Count (generated designs active in vitro, out of 24 tested; IS605-like family) of Evo fine-tuned on IS200/IS605 elements (Nguyen et al. 2024) on Evo-generated IS200-like and IS605-like designs selected for in vitro testing (Nguyen et al. 2024)
3 Count (generated designs active in vitro, out of 24 tested; IS605-like family)
Methods
- Tested configuration
- Evo fine-tuned on IS200/IS605 elements (Nguyen et al. 2024)
- Protocol
- In vitro activity of Evo-generated mobile-element designs (Nguyen et al. 2024)
- Dataset
- Evo-generated IS200-like and IS605-like designs selected for in vitro testing (Nguyen et al. 2024)
- Procedure
- In vitro activity of Evo-generated mobile-element designs (Nguyen et al. 2024)
- Evaluation
- Evo-generated IS605-like designs, in vitro activity (Nguyen et al. 2024)
- Coverage
- 24/24 designs scored (All 24 selected designs of the family were tested; the number of generations the 24 were selected from is not printed.)
- Uncertainty
- Not applicable: A single count of a binary assay outcome; no spread printed
- Evidence
- Author-reported evaluation · source checkedSequence modeling and design from molecular to genome scale with Evo (Nguyen et al., Science 2024) · Results, section 'Generative design of transposon systems', sentence beginning 'We observed that 11 out of 24': '3 out of 24 Evo-generated IS605-like elements'
A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.
Reproduction
- Split
- No split
- Adaptation
- Fine-tuned on mobile-element loci, then prompted
- Scoring implementation
- Not reported
No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.
Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.
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.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Reported result 3 Individual claims | Sequence modeling and design from molecular to genome scale with Evo (Nguyen et al., Science 2024) Results, section 'Generative design of transposon systems', sentence beginning 'We observed that 11 out of 24': '3 out of 24 Evo-generated IS605-like elements' Version: Science 386, eado9336 (15 November 2024); PubMed Central author manuscript PMC12057570, PMC version 1, JATS full text | source checked ["source-hash-verification","transcription","scope-review"] · 2026-10-14 author reported Audit detailsExtraction: Transcribed by hand from the pinned JATS full text; the extraction script asserts the exact sentence and the sentence stating the 24 designs tested per family before writing the records. Independent review 2026-10-14: matched. For the transposon results, 'active' means the source's 'evidence for both excision and insertion in vitro'. Kept in the catalogue as an author-selected laboratory outcome; see the protocol limitations. Field: Source artifact SHA-256: Hash scope: SHA-256 of the retrieved efetch JATS XML bytes Extraction artifact SHA-256: |
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
1 source record and release history
- Sequence modeling and design from molecular to genome scale with Evo (Nguyen et al., Science 2024) · Original source · Science 386, eado9336 (15 November 2024); PubMed Central author manuscript PMC12057570, PMC version 1, JATS full text
Technical metadata and extraction receipts
Stable ID: gfm-guides-20261014-evo-generation-result-evo-finetuned-is605-active-designs
- metric
- count
- metric direction
- higher
- unit
- count
- unit detail
- generated IS605-like designs scored active in the in vitro assay
- printed value
- 3
- numeric value
- 3
- metric qualifier
- generated designs active in vitro, out of 24 tested; IS605-like family
- coverage
- scored: 24; eligible: 24; unit: designs; note: All 24 selected designs of the family were tested; the number of generations the 24 were selected from is not printed.
- denominator
- 24
- source locator
- Results, section 'Generative design of transposon systems', sentence beginning 'We observed that 11 out of 24': '3 out of 24 Evo-generated IS605-like elements'
- review
- method: source-hash-verification; transcription; scope-review; method note: PMC JATS re-downloaded on 2026-10-14 (SHA-256 matches); the sentences re-read verbatim.; reviewer: claude; reviewer note: Claude (Opus 5.5) research agent, independent of the extractor; no human review claimed; date: 2026-10-14; artifact sha256: 6bf1e0563c2870088e9c6c46361052fd0e9418c3122ee29aa4a2373794e65caa; retrieval url: https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pmc&id=12057570; note: Extraction: Transcribed by hand from the pinned JATS full text; the extraction script asserts the exact sentence and the sentence stating the 24 designs tested per family before writing the records. Independent review 2026-10-14: matched. For the transposon results, 'active' means the source's 'evidence for both excision and insertion in vitro'. Kept in the catalogue as an author-selected laboratory outcome; see the protocol limitations.
- missing metadata
- uncertainty: reason: inapplicable; note: A single count of a binary assay outcome; no spread printed