rewirebio.iobenchmarks
Configuration

Transformer

Transformer as evaluated in the cited study. Transformer architecture in Table 2; single-task supervised encoder plus MLP; interaction additionally uses ESM-1b protein embeddings

SourcesGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Domain

11 evaluations · 11 results

Overview

Key specifications have not been extracted for this record. See the linked evaluation and sources for the reported setup.

limited source coverage · Automated source review, 2026-09-17. All specifications and missing details

Model Capabilities & Hardware Requirements

Deployment facts recorded for Transformer. Fields the record does not carry are marked not recorded.

ParametersNot recorded
Minimum VRAMNot recorded
Inference LatencyNot recorded
Context WindowNot recorded
AccessNot recorded
LicenseNot recorded

Evaluated Checkpoint: Transformer architecture in Table 2; single-task supervised encoder plus MLP; interaction additionally uses ESM-1b protein embeddings

Evaluations and results

11 evaluations · 11 results. Different protocols are not a single leaderboard.

Sorted by Accuracy (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configurationProtocol and datasetAccuracyAUPRCSpearman
TransformerEvaluationGlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction), GlyConnect glycosylation · Glycos95.90(1.45)% (best in column)Not reportedNot reported
TransformerEvaluationSugarBase taxonomy · Domain (GlycanML taxonomy prediction), SugarBase taxonomy · Domain91.98(0.27)%Not reportedNot reported
TransformerEvaluationSugarBase taxonomy · Kingdom (GlycanML taxonomy prediction), SugarBase taxonomy · Kingdom87.34(1.16)%Not reportedNot reported
TransformerEvaluationSugarBase taxonomy · Phylum (GlycanML taxonomy prediction), SugarBase taxonomy · Phylum80.49(1.91)%Not reportedNot reported
TransformerEvaluationSugarBase taxonomy · Class (GlycanML taxonomy prediction), SugarBase taxonomy · Class62.13(1.47)%Not reportedNot reported
TransformerEvaluationSugarBase taxonomy · Order (GlycanML taxonomy prediction), SugarBase taxonomy · Order38.30(1.10)%Not reportedNot reported
TransformerEvaluationSugarBase taxonomy · Family (GlycanML taxonomy prediction), SugarBase taxonomy · Family33.30(0.86)%Not reportedNot reported
TransformerEvaluationSugarBase taxonomy · Genus (GlycanML taxonomy prediction), SugarBase taxonomy · Genus27.97(1.61)%Not reportedNot reported
TransformerEvaluationSugarBase taxonomy · Species (GlycanML taxonomy prediction), SugarBase taxonomy · Species27.49(1.20)%Not reportedNot reported
TransformerEvaluationSugarBase immunogenicity · Immuno (GlycanML immunogenicity prediction), SugarBase immunogenicity · ImmunoNot reported0.729(0.069)Not reported
TransformerEvaluationLectinOracle interaction · Interaction (GlycanML protein-glycan interaction prediction), LectinOracle interaction · InteractionNot reportedNot reported0.244(0.009)
All 11 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: TransformerProtocol: SugarBase taxonomy · Species (GlycanML taxonomy prediction)
Dataset: SugarBase taxonomy · Species
27.49(1.20)% Accuracy
percent · higher

Uncertainty: SD 1.2

Coverage: Not reported scored / Not reported eligible

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

Transformer: SugarBase taxonomy · Species

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.

Aggregation: Not reported

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Species
Configuration: TransformerProtocol: SugarBase taxonomy · Order (GlycanML taxonomy prediction)
Dataset: SugarBase taxonomy · Order
38.30(1.10)% Accuracy
percent · higher

Uncertainty: SD 1.1

Coverage: Not reported scored / Not reported eligible

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

Transformer: SugarBase taxonomy · Order

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.

Aggregation: Not reported

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Order
Configuration: TransformerProtocol: SugarBase taxonomy · Domain (GlycanML taxonomy prediction)
Dataset: SugarBase taxonomy · Domain
91.98(0.27)% Accuracy
percent · higher

Uncertainty: SD 0.27

Coverage: Not reported scored / Not reported eligible

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

Transformer: SugarBase taxonomy · Domain

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.

Aggregation: Not reported

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Domain
Configuration: TransformerProtocol: SugarBase taxonomy · Genus (GlycanML taxonomy prediction)
Dataset: SugarBase taxonomy · Genus
27.97(1.61)% Accuracy
percent · higher

Uncertainty: SD 1.61

Coverage: Not reported scored / Not reported eligible

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

Transformer: SugarBase taxonomy · Genus

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.

Aggregation: Not reported

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Genus
Configuration: TransformerProtocol: SugarBase taxonomy · Family (GlycanML taxonomy prediction)
Dataset: SugarBase taxonomy · Family
33.30(0.86)% Accuracy
percent · higher

Uncertainty: SD 0.86

Coverage: Not reported scored / Not reported eligible

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

Transformer: 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.

Aggregation: Not reported

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Family
Configuration: TransformerProtocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction)
Dataset: SugarBase taxonomy · Kingdom
87.34(1.16)% Accuracy
percent · higher

Uncertainty: SD 1.16

Coverage: Not reported scored / Not reported eligible

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

Transformer: SugarBase taxonomy · Kingdom

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.

Aggregation: Not reported

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Kingdom
Configuration: TransformerProtocol: SugarBase immunogenicity · Immuno (GlycanML immunogenicity prediction)
Dataset: SugarBase immunogenicity · Immuno
0.729(0.069) AUPRC
unitless · higher

Uncertainty: SD 0.069

Coverage: Not reported scored / Not reported eligible

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

Transformer: SugarBase immunogenicity · Immuno

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.

Aggregation: Not reported

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Immuno
Configuration: TransformerProtocol: SugarBase taxonomy · Phylum (GlycanML taxonomy prediction)
Dataset: SugarBase taxonomy · Phylum
80.49(1.91)% Accuracy
percent · higher

Uncertainty: SD 1.91

Coverage: Not reported scored / Not reported eligible

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

Transformer: SugarBase taxonomy · Phylum

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.

Aggregation: Not reported

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Phylum
Configuration: TransformerProtocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction)
Dataset: SugarBase taxonomy · Class
62.13(1.47)% Accuracy
percent · higher

Uncertainty: SD 1.47

Coverage: Not reported scored / Not reported eligible

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

Transformer: SugarBase taxonomy · Class

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.

Aggregation: Not reported

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Class
Configuration: TransformerProtocol: LectinOracle interaction · Interaction (GlycanML protein-glycan interaction prediction)
Dataset: LectinOracle interaction · Interaction
0.244(0.009) Spearman
unitless · higher

Uncertainty: SD 0.009

Coverage: Not reported scored / Not reported eligible

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

Transformer: LectinOracle interaction · Interaction

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.

Aggregation: Not reported

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Interaction
Configuration: TransformerProtocol: GlyConnect glycosylation · Glycos (GlycanML glycosylation type prediction)
Dataset: GlyConnect glycosylation · Glycos
95.90(1.45)% Accuracy
percent · higher

Uncertainty: SD 1.45

Coverage: Not reported scored / Not reported eligible

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

Transformer: 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.

Aggregation: Not reported

GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Glycos

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Use this configuration

How it works, versions and access

How it works

Evaluation in this paper

Transformer architecture in Table 2; single-task supervised encoder plus MLP; interaction additionally uses ESM-1b protein embeddings

SourcesGlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning · Table 3, row Transformer, column Domain
Strengths, limitations and unresolved questions

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-model-ca686150d56cf81427

Specifications

Inputs, training, access and other details

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.

Inputs, outputs and configuration
PropertyDescription and evidence
Model typeNot extracted or verified for this record.
InputsNot extracted or verified for this record.
OutputsNot extracted or verified for this record.
ParametersNot extracted or verified for this record.
Known versionsNot extracted or verified for this record.
Training dataNot extracted or verified for this record.
Context limitsNot extracted or verified for this record.
AccessNot extracted or verified for this record.
Code licenceNot extracted or verified for this record.
Weights licenceNot extracted or verified for this record.

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.

2 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Evaluation in this paper
Transformer architecture in Table 2; single-task supervised encoder plus MLP; interaction additionally uses ESM-1b protein embeddings
Individual claims
GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning

Original source ↗

Table 3, row Transformer, column Domain

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
Transformer as evaluated in the cited study. Transformer architecture in Table 2; single-task supervised encoder plus MLP; interaction additionally uses ESM-1b protein embeddings
Individual claims
GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning

Original source ↗

Table 3, row Transformer, column Domain

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

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: needs review

1 source record and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID paper-model-ca686150d56cf81427.

Related records

How to cite

Transformer. Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/paper-model-ca686150d56cf81427/

Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.

The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence

Suggest a correction