pab1 · Fully connected

reference_pab1_fc_contiguousf3_20261104-162307

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	1.3592	0.8611	0.8804	0.6574	1489.0000	0.0892	831.0000	0.3000	-0.1477	0.1955	0.7132	0.5600	-0.0044	0.4896	0.0400	0.8041	0.5300	-0.0086	0.6080	0.0300	0.8251	0.4673	-0.0398	0.6496	0.0654	0.8398
validation	1.9056	-0.0121	-0.0224	-0.0216	931.0000	0.0977	4470.0000	0.3000	-0.7871	0.4591	0.0000	0.1064	0.3000	-0.5597	0.5441	0.0000	0.0000	0.2524	0.2700	-0.7104	0.7598	0.0300	0.0000	0.1799	0.3111	-0.5087	0.5441	0.0000	0.0000	0.2784
test	2.5708	0.0906	0.0815	-0.0131	383.0000	0.1114	1070.0000	0.1000	-0.3457	0.0016	0.0000	0.4239	0.1600	-0.4146	0.8142	0.0400	0.0000	0.4476	0.1500	-0.6485	0.8142	0.0400	0.0000	0.3392	0.1875	-0.4389	0.8142	0.0312	0.0000	0.4157

Loss per epoch

training validation

Config

name: reference_pab1_fc_contiguousf3
task: dms
data:
  dataset: pab1
  encoding: one_hot,aa_index
  split_dir: null
  split_scheme: contiguous
  split_fold: 3
model:
  name: fcn
  hidden:
  - 100
  - 100
  - 100
  dropout: 0.2
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.001
  patience: 15
  min_delta: 1.0e-05
  seed: 7