| Configuration: Shallow CNN / N-MTL | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 70.58(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 / N-MTL: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: CompGCN | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 69.28(0.99)% Accuracy percent · higher Uncertainty: SD 0.99 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceCompGCN: 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 CompGCN, column Class |
|---|
| Configuration: GCN | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 63.26(0.64)% Accuracy percent · higher Uncertainty: SD 0.64 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGCN: 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 GCN, column Class |
|---|
| Configuration: Shallow CNN | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 70.62(0.76)% Accuracy percent · higher Uncertainty: SD 0.76 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN: 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 Shallow CNN, column Class |
|---|
| Configuration: RGCN / TS | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 73.88(1.69)% Accuracy percent · higher Uncertainty: SD 1.69 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / TS: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: Shallow CNN / TS | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 71.49(0.58)% Accuracy percent · higher Uncertainty: SD 0.58 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN / TS: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: RGCN / DWA | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 69.42(1.25)% Accuracy percent · higher Uncertainty: SD 1.25 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / DWA: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: LSTM | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 63.47(1.95)% Accuracy percent · higher Uncertainty: SD 1.95 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceLSTM: 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 LSTM, column Class |
|---|
| Configuration: Shallow CNN / DWA | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 69.06(3.36)% Accuracy percent · higher Uncertainty: SD 3.36 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN / DWA: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: GIN | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 67.54(0.31)% Accuracy percent · higher Uncertainty: SD 0.31 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGIN: 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 GIN, column Class |
|---|
| Configuration: Shallow CNN / GN | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 70.29(0.66)% Accuracy percent · higher Uncertainty: SD 0.66 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN / GN: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: Shallow CNN / DTP | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 69.02(2.47)% Accuracy percent · higher Uncertainty: SD 2.47 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN / DTP: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: Shallow CNN / UW | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 69.57(2.24)% Accuracy percent · higher Uncertainty: SD 2.24 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceShallow CNN / UW: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: RGCN / DTP | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 69.60(1.75)% Accuracy percent · higher Uncertainty: SD 1.75 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / DTP: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: RGCN / UW | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 73.45(1.61)% Accuracy percent · higher Uncertainty: SD 1.61 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / UW: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: GAT | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 62.57(2.29)% Accuracy percent · higher Uncertainty: SD 2.29 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGAT: 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 GAT, column Class |
|---|
| Configuration: RGCN / N-MTL | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 72.33(1.57)% Accuracy percent · higher Uncertainty: SD 1.57 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / N-MTL: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: Transformer | Protocol: 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 checkedMethods, coverage and sourceTransformer: 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: RGCN / GN | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 70.80(0.33)% Accuracy percent · higher Uncertainty: SD 0.33 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN / GN: SugarBase taxonomy · Class 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 Class |
|---|
| Configuration: MPNN | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 66.52(1.76)% Accuracy percent · higher Uncertainty: SD 1.76 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMPNN: 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 MPNN, column Class |
|---|
| Configuration: ResNet | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 65.29(1.54)% Accuracy percent · higher Uncertainty: SD 1.54 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceResNet: 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 ResNet, column Class |
|---|
| Configuration: RGCN | Protocol: SugarBase taxonomy · Class (GlycanML taxonomy prediction) Dataset: SugarBase taxonomy · Class | 74.17(0.44)% Accuracy percent · higher Uncertainty: SD 0.44 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRGCN: 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 RGCN, column Class |
|---|