bgl3 · Graph CNN

reference_bgl3_gcn_mr5_randomf0_20261104-221615

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	0.6132	0.8239	0.8283	0.6735	134.0000	-0.0001	58.0000	0.4000	-0.0405	0.3940	0.1000	0.7003	0.2800	-0.1743	0.3940	0.1200	0.7515	0.2800	-0.1587	1.6908	0.2200	0.8080	0.3824	-0.1349	0.3940	0.1471	0.7432
validation	0.8990	0.7262	0.7300	0.5269	37.0000	0.2155	239.0000	0.1000	-0.2806	0.3347	0.1000	0.6672	0.1400	-0.4645	0.4008	0.1600	0.6726	0.1200	-0.4498	0.5578	0.3000	0.7270	0.0909	-0.2842	0.3347	0.0909	0.6691
test	0.9431	0.6948	0.6964	0.4806	46.0000	-0.0764	355.0000	0.1000	-1.1277	0.1561	0.0000	0.2222	0.1000	-0.6747	0.1704	0.1000	0.5216	0.1200	-0.5667	0.2388	0.2500	0.6248	0.0909	-1.0431	0.1561	0.0000	0.2650

Loss per epoch

training validation

Config

name: reference_bgl3_gcn_mr5_randomf0
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index
  split_dir: null
  graph_threshold: 6
  split_scheme: random
  split_fold: 0
  min_reads: 5
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