bgl3 · Graph CNN

reference_bgl3_gcn_mr5plm_randomf0_20261104-222215

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	0.6183	0.8213	0.8340	0.6708	134.0000	0.0181	77.0000	0.1000	-0.1680	0.0327	0.6461	0.2800	-0.0982	0.3707	0.1200	0.7893	0.2200	-0.1287	1.6908	0.1500	0.8239	0.3235	-0.0816	0.3707	0.0882	0.7687
validation	0.8534	0.7429	0.7595	0.5509	37.0000	0.1076	249.0000	0.1000	-0.1767	0.2792	0.7163	0.1600	-0.2827	0.5578	0.2200	0.7721	0.1200	-0.3203	0.5578	0.3800	0.8028	0.0909	-0.1660	0.2792	0.0000	0.7252
test	0.8829	0.7182	0.7393	0.5137	46.0000	0.1317	284.0000	0.0000	-0.5038	-0.1068	0.5137	0.1400	-0.3978	0.2446	0.1400	0.6771	0.1200	-0.3921	0.4991	0.2700	0.7302	0.0000	-0.4593	-0.0146	0.0000	0.5412

Loss per epoch

training validation

Config

name: reference_bgl3_gcn_mr5plm_randomf0
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index,plm,plm_sum
  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