Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
Task
vaccine-antigen candidate prediction
Vaccine-antigen classification tests transfer by withholding one organism’s labeled protein examples.
Sources
Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39At a glance
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 | Previously curated vaccine-antigen positive/negative datasets used by Vaxign-ML and Vaxign-DL.SourcesEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 |
| Splits | Leave-one-pathogen-out evaluation trains on the remaining organisms and predicts the withheld organism’s labels.SourcesEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 |
| Metrics | Accuracy, sensitivity, specificity, weighted F1, MCC, AUROC and AUPRC.SourcesEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 |
| Baselines | Vaxign-ML and Vaxign-DL are the referenced baseline datasets/methods.SourcesEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 |
| Leakage controls | Dataset curation removes positive-protein homologs above 30% sequence similarity and selects negative proteins below 30% similarity to positives. The LOPOV experiment additionally withholds one of ten pathogens. These controls do not establish that sequences were absent from ESM-1b pretraining.SourcesEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: Collection of Positive and Negative protein sequences; Leave-one-pathogen-out validation |
| Uncertainty | Tables 1–3 include ± terms for most metrics but not AUROC. Their captions and the Deep learning pipeline section do not define whether those terms are standard deviations, standard errors or confidence intervals, or specify their repetition count. · Not reported in inspected sourcesSourcesEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: Deep learning pipeline; Tables 1–3 |
| Entity type | Paper-specific computational evaluation protocol.SourcesEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 |
| Organisms | Multiple pathogen species in the curated antigen evaluation.SourcesEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 |
| Assays | Vaccine-antigen positive/negative annotations.SourcesEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 |
| Allowed inputs | Protein sequence representations.SourcesEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 |
| Adaptation | Supervised candidate classification with leave-one-pathogen-out evaluation.SourcesEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 |
How it works
How it worksComputational evaluation flow
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Sources
Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39Evaluation methodology
Previously curated vaccine-antigen positive/negative datasets used by Vaxign-ML and Vaxign-DL. Leave-one-pathogen-out evaluation trains on the remaining organisms and predicts the withheld organism’s labels. Accuracy, sensitivity, specificity, weighted F1, MCC, AUROC and AUPRC. Vaxign-ML and Vaxign-DL are the referenced baseline datasets/methods. Dataset curation removes positive-protein homologs above 30% sequence similarity and selects negative proteins below 30% similarity to positives. The LOPOV experiment additionally withholds one of ten pathogens. These controls do not establish that sequences were absent from ESM-1b pretraining.
Sources
Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39; Methods: Collection of Positive and Negative protein sequences; Leave-one-pathogen-out validationEvaluation design
Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.
Protocols
These source-backed links do not make different protocols or scores interchangeable.
Recorded evaluations
Each evaluation records what was tested and under which conditions.
Published comparisons
Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies.
Protective-antigen classification feature comparison · Table 1.
Val Accuracy (fraction) · Higher values are better for this metric.
Original 509 features vs ESM 1,280 features vs combined 1,789 features. 372 protection-positive and 3,720 protection-negative samples.
Evaluation protocol · Protective-antigen classification feature comparison
- Original · Configuration · Author-reported evaluation0.96 ± 0.008
- ESM Only · Configuration · Author-reported evaluation0.96 ± 0.005
- Combined · Configuration · Author-reported evaluation0.97 ± 0.004
Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.
Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1.: Val Accuracy, Protective-antigen classification feature comparisonValues, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| Original · Configuration | 0.96 ± 0.008 fraction | type: reported_plus_minus_type_unresolved; value: 0.008 | Author-reported evaluation · source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Original, column Val Accuracy; XML row2 column2 |
| ESM Only · Configuration | 0.96 ± 0.005 fraction | type: reported_plus_minus_type_unresolved; value: 0.005 | Author-reported evaluation · source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row ESM Only, column Val Accuracy; XML row3 column2 |
| Combined · Configuration | 0.97 ± 0.004 fraction | type: reported_plus_minus_type_unresolved; value: 0.004 | Author-reported evaluation · source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Combined, column Val Accuracy; XML row4 column2 |
Scope and limitations
- Reported± values preserved; uncertainty type and resampling denominator not established in inspected methods.
- Published prose states specificity equal but table contains differences; table values retained.
- No interval assigned unless printed in source cell.
Source transcription and grouping reviewed by automated source review on 2026-09-17. These experiments were not independently reproduced by rewire.
Tested entities and results
Release 2026-09-17-d277315f7d76 · 4 evaluations · 22 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Vaxign-DL + ESM: vaccine-antigen candidate prediction Pipeline: Vaxign-DL + ESMTask: vaccine-antigen candidate predictionDataset: vaccine candidate validation Combined skip architecture, four layers, ESM-generated sequence features Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.92 AUPRC Unit: fraction · Direction: unknown | Uncertainty: ±0.013 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 2, 4 Layers row, AUPRC column Source checking is not independent reproduction. |
| ESM Only: Protective-antigen classification feature comparison Configuration: ESM OnlyProtocol: Protective-antigen classification feature comparison (vaccine-antigen candidate prediction)Dataset: Protective-antigen classification feature comparison Original 509 features vs ESM 1,280 features vs combined 1,789 features. 372 protection-positive and 3,720 protection-negative samples. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.85 ± 0.036 AUPRC Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.036 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row ESM Only, column AUPRC; XML row3 column7 Source checking is not independent reproduction. |
| 0.98 ± 0.004 Specificity Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.004 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row ESM Only, column Specificity; XML row3 column4 Source checking is not independent reproduction. |
| 0.75 ± 0.063 Sensitivity Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.063 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row ESM Only, column Sensitivity; XML row3 column3 Source checking is not independent reproduction. |
| 0.96 ± 0.005 Val Accuracy Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.005 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row ESM Only, column Val Accuracy; XML row3 column2 Source checking is not independent reproduction. |
| 0.77 ± 0.043 MCC Unit: dimensionless · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.043 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row ESM Only, column MCC; XML row3 column6 Source checking is not independent reproduction. |
| 0.94 AUROC Unit: fraction · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row ESM Only, column AUROC; XML row3 column8 Source checking is not independent reproduction. |
| 0.96 ± 0.007 Weighted F1 Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.007 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row ESM Only, column Weighted F1; XML row3 column5 Source checking is not independent reproduction. |
| Combined: Protective-antigen classification feature comparison Configuration: CombinedProtocol: Protective-antigen classification feature comparison (vaccine-antigen candidate prediction)Dataset: Protective-antigen classification feature comparison Original 509 features vs ESM 1,280 features vs combined 1,789 features. 372 protection-positive and 3,720 protection-negative samples. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.85 ± 0.021 MCC Unit: dimensionless · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.021 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Combined, column MCC; XML row4 column6 Source checking is not independent reproduction. |
| 0.99 ± 0.004 Specificity Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.004 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Combined, column Specificity; XML row4 column4 Source checking is not independent reproduction. |
| 0.97 ± 0.004 Weighted F1 Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.004 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Combined, column Weighted F1; XML row4 column5 Source checking is not independent reproduction. |
| 0.97 ± 0.004 Val Accuracy Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.004 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Combined, column Val Accuracy; XML row4 column2 Source checking is not independent reproduction. |
| 0.92 ± 0.013 AUPRC Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.013 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Combined, column AUPRC; XML row4 column7 Source checking is not independent reproduction. |
| 0.83 ± 0.045 Sensitivity Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.045 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Combined, column Sensitivity; XML row4 column3 Source checking is not independent reproduction. |
| 0.97 AUROC Unit: fraction · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Combined, column AUROC; XML row4 column8 Source checking is not independent reproduction. |
| Original: Protective-antigen classification feature comparison Configuration: OriginalProtocol: Protective-antigen classification feature comparison (vaccine-antigen candidate prediction)Dataset: Protective-antigen classification feature comparison Original 509 features vs ESM 1,280 features vs combined 1,789 features. 372 protection-positive and 3,720 protection-negative samples. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.94 AUROC Unit: fraction · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Original, column AUROC; XML row2 column8 Source checking is not independent reproduction. |
| 0.96 ± 0.008 Weighted F1 Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.008 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Original, column Weighted F1; XML row2 column5 Source checking is not independent reproduction. |
| 0.78 ± 0.046 MCC Unit: dimensionless · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.046 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Original, column MCC; XML row2 column6 Source checking is not independent reproduction. |
| 0.84 ± 0.049 AUPRC Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.049 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Original, column AUPRC; XML row2 column7 Source checking is not independent reproduction. |
| 0.74 ± 0.071 Sensitivity Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.071 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Original, column Sensitivity; XML row2 column3 Source checking is not independent reproduction. |
| 0.96 ± 0.008 Val Accuracy Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.008 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Original, column Val Accuracy; XML row2 column2 Source checking is not independent reproduction. |
| 0.99 ± 0.004 Specificity Unit: fraction · Direction: higher | Uncertainty: type: reported plus minus type unresolved; value: 0.004 Scored: Not reported · Eligible: Not reported | source checkedEnhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Table 1., row Original, column Specificity; XML row2 column4 Source checking is not independent reproduction. |
Papers and result coverage
Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
| Paper or primary resource | Version | Reference |
|---|---|---|
| Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features | preprint version in PMC | Read source DOI: 10.1101/2024.09.04.611295 |
What is still missing
- Independent batch review before import; preserve existing observation identities.
Search and extraction details
complete comparison tables extracted pending publication review
Searches
- Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features primary paper benchmark results
Evidence locations
- Tables1–2; Performance analysis and feature sets
Strengths and limitations
Limitations and conditions
- Long proteins may be omitted or truncated, changing evaluation coverage.
Sources
Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39
Profile review details
Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.
Stable record: reported-task-47465954d606e6Evidence 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.
17 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 | Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Input: Protein sequence representations.","Evaluation: Leave-one-pathogen-out evaluation trains on the remaining organisms and predicts the withheld organism’s labels.","Readout: Accuracy, sensitivity, specificity, weighted F1, MCC, AUROC and AUPRC."] Individual claims | Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets Previously curated vaccine-antigen positive/negative datasets used by Vaxign-ML and Vaxign-DL. Individual claims | Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits Leave-one-pathogen-out evaluation trains on the remaining organisms and predicts the withheld organism’s labels. Individual claims | Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation Supervised candidate classification with leave-one-pathogen-out evaluation. Individual claims | Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics Accuracy, sensitivity, specificity, weighted F1, MCC, AUROC and AUPRC. Individual claims | Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines Vaxign-ML and Vaxign-DL are the referenced baseline datasets/methods. Individual claims | Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39 Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls Dataset curation removes positive-protein homologs above 30% sequence similarity and selects negative proteins below 30% similarity to positives. The LOPOV experiment additionally withholds one of ten pathogens. These controls do not establish that sequences were absent from ESM-1b pretraining. Individual claims | Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features Methods: Collection of Positive and Negative protein sequences; Leave-one-pathogen-out validation Version: preprint version in PMC | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty Tables 1–3 include ± terms for most metrics but not AUROC. Their captions and the Deep learning pipeline section do not define whether those terms are standard deviations, standard errors or confidence intervals, or specify their repetition count. Individual claims | Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features Methods: Deep learning pipeline; Tables 1–3 Version: preprint version in PMC | unreported automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. 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
- Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Original source · preprint version in PMC
- Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features · Original source · preprint version in PMC
Technical metadata and extraction receipts
Stable ID: reported-task-47465954d606e6
- areas
- proteins-complexes
- tasks
- vaccine-antigen candidate prediction
- entity level
- task
- version
- Not reported
- task
- vaccine-antigen candidate prediction
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- comparison panels
- id: part2-vaxign-esm-2024-T1-1dcdb2e905; title: Protective-antigen classification feature comparison · Table 1.; protocol id: paper-protocol-a7bf3c8f6b432c3093; dataset id: paper-dataset-c1edd1f6f7e93d9f6e; metric: Val Accuracy; unit: fraction; direction: higher; result ids: paper-result-cff4683107e593c8b4; paper-result-6884d284eba92a5c06; paper-result-7af576f4ade426848e; source ids: part2-vaxign-esm-2024; source locator: Table 1.: Val Accuracy, Protective-antigen classification feature comparison; context: Original 509 features vs ESM 1,280 features vs combined 1,789 features. 372 protection-positive and 3,720 protection-negative samples.; caveats: Reported± values preserved; uncertainty type and resampling denominator not established in inspected methods.; Published prose states specificity equal but table contains differences; table values retained.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-vaxign-esm-2024-T1-aaa5cd1083; title: Protective-antigen classification feature comparison · Table 1.; protocol id: paper-protocol-a7bf3c8f6b432c3093; dataset id: paper-dataset-c1edd1f6f7e93d9f6e; metric: Sensitivity; unit: fraction; direction: higher; result ids: paper-result-c8bfac2d90d81feeb3; paper-result-5b5f63e259d93937fa; paper-result-e97d7b6a6ecb22428f; source ids: part2-vaxign-esm-2024; source locator: Table 1.: Sensitivity, Protective-antigen classification feature comparison; context: Original 509 features vs ESM 1,280 features vs combined 1,789 features. 372 protection-positive and 3,720 protection-negative samples.; caveats: Reported± values preserved; uncertainty type and resampling denominator not established in inspected methods.; Published prose states specificity equal but table contains differences; table values retained.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-vaxign-esm-2024-T1-a4c286072e; title: Protective-antigen classification feature comparison · Table 1.; protocol id: paper-protocol-a7bf3c8f6b432c3093; dataset id: paper-dataset-c1edd1f6f7e93d9f6e; metric: Specificity; unit: fraction; direction: higher; result ids: paper-result-ef311f3bd240402622; paper-result-368137517fff441366; paper-result-4fbe5feb8bf19db3cf; source ids: part2-vaxign-esm-2024; source locator: Table 1.: Specificity, Protective-antigen classification feature comparison; context: Original 509 features vs ESM 1,280 features vs combined 1,789 features. 372 protection-positive and 3,720 protection-negative samples.; caveats: Reported± values preserved; uncertainty type and resampling denominator not established in inspected methods.; Published prose states specificity equal but table contains differences; table values retained.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-vaxign-esm-2024-T1-7185c1558b; title: Protective-antigen classification feature comparison · Table 1.; protocol id: paper-protocol-a7bf3c8f6b432c3093; dataset id: paper-dataset-c1edd1f6f7e93d9f6e; metric: Weighted F1; unit: fraction; direction: higher; result ids: paper-result-651ddc5c811de9e8bb; paper-result-f4fc84c79d3f4a5dd2; paper-result-6314ca1ea38e3cc0b5; source ids: part2-vaxign-esm-2024; source locator: Table 1.: Weighted F1, Protective-antigen classification feature comparison; context: Original 509 features vs ESM 1,280 features vs combined 1,789 features. 372 protection-positive and 3,720 protection-negative samples.; caveats: Reported± values preserved; uncertainty type and resampling denominator not established in inspected methods.; Published prose states specificity equal but table contains differences; table values retained.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-vaxign-esm-2024-T1-e43ff059cc; title: Protective-antigen classification feature comparison · Table 1.; protocol id: paper-protocol-a7bf3c8f6b432c3093; dataset id: paper-dataset-c1edd1f6f7e93d9f6e; metric: MCC; unit: dimensionless; direction: higher; result ids: paper-result-774bc1695cb59c05ac; paper-result-bc30cb500a5d4c0a21; paper-result-0588c3eaf97f2abf9e; source ids: part2-vaxign-esm-2024; source locator: Table 1.: MCC, Protective-antigen classification feature comparison; context: Original 509 features vs ESM 1,280 features vs combined 1,789 features. 372 protection-positive and 3,720 protection-negative samples.; caveats: Reported± values preserved; uncertainty type and resampling denominator not established in inspected methods.; Published prose states specificity equal but table contains differences; table values retained.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-vaxign-esm-2024-T1-6ed0c48e92; title: Protective-antigen classification feature comparison · Table 1.; protocol id: paper-protocol-a7bf3c8f6b432c3093; dataset id: paper-dataset-c1edd1f6f7e93d9f6e; metric: AUPRC; unit: fraction; direction: higher; result ids: paper-result-7b567777b97aa43653; paper-result-04617e3534e8f83c6d; paper-result-b0ccdc4a3d8bbe1ae7; source ids: part2-vaxign-esm-2024; source locator: Table 1.: AUPRC, Protective-antigen classification feature comparison; context: Original 509 features vs ESM 1,280 features vs combined 1,789 features. 372 protection-positive and 3,720 protection-negative samples.; caveats: Reported± values preserved; uncertainty type and resampling denominator not established in inspected methods.; Published prose states specificity equal but table contains differences; table values retained.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-vaxign-esm-2024-T1-0189da3e2b; title: Protective-antigen classification feature comparison · Table 1.; protocol id: paper-protocol-a7bf3c8f6b432c3093; dataset id: paper-dataset-c1edd1f6f7e93d9f6e; metric: AUROC; unit: fraction; direction: higher; result ids: paper-result-11bf48c7b68484cc04; paper-result-d002da139f31ba9e3f; paper-result-ff4ba6f92feb183bff; source ids: part2-vaxign-esm-2024; source locator: Table 1.: AUROC, Protective-antigen classification feature comparison; context: Original 509 features vs ESM 1,280 features vs combined 1,789 features. 372 protection-positive and 3,720 protection-negative samples.; caveats: Reported± values preserved; uncertainty type and resampling denominator not established in inspected methods.; Published prose states specificity equal but table contains differences; table values retained.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17
- benchmark research
- review date: 2026-09-17; status: complete_comparison_tables_extracted_pending_publication_review; primary sources: part2-vaxign-esm-2024; inspected locators: Tables1–2; Performance analysis and feature sets; searched queries: Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features primary paper benchmark results; gaps: Independent batch review before import; preserve existing observation identities.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
- 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: vaxign-esm-2024; source locator: Methods: leave-one-pathogen-out validation; Performance evaluation; Results: long-protein coverage; cached text lines 18, 25–26, 39; 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.