ube4b · Graph CNN

reference_ube4b_gcn_plm_contiguousf1_20261104-182112

Metrics

Set	mse	pearsonr	spearmanr	r2	above_wt_n	above_wt_spearmanr	budget_to_max	hit_rate_at_10	mean_at_10	max_at_10	captured_at_10	hit_rate_at_50	mean_at_50	max_at_50	precision_at_50	captured_at_50	hit_rate_at_100	mean_at_100	max_at_100	precision_at_100	captured_at_100	hit_rate_at_1pct	mean_at_1pct	max_at_1pct	precision_at_1pct	captured_at_1pct
train	2.8253	0.3315	0.3374	0.1051	9072.0000	-0.0335	22936.0000	0.3000	-0.3402	1.5635	0.1249	0.2600	-0.8788	1.5635	0.0000	0.0649	0.3100	-0.6319	1.8717	0.0000	0.1102	0.3099	-0.6305	3.5463	0.0047	0.1349
validation	5.1886	0.3688	0.4082	0.1054	88.0000	-0.0076	66.0000	0.6000	0.1191	1.6400	0.2722	0.3600	-0.1102	4.5327	0.1400	0.3201	0.3400	-0.0462	5.7047	0.3900	0.4623	0.7500	-0.0658	0.1707	0.0000	0.2166
test	3.2464	0.2976	0.3208	0.0852	458.0000	-0.0977	2022.0000	0.5000	-0.3492	0.8896	0.2320	0.5200	-0.0948	3.4686	0.0400	0.3459	0.4500	-0.1792	3.4686	0.1100	0.3720	0.5769	-0.0070	3.4686	0.0385	0.3292

Loss per epoch

training validation

Config

name: reference_ube4b_gcn_plm_contiguousf1
task: dms
data:
  dataset: ube4b
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  graph_threshold: 7
  split_scheme: contiguous
  split_fold: 1
model:
  name: gcn
  filters:
  - 128
  - 128
  - 128
  hidden:
  - 100
  dropout: 0.2
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.0001
  patience: 15
  min_delta: 1.0e-05
  seed: 7