[pos_loader, bin_loader, chr_loader],
[five_p_loader, three_p_loader, ref_loader, alt_loader, strand_loader],
]
# set y label
y_label = np.log(
sample_df['non_syn_counts'].values /
(panels.loc[panels['Panel'] == 'Agilent_kit']['cds'].values[0] / 1e6) +
1)[:, np.newaxis]
y_strat = np.argmax(samples['histology'], axis=-1)
losses = [Losses.QuantileLoss()]
metrics = [Metrics.QuantileLoss()]
encoders = [
InstanceModels.PassThrough(shape=(1, )),
InstanceModels.VariantPositionBin(24, 100),
InstanceModels.VariantSequence(6,
4,
2, [16, 16, 8, 8],
fusion_dimension=32)
]
all_weights = [
pickle.load(
open(
cwd / 'figures' / 'tmb' / 'tcga' / 'VICC_01_R2' / 'results' /
'run_naive.pkl', 'rb')),
pickle.load(
open(
cwd / 'figures' / 'tmb' / 'tcga' / 'VICC_01_R2' / 'results' /
runs = 3
initial_weights = []
losses = [Losses.QuantileLoss()]
metrics = [Metrics.QuantileLoss()]
callbacks = [
tf.keras.callbacks.EarlyStopping(monitor='val_QL',
min_delta=0.0001,
patience=40,
mode='min',
restore_best_weights=True)
]
##for sequence
for i in range(runs):
pass_encoder = InstanceModels.PassThrough(shape=(1, ))
# position_encoder = InstanceModels.VariantPositionBin(24, 100)
# sequence_encoder = InstanceModels.VariantSequence(6, 4, 2, [16, 16, 8, 8], fusion_dimension=32)
mil = RaggedModels.MIL(instance_encoders=[pass_encoder.model],
output_dim=1,
pooling='sum',
mil_hidden=(64, 32, 16),
output_type='quantiles',
regularization=0)
# mil = RaggedModels.MIL(instance_encoders=[position_encoder.model], output_dim=1, pooling='sum', mil_hidden=(64, 32, 16), output_type='quantiles', regularization=0)
# mil = RaggedModels.MIL(instance_encoders=[sequence_encoder.model], output_dim=1, pooling='sum', mil_hidden=(64, 32, 16), output_type='quantiles', regularization=0)
mil.model.compile(loss=losses,
metrics=metrics,
optimizer=tf.keras.optimizers.Adam(learning_rate=0.001))
initial_weights.append(mil.model.get_weights())