ube4b · Graph CNN

reference_ube4b_gcn_modulof2_20261104-163753

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	precision_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	3.0826	0.3353	0.3526	0.0681	5464.0000	0.0898	5546.0000	0.3000	-0.5951	2.3674	0.0000	0.1130	0.4600	0.1583	5.6776	0.0400	0.2506	0.4500	0.0598	5.6776	0.0500	0.2585	0.4409	-0.1504	5.9644	0.0466	0.2606
validation	3.0291	0.1216	0.1158	-0.0002	418.0000	0.0319	96.0000	0.3000	-0.5208	3.3635	0.1000	0.1661	0.4400	-0.6108	3.4202	0.0600	0.1901	0.3600	-0.7303	4.1936	0.1200	0.1829	0.5000	-0.1064	3.3635	0.1111	0.2750
test	4.8483	0.0314	0.0213	-0.0081	819.0000	-0.1668	2981.0000	0.2000	-1.5826	0.7786	0.0000	-0.0631	0.3400	-1.1194	4.9534	0.0200	0.0019	0.2300	-1.3233	4.9534	0.0100	-0.0348	0.3125	-1.1401	0.7786	0.0000	-0.0014

Loss per epoch

training validation

Config

name: reference_ube4b_gcn_modulof2
task: dms
data:
  dataset: ube4b
  encoding: one_hot,aa_index
  split_dir: null
  graph_threshold: 7
  split_scheme: modulo
  split_fold: 2
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