| Configuration: Shallow CNN | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 91.66(2.29)% Accuracy percent · higher Uncertainty: SD 2.29 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN: 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 Shallow CNN, column Kingdom |
|---|
| Configuration: RGCN / UW | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 91.77(0.23)% Accuracy percent · higher Uncertainty: SD 0.23 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / UW: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, RGCN, UW, column Kingdom |
|---|
| Configuration: Shallow CNN / TS | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 91.55(1.03)% Accuracy percent · higher Uncertainty: SD 1.03 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN / TS: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, Shallow CNN, TS, column Kingdom |
|---|
| Configuration: LSTM | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 88.43(1.55)% Accuracy percent · higher Uncertainty: SD 1.55 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceLSTM: 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 LSTM, column Kingdom |
|---|
| Configuration: Shallow CNN / DWA | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 92.31(0.44)% Accuracy percent · higher Uncertainty: SD 0.44 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN / DWA: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, Shallow CNN, DWA, column Kingdom |
|---|
| Configuration: MPNN | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 90.39(0.94)% Accuracy percent · higher Uncertainty: SD 0.94 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMPNN: 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 MPNN, column Kingdom |
|---|
| Configuration: GCN | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 92.06(0.11)% Accuracy percent · higher Uncertainty: SD 0.11 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGCN: 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 GCN, column Kingdom |
|---|
| Configuration: Shallow CNN / UW | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 91.59(1.34)% Accuracy percent · higher Uncertainty: SD 1.34 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN / UW: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, Shallow CNN, UW, column Kingdom |
|---|
| Configuration: Shallow CNN / DTP | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 90.79(1.26)% Accuracy percent · higher Uncertainty: SD 1.26 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN / DTP: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, Shallow CNN, DTP, column Kingdom |
|---|
| Configuration: RGCN / GN | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 91.88(0.80)% Accuracy percent · higher Uncertainty: SD 0.8 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / GN: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, RGCN, GN, column Kingdom |
|---|
| Configuration: RGCN / TS | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 91.62(0.78)% Accuracy percent · higher Uncertainty: SD 0.78 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / TS: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, RGCN, TS, column Kingdom |
|---|
| Configuration: RGCN / N-MTL | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 91.59(1.67)% Accuracy percent · higher Uncertainty: SD 1.67 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / N-MTL: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, RGCN, N-MTL, column Kingdom |
|---|
| Configuration: Shallow CNN / GN | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 91.08(0.89)% Accuracy percent · higher Uncertainty: SD 0.89 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN / GN: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, Shallow CNN, GN, column Kingdom |
|---|
| Configuration: RGCN | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 91.80(0.31)% Accuracy percent · higher Uncertainty: SD 0.31 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN: 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 RGCN, column Kingdom |
|---|
| Configuration: CompGCN | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 93.22(0.38)% Accuracy percent · higher Uncertainty: SD 0.38 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCompGCN: 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 CompGCN, column Kingdom |
|---|
| Configuration: GIN | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 92.35(0.17)% Accuracy percent · higher Uncertainty: SD 0.17 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGIN: 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 GIN, column Kingdom |
|---|
| Configuration: RGCN / DWA | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 91.80(1.11)% Accuracy percent · higher Uncertainty: SD 1.11 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / DWA: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, RGCN, DWA, column Kingdom |
|---|
| Configuration: Transformer | Protocol: 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 checkedMethods, coverage and sourceTransformer: 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: Shallow CNN / N-MTL | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 91.51(0.54)% Accuracy percent · higher Uncertainty: SD 0.54 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN / N-MTL: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, Shallow CNN, N-MTL, column Kingdom |
|---|
| Configuration: RGCN / DTP | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 92.53(0.44)% Accuracy percent · higher Uncertainty: SD 0.44 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / DTP: SugarBase taxonomy · Kingdom Fixed backbone; compare adaptation strategies, not standalone foundation models. 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 4, RGCN, DTP, column Kingdom |
|---|
| Configuration: ResNet | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 89.52(0.72)% Accuracy percent · higher Uncertainty: SD 0.72 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceResNet: 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 ResNet, column Kingdom |
|---|
| Configuration: GAT | Protocol: SugarBase taxonomy · Kingdom (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Kingdom | 92.56(0.25)% Accuracy percent · higher Uncertainty: SD 0.25 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGAT: 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 GAT, column Kingdom |
|---|