Protocol

GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)

GlycanML Glycos · Table 3, p. 8. Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column.

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, p. 8, Glycos

10 evaluations · 10 metric rows

At 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. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column.

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, p. 8, Glycos

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Benchmarks

GlycanML

Tasks

GlycanML glycosylation type prediction

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.

Comparison and metric

GlycanML Glycos · Table 3, p. 8

accuracy (percent) · Higher values are better for this metric.

Evaluation protocol · GlyConnect glycosylation · Glycos

Shallow CNN · Configuration · Author-reported evaluation97.22(0.44)
ResNet · Configuration · Author-reported evaluation98.55(0.58)
LSTM · Configuration · Author-reported evaluation96.28(1.42)
Transformer · Configuration · Author-reported evaluation95.90(1.45)
GCN · Configuration · Author-reported evaluation95.90(0.11)
GAT · Configuration · Author-reported evaluation94.63(0.39)
GIN · Configuration · Author-reported evaluation97.16(0.19)
MPNN · Configuration · Author-reported evaluation97.41(0.90)
RGCN · Configuration · Author-reported evaluation95.14(2.21)
CompGCN · Configuration · Author-reported evaluation94.38(3.13)

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, Glycos

Values, uncertainty and evidence

accuracy: original source values
Tested entity	Printed value	Uncertainty	Evidence
Shallow CNN · Configuration	97.22(0.44) percent	type: standard_deviation; value: 0.44; 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 Glycos
ResNet · Configuration	98.55(0.58) percent	type: standard_deviation; value: 0.58; 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 Glycos
LSTM · Configuration	96.28(1.42) percent	type: standard_deviation; value: 1.42; 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 Glycos
Transformer · Configuration	95.90(1.45) percent	type: standard_deviation; value: 1.45; 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 Glycos
GCN · Configuration	95.90(0.11) percent	type: standard_deviation; value: 0.11; 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 Glycos
GAT · Configuration	94.63(0.39) percent	type: standard_deviation; value: 0.39; 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 Glycos
GIN · Configuration	97.16(0.19) percent	type: standard_deviation; value: 0.19; 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 Glycos
MPNN · Configuration	97.41(0.90) percent	type: standard_deviation; value: 0.9; 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 Glycos
RGCN · Configuration	95.14(2.21) percent	type: standard_deviation; value: 2.21; 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 Glycos
CompGCN · Configuration	94.38(3.13) percent	type: standard_deviation; value: 3.13; 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 Glycos

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

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
MPNN: GlyConnect glycosylation · Glycos Configuration: MPNNProtocol: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)Dataset: GlyConnect glycosylation · Glycos Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Author-reported evaluation · Evaluation metadata: needs review
97.41(0.90)% accuracy Unit: percent · Direction: higher	Uncertainty: type: standard deviation; value: 0.9; 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 Glycos Source checking is not independent reproduction.
GIN: GlyConnect glycosylation · Glycos Configuration: GINProtocol: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)Dataset: GlyConnect glycosylation · Glycos Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Author-reported evaluation · Evaluation metadata: needs review
97.16(0.19)% accuracy Unit: percent · Direction: higher	Uncertainty: type: standard deviation; value: 0.19; 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 Glycos Source checking is not independent reproduction.
RGCN: GlyConnect glycosylation · Glycos Configuration: RGCNProtocol: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)Dataset: GlyConnect glycosylation · Glycos Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Author-reported evaluation · Evaluation metadata: needs review
95.14(2.21)% accuracy Unit: percent · Direction: higher	Uncertainty: type: standard deviation; value: 2.21; 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 Glycos Source checking is not independent reproduction.
CompGCN: GlyConnect glycosylation · Glycos Configuration: CompGCNProtocol: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)Dataset: GlyConnect glycosylation · Glycos Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Author-reported evaluation · Evaluation metadata: needs review
94.38(3.13)% accuracy Unit: percent · Direction: higher	Uncertainty: type: standard deviation; value: 3.13; 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 3, row CompGCN, column Glycos Source checking is not independent reproduction.
LSTM: GlyConnect glycosylation · Glycos Configuration: LSTMProtocol: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)Dataset: GlyConnect glycosylation · Glycos Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Author-reported evaluation · Evaluation metadata: needs review
96.28(1.42)% accuracy Unit: percent · Direction: higher	Uncertainty: type: standard deviation; value: 1.42; 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 Glycos Source checking is not independent reproduction.
ResNet: GlyConnect glycosylation · Glycos Configuration: ResNetProtocol: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)Dataset: GlyConnect glycosylation · Glycos Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Author-reported evaluation · Evaluation metadata: needs review
98.55(0.58)% accuracy Unit: percent · Direction: higher	Uncertainty: type: standard deviation; value: 0.58; 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 Glycos Source checking is not independent reproduction.
Transformer: GlyConnect glycosylation · Glycos Configuration: TransformerProtocol: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)Dataset: GlyConnect glycosylation · Glycos Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Author-reported evaluation · Evaluation metadata: needs review
95.90(1.45)% accuracy Unit: percent · Direction: higher	Uncertainty: type: standard deviation; value: 1.45; 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 Glycos Source checking is not independent reproduction.
GAT: GlyConnect glycosylation · Glycos Configuration: GATProtocol: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)Dataset: GlyConnect glycosylation · Glycos Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Author-reported evaluation · Evaluation metadata: needs review
94.63(0.39)% accuracy Unit: percent · Direction: higher	Uncertainty: type: standard deviation; value: 0.39; 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 Glycos Source checking is not independent reproduction.
GCN: GlyConnect glycosylation · Glycos Configuration: GCNProtocol: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)Dataset: GlyConnect glycosylation · Glycos Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Author-reported evaluation · Evaluation metadata: needs review
95.90(0.11)% accuracy Unit: percent · Direction: higher	Uncertainty: type: standard deviation; value: 0.11; 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 Glycos Source checking is not independent reproduction.
Shallow CNN: GlyConnect glycosylation · Glycos Configuration: Shallow CNNProtocol: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)Dataset: GlyConnect glycosylation · Glycos Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Author-reported evaluation · Evaluation metadata: needs review
97.22(0.44)% accuracy Unit: percent · Direction: higher	Uncertainty: type: standard deviation; value: 0.44; 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 Glycos 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, Glycos

Strengths and limitations

Strengths and considerations

No source-reviewed explanatory claims are recorded here yet.

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-1e0e586e8edab0dc26

Evidence 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

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
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. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Individual claims	GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning Original source ↗ Table 3, p. 8, Glycos Version: arXiv:2405.16206v1, 2024-05-25 Retrieved: 2026-09-16T21:04:56.017006+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated review. No human sign-off or experimental reproduction. Field: `attributes.profile.sections.0.body` Source artifact SHA-256: `9ba3db678b4550898a612b42e8832bf9dee40935090fc4d969ba8f6ac5106979` Hash scope: Exact retrieved primary paper artifact bytes. Inspected artifact
Introduction GlycanML Glycos · Table 3, p. 8. Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column. Individual claims	GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning Original source ↗ Table 3, p. 8, Glycos Version: arXiv:2405.16206v1, 2024-05-25 Retrieved: 2026-09-16T21:04:56.017006+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated review. No human sign-off or experimental reproduction. Field: `attributes.profile.summary` Source artifact SHA-256: `9ba3db678b4550898a612b42e8832bf9dee40935090fc4d969ba8f6ac5106979` Hash scope: Exact retrieved primary paper artifact bytes. Inspected artifact
Relationship: evaluates task discovery-benchmark-glycanml-glycosylation-type-prediction Individual claims	GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning Original source ↗ Table 3, p. 8, Glycos Version: arXiv:2405.16206v1, 2024-05-25 Retrieved: 2026-09-16T21:04:56.017006+00:00	source checked automated source review · 2026-09-17 Audit details Field: `links:evaluates_task:discovery-benchmark-glycanml-glycosylation-type-prediction` Claim: paper-claim-0b9d3bbf2ac04ab720 Source artifact SHA-256: `9ba3db678b4550898a612b42e8832bf9dee40935090fc4d969ba8f6ac5106979` Hash scope: Exact retrieved primary paper artifact bytes. Inspected artifact
Relationship: part of discovery-benchmark-glycanml Individual claims	GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning Original source ↗ Table 3, p. 8, Glycos Version: arXiv:2405.16206v1, 2024-05-25 Retrieved: 2026-09-16T21:04:56.017006+00:00	source checked automated source review · 2026-09-17 Audit details Field: `links:part_of:discovery-benchmark-glycanml` Claim: paper-claim-accb34acc7592660b4 Source artifact SHA-256: `9ba3db678b4550898a612b42e8832bf9dee40935090fc4d969ba8f6ac5106979` Hash scope: Exact retrieved primary paper artifact bytes. Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

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

Download this release

Technical metadata and extraction receipts

Stable ID: paper-protocol-1e0e586e8edab0dc26

areas: glycomics
entity level: protocol
protocol: Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column.
comparison panels: id: glycanml-v1-single-glycos; title: GlycanML Glycos · Table 3, p. 8; protocol id: paper-protocol-1e0e586e8edab0dc26; dataset id: paper-dataset-e797e17c76c1278706; metric: accuracy; unit: percent; direction: higher; result ids: paper-result-ee2fc7d3f24c74d26a; paper-result-cd7d5e177d170e4ce3; paper-result-c7fcf3af8b768565b7; paper-result-e2f3edb52244aed4ea; paper-result-edb19c124f6d9e2398; paper-result-ebfebb353d4b0a9e5a; paper-result-04b741864eefb0125e; paper-result-00ca74108e1dd8a295; paper-result-7ef41afc692b853ffd; paper-result-c4ba6aef76ee19b8d5; source ids: expansion-p3-glycanml-2405-16206v1; source locator: Table 3, p. 8, Glycos; context: Author-reported single-task models on the same held-out task; not a cross-paper ranking. Taxonomy, immunogenicity and glycosylation: motif-frequency K-means cluster allocation 8:1:1. Interaction: MMseqs2 protein clusters at minimum identity 0.5 allocated 8:1:1. Exact counts are attached to each column.; 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
benchmark research: review date: 2026-09-17; status: complete_comparison_extracted; primary sources: expansion-p3-glycanml-2405-16206v1; inspected locators: Table 3, p. 8, Glycos; 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, Glycos; ambiguities: None recorded

Related records

evaluates task: GlycanML glycosylation type prediction
part of: GlycanML
subject: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction): links:evaluates_task:discovery-benchmark-glycanml-glycosylation-type-prediction
subject: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction): links:part_of:discovery-benchmark-glycanml
benchmark: GIN: GlyConnect glycosylation · Glycos
benchmark: LSTM: GlyConnect glycosylation · Glycos
benchmark: GCN: GlyConnect glycosylation · Glycos
benchmark: MPNN: GlyConnect glycosylation · Glycos
benchmark: RGCN: GlyConnect glycosylation · Glycos
benchmark: Shallow CNN: GlyConnect glycosylation · Glycos
benchmark: CompGCN: GlyConnect glycosylation · Glycos
benchmark: Transformer: GlyConnect glycosylation · Glycos
benchmark: GAT: GlyConnect glycosylation · Glycos
benchmark: ResNet: GlyConnect glycosylation · Glycos

Suggest a correction