Protocol

Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2)

Pseudo-bulk Pearson correlations between predicted and observed post-perturbation expression for unseen perturbations, in raw and control-subtracted space.

15 evaluations · 88 results

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.

15 recorded evaluations, 88 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

15 evaluations · 88 results. Different protocols are not a single leaderboard.

Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) · Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)

Sorted by Pearson (raw expression, pseudo-bulk, all genes) (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.

Tested configuration	Pearson (raw expression, pseudo-bulk, all genes)	Pearson (raw expression, top 20 DE genes (t-test, GEARS list))	Pearson delta	Pearson delta (top 20 DE genes (t-test, GEARS list))	Pearson delta (top 20 DE genes (t-test) excluding the CRISPR target gene(s))	Pearson delta (top 20 DE genes (Wilcoxon test))
RF_scElmo (Csendes et al. 2025)Evaluation	0.99 (best in column)	0.928	0.663 (best in column)	0.75 (best in column)	0.793 (best in column)	0.788 (best in column)
KNN_scGPT (Csendes et al. 2025)Evaluation	0.989	0.935 (best in column)	0.603	0.643	0.681	0.705
KNN_scElmo (Csendes et al. 2025)Evaluation	0.989	0.935	0.638	0.73	0.768	0.756
KNN_go (Csendes et al. 2025)Evaluation	0.989	0.931	0.618	0.681	0.717	0.711
EN_scFoundation (Csendes et al. 2025)Evaluation	0.988	0.93	0.6	0.685	0.723	0.704
EN_scGPT (Csendes et al. 2025)Evaluation	0.988	0.924	0.614	0.681	0.72	0.729
RF_scFoundation (Csendes et al. 2025)Evaluation	0.988	0.917	0.623	0.703	0.745	0.743
KNN_scFoundation (Csendes et al. 2025)Evaluation	0.988	0.931	0.576	0.629	0.658	0.677
RF_go (Csendes et al. 2025)Evaluation	0.988	0.916	0.586	0.669	0.702	0.688
RF_scGPT (Csendes et al. 2025)Evaluation	0.988	0.914	0.583	0.647	0.685	0.71
scGPT (Csendes et al. 2025)Evaluation	0.988	0.935	0.554	0.732	0.7	Not reported
EN_scElmo (Csendes et al. 2025)Evaluation	0.987	0.903	0.58	0.678	0.719	0.716
mean (Csendes et al. 2025)Evaluation	0.986	0.889	0.557	0.642	0.682	0.685
EN_go (Csendes et al. 2025)Evaluation	0.986	0.917	0.535	0.62	0.636	0.619
scFoundation (Csendes et al. 2025)Evaluation	0.966	0.924	0.459	0.705	0.71	Not reported

All 88 result rows with coverage, uncertainty and sources

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: EN_go (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.986 Pearson (raw expression, pseudo-bulk, all genes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_go on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell C21, row 'Norman / EN_go', column 'Pearson'
Configuration: EN_go (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.917 Pearson (raw expression, top 20 DE genes (t-test, GEARS list)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_go on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell D21, row 'Norman / EN_go', column 'Pearson DE'
Configuration: EN_go (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.535 Pearson delta unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_go on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell E21, row 'Norman / EN_go', column 'Pearson Delta'
Configuration: EN_go (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.62 Pearson delta (top 20 DE genes (t-test, GEARS list)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_go on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell F21, row 'Norman / EN_go', column 'Pearson Delta DE'
Configuration: EN_go (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.636 Pearson delta (top 20 DE genes (t-test) excluding the CRISPR target gene(s)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_go on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell H21, row 'Norman / EN_go', column 'Pearson Delta DE without KOd gene'
Configuration: EN_go (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.619 Pearson delta (top 20 DE genes (Wilcoxon test)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_go on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell G21, row 'Norman / EN_go', column 'Pearson Delta DE (based on Wilcoxon)'
Configuration: EN_scElmo (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.987 Pearson (raw expression, pseudo-bulk, all genes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scElmo on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell C22, row 'Norman / EN_scElmo', column 'Pearson'
Configuration: EN_scElmo (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.903 Pearson (raw expression, top 20 DE genes (t-test, GEARS list)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scElmo on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell D22, row 'Norman / EN_scElmo', column 'Pearson DE'
Configuration: EN_scElmo (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.58 Pearson delta unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scElmo on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell E22, row 'Norman / EN_scElmo', column 'Pearson Delta'
Configuration: EN_scElmo (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.678 Pearson delta (top 20 DE genes (t-test, GEARS list)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scElmo on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell F22, row 'Norman / EN_scElmo', column 'Pearson Delta DE'
Configuration: EN_scElmo (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.719 Pearson delta (top 20 DE genes (t-test) excluding the CRISPR target gene(s)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scElmo on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell H22, row 'Norman / EN_scElmo', column 'Pearson Delta DE without KOd gene'
Configuration: EN_scElmo (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.716 Pearson delta (top 20 DE genes (Wilcoxon test)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scElmo on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell G22, row 'Norman / EN_scElmo', column 'Pearson Delta DE (based on Wilcoxon)'
Configuration: EN_scFoundation (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.988 Pearson (raw expression, pseudo-bulk, all genes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scFoundation on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell C23, row 'Norman / EN_scFoundation', column 'Pearson'
Configuration: EN_scFoundation (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.93 Pearson (raw expression, top 20 DE genes (t-test, GEARS list)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scFoundation on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell D23, row 'Norman / EN_scFoundation', column 'Pearson DE'
Configuration: EN_scFoundation (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.6 Pearson delta unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scFoundation on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell E23, row 'Norman / EN_scFoundation', column 'Pearson Delta'
Configuration: EN_scFoundation (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.685 Pearson delta (top 20 DE genes (t-test, GEARS list)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scFoundation on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell F23, row 'Norman / EN_scFoundation', column 'Pearson Delta DE'
Configuration: EN_scFoundation (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.723 Pearson delta (top 20 DE genes (t-test) excluding the CRISPR target gene(s)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scFoundation on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell H23, row 'Norman / EN_scFoundation', column 'Pearson Delta DE without KOd gene'
Configuration: EN_scFoundation (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.704 Pearson delta (top 20 DE genes (Wilcoxon test)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scFoundation on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell G23, row 'Norman / EN_scFoundation', column 'Pearson Delta DE (based on Wilcoxon)'
Configuration: EN_scGPT (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.988 Pearson (raw expression, pseudo-bulk, all genes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scGPT on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell C24, row 'Norman / EN_scGPT', column 'Pearson'
Configuration: EN_scGPT (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.924 Pearson (raw expression, top 20 DE genes (t-test, GEARS list)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scGPT on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell D24, row 'Norman / EN_scGPT', column 'Pearson DE'
Configuration: EN_scGPT (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.614 Pearson delta unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scGPT on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell E24, row 'Norman / EN_scGPT', column 'Pearson Delta'
Configuration: EN_scGPT (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.681 Pearson delta (top 20 DE genes (t-test, GEARS list)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scGPT on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell F24, row 'Norman / EN_scGPT', column 'Pearson Delta DE'
Configuration: EN_scGPT (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.72 Pearson delta (top 20 DE genes (t-test) excluding the CRISPR target gene(s)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scGPT on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell H24, row 'Norman / EN_scGPT', column 'Pearson Delta DE without KOd gene'
Configuration: EN_scGPT (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.729 Pearson delta (top 20 DE genes (Wilcoxon test)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EN_scGPT on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell G24, row 'Norman / EN_scGPT', column 'Pearson Delta DE (based on Wilcoxon)'
Configuration: KNN_go (Csendes et al. 2025)	Protocol: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations: unseen-perturbation expression prediction (Csendes et al. 2025 Supplementary Table 2) Dataset: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)	0.989 Pearson (raw expression, pseudo-bulk, all genes) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source KNN_go on Norman (Csendes et al. 2025) perturbation-response-20261009-protocol-csendes2025-norman-pex Aggregation: Not reported Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Supplementary Table 2, cell C25, row 'Norman / KNN_go', column 'Pearson'

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations: 13
External evaluations: 2

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

No-change prediction under matched control conditions

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Training-only mean-effect or linear prediction

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-11-02-a7f03c9e55a5. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

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 2026-11-02-a7f03c9e55a5
Property and statement	Original source and location	Review and provenance

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

How to read the evidence

Sources and history

Release 2026-11-02-a7f03c9e55a5 · Record review: source checked

2 source records and release history

Benchmarking foundation cell models for post-perturbation RNA-seq prediction · Original source · BMC Genomics 26:393, published 2025-04-23; PMC12016270 full-text XML
Csendes et al. 2025, Supplementary Material 4 (Supplementary Tables 1-3) · Original source · 12864_2025_11600_MOESM4_ESM.xlsx from the Europe PMC supplementary bundle (hash is of the workbook; the bundle zip is rebuilt per request)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: perturbation-response-20261009-protocol-csendes2025-norman-pex

areas: cells-tissues
contexts: research
protocol: Single-cell predictions are averaged per perturbation and compared with the observed pseudo-bulk profile. Pearson: raw expression. Pearson Delta: perturbed minus control expression. DE variants use the top 20 differentially expressed genes from the GEARS publication (t-test), the top 20 by Wilcoxon test, or the top 20 with the CRISPR target gene(s) removed.
version: Supplementary Table 2 rows for 'Norman'
denominator: 116
source locator: Results 'Benchmarking of post-perturbation RNA-seq prediction methods' paragraph 3; Methods 'Model evaluation'
limitations: One split per dataset; no seeds or spread printed.; Raw-expression Pearson is near 1 for every model and the authors do not consider it meaningful (Results paragraph 5).; Low perturbation-specific variance in these datasets limits how well they separate models (Results 'Limited perturbation diversity biases benchmarking outcomes').
missing metadata: uncertainty: reason: unreported; note: Single values per model and dataset

Related records

uses data: Norman et al. 2019 Perturb-seq, K562 CRISPRa single and double perturbations (GEARS processing, Csendes et al. 2025)
subject: norman_test_subgroups: perturbation-response-20261009-protocol-csendes2025-norman-pex
subject: pearson_delta_de_target_gene: perturbation-response-20261009-protocol-csendes2025-norman-pex
assessment: EN_go on Norman (Csendes et al. 2025)
assessment: EN_scElmo on Norman (Csendes et al. 2025)
assessment: EN_scFoundation on Norman (Csendes et al. 2025)
assessment: EN_scGPT on Norman (Csendes et al. 2025)
assessment: KNN_go on Norman (Csendes et al. 2025)
assessment: KNN_scElmo on Norman (Csendes et al. 2025)
assessment: KNN_scFoundation on Norman (Csendes et al. 2025)
assessment: KNN_scGPT on Norman (Csendes et al. 2025)
assessment: mean on Norman (Csendes et al. 2025)
assessment: RF_go on Norman (Csendes et al. 2025)
assessment: RF_scElmo on Norman (Csendes et al. 2025)
assessment: RF_scFoundation on Norman (Csendes et al. 2025)
assessment: RF_scGPT on Norman (Csendes et al. 2025)
assessment: scFoundation on Norman (Csendes et al. 2025)
assessment: scGPT on Norman (Csendes et al. 2025)
assessed by: Assess models for genetic perturbation experiments

Suggest a correction