gb1 · Sequence CNN
reference_gb1_cnn_modulof4_20261104-165804
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 | tie_share_at_10 | captured_at_10 | hit_rate_at_50 | mean_at_50 | max_at_50 | precision_at_50 | tie_share_at_50 | captured_at_50 | hit_rate_at_100 | mean_at_100 | max_at_100 | precision_at_100 | tie_share_at_100 | captured_at_100 | hit_rate_at_1pct | mean_at_1pct | max_at_1pct | precision_at_1pct | tie_share_at_1pct | captured_at_1pct |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| train | 0.3494 | 0.9704 | 0.9730 | 0.9315 | 35489.0000 | 0.8225 | 93.0000 | 1.0000 | 1.7908 | 1.9951 | 0.0000 | 0.0000 | 0.9116 | 1.0000 | 1.6802 | 2.1110 | 0.1600 | 0.0000 | 0.9324 | 1.0000 | 1.6816 | 2.5295 | 0.3200 | 0.0000 | 0.9525 | 1.0000 | 1.3786 | 2.5295 | 0.7854 | 0.0000 | 0.9856 |
| validation | 10.2623 | -0.2944 | -0.2740 | -0.8386 | 2689.0000 | -0.0323 | 1579.0000 | 0.0000 | -4.9989 | -3.2989 | 0.0000 | 0.0000 | -0.5544 | 0.0400 | -5.2717 | 0.2999 | 0.0000 | 0.0000 | -0.6552 | 0.0200 | -5.1766 | 0.2999 | 0.0000 | 0.0000 | -0.6462 | 0.0149 | -5.0495 | 0.2999 | 0.0000 | 0.0000 | -0.6277 |
| test | 8.7808 | -0.4142 | -0.4109 | -0.9004 | 3230.0000 | -0.3208 | 19997.0000 | 0.0000 | -3.7456 | -0.3341 | 0.0000 | 0.0000 | -0.3861 | 0.0200 | -4.4897 | 0.3857 | 0.0000 | 0.0000 | -0.6036 | 0.0100 | -4.7067 | 0.3857 | 0.0000 | 0.0000 | -0.6774 | 0.0050 | -4.4830 | 0.3857 | 0.0000 | 0.0000 | -0.6320 |
Loss per epoch
training
validation
Config
name: reference_gb1_cnn_modulof4
task: dms
data:
dataset: gb1
encoding: one_hot,aa_index
split_dir: null
split_scheme: modulo
split_fold: 4
model:
name: cnn
conv:
- - 128
- 17
- - 128
- 17
- - 128
- 17
hidden:
- 100
dropout: 0.2
train:
epochs: 300
batch_size: 32
learning_rate: 0.0001
patience: 15
min_delta: 1.0e-05
seed: 7