GenomeFlowInterface Settings:
shuffle: True
pos_sampling_rate: 0.05
validation_chroms: ['chr22']
holdout_chroms: ['chr1', 'chr8', 'chr21']
optimizer: adam
learning rate: 0.0003
batch size: 256
epoch size: 2500000
max num of epochs: 100
early stopping metrics: auPRC
early stopping patience: 4

Epoch 1:
Metrics across all datasets:
Balanced Accuracy: 88.75%	auROC: 0.985	 auPRC: 0.290
Recall at 5% | 10% | 25% | 50% FDR: 0.6% | 0.6% | 0.9% | 19.2%	Num Positives: 1135	 Num Negatives: 1022650


New best auPRC. Saving model.


Epoch 2:
Metrics across all datasets:
Balanced Accuracy: 83.18%	auROC: 0.967	 auPRC: 0.278
Recall at 5% | 10% | 25% | 50% FDR: 0.0% | 0.0% | 0.0% | 0.0%	Num Positives: 1135	 Num Negatives: 1022650



Epoch 3:
Metrics across all datasets:
Balanced Accuracy: 79.32%	auROC: 0.968	 auPRC: 0.278
Recall at 5% | 10% | 25% | 50% FDR: 0.0% | 0.0% | 0.0% | 0.0%	Num Positives: 1135	 Num Negatives: 1022650



Epoch 4:
Metrics across all datasets:
Balanced Accuracy: 79.39%	auROC: 0.977	 auPRC: 0.254
Recall at 5% | 10% | 25% | 50% FDR: 0.0% | 0.0% | 0.0% | 2.5%	Num Positives: 1135	 Num Negatives: 1022650



Epoch 5:
Metrics across all datasets:
Balanced Accuracy: 73.37%	auROC: 0.958	 auPRC: 0.268
Recall at 5% | 10% | 25% | 50% FDR: 0.1% | 0.1% | 0.1% | 16.1%	Num Positives: 1135	 Num Negatives: 1022650



Epoch 6:
Metrics across all datasets:
Balanced Accuracy: 77.16%	auROC: 0.971	 auPRC: 0.260
Recall at 5% | 10% | 25% | 50% FDR: 0.0% | 0.0% | 0.0% | 0.0%	Num Positives: 1135	 Num Negatives: 1022650


Finished training after 6 epochs.
The best model's architecture and weights (from epoch 1) were saved to /users/marinovg/2018-01-25-histone-mods/tfdragonn-SequenceAndDnaseClassifier-K562-ATAC-cuts-SP1/model.arch.json and /users/marinovg/2018-01-25-histone-mods/tfdragonn-SequenceAndDnaseClassifier-K562-ATAC-cuts-SP1/model.weights.h5