import os
from scipy.stats import ttest_ind
#Run VAE
DTCRU = DeepTCR_U('Sequence_C', device=1)
DTCRU.Get_Data(directory='../../Data/Murine_Antigens',
Load_Prev_Data=False,
aggregate_by_aa=True,
aa_column_beta=0,
count_column=1,
v_beta_column=2,
j_beta_column=3)
graph_seed = 0
split_seed = 0
DTCRU.Train_VAE(Load_Prev_Data=False,
graph_seed=graph_seed,
split_seed=split_seed)
distances_vae_seq_gene = pdist(DTCRU.features, metric='euclidean')
distances_list = [distances_vae_seq_gene]
names = ['VAE-Seq-VDJ']
dir_results = 'sup_v_unsup_results'
if not os.path.exists(dir_results):
os.makedirs(dir_results)
df_metrics = Assess_Performance_KNN(distances_list,
names,
DTCRU.class_id,
dir_results,
metrics=['AUC'])
os.makedirs(dir_results)
# Instantiate training object
DTCRU = DeepTCR_U('Repertoire_Classification')
DTCRU.Get_Data(directory='../../Data/Rudqvist',
Load_Prev_Data=False,
aggregate_by_aa=True,
aa_column_beta=1,
count_column=2,
v_beta_column=7,
d_beta_column=14,
j_beta_column=21)
# VAE-Gene
DTCRU.Train_VAE(use_only_gene=True)
d_vae_gene = squareform(pdist(DTCRU.features))
prop_vae_gene, _ = phenograph_clustering_freq(d_vae_gene, DTCRU)
# VAE-Seq
DTCRU.Train_VAE(use_only_seq=True)
d_vae_seq = squareform(pdist(DTCRU.features))
prop_vae_seq, _ = phenograph_clustering_freq(d_vae_seq, DTCRU)
# VAE-Seq-Gene
DTCRU.Train_VAE(Load_Prev_Data=False)
d_vae_seq_gene = squareform(pdist(DTCRU.features))
prop_vae_seq_gene, _ = phenograph_clustering_freq(d_vae_seq_gene, DTCRU)
# Hamming
d_hamming = squareform(pdist(np.squeeze(DTCRU.X_Seq_beta, 1),
# Instantiate training object
DTCRU = DeepTCR_U('Rep_Dendrogram', device='/device:GPU:1')
#Load Data from directories
DTCRU.Get_Data(directory='../../Data/Rudqvist',
Load_Prev_Data=True,
aggregate_by_aa=True,
aa_column_beta=1,
count_column=2,
v_beta_column=7,
d_beta_column=14,
j_beta_column=21)
#Train VAE
DTCRU.Train_VAE(accuracy_min=0.9, Load_Prev_Data=True)
#Create Repertoire Dendrogram
color_dict = {
'Control': 'limegreen',
'9H10': 'red',
'RT': 'darkorange',
'Combo': 'magenta'
}
DTCRU.Repertoire_Dendrogram(n_jobs=40,
distance_metric='KL',
log_scale=True,
dendrogram_radius=0.28,
repertoire_radius=0.35,
Load_Prev_Data=True,
gridsize=60,
from DeepTCR.DeepTCR import DeepTCR_U
# Instantiate training object
DTCRU = DeepTCR_U('Rep_Dendrogram',device='/gpu:2')
#Load Data from directories
DTCRU.Get_Data(directory='../../Data/Rudqvist',Load_Prev_Data=False,aggregate_by_aa=True,
aa_column_beta=1,count_column=2,v_beta_column=7,d_beta_column=14,j_beta_column=21)
#Train VAE
DTCRU.Train_VAE(accuracy_min=0.9)
color_dict = {'Control':'limegreen','9H10':'red','RT':'darkorange','Combo':'magenta'}
DTCRU.Repertoire_Dendrogram(n_jobs=40,distance_metric='KL',
dendrogram_radius=0.28,repertoire_radius=0.35,Load_Prev_Data=True,gridsize=6,
color_dict=color_dict)
v_beta = DTCR.v_beta
j_beta = DTCR.j_beta
d_beta = DTCR.d_beta
hla = DTCR.hla_data_seq
sample_id = DTCR.sample_id
file = 'cm038_x2_u.pkl'
featurize = False
if featurize:
DTCR_U = DeepTCR_U('test_hum', device='/device:GPU:6')
DTCR_U.Load_Data(beta_sequences=beta_sequences,
v_beta=v_beta,
d_beta=d_beta,
j_beta=j_beta,
hla=hla)
DTCR_U.Train_VAE(Load_Prev_Data=False, latent_dim=64, stop_criterion=0.01)
X_2 = umap.UMAP().fit_transform(DTCR_U.features)
with open(file, 'wb') as f:
pickle.dump(X_2, f, protocol=4)
else:
with open(file, 'rb') as f:
X_2 = pickle.load(f)
df_plot['x'] = X_2[:, 0]
df_plot['y'] = X_2[:, 1]
def histogram_2d_cohort(d, w, grid_size):
# center of data
d_center = np.mean(np.concatenate(d, axis=0), axis=0)
# largest radius
# Assess ability for structural entropy to be of measure of number of antigens
classes_all = np.array([
'Db-F2', 'Kb-M38', 'Db-M45', 'Db-NP', 'Db-PA', 'Db-PB1', 'Kb-m139',
'Kb-SIY', 'Kb-TRP2'
])
DTCRU.Get_Data(directory='../../Data/Murine_Antigens',
Load_Prev_Data=False,
aggregate_by_aa=True,
aa_column_beta=0,
count_column=1,
v_beta_column=2,
j_beta_column=3)
# VAE-Gene
DTCRU.Train_VAE(use_only_gene=True)
d_vae_gene = squareform(pdist(DTCRU.features))
# VAE-Seq
DTCRU.Train_VAE(use_only_seq=True)
d_vae_seq = squareform(pdist(DTCRU.features))
# VAE-Seq-Gene
DTCRU.Train_VAE()
d_vae_seq_gene = squareform(pdist(DTCRU.features))
# Hamming
d_hamming = squareform(pdist(np.squeeze(DTCRU.X_Seq_beta, 1),
metric='hamming'))
# Kmer
