Datasets
Four gut-microbiome datasets with IBD, type-2 diabetes, liver-cirrhosis or colorectal-cancer labels and controls.
Task
microbiome disease-state classification
Microbiome disease-state classification evaluates independent disease/control cohorts through leave-one-out prediction.
Sources
Multimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30Overview
Metrics
Accuracy, precision and recall.
Allowed inputs
Microbiome composition/features.
Sources
Multimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30Evaluation procedure diagram
How it worksComputational evaluation flow
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Sources
Multimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
1 evaluation · 1 result. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: MDL4Microbiome | Task: microbiome disease-state classification Dataset: CRC microbiome cohort | 0.97 accuracy fraction · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMDL4Microbiome: microbiome disease-state classification Multimodal deep learning model on colorectal-cancer versus healthy microbiome samples Aggregation: Not reported Multimodal deep learning applied to classify healthy and disease states of human microbiome · Table 3, CRC row, MDL4Microbiome column |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
Methods and evaluation design
Procedure, tasks and evaluated configurations
How it works
Evaluation methodology
Four gut-microbiome datasets with IBD, type-2 diabetes, liver-cirrhosis or colorectal-cancer labels and controls. Leave-one-out cross-validation excludes the held-out sample from both embedding training and final classifier training. Accuracy, precision and recall. Random forest, XGBoost, principal-component regression, lasso and SVM. The source explicitly removes the held-out sample from both learning stages. The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim.
Sources
Multimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30Recorded evaluations
Each evaluation records what was tested and under which conditions.
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Strengths, limitations and unresolved questions
Strengths and limitations
Strengths and considerations
- The held-out sample is excluded from both representation fitting and the final classifier.
Sources
Multimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30
Limitations and conditions
- Within-cohort leave-one-out performance does not establish transfer across cohorts or clinical validity. Cohort confounding remain unextracted.
Sources
Multimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30
Profile review details
Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.
Stable record: reported-task-e2009c35eabd69Specifications
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 |
|---|---|
| Datasets | Four gut-microbiome datasets with IBD, type-2 diabetes, liver-cirrhosis or colorectal-cancer labels and controls.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Splits | Leave-one-out cross-validation excludes the held-out sample from both embedding training and final classifier training.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Metrics | Accuracy, precision and recall.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Baselines | Random forest, XGBoost, principal-component regression, lasso and SVM.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Leakage controls | The source explicitly removes the held-out sample from both learning stages.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Uncertainty | The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. · Not reported in inspected sourcesSourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Entity type | Paper-specific computational evaluation protocol.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Organisms | Human gut microbial communities.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Assays | Microbiome profiles with disease/control labels.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Allowed inputs | Microbiome composition/features.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
| Adaptation | Embedding and classifier training are repeated inside leave-one-out folds, excluding the held-out subject sample.SourcesMultimodal deep learning applied to classify healthy and disease states of human microbiome · Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 |
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Papers and result coverage
Last literature check: 2026-09-17. Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
| Paper or primary resource | Version | Reference |
|---|---|---|
| Multimodal deep learning applied to classify healthy and disease states of human microbiome | PMC archival version PMC8763943.1 | Read source DOI: 10.1038/s41598-022-04773-3 |
Historical gaps recorded on 2026-09-17
The catalogue now holds 1 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.
- Disease datasets and cohort prevalences differ; do not pool accuracy.
- No uncertainty in Table 3. Visualization using a 7:3 split is not the evaluation split.
Search and extraction details
primary comparison table screened
Searches
- "PMC8763943"
Evidence locations
- Table 3
- Methods: Performance evaluation
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.
18 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Diagram steps
| Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets Four gut-microbiome datasets with IBD, type-2 diabetes, liver-cirrhosis or colorectal-cancer labels and controls. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits Leave-one-out cross-validation excludes the held-out sample from both embedding training and final classifier training. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation Embedding and classifier training are repeated inside leave-one-out folds, excluding the held-out subject sample. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics Accuracy, precision and recall. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines Random forest, XGBoost, principal-component regression, lasso and SVM. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls The source explicitly removes the held-out sample from both learning stages. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | source checked automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. Individual claims | Multimodal deep learning applied to classify healthy and disease states of human microbiome Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30 Version: PMC archival version PMC8763943.1 | unreported automated source review · 2026-09-16 Audit detailsTask-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: needs review
2 source records and release history
- Multimodal deep learning applied to classify healthy and disease states of human microbiome · Original source · PMC archival version PMC8763943.1
- Multimodal deep learning applied to classify healthy and disease states of human microbiome · Original source · PMC archival version PMC8763943.1
Technical metadata and extraction receipts
Stable ID: reported-task-e2009c35eabd69
- areas
- microbes-communities
- tasks
- microbiome disease-state classification
- entity level
- task
- version
- Not reported
- task
- microbiome disease-state classification
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: primary_comparison_table_screened; primary sources: expansion-p3-mdl4microbiome-2022; inspected locators: Table 3; Methods: Performance evaluation; searched queries: "PMC8763943"; gaps: Disease datasets and cohort prevalences differ; do not pool accuracy.; No uncertainty in Table 3. Visualization using a 7:3 split is not the evaluation split.; claim scope: Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
- historical missing metadata
- protocol version: not_reported_in_legacy_extract; split: 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
- benchmark
- entity classification
- review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: mdl4microbiome-2022; source locator: Methods: Data preparation and preprocessing; Performance evaluation; cached text lines 10–12, 28–30; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.
Related records
- dataset: CRC microbiome cohort
- benchmark: MDL4Microbiome: microbiome disease-state classification