Model type
Graph-based predictive method; this record is the paper-specific evaluated configuration.
Configuration
DETIRE
DETIRE classifies short metagenomic DNA fragments as viral or non-viral.
Sources
DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 3. Results/3.4. Performance on the testing dataset (paragraph 1); 3. Results/3.2. A real human gut metagenome dataset (paragraph 1)How it worksEvaluated procedure (conceptual)
Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.
Sources
DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 2. Materials and methods/2.2. Composition of DETIRE (paragraph 3); 2. Materials and methods/2.2. Composition of DETIRE (paragraph 2)At a glance
Biological inputs
Short DNA fragments, with 500-bp fragments used for training
Sources
DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 3. Results/3.2. A real human gut metagenome dataset (paragraph 1); 4. Discussions (paragraph 2)Outputs
Viral-sequence classification scores
Sources
DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 3. Results/3.4. Performance on the testing dataset (paragraph 1); 3. Results/3.5. Performance on the CAMI Marine metagenome (paragraph 2)limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| DETIRE: viral sequence detection Hybrid deep learning virus-fragment classifier on paper testing dataset Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.8772 accuracy Unit: fraction · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedDETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · Table 1, Accuracy row, DETIRE column Source checking is not independent reproduction. |
How it works
How the evaluated method works
TextGCN learns embeddings of 3-mers from a heterogeneous sequence/token graph. CNN and bidirectional-LSTM branches extract spatial and sequential features, which are weighted together for classification.
Sources
DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 2. Materials and methods/2.2. Composition of DETIRE (paragraph 3); 2. Materials and methods/2.2. Composition of DETIRE (paragraph 2)What was evaluated
The linked evaluation record identifies DETIRE: viral sequence detection. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-b4-018Strengths and limitations
Strengths and considerations
- Combines local and sequential features and evaluates the difficult short-fragment regime.
Sources
DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 1. Introduction (paragraph 5); 4. Discussions (paragraph 1)
Limitations and conditions
- Reference-derived fragments may differ from highly novel environmental viruses; this is a viral detector, not a complete taxonomy or abundance estimator.
Sources
DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · Abstract (paragraph 1); 4. Discussions (paragraph 4)
Profile review details
Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.
Stable record: reported-model-6d9dbac97852d8Specifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | Graph-based predictive method; this record is the paper-specific evaluated configuration.SourcesDETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 2. Materials and methods/2.2. Composition of DETIRE (paragraph 3); 2. Materials and methods/2.2. Composition of DETIRE (paragraph 2) |
| Architecture / procedure | TextGCN learns embeddings of 3-mers from a heterogeneous sequence/token graph. CNN and bidirectional-LSTM branches extract spatial and sequential features, which are weighted together for classification.SourcesDETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 2. Materials and methods/2.2. Composition of DETIRE (paragraph 3); 2. Materials and methods/2.2. Composition of DETIRE (paragraph 2) |
| Biological inputs | Short DNA fragments, with 500-bp fragments used for trainingSourcesDETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 3. Results/3.2. A real human gut metagenome dataset (paragraph 1); 4. Discussions (paragraph 2) |
| Outputs | Viral-sequence classification scoresSourcesDETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 3. Results/3.4. Performance on the testing dataset (paragraph 1); 3. Results/3.5. Performance on the CAMI Marine metagenome (paragraph 2) |
| Parameters | An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes; crazyinter/DETIRE README.md · 2. Materials and methods/2.1. Virus and host RefSeq genome datasets for training and testing; 2. Materials and methods/2.2. Composition of DETIRE; 2. Materials and methods/2.3. Evaluation criteria; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision |
| Known versions / configuration | DETIRE is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesDETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | 220,000 sampled 500-bp Virus/Host RefSeq fragments for the classifier; the graph-embedding corpus uses viral RefSeq available through 11 October 2022 and prokaryotic host sequences.SourcesDETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 2. Materials and methods/2.1. Virus and host RefSeq genome datasets for training and testing (paragraph 1); Abstract (paragraph 1) |
| Context limits | 500 bp during the reported classifier training; the paper separately examines short fragments below 1,000 bp.SourcesDETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · 4. Discussions (paragraph 2); 1. Introduction (paragraph 2) |
| Access | Official study implementation and usage documentation: https://github.com/crazyinter/DETIRE/blob/6b48c5bcb1303abe593173633d1f13da1d8d5869/README.md. This pinned documentation revision is not automatically the evaluated weight revision.Sourcescrazyinter/DETIRE README.md · README.md; installation, model download and usage instructions |
| Code licence | No explicit code licence was established from the paper’s availability statement and inspected repository-root documentation. · Not reported in inspected sourcesSourcescrazyinter/DETIRE README.md · README.md and repository-root licence-file search |
| Weights licence | The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. · Not reported in inspected sourcesSourcescrazyinter/DETIRE README.md · README.md; checkpoint/access documentation and licence scope |
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.
20 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims | DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes 2. Materials and methods/2.2. Composition of DETIRE (paragraph 3); 2. Materials and methods/2.2. Composition of DETIRE (paragraph 2) Version: PMC archival version PMC10313334.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Short DNA fragments, with 500-bp fragments used for training","DETIRE","Viral-sequence classification scores"] Individual claims | DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes 2. Materials and methods/2.2. Composition of DETIRE (paragraph 3); 2. Materials and methods/2.2. Composition of DETIRE (paragraph 2) Version: PMC archival version PMC10313334.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Evaluated procedure (conceptual) Individual claims | DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes 2. Materials and methods/2.2. Composition of DETIRE (paragraph 3); 2. Materials and methods/2.2. Composition of DETIRE (paragraph 2) Version: PMC archival version PMC10313334.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Model type Graph-based predictive method; this record is the paper-specific evaluated configuration. Individual claims | DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes 2. Materials and methods/2.2. Composition of DETIRE (paragraph 3); 2. Materials and methods/2.2. Composition of DETIRE (paragraph 2) Version: PMC archival version PMC10313334.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Architecture / procedure TextGCN learns embeddings of 3-mers from a heterogeneous sequence/token graph. CNN and bidirectional-LSTM branches extract spatial and sequential features, which are weighted together for classification. Individual claims | DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes 2. Materials and methods/2.2. Composition of DETIRE (paragraph 3); 2. Materials and methods/2.2. Composition of DETIRE (paragraph 2) Version: PMC archival version PMC10313334.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Weights licence The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. Individual claims | crazyinter/DETIRE README.md README.md; checkpoint/access documentation and licence scope Version: 6b48c5bcb1303abe593173633d1f13da1d8d5869 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Biological inputs Short DNA fragments, with 500-bp fragments used for training Individual claims | DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes 3. Results/3.2. A real human gut metagenome dataset (paragraph 1); 4. Discussions (paragraph 2) Version: PMC archival version PMC10313334.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Outputs Viral-sequence classification scores Individual claims | DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes 3. Results/3.4. Performance on the testing dataset (paragraph 1); 3. Results/3.5. Performance on the CAMI Marine metagenome (paragraph 2) Version: PMC archival version PMC10313334.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes 2. Materials and methods/2.1. Virus and host RefSeq genome datasets for training and testing; 2. Materials and methods/2.2. Composition of DETIRE; 2. Materials and methods/2.3. Evaluation criteria; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC archival version PMC10313334.1 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | crazyinter/DETIRE README.md 2. Materials and methods/2.1. Virus and host RefSeq genome datasets for training and testing; 2. Materials and methods/2.2. Composition of DETIRE; 2. Materials and methods/2.3. Evaluation criteria; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 6b48c5bcb1303abe593173633d1f13da1d8d5869 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: needs review
2 source records and release history
- DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes · Original source · PMC archival version PMC10313334.1
- crazyinter/DETIRE README.md · Original source · 6b48c5bcb1303abe593173633d1f13da1d8d5869
Technical metadata and extraction receipts
Stable ID: reported-model-6d9dbac97852d8
- areas
- microbes-communities
- entity level
- method
- version
- Not reported
- reported name
- DETIRE
- historical missing metadata
- version: not_reported_in_legacy_extract; checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: not_reported_in_legacy_extract
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- model
- entity classification
- review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: detire-viral-metagenomes-2023; source locator: 2. Materials and methods/2.2. Composition of DETIRE (paragraph 3); 2. Materials and methods/2.2. Composition of DETIRE (paragraph 2) | 3. Results/3.4. Performance on the testing dataset (paragraph 1); 3. Results/3.2. A real human gut metagenome dataset (paragraph 1); ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.