Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
Protocol
SugarBase taxonomy · Family (GlycanML taxonomy prediction)
GlycanML Family · Table 3, p. 8. Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1.
GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, p. 8, FamilyAt a glance
Explanatory profile: limited source coverage · Automated source review, 2026-09-17. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
How it works
Evaluation in this paper
Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1.
GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, p. 8, FamilyEvaluation design
Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.
Benchmarks
Tasks
These source-backed links do not make different protocols or scores interchangeable.
Recorded evaluations
Each evaluation records what was tested and under which conditions.
- MPNN: SugarBase taxonomy · Family
- Shallow CNN: SugarBase taxonomy · Family
- Shallow CNN / TS: SugarBase taxonomy · Family
- Shallow CNN / N-MTL: SugarBase taxonomy · Family
- RGCN / UW: SugarBase taxonomy · Family
- CompGCN: SugarBase taxonomy · Family
- LSTM: SugarBase taxonomy · Family
- RGCN / DTP: SugarBase taxonomy · Family
- GIN: SugarBase taxonomy · Family
- Transformer: SugarBase taxonomy · Family
- GAT: SugarBase taxonomy · Family
- RGCN / GN: SugarBase taxonomy · Family
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.
GlycanML Family · Table 3, p. 8
accuracy (percent) · Higher values are better for this metric.
Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1.
- Shallow CNN · Configuration · Author-reported evaluation45.27(1.52)
- ResNet · Configuration · Author-reported evaluation37.36(0.99)
- LSTM · Configuration · Author-reported evaluation38.74(1.47)
- Transformer · Configuration · Author-reported evaluation33.30(0.86)
- GCN · Configuration · Author-reported evaluation34.93(0.76)
- GAT · Configuration · Author-reported evaluation37.50(0.91)
- GIN · Configuration · Author-reported evaluation40.04(0.86)
- MPNN · Configuration · Author-reported evaluation41.60(0.64)
- RGCN · Configuration · Author-reported evaluation46.35(0.50)
- CompGCN · Configuration · Author-reported evaluation44.03(1.51)
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.
GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, p. 8, FamilyValues, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| Shallow CNN · Configuration | 45.27(1.52) percent | type: standard_deviation; value: 1.52; n: 3; unit: same_as_metric | Author-reported evaluation · source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Shallow CNN, column Family |
| ResNet · Configuration | 37.36(0.99) percent | type: standard_deviation; value: 0.99; n: 3; unit: same_as_metric | Author-reported evaluation · source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row ResNet, column Family |
| LSTM · Configuration | 38.74(1.47) percent | type: standard_deviation; value: 1.47; n: 3; unit: same_as_metric | Author-reported evaluation · source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row LSTM, column Family |
| Transformer · Configuration | 33.30(0.86) percent | type: standard_deviation; value: 0.86; n: 3; unit: same_as_metric | Author-reported evaluation · source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Family |
| GCN · Configuration | 34.93(0.76) percent | type: standard_deviation; value: 0.76; n: 3; unit: same_as_metric | Author-reported evaluation · source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row GCN, column Family |
| GAT · Configuration | 37.50(0.91) percent | type: standard_deviation; value: 0.91; n: 3; unit: same_as_metric | Author-reported evaluation · source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row GAT, column Family |
| GIN · Configuration | 40.04(0.86) percent | type: standard_deviation; value: 0.86; n: 3; unit: same_as_metric | Author-reported evaluation · source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row GIN, column Family |
| MPNN · Configuration | 41.60(0.64) percent | type: standard_deviation; value: 0.64; n: 3; unit: same_as_metric | Author-reported evaluation · source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row MPNN, column Family |
| RGCN · Configuration | 46.35(0.50) percent | type: standard_deviation; value: 0.5; n: 3; unit: same_as_metric | Author-reported evaluation · source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row RGCN, column Family |
| CompGCN · Configuration | 44.03(1.51) percent | type: standard_deviation; value: 1.51; n: 3; unit: same_as_metric | Author-reported evaluation · source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row CompGCN, column Family |
Scope and limitations
- Taxonomic levels are distinct tasks; do not combine raw accuracy across levels.
- Protein–glycan scores evaluate combined glycan encoders plus ESM-1b/MLP, not an ESM-1b standalone checkpoint.
- Cluster manifests and trained checkpoint hashes are not enumerated in the paper table.
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 · 22 evaluations · 22 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Shallow CNN: SugarBase taxonomy · Family Configuration: Shallow CNNProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 45.27(1.52)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.52; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Shallow CNN, column Family Source checking is not independent reproduction. |
| Shallow CNN / DWA: SugarBase taxonomy · Family Configuration: Shallow CNN / DWAProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 41.57(2.17)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 2.17; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, Shallow CNN, DWA, column Family Source checking is not independent reproduction. |
| CompGCN: SugarBase taxonomy · Family Configuration: CompGCNProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 44.03(1.51)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.51; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row CompGCN, column Family Source checking is not independent reproduction. |
| GCN: SugarBase taxonomy · Family Configuration: GCNProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 34.93(0.76)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.76; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row GCN, column Family Source checking is not independent reproduction. |
| Shallow CNN / GN: SugarBase taxonomy · Family Configuration: Shallow CNN / GNProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 42.40(1.49)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.49; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, Shallow CNN, GN, column Family Source checking is not independent reproduction. |
| RGCN / DWA: SugarBase taxonomy · Family Configuration: RGCN / DWAProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 44.11(1.24)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.24; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, RGCN, DWA, column Family Source checking is not independent reproduction. |
| MPNN: SugarBase taxonomy · Family Configuration: MPNNProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 41.60(0.64)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.64; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row MPNN, column Family Source checking is not independent reproduction. |
| Shallow CNN / DTP: SugarBase taxonomy · Family Configuration: Shallow CNN / DTPProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 42.76(2.02)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 2.02; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, Shallow CNN, DTP, column Family Source checking is not independent reproduction. |
| GAT: SugarBase taxonomy · Family Configuration: GATProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 37.50(0.91)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.91; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row GAT, column Family Source checking is not independent reproduction. |
| RGCN / GN: SugarBase taxonomy · Family Configuration: RGCN / GNProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 44.11(0.13)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.13; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, RGCN, GN, column Family Source checking is not independent reproduction. |
| Shallow CNN / TS: SugarBase taxonomy · Family Configuration: Shallow CNN / TSProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 45.19(2.50)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 2.5; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, Shallow CNN, TS, column Family Source checking is not independent reproduction. |
| GIN: SugarBase taxonomy · Family Configuration: GINProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 40.04(0.86)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.86; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row GIN, column Family Source checking is not independent reproduction. |
| RGCN / N-MTL: SugarBase taxonomy · Family Configuration: RGCN / N-MTLProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 45.67(1.64)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.64; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, RGCN, N-MTL, column Family Source checking is not independent reproduction. |
| RGCN / TS: SugarBase taxonomy · Family Configuration: RGCN / TSProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 47.99(0.22)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.22; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, RGCN, TS, column Family Source checking is not independent reproduction. |
| Shallow CNN / N-MTL: SugarBase taxonomy · Family Configuration: Shallow CNN / N-MTLProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 44.11(1.63)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.63; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, Shallow CNN, N-MTL, column Family Source checking is not independent reproduction. |
| ResNet: SugarBase taxonomy · Family Configuration: ResNetProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 37.36(0.99)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.99; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row ResNet, column Family Source checking is not independent reproduction. |
| Transformer: SugarBase taxonomy · Family Configuration: TransformerProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 33.30(0.86)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.86; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Family Source checking is not independent reproduction. |
| Shallow CNN / UW: SugarBase taxonomy · Family Configuration: Shallow CNN / UWProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 44.40(0.00)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, Shallow CNN, UW, column Family Source checking is not independent reproduction. |
| RGCN / UW: SugarBase taxonomy · Family Configuration: RGCN / UWProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 44.90(0.88)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.88; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, RGCN, UW, column Family Source checking is not independent reproduction. |
| RGCN / DTP: SugarBase taxonomy · Family Configuration: RGCN / DTPProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 44.29(0.47)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.47; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 4, RGCN, DTP, column Family Source checking is not independent reproduction. |
| RGCN: SugarBase taxonomy · Family Configuration: RGCNProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 46.35(0.50)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.5; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row RGCN, column Family Source checking is not independent reproduction. |
| LSTM: SugarBase taxonomy · Family Configuration: LSTMProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)Dataset: SugarBase taxonomy · Family Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Author-reported evaluation · Evaluation metadata: needs review | ||
| 38.74(1.47)% accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.47; n: 3; unit: same as metric Scored: Not reported · Eligible: Not reported | source checkedGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row LSTM, column Family Source checking is not independent reproduction. |
Papers and result coverage
Last literature check: 2026-09-17. Primary-paper within-study comparison; numerical results not independently reproduced.
| Paper or primary resource | Version | Reference |
|---|---|---|
| GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning | arXiv:2405.16206v1, 2024-05-25 | Read source |
What is still missing
- Paper table does not enumerate trained checkpoint hashes; source configuration names retained.
Search and extraction details
complete comparison extracted
Searches
- GlycanML benchmark 2405.16206
Evidence locations
- Table 3, p. 8, Family
Strengths and limitations
Limitations and conditions
No source-reviewed explanatory claims are recorded here yet.
Profile review details
Primary-source transcription and separate automated review. No human sign-off or experimental reproduction.
Stable record: paper-protocol-8dca9eabea26dee766Evidence table
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
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Evaluation in this paper Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Individual claims | GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning Table 3, p. 8, Family Version: arXiv:2405.16206v1, 2024-05-25 | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated review. No human sign-off or experimental reproduction. Field: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Introduction GlycanML Family · Table 3, p. 8. Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1. Individual claims | GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning Table 3, p. 8, Family Version: arXiv:2405.16206v1, 2024-05-25 | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated review. No human sign-off or experimental reproduction. Field: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Relationship: evaluates task discovery-benchmark-glycanml-taxonomy-prediction Individual claims | GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning Table 3, p. 8, Family Version: arXiv:2405.16206v1, 2024-05-25 | source checked automated source review · 2026-09-17 Audit detailsField: Claim: paper-claim-150fbfaa8b1348b44a Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Relationship: part of discovery-benchmark-glycanml Individual claims | GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning Table 3, p. 8, Family Version: arXiv:2405.16206v1, 2024-05-25 | source checked automated source review · 2026-09-17 Audit detailsField: Claim: paper-claim-a0dd61e8be7a9bf8b5 Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: needs review
- GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Original source · arXiv:2405.16206v1, 2024-05-25
Technical metadata and extraction receipts
Stable ID: paper-protocol-8dca9eabea26dee766
- areas
- glycomics
- entity level
- protocol
- protocol
- Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1.
- comparison panels
- id: glycanml-v1-single-family; title: GlycanML Family · Table 3, p. 8; protocol id: paper-protocol-8dca9eabea26dee766; dataset id: paper-dataset-8d5d79e4a6a070bfff; metric: accuracy; unit: percent; direction: higher; result ids: paper-result-09e347c7674f561706; paper-result-8bbf97e6e23787da99; paper-result-f5c63db202d546dd8a; paper-result-941024aaffa398c454; paper-result-32c123a2e27ebbe79e; paper-result-4a140ae1cf5519925c; paper-result-76cbc3d2466076b944; paper-result-42fcbda81a387d226d; paper-result-e4ad7f8d96df00ea4b; paper-result-1337bae859236e6dcf; source ids: expansion-p3-glycanml-2405-16206v1; source locator: Table 3, p. 8, Family; context: Author-reported single-task models on the same held-out task; not a cross-paper ranking. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1.; caveats: Taxonomic levels are distinct tasks; do not combine raw accuracy across levels.; Protein–glycan scores evaluate combined glycan encoders plus ESM-1b/MLP, not an ESM-1b standalone checkpoint.; Cluster manifests and trained checkpoint hashes are not enumerated in the paper table.; review: method: automated_source_review; date: 2026-09-17; id: glycanml-v1-mtl-0-family; title: GlycanML Family · Table 4, p. 9; protocol id: paper-protocol-8dca9eabea26dee766; dataset id: paper-dataset-8d5d79e4a6a070bfff; metric: accuracy; unit: percent; direction: higher; result ids: paper-result-09e347c7674f561706; paper-result-89df39b51fc8f73a18; paper-result-3710d0e01f022a8f58; paper-result-76b9f005da338ff5f4; paper-result-97cf3af868ea202c20; paper-result-0f26b2626d93d81e1a; paper-result-45cd9dbf505c6c3edf; source ids: expansion-p3-glycanml-2405-16206v1; source locator: Table 4, p. 9, Family; context: Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1.; caveats: Mean accuracy is an unweighted aggregate of eight taxonomic tasks as reported; keep separate from every individual level.; The six MTL approaches change training, so do not label their scores as the base encoder alone.; review: method: automated_source_review; date: 2026-09-17; id: glycanml-v1-mtl-1-family; title: GlycanML Family · Table 4, p. 9; protocol id: paper-protocol-8dca9eabea26dee766; dataset id: paper-dataset-8d5d79e4a6a070bfff; metric: accuracy; unit: percent; direction: higher; result ids: paper-result-e4ad7f8d96df00ea4b; paper-result-7e5eb5e5def1997d2a; paper-result-6189ade0e2553e6a5f; paper-result-850116eec75fde4e16; paper-result-a90400ff944a9dba82; paper-result-4089bd143f1ec302b3; paper-result-b691a9c8c205144c7f; source ids: expansion-p3-glycanml-2405-16206v1; source locator: Table 4, p. 9, Family; context: Fixed backbone; compare adaptation strategies, not standalone foundation models. SugarBase taxonomy: motif-frequency K-means cluster allocation 8:1:1.; caveats: Mean accuracy is an unweighted aggregate of eight taxonomic tasks as reported; keep separate from every individual level.; The six MTL approaches change training, so do not label their scores as the base encoder alone.; review: method: automated_source_review; date: 2026-09-17
- benchmark research
- review date: 2026-09-17; status: complete_comparison_extracted; primary sources: expansion-p3-glycanml-2405-16206v1; inspected locators: Table 3, p. 8, Family; searched queries: GlycanML benchmark 2405.16206; gaps: Paper table does not enumerate trained checkpoint hashes; source configuration names retained.; claim scope: Primary-paper within-study comparison; numerical results not independently reproduced.
- legacy kinds
- benchmark
- entity classification
- review date: 2026-09-17; rationale: The source-backed record identifies a specified evaluated procedure and its dataset/split/scoring context. Classify it as a protocol while preserving version and comparison restrictions.; source ids: expansion-p3-glycanml-2405-16206v1; source locator: Table 3, p. 8, Family; ambiguities: None recorded
Related records
- evaluates task: GlycanML taxonomy prediction
- part of: GlycanML
- subject: SugarBase taxonomy · Family (GlycanML taxonomy prediction): links:evaluates_task:discovery-benchmark-glycanml-taxonomy-prediction
- subject: SugarBase taxonomy · Family (GlycanML taxonomy prediction): links:part_of:discovery-benchmark-glycanml
- benchmark: MPNN: SugarBase taxonomy · Family
- benchmark: Shallow CNN: SugarBase taxonomy · Family
- benchmark: Shallow CNN / TS: SugarBase taxonomy · Family
- benchmark: Shallow CNN / N-MTL: SugarBase taxonomy · Family
- benchmark: RGCN / UW: SugarBase taxonomy · Family
- benchmark: CompGCN: SugarBase taxonomy · Family
- benchmark: LSTM: SugarBase taxonomy · Family
- benchmark: RGCN / DTP: SugarBase taxonomy · Family
- benchmark: GIN: SugarBase taxonomy · Family
- benchmark: Transformer: SugarBase taxonomy · Family
- benchmark: GAT: SugarBase taxonomy · Family
- benchmark: RGCN / GN: SugarBase taxonomy · Family
- benchmark: RGCN / TS: SugarBase taxonomy · Family
- benchmark: Shallow CNN / UW: SugarBase taxonomy · Family
- benchmark: RGCN: SugarBase taxonomy · Family
- benchmark: Shallow CNN / GN: SugarBase taxonomy · Family
- benchmark: Shallow CNN / DWA: SugarBase taxonomy · Family
- benchmark: ResNet: SugarBase taxonomy · Family
- benchmark: RGCN / N-MTL: SugarBase taxonomy · Family
- benchmark: Shallow CNN / DTP: SugarBase taxonomy · Family
- benchmark: RGCN / DWA: SugarBase taxonomy · Family
- benchmark: GCN: SugarBase taxonomy · Family