Protocol
Retrospective active learning on a fully measured two-gene CRISPR viability screen: top-200 gene pairs found by round 4
Starting from a uniformly sampled seed set shared by all acquisition functions, a model ensemble is retrained each round on the measured pairs acquired so far and an acquisition function picks the next batch; the score counts how many of the screen's 200 strongest measured pairs are among the 200 strongest of the measured-plus-predicted values.
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.
5 recorded evaluations, 152 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
5 evaluations · 152 results. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.
Methods and evaluation design
Procedure, tasks and evaluated configurations
Recorded evaluations
Each evaluation records what was tested and under which conditions.
- NAIAD with MPE acquisition on Horlbeck Jurkat (Tables 2 and 3, acquisition functions with NAIAD)
- NAIAD with MPE acquisition on Horlbeck K562 (Tables 2 and 3, acquisition functions with NAIAD)
- NAIAD with MPE acquisition on Norman (Tables 2 and 3, acquisition functions with NAIAD)
- NAIAD with MPE acquisition on Simpson (Tables 2 and 3, acquisition functions with NAIAD)
- NAIAD with UCB acquisition on Horlbeck Jurkat (Tables 2 and 3, acquisition functions with NAIAD)
- NAIAD with UCB acquisition on Horlbeck K562 (Tables 2 and 3, acquisition functions with NAIAD)
- NAIAD with UCB acquisition on Norman (Tables 2 and 3, acquisition functions with NAIAD)
- NAIAD with UCB acquisition on Simpson (Tables 2 and 3, acquisition functions with NAIAD)
- NAIAD with Uncertainty acquisition on Horlbeck Jurkat (Tables 2 and 3, acquisition functions with NAIAD)
- NAIAD with Uncertainty acquisition on Horlbeck K562 (Tables 2 and 3, acquisition functions with NAIAD)
- NAIAD with Uncertainty acquisition on Norman (Tables 2 and 3, acquisition functions with NAIAD)
- NAIAD with Uncertainty acquisition on Simpson (Tables 2 and 3, acquisition functions with NAIAD)
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
- 106
- External evaluations
- 14
Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.
Null control
Proposed control: requires review
Unintegrated representation using protocol preprocessing
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
Protocol-specific conventional integration method
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 2026-10-23-5347695500ed. 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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
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.
Technical metadata and extraction receipts
Stable ID: pheno-20261022-qin2025-protocol-al-top200
- areas
- cells-tissues
- contexts
- research
- protocol
- Round 0 trains on a uniformly sampled seed set (100 pairs for Norman, 500 for Simpson and both Horlbeck screens). In each of 4 further rounds the trained ensemble predicts every unmeasured pair, the acquisition function selects 100 (Norman) or 500 (others) more pairs whose measured values are revealed from the screen, and the model is retrained. Acquisition functions: Uniform, Maximum Predicted Effect (MPE), Upper Confidence Bound (UCB, residual from a linear model plus ensemble standard deviation, kappa = 1), Uncertainty (ensemble standard deviation) and Mean-UCB (alpha times ensemble mean plus beta times ensemble standard deviation).
- procedure
- Fraction Discovered (Appendix D): after training in round i, predictions for all unseen pairs are concatenated with the measured values of the seen pairs to form X_i; X_i,P is the top P values of X_i, Y_i,P the top P measured values across all samples, and P_i = |X_i,P ∩ Y_i,P|. Tables 2, 4, 5, 7 and 8 print P_i at P = 200; Table 3 prints the marginal gain (P_4 - P_0)/4.
- version
- Qin et al. 2025, PMLR 267, Sections 4.3 and 5.3, Appendices C and D
- metric
- true-positive-count
- metric direction
- higher
- unit
- count
- unit detail
- gene pairs, out of the 200 strongest measured pairs
- metric definition
- P_200 = number of the 200 strongest measured gene pairs in the whole screen that are among the 200 strongest values of the combined set of measured (acquired) and predicted (unacquired) pairs. Pairs counted as found need not have been measured.
- denominator
- 200
- task
- Choose which two-gene combinations to measure next so that the strongest combinations are identified with few measurements
- selection
- Candidate pool is every pair in the screen; the seed set is drawn uniformly and shared by all acquisition functions
- replicates
- Tables 4, 5, 7 and 8: three cross-fold replicates with standard error printed. Tables 2 and 3: not stated.
- random seeds
- Not stated
- scope note
- Retrospective replay over already-measured screens; no new experiment is run. 'Strongest' is not defined by sign: Appendix C.2 says MPE selects the highest absolute predicted effects, and Appendix D says top P values.
- limitations
- A pair counts as discovered when it is in the top 200 of the measured-plus-predicted ranking, so the count mixes pairs actually measured with pairs only predicted; it is not the number of strong pairs among those tested.; Ground truth is the 200 strongest measured viability effects in the same screen, not an independently confirmed phenotype or a significance threshold; the 200 are 3.2% of Norman's 6,328 pairs and 0.14% to 0.21% of the other screens.; The measurement budget differs by screen (500 pairs of 6,328 for Norman; 2,500 of 95,703 to 147,658 for the others).; Single-gene effects of every gene are available to the model throughout.; All values come from the NAIAD authors, who also adapted RECOVER and GEARS to this setting.; The paper does not define a cross-fold replicate for the active-learning experiments.
- source locator
- Section 4.3; Section 5.3; Appendix C; Appendix D 'Fraction Discovered' and 'Marginal Gain'
- publication status
- peer_reviewed
- 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.
Related records
- uses data: Norman et al. 2019 combinatorial CRISPRa in K562, gene-level viability (as processed by Qin et al. 2025)
- uses data: Simpson et al. 2023 combinatorial CRISPRi in K562, gene-level viability (as processed by Qin et al. 2025)
- uses data: Horlbeck et al. 2018 combinatorial CRISPRi in K562, gene-level viability (as processed by Qin et al. 2025)
- uses data: Horlbeck et al. 2018 combinatorial CRISPRi in Jurkat T cells, gene-level viability (as processed by Qin et al. 2025)
- assessment: NAIAD with MPE acquisition on Horlbeck Jurkat (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with MPE acquisition on Horlbeck K562 (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with MPE acquisition on Norman (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with MPE acquisition on Simpson (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with UCB acquisition on Horlbeck Jurkat (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with UCB acquisition on Horlbeck K562 (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with UCB acquisition on Norman (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with UCB acquisition on Simpson (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with Uncertainty acquisition on Horlbeck Jurkat (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with Uncertainty acquisition on Horlbeck K562 (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with Uncertainty acquisition on Norman (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with Uncertainty acquisition on Simpson (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with Uniform acquisition on Horlbeck Jurkat (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with Uniform acquisition on Horlbeck K562 (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with Uniform acquisition on Norman (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with Uniform acquisition on Simpson (Tables 2 and 3, acquisition functions with NAIAD)
- assessment: NAIAD with MPE acquisition on Horlbeck Jurkat (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with MPE acquisition on Horlbeck K562 (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with MPE acquisition on Norman (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with MPE acquisition on Simpson (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with UCB acquisition on Horlbeck Jurkat (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with UCB acquisition on Horlbeck K562 (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with UCB acquisition on Norman (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with UCB acquisition on Simpson (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with Uniform acquisition on Horlbeck Jurkat (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with Uniform acquisition on Horlbeck K562 (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with Uniform acquisition on Norman (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with Uniform acquisition on Simpson (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with MPE acquisition on Horlbeck Jurkat (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with MPE acquisition on Horlbeck K562 (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with MPE acquisition on Norman (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with MPE acquisition on Simpson (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with UCB acquisition on Horlbeck Jurkat (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with UCB acquisition on Horlbeck K562 (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with UCB acquisition on Norman (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with UCB acquisition on Simpson (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with Uniform acquisition on Horlbeck Jurkat (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with Uniform acquisition on Horlbeck K562 (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with Uniform acquisition on Norman (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: RECOVER (gene adaptation) with Uniform acquisition on Simpson (Table 4, NAIAD against RECOVER by acquisition function)
- assessment: NAIAD with MPE acquisition, ensemble of 1 on Horlbeck Jurkat (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 1 on Horlbeck K562 (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 1 on Norman (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 1 on Simpson (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 3 on Horlbeck Jurkat (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 3 on Horlbeck K562 (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 3 on Norman (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 3 on Simpson (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 5 on Horlbeck Jurkat (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 5 on Horlbeck K562 (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 5 on Norman (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 5 on Simpson (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 7 on Horlbeck Jurkat (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 7 on Horlbeck K562 (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 7 on Norman (Table 5, NAIAD ensemble size)
- assessment: NAIAD with MPE acquisition, ensemble of 7 on Simpson (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 1 on Horlbeck Jurkat (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 1 on Horlbeck K562 (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 1 on Norman (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 1 on Simpson (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 3 on Horlbeck Jurkat (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 3 on Horlbeck K562 (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 3 on Norman (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 3 on Simpson (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 5 on Horlbeck Jurkat (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 5 on Horlbeck K562 (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 5 on Norman (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 5 on Simpson (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 7 on Horlbeck Jurkat (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 7 on Horlbeck K562 (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 7 on Norman (Table 5, NAIAD ensemble size)
- assessment: NAIAD with Uniform acquisition, ensemble of 7 on Simpson (Table 5, NAIAD ensemble size)
- assessment: GEARS with MPE acquisition on Norman (Table 7, NAIAD, RECOVER and GEARS over rounds on Norman)
- assessment: NAIAD with MPE acquisition on Norman (Table 7, NAIAD, RECOVER and GEARS over rounds on Norman)
- assessment: NAIAD with Uniform acquisition on Norman (Table 7, NAIAD, RECOVER and GEARS over rounds on Norman)
- assessment: RECOVER (gene adaptation) with MPE acquisition on Norman (Table 7, NAIAD, RECOVER and GEARS over rounds on Norman)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.25 on Horlbeck Jurkat (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.25 on Horlbeck K562 (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.25 on Norman (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.25 on Simpson (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.5 on Horlbeck Jurkat (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.5 on Horlbeck K562 (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.5 on Norman (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.5 on Simpson (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.75 on Horlbeck Jurkat (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.75 on Horlbeck K562 (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.75 on Norman (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0.75 on Simpson (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0 on Horlbeck Jurkat (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0 on Horlbeck K562 (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0 on Norman (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 0 on Simpson (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 1.5 on Horlbeck Jurkat (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 1.5 on Horlbeck K562 (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 1.5 on Norman (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 1.5 on Simpson (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 1 on Horlbeck Jurkat (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 1 on Horlbeck K562 (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 1 on Norman (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 1 on Simpson (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 10 on Horlbeck Jurkat (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 10 on Horlbeck K562 (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 10 on Norman (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 10 on Simpson (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 2 on Horlbeck Jurkat (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 2 on Horlbeck K562 (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 2 on Norman (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 2 on Simpson (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 25 on Horlbeck Jurkat (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 25 on Horlbeck K562 (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 25 on Norman (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 25 on Simpson (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 5 on Horlbeck Jurkat (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 5 on Horlbeck K562 (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 5 on Norman (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Mean-UCB acquisition, beta = 5 on Simpson (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Uniform acquisition on Horlbeck Jurkat (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Uniform acquisition on Horlbeck K562 (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Uniform acquisition on Norman (Table 8, Mean-UCB beta with NAIAD)
- assessment: NAIAD with Uniform acquisition on Simpson (Table 8, Mean-UCB beta with NAIAD)
- assessed by: Select perturbations for a defined cellular response