rewire.it
Dataset subset

SugarBase taxonomy class; GlycanML official motif split (GlycanML split)

Dataset subset reported in GlycanGT published supplementary archive, Table S4. Exact split manifest remains unextracted; source-table identity is retained.

Evaluation results

10 evaluations · 10 metric rows. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: GlycanAAProtocol: GlycanML class Accuracy: GlycanGT study: class Accuracy
Dataset subset: SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
0.74646666666666595 ± 0.0136313364470742 accuracy
fraction · higher

Uncertainty: type: standard_deviation; value: 0.0136313364470742

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · source checked
Methods, coverage and source

GlycanAA on GlycanML class Accuracy: GlycanGT study: class Accuracy

Taxonomy: 13,209 glycans total across eight levels, 4–1,737 classes per level. Official fixed GlycanML motif-based train/validation/test splits (8:1:1). Section 2.5 reports class-balanced classifiers, train ∪ validation hyperparameter selection by randomized search with 3-fold cross-validation, followed by one evaluation on the held-out test set; complete procedure repeated with three random seeds, reporting mean and standard deviation. GlycanGT large model pretrained with 35% masking provides [Graph] embeddings to SVM/LightGBM; the selected classifier for each S4 row is not identified. Section 2.6 states that all four graph baselines were trained and evaluated on the same datasets/splits; it does not establish that each baseline used the GlycanGT downstream classifier search. SVM search: 10 iterations, RBF/linear, C logU(1e-3,1e2), gamma logU(1e-4,1e-1); LightGBM: 15 randomized iterations. Do not combine with separate original GlycanML-paper protocols.

Aggregation: Not reported

GlycanGT published supplementary archive, Table S4; glycangt: Journal full-text XML · btag147_supplementary_data.zip / Table_S4.xlsx / Sheet1!A24:E24 (mean D24, SD E24)
Configuration: GlycanAAProtocol: GlycanML class Macro-F1: GlycanGT study: class Macro-F1
Dataset subset: SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
0.41666666666666602 ± 0.0177798575172393 macro_f1
dimensionless · higher

Uncertainty: type: standard_deviation; value: 0.0177798575172393

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · source checked
Methods, coverage and source

GlycanAA on GlycanML class Macro-F1: GlycanGT study: class Macro-F1

Taxonomy: 13,209 glycans total across eight levels, 4–1,737 classes per level. Official fixed GlycanML motif-based train/validation/test splits (8:1:1). Section 2.5 reports class-balanced classifiers, train ∪ validation hyperparameter selection by randomized search with 3-fold cross-validation, followed by one evaluation on the held-out test set; complete procedure repeated with three random seeds, reporting mean and standard deviation. GlycanGT large model pretrained with 35% masking provides [Graph] embeddings to SVM/LightGBM; the selected classifier for each S4 row is not identified. Section 2.6 states that all four graph baselines were trained and evaluated on the same datasets/splits; it does not establish that each baseline used the GlycanGT downstream classifier search. SVM search: 10 iterations, RBF/linear, C logU(1e-3,1e2), gamma logU(1e-4,1e-1); LightGBM: 15 randomized iterations. Do not combine with separate original GlycanML-paper protocols.

Aggregation: Not reported

GlycanGT published supplementary archive, Table S4; glycangt: Journal full-text XML · btag147_supplementary_data.zip / Table_S4.xlsx / Sheet1!A25:E25 (mean D25, SD E25)
Pipeline: GlycanGTProtocol: GlycanML class Accuracy: GlycanGT study: class Accuracy
Dataset subset: SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
0.69350743561842498 ± 0.0072451883770178003 accuracy
fraction · higher

Uncertainty: type: standard_deviation; value: 0.0072451883770178003

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · source checked
Methods, coverage and source

GlycanGT on GlycanML class Accuracy: GlycanGT study: class Accuracy

Taxonomy: 13,209 glycans total across eight levels, 4–1,737 classes per level. Official fixed GlycanML motif-based train/validation/test splits (8:1:1). Section 2.5 reports class-balanced classifiers, train ∪ validation hyperparameter selection by randomized search with 3-fold cross-validation, followed by one evaluation on the held-out test set; complete procedure repeated with three random seeds, reporting mean and standard deviation. GlycanGT large model pretrained with 35% masking provides [Graph] embeddings to SVM/LightGBM; the selected classifier for each S4 row is not identified. Section 2.6 states that all four graph baselines were trained and evaluated on the same datasets/splits; it does not establish that each baseline used the GlycanGT downstream classifier search. SVM search: 10 iterations, RBF/linear, C logU(1e-3,1e2), gamma logU(1e-4,1e-1); LightGBM: 15 randomized iterations. Do not combine with separate original GlycanML-paper protocols.

Aggregation: Not reported

GlycanGT published supplementary archive, Table S4; glycangt: Journal full-text XML · btag147_supplementary_data.zip / Table_S4.xlsx / Sheet1!A71:E71 (mean D71, SD E71)
Pipeline: GlycanGTProtocol: GlycanML class Macro-F1: GlycanGT study: class Macro-F1
Dataset subset: SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
0.39715349769695701 ± 0.0084870172846663004 macro_f1
dimensionless · higher

Uncertainty: type: standard_deviation; value: 0.0084870172846663004

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · source checked
Methods, coverage and source

GlycanGT on GlycanML class Macro-F1: GlycanGT study: class Macro-F1

Taxonomy: 13,209 glycans total across eight levels, 4–1,737 classes per level. Official fixed GlycanML motif-based train/validation/test splits (8:1:1). Section 2.5 reports class-balanced classifiers, train ∪ validation hyperparameter selection by randomized search with 3-fold cross-validation, followed by one evaluation on the held-out test set; complete procedure repeated with three random seeds, reporting mean and standard deviation. GlycanGT large model pretrained with 35% masking provides [Graph] embeddings to SVM/LightGBM; the selected classifier for each S4 row is not identified. Section 2.6 states that all four graph baselines were trained and evaluated on the same datasets/splits; it does not establish that each baseline used the GlycanGT downstream classifier search. SVM search: 10 iterations, RBF/linear, C logU(1e-3,1e2), gamma logU(1e-4,1e-1); LightGBM: 15 randomized iterations. Do not combine with separate original GlycanML-paper protocols.

Aggregation: Not reported

GlycanGT published supplementary archive, Table S4; glycangt: Journal full-text XML · btag147_supplementary_data.zip / Table_S4.xlsx / Sheet1!A72:E72 (mean D72, SD E72)
Configuration: GraphormerProtocol: GlycanML class Accuracy: GlycanGT study: class Accuracy
Dataset subset: SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
0.66340200000000005 ± 0.013518000000000001 accuracy
fraction · higher

Uncertainty: type: standard_deviation; value: 0.013518000000000001

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · source checked
Methods, coverage and source

Graphormer on GlycanML class Accuracy: GlycanGT study: class Accuracy

Taxonomy: 13,209 glycans total across eight levels, 4–1,737 classes per level. Official fixed GlycanML motif-based train/validation/test splits (8:1:1). Section 2.5 reports class-balanced classifiers, train ∪ validation hyperparameter selection by randomized search with 3-fold cross-validation, followed by one evaluation on the held-out test set; complete procedure repeated with three random seeds, reporting mean and standard deviation. GlycanGT large model pretrained with 35% masking provides [Graph] embeddings to SVM/LightGBM; the selected classifier for each S4 row is not identified. Section 2.6 states that all four graph baselines were trained and evaluated on the same datasets/splits; it does not establish that each baseline used the GlycanGT downstream classifier search. SVM search: 10 iterations, RBF/linear, C logU(1e-3,1e2), gamma logU(1e-4,1e-1); LightGBM: 15 randomized iterations. Do not combine with separate original GlycanML-paper protocols.

Aggregation: Not reported

GlycanGT published supplementary archive, Table S4; glycangt: Journal full-text XML · btag147_supplementary_data.zip / Table_S4.xlsx / Sheet1!A86:E86 (mean D86, SD E86)
Configuration: GraphormerProtocol: GlycanML class Macro-F1: GlycanGT study: class Macro-F1
Dataset subset: SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
0.275447 ± 0.017925 macro_f1
dimensionless · higher

Uncertainty: type: standard_deviation; value: 0.017925

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · source checked
Methods, coverage and source

Graphormer on GlycanML class Macro-F1: GlycanGT study: class Macro-F1

Taxonomy: 13,209 glycans total across eight levels, 4–1,737 classes per level. Official fixed GlycanML motif-based train/validation/test splits (8:1:1). Section 2.5 reports class-balanced classifiers, train ∪ validation hyperparameter selection by randomized search with 3-fold cross-validation, followed by one evaluation on the held-out test set; complete procedure repeated with three random seeds, reporting mean and standard deviation. GlycanGT large model pretrained with 35% masking provides [Graph] embeddings to SVM/LightGBM; the selected classifier for each S4 row is not identified. Section 2.6 states that all four graph baselines were trained and evaluated on the same datasets/splits; it does not establish that each baseline used the GlycanGT downstream classifier search. SVM search: 10 iterations, RBF/linear, C logU(1e-3,1e2), gamma logU(1e-4,1e-1); LightGBM: 15 randomized iterations. Do not combine with separate original GlycanML-paper protocols.

Aggregation: Not reported

GlycanGT published supplementary archive, Table S4; glycangt: Journal full-text XML · btag147_supplementary_data.zip / Table_S4.xlsx / Sheet1!A87:E87 (mean D87, SD E87)
Configuration: RGCNProtocol: GlycanML class Accuracy: GlycanGT study: class Accuracy
Dataset subset: SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
0.10518679724338 ± 0.0041196288326443 accuracy
fraction · higher

Uncertainty: type: standard_deviation; value: 0.0041196288326443

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · source checked
Methods, coverage and source

RGCN on GlycanML class Accuracy: GlycanGT study: class Accuracy

Taxonomy: 13,209 glycans total across eight levels, 4–1,737 classes per level. Official fixed GlycanML motif-based train/validation/test splits (8:1:1). Section 2.5 reports class-balanced classifiers, train ∪ validation hyperparameter selection by randomized search with 3-fold cross-validation, followed by one evaluation on the held-out test set; complete procedure repeated with three random seeds, reporting mean and standard deviation. GlycanGT large model pretrained with 35% masking provides [Graph] embeddings to SVM/LightGBM; the selected classifier for each S4 row is not identified. Section 2.6 states that all four graph baselines were trained and evaluated on the same datasets/splits; it does not establish that each baseline used the GlycanGT downstream classifier search. SVM search: 10 iterations, RBF/linear, C logU(1e-3,1e2), gamma logU(1e-4,1e-1); LightGBM: 15 randomized iterations. Do not combine with separate original GlycanML-paper protocols.

Aggregation: Not reported

GlycanGT published supplementary archive, Table S4; glycangt: Journal full-text XML · btag147_supplementary_data.zip / Table_S4.xlsx / Sheet1!A9:E9 (mean D9, SD E9)
Configuration: RGCNProtocol: GlycanML class Macro-F1: GlycanGT study: class Macro-F1
Dataset subset: SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
0.0260332801336721 ± 0.0019212473071402001 macro_f1
dimensionless · higher

Uncertainty: type: standard_deviation; value: 0.0019212473071402001

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · source checked
Methods, coverage and source

RGCN on GlycanML class Macro-F1: GlycanGT study: class Macro-F1

Taxonomy: 13,209 glycans total across eight levels, 4–1,737 classes per level. Official fixed GlycanML motif-based train/validation/test splits (8:1:1). Section 2.5 reports class-balanced classifiers, train ∪ validation hyperparameter selection by randomized search with 3-fold cross-validation, followed by one evaluation on the held-out test set; complete procedure repeated with three random seeds, reporting mean and standard deviation. GlycanGT large model pretrained with 35% masking provides [Graph] embeddings to SVM/LightGBM; the selected classifier for each S4 row is not identified. Section 2.6 states that all four graph baselines were trained and evaluated on the same datasets/splits; it does not establish that each baseline used the GlycanGT downstream classifier search. SVM search: 10 iterations, RBF/linear, C logU(1e-3,1e2), gamma logU(1e-4,1e-1); LightGBM: 15 randomized iterations. Do not combine with separate original GlycanML-paper protocols.

Aggregation: Not reported

GlycanGT published supplementary archive, Table S4; glycangt: Journal full-text XML · btag147_supplementary_data.zip / Table_S4.xlsx / Sheet1!A10:E10 (mean D10, SD E10)
Configuration: SweetNetProtocol: GlycanML class Accuracy: GlycanGT study: class Accuracy
Dataset subset: SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
0.66376496191512502 ± 0.0116181482611874 accuracy
fraction · higher

Uncertainty: type: standard_deviation; value: 0.0116181482611874

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · source checked
Methods, coverage and source

SweetNet on GlycanML class Accuracy: GlycanGT study: class Accuracy

Taxonomy: 13,209 glycans total across eight levels, 4–1,737 classes per level. Official fixed GlycanML motif-based train/validation/test splits (8:1:1). Section 2.5 reports class-balanced classifiers, train ∪ validation hyperparameter selection by randomized search with 3-fold cross-validation, followed by one evaluation on the held-out test set; complete procedure repeated with three random seeds, reporting mean and standard deviation. GlycanGT large model pretrained with 35% masking provides [Graph] embeddings to SVM/LightGBM; the selected classifier for each S4 row is not identified. Section 2.6 states that all four graph baselines were trained and evaluated on the same datasets/splits; it does not establish that each baseline used the GlycanGT downstream classifier search. SVM search: 10 iterations, RBF/linear, C logU(1e-3,1e2), gamma logU(1e-4,1e-1); LightGBM: 15 randomized iterations. Do not combine with separate original GlycanML-paper protocols.

Aggregation: Not reported

GlycanGT published supplementary archive, Table S4; glycangt: Journal full-text XML · btag147_supplementary_data.zip / Table_S4.xlsx / Sheet1!A47:E47 (mean D47, SD E47)
Configuration: SweetNetProtocol: GlycanML class Macro-F1: GlycanGT study: class Macro-F1
Dataset subset: SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
0.27351444034146899 ± 0.035852517550952402 macro_f1
dimensionless · higher

Uncertainty: type: standard_deviation; value: 0.035852517550952402

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · source checked
Methods, coverage and source

SweetNet on GlycanML class Macro-F1: GlycanGT study: class Macro-F1

Taxonomy: 13,209 glycans total across eight levels, 4–1,737 classes per level. Official fixed GlycanML motif-based train/validation/test splits (8:1:1). Section 2.5 reports class-balanced classifiers, train ∪ validation hyperparameter selection by randomized search with 3-fold cross-validation, followed by one evaluation on the held-out test set; complete procedure repeated with three random seeds, reporting mean and standard deviation. GlycanGT large model pretrained with 35% masking provides [Graph] embeddings to SVM/LightGBM; the selected classifier for each S4 row is not identified. Section 2.6 states that all four graph baselines were trained and evaluated on the same datasets/splits; it does not establish that each baseline used the GlycanGT downstream classifier search. SVM search: 10 iterations, RBF/linear, C logU(1e-3,1e2), gamma logU(1e-4,1e-1); LightGBM: 15 randomized iterations. Do not combine with separate original GlycanML-paper protocols.

Aggregation: Not reported

GlycanGT published supplementary archive, Table S4; glycangt: Journal full-text XML · btag147_supplementary_data.zip / Table_S4.xlsx / Sheet1!A57:E57 (mean D57, SD E57)

Source checking is not independent reproduction. Release 2026-09-23-2b89723c6dd9.

Subset and evaluation context

This record describes a particular subset or cohort used in an evaluation. Its results do not describe the full dataset.

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.

4 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-23-2b89723c6dd9
Property and statementOriginal source and locationReview and provenance
description
Dataset subset reported in GlycanGT published supplementary archive, Table S4. Exact split manifest remains unextracted; source-table identity is retained.
Context-only references
glycangt: Journal full-text XML

Original source ↗

No field-specific location recorded

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Primary article XML snapshot
Retrieved: 2026-09-16T20:20:56.439056+00:00

not individually reviewed

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: 53e89a636c868c0329ee7eb6ae92f1028ec891940bc61730a148981b647fbbe5

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

description
Dataset subset reported in GlycanGT published supplementary archive, Table S4. Exact split manifest remains unextracted; source-table identity is retained.
Context-only references
GlycanGT published supplementary archive, Table S4

Original source ↗

No field-specific location recorded

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Published Bioinformatics btag147 supplementary archive, retrieved 2026-09-23; Table_S4.xlsx SHA-256 d7c35909bac6bcb78ca8fdb32c0463f05e692f15861a8184e65e415e7216f493
Retrieved: 2026-09-23T11:31:33.520570+00:00

not individually reviewed

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: 27748c6c0c0bb07b0105d274fb745fd4dfe702d34b9ee367d1ddacbc71c56ab0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

name
SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
Context-only references
glycangt: Journal full-text XML

Original source ↗

No field-specific location recorded

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Primary article XML snapshot
Retrieved: 2026-09-16T20:20:56.439056+00:00

not individually reviewed

No individual claim review recorded

Audit details

Field: name

Source artifact SHA-256: 53e89a636c868c0329ee7eb6ae92f1028ec891940bc61730a148981b647fbbe5

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

name
SugarBase taxonomy class; GlycanML official motif split (GlycanML split)
Context-only references
GlycanGT published supplementary archive, Table S4

Original source ↗

No field-specific location recorded

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: Published Bioinformatics btag147 supplementary archive, retrieved 2026-09-23; Table_S4.xlsx SHA-256 d7c35909bac6bcb78ca8fdb32c0463f05e692f15861a8184e65e415e7216f493
Retrieved: 2026-09-23T11:31:33.520570+00:00

not individually reviewed

No individual claim review recorded

Audit details

Field: name

Source artifact SHA-256: 27748c6c0c0bb07b0105d274fb745fd4dfe702d34b9ee367d1ddacbc71c56ab0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Sources and history

View linked audit checks and correction history

Release 2026-09-23-2b89723c6dd9 · Record review: source checked

2 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: glycangt-2026-table-s4-dataset-sugarbase-taxonomy-class-glycanml-official-motif-split

areas
glycans
missing metadata
version: unreported; url: unextracted
Related records

Suggest a correction