pab1 · Graph CNN

reference_pab1_gcn_modulof4_20261104-170223

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	3.2634	0.6456	0.6468	0.1541	1414.0000	0.1390	4670.0000	0.0000	-0.3532	-0.0393	0.5454	0.0200	-0.4748	0.3426	0.0000	0.5607	0.0900	-0.4635	0.7491	0.0100	0.5879	0.1469	-0.3986	0.7491	0.0280	0.6251
validation	3.2825	-0.1471	-0.1837	-0.0218	171.0000	0.1436	609.0000	0.0000	-1.6142	-0.2869	0.0820	0.0600	-2.1167	0.9033	0.0200	-0.1371	0.0900	-1.6940	0.9033	0.0600	0.0617	0.0588	-1.5731	0.0942	0.0000	0.1040
test	3.8148	0.2329	0.2396	-0.0261	234.0000	0.2464	1036.0000	0.1000	-1.1881	0.0758	0.2085	0.1600	-1.4010	0.2969	0.0400	0.1250	0.1700	-1.1786	0.5502	0.0900	0.2454	0.1333	-1.4792	0.1414	0.0000	0.0808

Loss per epoch

training validation

Config

name: reference_pab1_gcn_modulof4
task: dms
data:
  dataset: pab1
  encoding: one_hot,aa_index
  split_dir: null
  graph_threshold: 7
  split_scheme: modulo
  split_fold: 4
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