Levenshtein | method

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

11 evaluations · 11 results. Different protocols are not a single leaderboard.

Sorted by Spearman (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	Protocol and dataset	Spearman	AUROC (ROC-AUC, pathogenic versus benign ClinVar all in-frame indels; zero-shot)
LevenshteinEvaluation	FLIP AAV-MUT-DES: AAV fitness prediction, Mut-Des split, FLIP AAV, Mut-Des split (FLIP split)	0.6 (best in column)	Not reported
LevenshteinEvaluation	FLIP AAV-2-VS-REST: AAV fitness prediction, 2-vs-rest split, FLIP AAV, 2-vs-rest split (FLIP split)	0.57	Not reported
LevenshteinEvaluation	FLIP AAV-7-VS-REST: AAV fitness prediction, 7-vs-rest split, FLIP AAV, 7-vs-rest split (FLIP split)	0.53	Not reported
LevenshteinEvaluation	FLIP AAV-LOW-VS-HIGH: AAV fitness prediction, low-vs-high split, FLIP AAV, low-vs-high split (FLIP split)	0.25	Not reported
LevenshteinEvaluation	FLIP GB1-1-VS-REST: GB1 fitness prediction, 1-vs-rest split, FLIP GB1, 1-vs-rest split (FLIP split)	0.17	Not reported
LevenshteinEvaluation	FLIP GB1-2-VS-REST: GB1 fitness prediction, 2-vs-rest split, FLIP GB1, 2-vs-rest split (FLIP split)	0.16	Not reported
LevenshteinEvaluation	FLIP GB1-3-VS-REST: GB1 fitness prediction, 3-vs-rest split, FLIP GB1, 3-vs-rest split (FLIP split)	-0.04	Not reported
LevenshteinEvaluation	FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split, FLIP AAV, Des-Mut split (FLIP split)	-0.07	Not reported
LevenshteinEvaluation	FLIP GB1-LOW-VS-HIGH: GB1 fitness prediction, low-vs-high split, FLIP GB1, low-vs-high split (FLIP split)	-0.1	Not reported
LevenshteinEvaluation	FLIP AAV-1-VS-REST: AAV fitness prediction, 1-vs-rest split, FLIP AAV, 1-vs-rest split (FLIP split)	-0.11	Not reported
LevenshteinEvaluation	ClinVar in-frame indel pathogenicity, ROC-AUC (Brandes et al. 2023 Fig. 6b, Supplementary Table 2), ClinVar in-frame indels, pathogenic vs benign (Brandes et al. 2023)	Not reported	0.502

All 11 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
Method: Levenshtein	Task: FLIP AAV-1-VS-REST: AAV fitness prediction, 1-vs-rest split Dataset subset: FLIP AAV, 1-vs-rest split (FLIP split)	-0.11 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Levenshtein on FLIP AAV-1-VS-REST: AAV fitness prediction, 1-vs-rest split Trained on the split's training set with ten percent held out for validation, scored on its test set. Aggregation: Not reported flip primary benchmark evidence · Table 5, row(Levenshtein), column(1-vs-rest)
Method: Levenshtein	Task: FLIP AAV-2-VS-REST: AAV fitness prediction, 2-vs-rest split Dataset subset: FLIP AAV, 2-vs-rest split (FLIP split)	0.57 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Levenshtein on FLIP AAV-2-VS-REST: AAV fitness prediction, 2-vs-rest split Trained on the split's training set with ten percent held out for validation, scored on its test set. Aggregation: Not reported flip primary benchmark evidence · Table 5, row(Levenshtein), column(2-vs-rest)
Method: Levenshtein	Task: FLIP AAV-7-VS-REST: AAV fitness prediction, 7-vs-rest split Dataset subset: FLIP AAV, 7-vs-rest split (FLIP split)	0.53 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Levenshtein on FLIP AAV-7-VS-REST: AAV fitness prediction, 7-vs-rest split Trained on the split's training set with ten percent held out for validation, scored on its test set. Aggregation: Not reported flip primary benchmark evidence · Table 5, row(Levenshtein), column(7-vs-rest)
Method: Levenshtein	Task: FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split Dataset subset: FLIP AAV, Des-Mut split (FLIP split)	-0.07 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Levenshtein on FLIP AAV-DES-MUT: AAV fitness prediction, Des-Mut split Trained on the split's training set with ten percent held out for validation, scored on its test set. Aggregation: Not reported flip primary benchmark evidence · Table 5, row(Levenshtein), column(Des-Mut)
Method: Levenshtein	Task: FLIP AAV-LOW-VS-HIGH: AAV fitness prediction, low-vs-high split Dataset subset: FLIP AAV, low-vs-high split (FLIP split)	0.25 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Levenshtein on FLIP AAV-LOW-VS-HIGH: AAV fitness prediction, low-vs-high split Trained on the split's training set with ten percent held out for validation, scored on its test set. Aggregation: Not reported flip primary benchmark evidence · Table 5, row(Levenshtein), column(low-vs-high)
Method: Levenshtein	Task: FLIP AAV-MUT-DES: AAV fitness prediction, Mut-Des split Dataset subset: FLIP AAV, Mut-Des split (FLIP split)	0.6 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Levenshtein on FLIP AAV-MUT-DES: AAV fitness prediction, Mut-Des split Trained on the split's training set with ten percent held out for validation, scored on its test set. Aggregation: Not reported flip primary benchmark evidence · Table 5, row(Levenshtein), column(Mut-Des)
Method: Levenshtein	Task: FLIP GB1-1-VS-REST: GB1 fitness prediction, 1-vs-rest split Dataset subset: FLIP GB1, 1-vs-rest split (FLIP split)	0.17 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Levenshtein on FLIP GB1-1-VS-REST: GB1 fitness prediction, 1-vs-rest split Trained on the split's training set with ten percent held out for validation, scored on its test set. Aggregation: Not reported flip primary benchmark evidence · Table 4, row(Levenshtein), column(1-vs-rest)
Method: Levenshtein	Task: FLIP GB1-2-VS-REST: GB1 fitness prediction, 2-vs-rest split Dataset subset: FLIP GB1, 2-vs-rest split (FLIP split)	0.16 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Levenshtein on FLIP GB1-2-VS-REST: GB1 fitness prediction, 2-vs-rest split Trained on the split's training set with ten percent held out for validation, scored on its test set. Aggregation: Not reported flip primary benchmark evidence · Table 4, row(Levenshtein), column(2-vs-rest)
Method: Levenshtein	Task: FLIP GB1-3-VS-REST: GB1 fitness prediction, 3-vs-rest split Dataset subset: FLIP GB1, 3-vs-rest split (FLIP split)	-0.04 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Levenshtein on FLIP GB1-3-VS-REST: GB1 fitness prediction, 3-vs-rest split Trained on the split's training set with ten percent held out for validation, scored on its test set. Aggregation: Not reported flip primary benchmark evidence · Table 4, row(Levenshtein), column(3-vs-rest)
Method: Levenshtein	Task: FLIP GB1-LOW-VS-HIGH: GB1 fitness prediction, low-vs-high split Dataset subset: FLIP GB1, low-vs-high split (FLIP split)	-0.1 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Levenshtein on FLIP GB1-LOW-VS-HIGH: GB1 fitness prediction, low-vs-high split Trained on the split's training set with ten percent held out for validation, scored on its test set. Aggregation: Not reported flip primary benchmark evidence · Table 4, row(Levenshtein), column(low-vs-high)
Method: Levenshtein	Protocol: ClinVar in-frame indel pathogenicity, ROC-AUC (Brandes et al. 2023 Fig. 6b, Supplementary Table 2) Dataset: ClinVar in-frame indels, pathogenic vs benign (Brandes et al. 2023)	0.502 AUROC (ROC-AUC, pathogenic versus benign ClinVar all in-frame indels; zero-shot) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Edit distance on all in-frame indels (Brandes et al. 2023) gfm-guides-20261014-esm1b-protocol-clinvar-inframe-indels Aggregation: Not reported Brandes et al. 2023 Supplementary Table 2: full benchmark evaluations of ESM1b and all other methods · Supplementary Table 2 sheet 'Table_of_results_indels' cell B8, row 'Edit distance', column 'AUC_indels'

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

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

Claims, original sources and review scope · Release 2026-11-02-a7f03c9e55a5
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 2026-11-02-a7f03c9e55a5 · Record review: source checked

1 source record and release history

flip primary benchmark evidence · Original source · 2021 manuscript

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: flip-method-levenshtein

areas: proteins-complexes
source locator: Table 4, row(Levenshtein)
missing metadata: checkpoint revision: reason: unreported; parameters: reason: unextracted

Related records