ube4b · Graph CNN

reference_ube4b_gcn_contiguousf1_20261104-154654

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	3.0837	0.2923	0.2743	0.0232	9072.0000	0.1081	13856.0000	0.4000	-0.5145	3.1043	0.1027	0.4200	-0.5746	3.1043	0.0000	0.1096	0.4100	-0.5424	4.9591	0.0100	0.1245	0.4108	-0.3955	6.4653	0.0516	0.1809
validation	5.9185	-0.0601	-0.0510	-0.0205	88.0000	-0.0722	108.0000	0.1000	-2.0405	0.0941	0.0000	-0.0710	0.0600	-2.7751	2.6559	0.0200	0.0000	-0.2548	0.1800	-2.0395	5.2979	0.2000	0.0000	-0.1331	0.0000	-3.0848	-1.0028	0.0000	0.0000	-0.2113
test	3.6861	0.0366	0.0562	-0.0387	458.0000	0.0144	1948.0000	0.2000	-1.6607	1.0237	0.0000	-0.0011	0.1800	-1.5139	1.8515	0.0000	0.0000	0.0312	0.2000	-1.5470	1.8515	0.0200	0.0000	0.0271	0.1538	-1.6541	1.1936	0.0000	0.0000	0.0001

Loss per epoch

training validation

Config

name: reference_ube4b_gcn_contiguousf1
task: dms
data:
  dataset: ube4b
  encoding: one_hot,aa_index
  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