Protocol

RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7)

Accuracy, macro F1, precision and recall for blastn, megablast and the best foundation-model configuration on the 40- and 33-class datasets.

6 evaluations · 24 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.

6 recorded evaluations, 24 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

6 evaluations · 24 results. Different protocols are not a single leaderboard.

Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7)

Sorted by Accuracy (33-class RVDB dataset) (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	Accuracy (33-class RVDB dataset)	Accuracy (40-class RVDB dataset)	Macro F1 (33-class RVDB dataset)	Macro F1 (40-class RVDB dataset)	Precision (33-class RVDB dataset, macro-averaged over classes)	Precision (40-class RVDB dataset, macro-averaged over classes)	Recall (33-class RVDB dataset, macro-averaged over classes)	Recall (40-class RVDB dataset, macro-averaged over classes)
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)Evaluation	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.968 (best in column)	Not reported	0.938 (best in column)	Not reported	0.94	Not reported	0.939 (best in column)	Not reported
NTv3-650M, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)Evaluation	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.926	Not reported	0.925	Not reported	0.926	Not reported	0.926	Not reported
BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)Evaluation	RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.899	Not reported	0.899	Not reported	0.96 (best in column)	Not reported	0.873	Not reported
BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)Evaluation	RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	Not reported	0.912 (best in column)	Not reported	0.889 (best in column)	Not reported	0.892	Not reported	0.89 (best in column)
BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)Evaluation	RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	Not reported	0.849	Not reported	0.851	Not reported	0.906 (best in column)	Not reported	0.828
NTv3-650M, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)Evaluation	RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	Not reported	0.875	Not reported	0.874	Not reported	0.874	Not reported	0.875

All 24 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: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.968 Accuracy (33-class RVDB dataset) fraction · higher Uncertainty: 95% CI 0.962 to 0.972. Wilson binomial interval quoted in Section 3.6, paragraph 1; method stated in Section 2.9 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source blastn on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / blastn', column 'Accuracy'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.938 Macro F1 (33-class RVDB dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source blastn on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / blastn', column 'F1'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.94 Precision (33-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source blastn on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / blastn', column 'Precision'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.939 Recall (33-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source blastn on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / blastn', column 'Recall'
Configuration: BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.899 Accuracy (33-class RVDB dataset) fraction · higher Uncertainty: 95% CI 0.891 to 0.907. Wilson binomial interval quoted in Section 3.6, paragraph 1; method stated in Section 2.9 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source megablast on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / megablast', column 'Accuracy'
Configuration: BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.899 Macro F1 (33-class RVDB dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source megablast on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / megablast', column 'F1'
Configuration: BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.96 Precision (33-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source megablast on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / megablast', column 'Precision'
Configuration: BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.873 Recall (33-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source megablast on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / megablast', column 'Recall'
Configuration: NTv3-650M, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.926 Accuracy (33-class RVDB dataset) fraction · higher Uncertainty: 95% CI 0.919 to 0.933. Wilson binomial interval quoted in Section 3.6, paragraph 1; method stated in Section 2.9 Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv3-650M (max) on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / NTv3-650M (max)', column 'Accuracy'
Configuration: NTv3-650M, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.925 Macro F1 (33-class RVDB dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv3-650M (max) on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / NTv3-650M (max)', column 'F1'
Configuration: NTv3-650M, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.926 Precision (33-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv3-650M (max) on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / NTv3-650M (max)', column 'Precision'
Configuration: NTv3-650M, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 33 refined classes	0.926 Recall (33-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv3-650M (max) on the RVDB 33-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '33 classes / NTv3-650M (max)', column 'Recall'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.912 Accuracy (40-class RVDB dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source blastn on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / blastn', column 'Accuracy'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.889 Macro F1 (40-class RVDB dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source blastn on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / blastn', column 'F1'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.892 Precision (40-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source blastn on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / blastn', column 'Precision'
Configuration: BLAST 2.12.0 blastn, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.89 Recall (40-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source blastn on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / blastn', column 'Recall'
Configuration: BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.849 Accuracy (40-class RVDB dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source megablast on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / megablast', column 'Accuracy'
Configuration: BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.851 Macro F1 (40-class RVDB dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source megablast on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / megablast', column 'F1'
Configuration: BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.906 Precision (40-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source megablast on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / megablast', column 'Precision'
Configuration: BLAST 2.12.0 megablast, top hit (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.828 Recall (40-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source megablast on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / megablast', column 'Recall'
Configuration: NTv3-650M, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.875 Accuracy (40-class RVDB dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv3-650M (max) on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / NTv3-650M (max)', column 'Accuracy'
Configuration: NTv3-650M, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.874 Macro F1 (40-class RVDB dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv3-650M (max) on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / NTv3-650M (max)', column 'F1'
Configuration: NTv3-650M, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.874 Precision (40-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv3-650M (max) on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / NTv3-650M (max)', column 'Precision'
Configuration: NTv3-650M, frozen embeddings, max, all tokens pooling, 1-NN (Bůžková et al. 2026)	Protocol: RVDB viral classification: best frozen-embedding configuration against BLAST (Bůžková et al. 2026 Table 7) Dataset: RVDB C-RVDB v31.0 primary dataset, 40 sampled classes	0.875 Recall (40-class RVDB dataset, macro-averaged over classes) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NTv3-650M (max) on the RVDB 40-class dataset (BLAST comparison) gfm2-20261011-buzkova2026-protocol-blast-compare Aggregation: Not reported Analyzing Genomic Foundation Models for Viral Sequence Identification · Table 7, row '40 classes / NTv3-650M (max)', column 'Recall'

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

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

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.

External evaluations: 6

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Training-set class prior where supervised fitting is permitted

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

Regularised classifier on simple permitted features, or protocol's conventional reference

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 2026-11-02-a7f03c9e55a5. 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

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

Analyzing Genomic Foundation Models for Viral Sequence Identification · Original source · bioRxiv v1, posted 2026-09-28

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm2-20261011-buzkova2026-protocol-blast-compare

areas: dna-genomes
contexts: research
protocol: Both pipelines index the same 350 training sequences per class. BLAST builds a nucleotide database from the training FASTA and takes the top hit's label (max_target_seqs = 1); the foundation model retrieves the nearest frozen embedding. Neither can return a label outside the reference set.
version: Table 7 (max_target_seqs = 1)
metric direction: higher
unit: fraction
aggregation: Accuracy over test sequences; F1, precision and recall macro-averaged over classes
limitations: Nearest-neighbour probe over labelled reference embeddings, not zero-shot classification: the index holds the training labels (Section 2.7).; Point estimates from one fixed split with a fixed random seed; 95% Wilson intervals are quoted in the text, not in the tables.; RVDB organism labels are not a controlled taxonomy; the 33-class refinement removed seven ambiguous labels found through the models' own confusions (Sections 3.2 and 4).; Only the best foundation-model configuration (NTv3-650M, max pooling) appears in this table.; ICTV reconciliation found one further redundant label pair still inside the 33-class dataset (Section 3.2; Section 4, Table 11).
source locator: Table 7; Sections 2.8, 2.9 and 3.6

Related records

uses data: RVDB C-RVDB v31.0 primary dataset, 33 refined classes
assessment: blastn on the RVDB 33-class dataset (BLAST comparison)
assessment: megablast on the RVDB 33-class dataset (BLAST comparison)
assessment: NTv3-650M (max) on the RVDB 33-class dataset (BLAST comparison)
assessment: blastn on the RVDB 40-class dataset (BLAST comparison)
assessment: megablast on the RVDB 40-class dataset (BLAST comparison)
assessment: NTv3-650M (max) on the RVDB 40-class dataset (BLAST comparison)

Suggest a correction