Protocol

Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3)

Enhancer-gene link prediction on the combined K562 CRISPR data used to train ENCODE-rE2G, with direct-effect weighting.

Overview

Enhancer-gene link prediction on the combined K562 CRISPR data used to train ENCODE-rE2G, with direct-effect weighting.

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

6 recorded evaluations, 18 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

6 evaluations · 18 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: ABC_A=DNase, C=Average ENCODE Hi-C (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.561 auprc fraction · higher Uncertainty: 95% CI 0.505742840168912 to 0.609499053593117 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ABC_A=DNase, C=Average ENCODE Hi-C on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 20 (D20:F20); Dataset 'Combined K562 (training)', Predictor 'ABC_A=DNase, C=Average ENCODE Hi-C', metric 'Weighted AUPRC'
Configuration: ABC_A=DNase, C=Average ENCODE Hi-C (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.453 precision fraction · higher Uncertainty: 95% CI 0.413472264469473 to 0.492071262218147 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ABC_A=DNase, C=Average ENCODE Hi-C on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 26 (D26:F26); Dataset 'Combined K562 (training)', Predictor 'ABC_A=DNase, C=Average ENCODE Hi-C', metric 'Weighted precision at threshold'
Configuration: ABC_A=DNase, C=Average ENCODE Hi-C (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.739 recall fraction · higher Uncertainty: 95% CI 0.69600194650038 to 0.782655613574707 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ABC_A=DNase, C=Average ENCODE Hi-C on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 32 (D32:F32); Dataset 'Combined K562 (training)', Predictor 'ABC_A=DNase, C=Average ENCODE Hi-C', metric 'Weighted recall at threshold'
Configuration: Distance to TSS (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.435 auprc fraction · higher Uncertainty: 95% CI 0.381294301517761 to 0.487138690854213 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Distance to TSS on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 24 (D24:F24); Dataset 'Combined K562 (training)', Predictor 'Distance to TSS', metric 'Weighted AUPRC'
Configuration: Distance to TSS (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.291 precision fraction · higher Uncertainty: 95% CI 0.262423650910323 to 0.319101531577943 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Distance to TSS on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 30 (D30:F30); Dataset 'Combined K562 (training)', Predictor 'Distance to TSS', metric 'Weighted precision at threshold'
Configuration: Distance to TSS (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.755 recall fraction · higher Uncertainty: 95% CI 0.712739109282484 to 0.795269968200388 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Distance to TSS on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 36 (D36:F36); Dataset 'Combined K562 (training)', Predictor 'Distance to TSS', metric 'Weighted recall at threshold'
Configuration: ENCODE-rE2G (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.666 auprc fraction · higher Uncertainty: 95% CI 0.614835111980482 to 0.711557617708767 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ENCODE-rE2G on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 21 (D21:F21); Dataset 'Combined K562 (training)', Predictor 'ENCODE-rE2G', metric 'Weighted AUPRC'
Configuration: ENCODE-rE2G (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.548 precision fraction · higher Uncertainty: 95% CI 0.502957160758294 to 0.58983971918054 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ENCODE-rE2G on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 27 (D27:F27); Dataset 'Combined K562 (training)', Predictor 'ENCODE-rE2G', metric 'Weighted precision at threshold'
Configuration: ENCODE-rE2G (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.73 recall fraction · higher Uncertainty: 95% CI 0.68634462 to 0.77396333 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ENCODE-rE2G on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 33 (D33:F33); Dataset 'Combined K562 (training)', Predictor 'ENCODE-rE2G', metric 'Weighted recall at threshold'
Configuration: Correlation_E-P DNase-seq signal (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.188 auprc fraction · higher Uncertainty: 95% CI 0.153700202257717 to 0.226562560550906 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Correlation_E-P DNase-seq signal on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 25 (D25:F25); Dataset 'Combined K562 (training)', Predictor 'Correlation_E-P DNase-seq signal', metric 'Weighted AUPRC'
Configuration: Correlation_E-P DNase-seq signal (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.0846 precision fraction · higher Uncertainty: 95% CI 0.0748657 to 0.09422633 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Correlation_E-P DNase-seq signal on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 31 (D31:F31); Dataset 'Combined K562 (training)', Predictor 'Correlation_E-P DNase-seq signal', metric 'Weighted precision at threshold'
Configuration: Correlation_E-P DNase-seq signal (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.71 recall fraction · higher Uncertainty: 95% CI 0.663954244027132 to 0.754126177061213 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Correlation_E-P DNase-seq signal on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 37 (D37:F37); Dataset 'Combined K562 (training)', Predictor 'Correlation_E-P DNase-seq signal', metric 'Weighted recall at threshold'
Configuration: EpiMap (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.311 auprc fraction · higher Uncertainty: 95% CI 0.261110315175289 to 0.361017256946356 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EpiMap on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 23 (D23:F23); Dataset 'Combined K562 (training)', Predictor 'EpiMap', metric 'Weighted AUPRC'
Configuration: EpiMap (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.187 precision fraction · higher Uncertainty: 95% CI 0.166855358972052 to 0.2065905167216 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EpiMap on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 29 (D29:F29); Dataset 'Combined K562 (training)', Predictor 'EpiMap', metric 'Weighted precision at threshold'
Configuration: EpiMap (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.714 recall fraction · higher Uncertainty: 95% CI 0.669049563420841 to 0.757391291403457 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EpiMap on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 35 (D35:F35); Dataset 'Combined K562 (training)', Predictor 'EpiMap', metric 'Weighted recall at threshold'
Configuration: EPIraction (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.446 auprc fraction · higher Uncertainty: 95% CI 0.39383868 to 0.500921087804116 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EPIraction on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 22 (D22:F22); Dataset 'Combined K562 (training)', Predictor 'EPIraction', metric 'Weighted AUPRC'
Configuration: EPIraction (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.381 precision fraction · higher Uncertainty: 95% CI 0.345706679909842 to 0.414719708782195 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EPIraction on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 28 (D28:F28); Dataset 'Combined K562 (training)', Predictor 'EPIraction', metric 'Weighted precision at threshold'
Configuration: EPIraction (Gschwind et al. 2026)	Protocol: Combined K562 CRISPR training pairs, weighted metrics (Gschwind et al. 2026 Supplementary Table 3) Dataset: MPRabc K562 CRISPRi benchmark	0.749 recall fraction · higher Uncertainty: 95% CI 0.705437423576133 to 0.791130313360929 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source EPIraction on combined K562 CRISPR training pairs regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted Aggregation: Not reported An encyclopedia of human enhancer-gene regulatory interactions; Gschwind et al. 2026, Supplementary Table 3 · Supplementary Table 3 'Held-out benchmarks', row 34 (D34:F34); Dataset 'Combined K562 (training)', Predictor 'EPIraction', metric 'Weighted recall at threshold'

Source checking is not independent reproduction. Release 2026-10-10-7fcc3e48a123.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

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: 6

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

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

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

Select an upstream conventional reference after reviewing the full protocol

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 2026-10-10-7fcc3e48a123. 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.

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 2026-10-10-7fcc3e48a123
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 2026-10-10-7fcc3e48a123 · Record review: source checked

2 source records and release history

An encyclopedia of human enhancer-gene regulatory interactions · Original source · Nature 657(8130):179, published online 2026-07-15; PMC13471189 full-text XML
Gschwind et al. 2026, Supplementary Table 3 · Original source · Supplementary_Table_3.xlsx in 41586_2026_10781_MOESM3_ESM.zip (folder 2023-11-20318B-s3) inside the Europe PMC supplementaryFiles zip

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: regulatory-variant-20261009-protocol-gschwind2026-k562-training-weighted

areas: dna-genomes
contexts: research
protocol: Overlap CRISPR-tested elements with each predictor's elements (matched by gene symbol; sum or max aggregation per Supplementary Table 1; unmatched pairs get the minimum score). Weighted precision-recall (yardstick 1.2.0), each pair weighted by its estimated probability of a direct cis-regulatory effect; weighted AUPRC, and weighted precision and recall at the predictor threshold, with 95% bootstrap intervals (10,000 iterations).
version: Supplementary Table 3 sheet 'Held-out benchmarks', Dataset 'Combined K562 (training)'
limitations: Developer comparison: ENCODE-rE2G and ABC are the authors' models, and EPIraction and EpiMap come from co-authors' groups; all six rows are author_reported, and the baselines were computed by the authors.; Whole-element CRISPR perturbation, not allele editing; a regulatory link does not establish a causal disease role.; Each pair is weighted by the authors' estimate of its probability of being a direct effect (Methods 'Calculating direct and indirect effect rates').; Precision and recall 'at threshold' use each predictor's threshold set at 70% recall on the combined K562 CRISPR data (Methods; Supplementary Table 3 legend).; Training data: ENCODE-rE2G was fitted on these pairs (scored by hold-one-chromosome-out cross-validation per Results), and every predictor's threshold was set at 70% recall on them, so recall at threshold is close to 0.7 by construction. Not held-out performance.; Same 10,356 pairs and 471 positives as the existing K562 mapping's dataset, with different weighting; do not pool.
source locator: Supplementary Table 3 'Held-out benchmarks' rows 20-37

Related records

uses data: MPRabc K562 CRISPRi benchmark
assessment: ABC_A=DNase, C=Average ENCODE Hi-C on combined K562 CRISPR training pairs
assessment: Distance to TSS on combined K562 CRISPR training pairs
assessment: ENCODE-rE2G on combined K562 CRISPR training pairs
assessment: Correlation_E-P DNase-seq signal on combined K562 CRISPR training pairs
assessment: EpiMap on combined K562 CRISPR training pairs
assessment: EPIraction on combined K562 CRISPR training pairs
assessed by: Select regulatory variants and genes for functional follow-up

Suggest a correction