pab1 · Graph CNN

reference_pab1_gcn_modulof0_20261104-144630

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	3.1899	0.6328	0.6243	0.1384	1755.0000	0.1476	4752.0000	0.2000	-0.2920	0.4346	0.5348	0.1800	-0.2731	0.7565	0.0200	0.5918	0.1700	-0.3952	0.7565	0.0100	0.5684	0.1957	-0.3842	0.7565	0.0145	0.5848
validation	4.0714	0.0210	-0.0512	-0.0199	132.0000	-0.0645	72.0000	0.0000	-2.2043	-0.5300	0.0000	0.0106	0.0200	-2.3183	0.0899	0.0000	0.0000	-0.0331	0.0300	-2.2678	1.1524	0.0300	0.0000	-0.0137	0.0000	-2.2380	-0.1819	0.0000	0.0000	-0.0012
test	3.2584	-0.1789	-0.1906	-0.0143	171.0000	0.0836	507.0000	0.0000	-1.8604	-0.2869	0.0000	-0.0159	0.0400	-2.3247	0.1771	0.0200	0.0000	-0.2334	0.0700	-2.1092	0.1771	0.0400	0.0000	-0.1410	0.0000	-2.5891	-0.2413	0.0000	0.0000	-0.3233

Loss per epoch

training validation

Config

name: reference_pab1_gcn_modulof0
task: dms
data:
  dataset: pab1
  encoding: one_hot,aa_index
  split_dir: null
  graph_threshold: 7
  split_scheme: modulo
  split_fold: 0
model:
  name: gcn
  filters:
  - 32
  hidden:
  - 100
  dropout: 0.2
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.0001
  patience: 15
  min_delta: 1.0e-05
  seed: 7