ube4b · Graph CNN

reference_ube4b_gcn_plm_modulof1_20261104-181451

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	2.8486	0.3651	0.3820	0.1292	4756.0000	-0.0447	20997.0000	0.5000	-0.6426	1.3742	0.1070	0.4000	-0.6684	1.5635	0.0000	0.1241	0.4600	-0.4251	1.5635	0.0000	0.1787	0.4188	-0.4241	3.9986	0.0085	0.2030
validation	4.4216	0.3038	0.3185	0.0806	819.0000	-0.1347	2894.0000	0.4000	-0.1118	1.3437	0.1424	0.3200	-0.4897	1.7887	0.0000	0.1045	0.3900	-0.4692	2.2502	0.0000	0.1195	0.3125	-0.4109	1.7887	0.0000	0.1117
test	2.7018	0.3410	0.3640	0.1129	571.0000	0.0352	1524.0000	0.4000	-0.2775	0.7691	0.2284	0.3200	-0.4924	1.8151	0.0200	0.2440	0.3000	-0.5598	1.8151	0.0300	0.2608	0.4194	-0.2513	1.2282	0.0000	0.2745

Loss per epoch

training validation

Config

name: reference_ube4b_gcn_plm_modulof1
task: dms
data:
  dataset: ube4b
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  graph_threshold: 7
  split_scheme: modulo
  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