"""Figure 2B"""
"""This script is used to create the ROC curves for assessing the ability
of supervised sequence classifier to correctly predict the antigen-specificity of
the 9 murine antigens in the manuscript.."""
from DeepTCR.DeepTCR import DeepTCR_SS
#Run Supervised Sequence Classifier
DTCRS = DeepTCR_SS('Sequence_C')
DTCRS.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)
DTCRS.Monte_Carlo_CrossVal(folds=10)
DTCRS.AUC_Curve()
DTCR.Get_Data(directory='../../Data/Zhang/' + a,
aa_column_alpha=0,
p=p)
elif o == 'beta':
DTCR = DeepTCR_SS('alpha_v_beta_SS')
DTCR.Get_Data(directory='../../Data/Zhang/' + a,
aa_column_beta=1,
p=p)
elif o == 'alpha_beta':
DTCR = DeepTCR_SS('alpha_v_beta_SS')
DTCR.Get_Data(directory='../../Data/Zhang/' + a,
aa_column_alpha=0,
aa_column_beta=1,
p=p)
DTCR.Monte_Carlo_CrossVal(folds=50, weight_by_class=True)
y_pred_list.append(DTCR.y_pred)
y_test_list.append(DTCR.y_test)
plt.figure()
plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate', fontsize=14)
plt.ylabel('True Positive Rate', fontsize=14)
for ii, o in enumerate(opt, 0):
y_test = y_test_list[ii]
y_pred = y_pred_list[ii]
roc_score = roc_auc_score(y_test[:, 1], y_pred[:, 1])
fpr, tpr, _ = roc_curve(y_test[:, 1], y_pred[:, 1])
plt.plot(fpr, tpr, lw=2, label='%s (area = %0.4f)' % (o, roc_score))
of supervised sequence classifier to correctly predict the antigen-specificity of
the 9 murine antigens in the manuscript.."""
from DeepTCR.DeepTCR import DeepTCR_SS
import numpy as np
import matplotlib.pyplot as plt
import matplotlib
matplotlib.rc('font', family='Arial')
#Run Supervised Sequence Classifier
DTCRS = DeepTCR_SS('Sequence_C', device=2)
DTCRS.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)
folds = 10
seeds = np.array(range(folds))
graph_seed = 0
DTCRS.Monte_Carlo_CrossVal(folds=folds, seeds=seeds, graph_seed=graph_seed)
DTCRS.AUC_Curve(xlabel_size=24,
ylabel_size=24,
xtick_size=18,
ytick_size=18,
legend_font_size=14,
frameon=False,
diag_line=False)
from DeepTCR.DeepTCR import DeepTCR_SS, DeepTCR_U
import numpy as np
import seaborn as sns
#Run Supervised Sequence Classifier
DTCRS = DeepTCR_SS('Sequence_C')
DTCRS.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)
DTCRS.Monte_Carlo_CrossVal(folds=10, stop_criterion=0.01)
DTCRS.Representative_Sequences(top_seq=10, unique=True)
from Bio import SeqIO
from Bio.SeqRecord import SeqRecord
from Bio.Seq import Seq
from Bio.Alphabet import IUPAC
for item in DTCRS.Rep_Seq:
break
t = DTCRS.Rep_Seq[item]
t = t.groupby(['beta']).agg({item: 'first'})
t = t.sort_values(by=item, ascending=False)
t.reset_index(inplace=True)
seq = t['beta'].tolist()
seq = seq[:10]
out = []
from DeepTCR.DeepTCR import DeepTCR_SS, DeepTCR_WF
#Train Sequence Classifier
DTCR_SS = DeepTCR_SS('Rudqvist')
DTCR_SS.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)
DTCR_SS.Monte_Carlo_CrossVal(folds=100, test_size=0.25)
DTCR_SS.AUC_Curve()
#Train Repertoire Classifier without on-graph clustering
DTCR_WF = DeepTCR_WF('Rudqvist')
DTCR_WF.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)
DTCR_WF.Monte_Carlo_CrossVal(folds=100, LOO=4, epochs_min=50)
DTCR_WF.AUC_Curve()
#Train Repertoire Classifier with on-graph clustering
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)
plt.plot(fpr, tpr, lw=2, label=label)
plt.legend(loc='lower right', frameon=False, prop={'size': 10})
ax = plt.gca()
seeds = np.array(range(folds))
for a in antigens:
y_pred_list = []
y_test_list = []
for o in opt:
if o == 'alpha':
DTCR = DeepTCR_SS('alpha_v_beta_SS')
DTCR.Get_Data(directory='../../Data/Zhang/'+a,aa_column_alpha=0,p=p)
elif o == 'beta':
DTCR = DeepTCR_SS('alpha_v_beta_SS')
DTCR.Get_Data(directory='../../Data/Zhang/'+a,aa_column_beta=1,p=p)
elif o == 'alpha_beta':
DTCR = DeepTCR_SS('alpha_v_beta_SS')
DTCR.Get_Data(directory='../../Data/Zhang/'+a,aa_column_alpha=0,aa_column_beta=1,p=p)
DTCR.Monte_Carlo_CrossVal(folds=folds,weight_by_class=True,graph_seed=graph_seed,seeds=seeds)
y_pred_list.append(DTCR.y_pred)
y_test_list.append(DTCR.y_test)
plt.figure()
plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate',fontsize=24)
plt.ylabel('True Positive Rate',fontsize=24)
for ii, o in enumerate(opt, 0):
y_test = y_test_list[ii]
y_pred = y_pred_list[ii]
roc_score = roc_auc_score(y_test[:, 1], y_pred[:, 1])
fpr, tpr, _ = roc_curve(y_test[:, 1], y_pred[:, 1])
plt.plot(fpr, tpr, lw=2, label='%s (area = %0.4f)' % (o, roc_score))