tf.float32)
loaders = [
[ones_loader],
[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' /
ds_test = ds_test.map(lambda x, y: (
(five_p_loader(x, ragged_output=True),
three_p_loader(x, ragged_output=True),
ref_loader(x, ragged_output=True), alt_loader(x, ragged_output=True),
strand_loader(x, ragged_output=True)), y))
X = False
while X == False:
try:
tile_encoder = InstanceModels.VariantSequence(
6, 4, 2, [16, 16, 8, 8])
mil = RaggedModels.MIL(instance_encoders=[tile_encoder.model],
output_dim=1,
pooling='sum',
output_type='other',
instance_layers=[128, 64])
losses = [Losses.CoxPH()]
mil.model.compile(loss=losses,
metrics=[Losses.CoxPH()],
optimizer=tf.keras.optimizers.Adam(
learning_rate=0.001, ))
callbacks = [
tf.keras.callbacks.EarlyStopping(monitor='val_coxph',
min_delta=0.0001,
patience=20,
mode='min',
restore_best_weights=True)
]
history = mil.model.fit(ds_train,
steps_per_epoch=4,
validation_data=ds_valid,
epochs=10000,
ds_test = ds_test.batch(len(idx_test), drop_remainder=False)
ds_test = ds_test.map(lambda x, y: ((tf.gather(tf.constant(D['seq_5p'], dtype=tf.int32), x),
tf.gather(tf.constant(D['seq_3p'], dtype=tf.int32), x),
tf.gather(tf.constant(D['seq_ref'], dtype=tf.int32), x),
tf.gather(tf.constant(D['seq_alt'], dtype=tf.int32), x),
tf.gather(tf.constant(D['strand_emb'], dtype=tf.float32), x),
tf.gather(tf.constant(D['cds_emb'], dtype=tf.float32), x)
),
y,
))
sequence_encoder = InstanceModels.VariantSequence(6, 4, 2, [64, 64, 64, 64], fusion_dimension=128, use_frame=True)
mil = RaggedModels.MIL(instance_encoders=[], sample_encoders=[sequence_encoder.model], output_dim=y_label.shape[-1], output_type='other', mil_hidden=[128, 128, 64, 32], mode='none')
losses = [Losses.CrossEntropy()]
mil.model.compile(loss=losses,
metrics=[Metrics.Accuracy(), Metrics.CrossEntropy()],
weighted_metrics=[Metrics.Accuracy(), Metrics.CrossEntropy()],
optimizer=tf.keras.optimizers.Adam(learning_rate=0.001,
))
callbacks = [tf.keras.callbacks.EarlyStopping(monitor='val_weighted_CE', min_delta=0.001, patience=10, mode='min', restore_best_weights=True)]
mil.model.fit(ds_train, steps_per_epoch=50,
validation_data=ds_valid,
epochs=10000,
callbacks=callbacks,
)
strat_dict[(group, event)]
for group, event in zip(cancer_labels, y_label[:, 1])
])
class_counts = dict(zip(*np.unique(y_strat, return_counts=True)))
y_weights = np.array([1 / class_counts[_] for _ in y_strat])
y_weights /= np.sum(y_weights)
weights = []
callbacks = [
tf.keras.callbacks.EarlyStopping(monitor='val_CE',
min_delta=0.0001,
patience=50,
mode='min',
restore_best_weights=True)
]
losses = [Losses.CrossEntropy(from_logits=False)]
sequence_encoder = InstanceModels.VariantSequence(20, 4, 2, [8, 8, 8, 8])
mil = RaggedModels.MIL(instance_encoders=[sequence_encoder.model],
output_dim=2,
pooling='sum',
mil_hidden=(64, 64, 32, 16),
output_type='classification_probability')
mil.model.compile(
loss=losses,
metrics=[Metrics.CrossEntropy(from_logits=False),
Metrics.Accuracy()],
optimizer=tf.keras.optimizers.Adam(learning_rate=0.001, clipvalue=10000))
initial_weights = mil.model.get_weights()
##stratified K fold for test
for idx_train, idx_test in StratifiedKFold(n_splits=9,
