ube4b · Graph CNN

reference_ube4b_gcn_modulof1_20261104-153902

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	3.0853	0.2797	0.2912	0.0568	4756.0000	0.0335	14878.0000	0.5000	-0.0591	1.6884	0.1854	0.5800	0.1083	2.8259	0.0000	0.2492	0.5500	0.0612	4.1436	0.0200	0.2644	0.5000	-0.2460	4.1436	0.0342	0.2387
validation	4.8136	0.0539	0.0462	-0.0009	819.0000	0.0253	2075.0000	0.3000	-0.7900	2.3073	0.0000	0.0476	0.2200	-1.4728	3.4022	0.0000	0.0000	-0.0557	0.1700	-1.4354	3.4022	0.0000	0.0000	-0.0550	0.2500	-1.1557	3.4022	0.0000	0.0000	-0.0039
test	3.0610	0.1431	0.1177	-0.0050	571.0000	-0.0232	2581.0000	0.1000	-2.7441	0.9112	0.0000	-0.2403	0.1000	-2.4326	1.6086	0.0000	0.0000	-0.2357	0.1500	-1.8821	2.6073	0.0300	0.0000	-0.1142	0.0645	-2.5549	0.9112	0.0000	0.0000	-0.2404

Loss per epoch

training validation

Config

name: reference_ube4b_gcn_modulof1
task: dms
data:
  dataset: ube4b
  encoding: one_hot,aa_index
  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