aggregate_by_aa=True,
aa_column_beta=0,
count_column=1,
v_beta_column=2,
j_beta_column=3)
AUC = []
Class = []
Method = []
folds = 100
seeds = np.array(range(folds))
for i in range(folds):
np.random.seed(seeds[i])
DTCRS.Get_Train_Valid_Test()
DTCRS.Train(graph_seed=graph_seed)
DTCRS.AUC_Curve(plot=False)
AUC.extend(DTCRS.AUC_DF['AUC'].tolist())
Class.extend(DTCRS.AUC_DF['Class'].tolist())
Method.extend(['Sup-Seq-VDJ'] * len(DTCRS.AUC_DF))
df_s = pd.DataFrame()
df_s['Class'] = Class
df_s['AUC'] = AUC
df_s['Method'] = Method
df_s['Type'] = 'Supervised'
df_comp = pd.concat((df_u, df_s), axis=0)
dir_results = 'Sup_V_Unsup_Results'
if not os.path.exists(dir_results):
os.makedirs(dir_results)
"""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()
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
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)
folds = 100
LOO = 4
epochs_min = 100
#Train Sequence Classifier
DTCR_SS = DeepTCR_SS('Rudqvist_SS')
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.Monte_Carlo_CrossVal(folds=folds, test_size=0.25)
DTCR_SS.AUC_Curve(filename='AUC.eps')
#Train Repertoire Classifier without on-graph clustering
DTCR_WF = DeepTCR_WF('Rudqvist_WF')
DTCR_WF.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_WF.Monte_Carlo_CrossVal(folds=folds, LOO=LOO, epochs_min=epochs_min)
DTCR_WF.AUC_Curve(filename='Rep_AUC.eps')
#Train Repertoire Classifier with on-graph clustering
