Configuration

GEARS with MPE acquisition

GEARS retrained each round on a bulk viability screen, with the next pairs chosen by MPE acquisition.

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

1 evaluation · 5 results. Different protocols are not a single leaderboard.

Protocol: Retrospective active learning on a fully measured two-gene CRISPR viability screen: top-200 gene pairs found by round 4 · Dataset: Norman et al. 2019 combinatorial CRISPRa in K562, gene-level viability (as processed by Qin et al. 2025)

Sorted by True positives (the screen's 200 strongest measured gene pairs found among the 200 strongest measured-plus-predicted values, round 0 of active learning) (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	True positives (the screen's 200 strongest measured gene pairs found among the 200 strongest measured-plus-predicted values, round 0 of active learning)	True positives (the screen's 200 strongest measured gene pairs found among the 200 strongest measured-plus-predicted values, round 1 of active learning)	True positives (the screen's 200 strongest measured gene pairs found among the 200 strongest measured-plus-predicted values, round 2 of active learning)	True positives (the screen's 200 strongest measured gene pairs found among the 200 strongest measured-plus-predicted values, round 3 of active learning)	True positives (the screen's 200 strongest measured gene pairs found among the 200 strongest measured-plus-predicted values, round 4 of active learning)
GEARS with MPE acquisitionEvaluation	42.0 (2.1)	80.0 (1.5)	91.7 (0.7)	99.7 (0.3)	109.3 (1.5)

All 5 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: GEARS with MPE acquisition	Protocol: Retrospective active learning on a fully measured two-gene CRISPR viability screen: top-200 gene pairs found by round 4 Dataset: Norman et al. 2019 combinatorial CRISPRa in K562, gene-level viability (as processed by Qin et al. 2025)	42.0 (2.1) True positives (the screen's 200 strongest measured gene pairs found among the 200 strongest measured-plus-predicted values, round 0 of active learning) count · higher Uncertainty: SE 2.1. Caption: error is SE across three cross-fold replicates Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GEARS with MPE acquisition on Norman (Table 7, NAIAD, RECOVER and GEARS over rounds on Norman) pheno-20261022-qin2025-protocol-al-top200 Aggregation: Not reported Qin et al. 2025, Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations (ICML 2025, PMLR 267) · Table 7, row "GEARS MPE", column "Round 0"
Configuration: GEARS with MPE acquisition	Protocol: Retrospective active learning on a fully measured two-gene CRISPR viability screen: top-200 gene pairs found by round 4 Dataset: Norman et al. 2019 combinatorial CRISPRa in K562, gene-level viability (as processed by Qin et al. 2025)	80.0 (1.5) True positives (the screen's 200 strongest measured gene pairs found among the 200 strongest measured-plus-predicted values, round 1 of active learning) count · higher Uncertainty: SE 1.5. Caption: error is SE across three cross-fold replicates Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GEARS with MPE acquisition on Norman (Table 7, NAIAD, RECOVER and GEARS over rounds on Norman) pheno-20261022-qin2025-protocol-al-top200 Aggregation: Not reported Qin et al. 2025, Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations (ICML 2025, PMLR 267) · Table 7, row "GEARS MPE", column "Round 1"
Configuration: GEARS with MPE acquisition	Protocol: Retrospective active learning on a fully measured two-gene CRISPR viability screen: top-200 gene pairs found by round 4 Dataset: Norman et al. 2019 combinatorial CRISPRa in K562, gene-level viability (as processed by Qin et al. 2025)	91.7 (0.7) True positives (the screen's 200 strongest measured gene pairs found among the 200 strongest measured-plus-predicted values, round 2 of active learning) count · higher Uncertainty: SE 0.7. Caption: error is SE across three cross-fold replicates Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GEARS with MPE acquisition on Norman (Table 7, NAIAD, RECOVER and GEARS over rounds on Norman) pheno-20261022-qin2025-protocol-al-top200 Aggregation: Not reported Qin et al. 2025, Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations (ICML 2025, PMLR 267) · Table 7, row "GEARS MPE", column "Round 2"
Configuration: GEARS with MPE acquisition	Protocol: Retrospective active learning on a fully measured two-gene CRISPR viability screen: top-200 gene pairs found by round 4 Dataset: Norman et al. 2019 combinatorial CRISPRa in K562, gene-level viability (as processed by Qin et al. 2025)	99.7 (0.3) True positives (the screen's 200 strongest measured gene pairs found among the 200 strongest measured-plus-predicted values, round 3 of active learning) count · higher Uncertainty: SE 0.3. Caption: error is SE across three cross-fold replicates Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GEARS with MPE acquisition on Norman (Table 7, NAIAD, RECOVER and GEARS over rounds on Norman) pheno-20261022-qin2025-protocol-al-top200 Aggregation: Not reported Qin et al. 2025, Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations (ICML 2025, PMLR 267) · Table 7, row "GEARS MPE", column "Round 3"
Configuration: GEARS with MPE acquisition	Protocol: Retrospective active learning on a fully measured two-gene CRISPR viability screen: top-200 gene pairs found by round 4 Dataset: Norman et al. 2019 combinatorial CRISPRa in K562, gene-level viability (as processed by Qin et al. 2025)	109.3 (1.5) True positives (the screen's 200 strongest measured gene pairs found among the 200 strongest measured-plus-predicted values, round 4 of active learning) count · higher Uncertainty: SE 1.5. Caption: error is SE across three cross-fold replicates Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GEARS with MPE acquisition on Norman (Table 7, NAIAD, RECOVER and GEARS over rounds on Norman) pheno-20261022-qin2025-protocol-al-top200 Aggregation: Not reported Qin et al. 2025, Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations (ICML 2025, PMLR 267) · Table 7, row "GEARS MPE", column "Round 4"

Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

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 2026-10-23-5347695500ed
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 2026-10-23-5347695500ed · Record review: source checked

1 source record and release history

Qin et al. 2025, Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations (ICML 2025, PMLR 267) · Original source · Proceedings of the 42nd ICML, PMLR 267:50363-50383, 2025; proceedings PDF qin25g.pdf. The arXiv preprint 2411.12010 was not read.

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: pheno-20261022-qin2025-config-gears-mpe

areas: cells-tissues
contexts: research
method types: specialist
reported name: GEARS, MPE
configuration type: reported_configuration
foundation model eligible: false
version: As run by Qin et al. 2025 (PMLR 267); no release or commit is printed
access reuse: Run by Qin et al. 2025; their code for this comparator is not separately identified
parameters: GEARS with the original settings for cell-viability prediction; for bulk screens without single-cell data, synthetic Perturb-seq matrices with each gene drawn from N(0, 1) were generated (Appendix B); package default hyperparameters (Appendix F).
source locator: Table 7 row 'GEARS MPE'; Appendix B 'GEARS'
provenance note: Configuration run by Qin et al. 2025 in this comparison.
review: method: source-hash-verification; scope-review; reviewer: claude; reviewer note: Claude (Opus 5.5) review agent, independent of the extraction agent; no human review claimed; date: 2026-10-22; artifact sha256: 983b2da8aed78f0aced27053301c15f0f67ebd0fac706435bb6800e309dd64eb; retrieval url: https://raw.githubusercontent.com/mlresearch/v267/main/assets/qin25g/qin25g.pdf; method note: Re-hashed the PDF in the scratchpad (SHA-256 matches the source record). Read the cited sections in the pdftotext layer of the pinned PDF.; note: Fields checked against the cited locator; nothing found that the source does not state.
selection: Maximum Predicted Effect acquisition: pairs with the highest absolute ensemble-mean prediction (Appendix C.2)

Related records

configuration of: GEARS
system: GEARS with MPE acquisition on Norman (Table 7, NAIAD, RECOVER and GEARS over rounds on Norman)

Suggest a correction