from DeepTCR.DeepTCR import DeepTCR_SS, DeepTCR_WF
from sklearn.metrics import roc_curve, roc_auc_score
import numpy as np
from matplotlib import pyplot as plt
#Train Sequence Classifier
DTCR_SS = DeepTCR_SS('Rudqvist_SS', device='/device:GPU:0')
DTCR_SS.Get_Data(directory='../../Data/Rudqvist',
Load_Prev_Data=False,
aa_column_beta=1,
count_column=2,
v_beta_column=7,
d_beta_column=14,
j_beta_column=21)
DTCR_SS.K_Fold_CrossVal(folds=5)
#Train Repertoire Classifier
folds = 100
LOO = 4
epochs_min = 10
size_of_net = 'small'
num_concepts = 64
hinge_loss_t = 0.1
train_loss_min = 0.1
seeds = np.array(range(folds))
graph_seed = 0
DTCR_WF = DeepTCR_WF('Rudqvist_WF', device='/device:GPU:0')
DTCR_WF.Get_Data(directory='../../Data/Rudqvist',
Load_Prev_Data=False,
import pandas as pd
from DeepTCR.DeepTCR import DeepTCR_SS
import numpy as np
from scipy.stats import gaussian_kde
import matplotlib.pyplot as plt
import matplotlib
matplotlib.rc('font', family='Arial')
import pickle
df = pd.read_csv('../../../Data/10x_Data/Data_Regression.csv')
antigen = 'A0201_ELAGIGILTV_MART-1_Cancer'
DTCRS = DeepTCR_SS('reg_mart1', device=2)
#Get alpha/beta sequences
alpha = np.asarray(df['alpha'].tolist())
beta = np.asarray(df['beta'].tolist())
i = np.where(df.columns == antigen)[0][0]
sel = df.iloc[:, i]
Y = np.log2(np.asarray(sel.tolist()) + 1)
DTCRS.Load_Data(alpha_sequences=alpha, beta_sequences=beta, Y=Y)
folds = 5
seeds = np.array(range(folds))
graph_seed = 0
DTCRS.K_Fold_CrossVal(split_by_sample=False,
folds=folds,
seeds=seeds,
graph_seed=graph_seed)
with open('mart1_preds.pkl', 'wb') as f:
pickle.dump([antigen, np.squeeze(DTCRS.predicted), Y], f, protocol=4)
p = Pool(40)
#Get alpha/beta sequences
alpha = np.asarray(df['alpha'].tolist())
beta = np.asarray(df['beta'].tolist())
y_pred = []
y_test = []
antigen = []
#Iterate through all antigens
for i in range(2,df.columns.shape[0]):
print(df.iloc[:,i].name)
sel = df.iloc[:,i]
Y = np.log2(np.asarray(sel.tolist()) + 1)
DTCRS.Load_Data(alpha_sequences=alpha, beta_sequences=beta, Y=Y,p=p)
DTCRS.K_Fold_CrossVal(split_by_sample=False,folds=5)
y_pred.append(DTCRS.y_pred)
y_test.append(DTCRS.y_test)
antigen.append([sel.name]*len(DTCRS.y_pred))
antigen = np.hstack(antigen)
y_pred = np.vstack(y_pred)
y_test = np.vstack(y_test)
#Save Data
df_out = pd.DataFrame()
df_out['Antigen'] = antigen
df_out['Y_Pred'] = y_pred
df_out['Y_Test'] = y_test
df_out.to_csv('Regression_Results.csv',index=False)
alpha = np.asarray(df['alpha'].tolist())
beta = np.asarray(df['beta'].tolist())
y_pred = []
y_test = []
antigen = []
folds = 5
seeds = np.array(range(folds))
graph_seed = 0
#Iterate through all antigens
for i in range(2, df.columns.shape[0]):
print(df.iloc[:, i].name)
sel = df.iloc[:, i]
Y = np.log2(np.asarray(sel.tolist()) + 1)
DTCRS.Load_Data(alpha_sequences=alpha, beta_sequences=beta, Y=Y, p=p)
DTCRS.K_Fold_CrossVal(folds=folds, seeds=seeds, graph_seed=graph_seed)
y_pred.append(DTCRS.y_pred)
y_test.append(DTCRS.y_test)
antigen.append([sel.name] * len(DTCRS.y_pred))
antigen = np.hstack(antigen)
y_pred = np.vstack(y_pred)
y_test = np.vstack(y_test)
#Save Data
df_out = pd.DataFrame()
df_out['Antigen'] = antigen
df_out['Y_Pred'] = y_pred
df_out['Y_Test'] = y_test
df_out.to_csv('Regression_Results.csv', index=False)