[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())
ds_test = tf.data.Dataset.from_tensor_slices((idx_test, y_label[idx_test]))
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,
ds_test = tf.data.Dataset.from_tensor_slices((idx_test, y_label[idx_test]))
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),
),
y,
))
sequence_encoder = InstanceModels.VariantSequence(6,
4,
2, [16, 16, 8, 8],
fusion_dimension=128)
mil = RaggedModels.MIL(instance_encoders=[],
sample_encoders=[sequence_encoder.model],
output_dim=y_label.shape[-1],
output_type='other',
mil_hidden=[128, 128],
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, ))
alt_loader(x, ragged_output=True), strand_loader(x, ragged_output=True),
tf.gather(tf.constant(types), x)), y))
ds_test = tf.data.Dataset.from_tensor_slices((idx_test, y_label[idx_test]))
ds_test = ds_test.batch(len(idx_test), drop_remainder=False)
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),
tf.gather(tf.constant(types), x)), y))
histories = []
evaluations = []
weights = []
for i in range(3):
sequence_encoder = InstanceModels.VariantSequence(6, 4, 2, [16, 16, 8, 8])
sample_encoder = SampleModels.Type(shape=(), dim=len(np.unique(types)))
# mil = RaggedModels.MIL(instance_encoders=[sequence_encoder.model], sample_encoders=[sample_encoder.model], sample_layers=[64, ], output_dim=1, pooling='both', output_type='other', pooled_layers=[32, ])
mil = RaggedModels.MIL(instance_encoders=[sequence_encoder.model],
sample_encoders=[sample_encoder.model],
fusion='before',
output_dim=1,
pooling='both',
output_type='other',
pooled_layers=[
32,
])
losses = ['mse']
mil.model.compile(loss=losses,
metrics=['mse'],
optimizer=tf.keras.optimizers.Adam(
y,
tf.gather(tf.constant(y_weights, dtype=tf.float32), x)
))
ds_valid = tf.data.Dataset.from_tensor_slices((idx_valid, y_label[idx_valid]))
ds_valid = ds_valid.batch(len(idx_valid), drop_remainder=False)
ds_valid = ds_valid.map(lambda x, y: ((pos_loader(x, ragged_output=True),
bin_loader(x, ragged_output=True),
chr_loader(x, ragged_output=True),
),
y,
tf.gather(tf.constant(y_weights, dtype=tf.float32), x)
))
while True:
position_encoder = InstanceModels.VariantPositionBin(24, 100)
mil = RaggedModels.MIL(instance_encoders=[position_encoder.model], output_dim=2, pooling='sum', mil_hidden=(64, 32, 16, 8), output_type='anlulogits')
mil.model.compile(loss=losses,
metrics=[Metrics.CrossEntropy(), Metrics.Accuracy()],
weighted_metrics=[Metrics.CrossEntropy(), Metrics.Accuracy()],
optimizer=tf.keras.optimizers.Adam(learning_rate=0.005,
clipvalue=10000))
mil.model.fit(ds_train,
steps_per_epoch=20,
validation_data=ds_valid,
epochs=10000,
callbacks=callbacks)
eval = mil.model.evaluate(ds_valid)
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,
random_state=0,
loaders = [
[ones_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, )),
]
all_weights = [
pickle.load(
open(
cwd / 'figures' / 'tmb' / 'tcga' / 'nonsyn_table' / 'DFCI_ONCO' /
'results' / 'run_naive.pkl', 'rb'))
]
results = {}
for encoder, loaders, weights, name in zip(encoders, loaders, all_weights,
['naive']):
mil = RaggedModels.MIL(instance_encoders=[encoder.model],
