DTCRS = DeepTCR_SS('reg',device='/gpu:2')
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)
seq_train = []
label_train = []
count_train = []
for s, seq_cl, p, c in zip(sequences, seq_class_labels, predicted, counts):
sel_idx = p > thresh
seq_train.append(s[sel_idx])
label_train.append(seq_cl[sel_idx])
count_train.append(c[sel_idx])
seq_train = np.hstack(seq_train)
label_train = np.hstack(label_train)
count_train = np.hstack(count_train)
#Train Sequence Classifier
DTCR = DeepTCR_SS('tw10_seq', device=gpu)
DTCR.Load_Data(beta_sequences=seq_train, class_labels=label_train)
DTCR.Monte_Carlo_CrossVal(folds=folds,
graph_seed=graph_seed,
seeds=seeds,
convergence='training')
y_pred = DTCR.predicted
y_test = DTCR.Y
plt.figure(figsize=(6, 5))
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
for ii, cl in enumerate(DTCR.lb.classes_, 0):
fpr, tpr, _ = roc_curve(y_test[:, ii], y_pred[:, ii])
roc_score = roc_auc_score(y_test[:, ii], y_pred[:, ii])
label = '%s = %0.3f' % (cl, roc_score)
