cubuk et al. 2021) Dataset: BRCA2 functional truth set: 188 missense variants classed deleterious or tolerated by Homology-directed repair	6.78 likelihood-ratio unitless · higher Uncertainty: CI 2.32 to 19.7. Interval level and method not printed. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source primateAI_b on the BRCA2 functional truth set (Cubuk et al. 2021) brca-20261009-protocol-cubuk2021-brca2 Aggregation: Not reported Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes; Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx) · Supplementary Table 9 (sheet 'SupTable9_Likelihood_Ratios'), H42; tool 'primateAI_b'; column 'BRCA2_positive_LR'

Source checking is not independent reproduction. Release 2026-10-10-84341e0b121f.

Use this model

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

Claims, original sources and review scope · Release 2026-10-10-84341e0b121f
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-10-84341e0b121f · Record review: source checked

2 source records and release history

Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes · Original source · Genetics in Medicine 23(11):2096, published 2021-07-06; PMC8553612 full-text XML
Cubuk et al. 2021, Supplementary tables 1-13 (41436_2021_1265_MOESM3_ESM.xlsx) · Original source · 41436_2021_1265_MOESM3_ESM.xlsx

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: brca-20261009-config-cubuk2021-primateai-b

areas: dna-genomes
contexts: clinical_research
method types: supervised_machine_learning
reported name: primateAI_b
foundation model eligible: false
protocol: Discretisation: TOL (<0.7); DEL (>=0.7)
source locator: Supplementary Table 5 row 59 ('primateAI', 'primateAI_b')
missing metadata: version: reason: unreported; note: Score source: Precomputed scores (https://basespace.illumina.com)

Related records

configuration of: PrimateAI
system: primateAI_b on the BRCA1 functional truth set (Cubuk et al. 2021)
system: primateAI_b on the BRCA2 functional truth set (Cubuk et al. 2021)

Suggest a correction