NAIAD
Active-learning framework that predicts the phenotype of a two-gene perturbation from over-parameterised single-gene effects plus learned gene embeddings whose size grows with the training set, and uses an ensemble of these models with an acquisition function to choose the next combinations to measure.
Results are recorded on linked configurations and versions of this method. Their settings and evaluations are kept separate below.
Results on linked records
This method has no results of its own in this release. 23 linked records have results. They are not assigned to the underlying method: each record keeps its own settings and evaluations, and its scores are on its own page.
- NAIAD with Mean-UCB acquisition, beta = 0 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Mean-UCB acquisition, beta = 0.25 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Mean-UCB acquisition, beta = 0.5 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Mean-UCB acquisition, beta = 0.75 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Mean-UCB acquisition, beta = 1 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Mean-UCB acquisition, beta = 1.5 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Mean-UCB acquisition, beta = 10 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Mean-UCB acquisition, beta = 2 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Mean-UCB acquisition, beta = 25 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Mean-UCB acquisition, beta = 5 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with MPE acquisition Configuration · configuration of this method · 3 evaluations · 17 results
- NAIAD with MPE acquisition, ensemble of 1 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with MPE acquisition, ensemble of 3 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with MPE acquisition, ensemble of 5 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with MPE acquisition, ensemble of 7 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD, trained once on a downsampled set Configuration · configuration of this method · 1 evaluation · 12 results
- NAIAD with UCB acquisition Configuration · configuration of this method · 2 evaluations · 12 results
- NAIAD with Uncertainty acquisition Configuration · configuration of this method · 1 evaluation · 8 results
- NAIAD with Uniform acquisition Configuration · configuration of this method · 4 evaluations · 21 results
- NAIAD with Uniform acquisition, ensemble of 1 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Uniform acquisition, ensemble of 3 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Uniform acquisition, ensemble of 5 Configuration · configuration of this method · 1 evaluation · 4 results
- NAIAD with Uniform acquisition, ensemble of 7 Configuration · configuration of this method · 1 evaluation · 4 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.
Use this method
How it works, versions and access
Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this method. 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
| 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-method-naiad
- areas
- cells-tissues
- contexts
- research
- method types
- supervised_machine_learning
- reported name
- NAIAD
- entity level
- method
- source locator
- Section 3.1 (Eq. 1), Section 3.3, Appendix C
- missing metadata
- version: reason: inapplicable; note: Family record; settings are on configurations
- provenance note
- The paper's own method.
- 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.
- access
- Code at github.com/NeptuneBio/NAIAD (Software and Data)
Related records
- subject: architecture: pheno-20261022-qin2025-method-naiad
- subject: code_availability: pheno-20261022-qin2025-method-naiad
- subject: hardware: pheno-20261022-qin2025-method-naiad
- subject: input_requirement: pheno-20261022-qin2025-method-naiad
- configuration of: NAIAD with Mean-UCB acquisition, beta = 0
- configuration of: NAIAD with Mean-UCB acquisition, beta = 0.25
- configuration of: NAIAD with Mean-UCB acquisition, beta = 0.5
- configuration of: NAIAD with Mean-UCB acquisition, beta = 0.75
- configuration of: NAIAD with Mean-UCB acquisition, beta = 1
- configuration of: NAIAD with Mean-UCB acquisition, beta = 1.5
- configuration of: NAIAD with Mean-UCB acquisition, beta = 10
- configuration of: NAIAD with Mean-UCB acquisition, beta = 2
- configuration of: NAIAD with Mean-UCB acquisition, beta = 25
- configuration of: NAIAD with Mean-UCB acquisition, beta = 5
- configuration of: NAIAD with MPE acquisition
- configuration of: NAIAD with MPE acquisition, ensemble of 1
- configuration of: NAIAD with MPE acquisition, ensemble of 3
- configuration of: NAIAD with MPE acquisition, ensemble of 5
- configuration of: NAIAD with MPE acquisition, ensemble of 7
- configuration of: NAIAD, trained once on a downsampled set
- configuration of: NAIAD with UCB acquisition
- configuration of: NAIAD with Uncertainty acquisition
- configuration of: NAIAD with Uniform acquisition
- configuration of: NAIAD with Uniform acquisition, ensemble of 1
- configuration of: NAIAD with Uniform acquisition, ensemble of 3
- configuration of: NAIAD with Uniform acquisition, ensemble of 5
- configuration of: NAIAD with Uniform acquisition, ensemble of 7