def Protein_gen(data, Proteingroup):
import numpy as np
from pydpi.pypro import PyPro
protein = PyPro()
HP_list, D_list = [], []
for ii in range(len(data)):
p = data[ii]
protein.ReadProteinSequence(p)
keys, values = [], []
for jj in Proteingroup:
if jj == '0': #All descriptors 2049
res = protein.GetALL()
elif jj == '1': #amino acid composition 20
res = protein.GetAAComp()
elif jj == '2': #dipeptide composition 400
res = protein.GetDPComp()
elif jj == '3': #Tripeptide composition 8000
res = protein.GetTPComp()
elif jj == '4': #Moreau-Broto autocorrelation 240
res = protein.GetMoreauBrotoAuto()
elif jj == '5': #Moran autocorrelation 240
res = protein.GetMoranAuto()
elif jj == '6': #Geary autocorrelation 240
res = protein.GetGearyAuto()
elif jj == '7': #composition,transition,distribution 21+21+105
res = protein.GetCTD()
elif jj == '8': #conjoint triad features 343
res = protein.GetTriad()
elif jj == '9': #sequence order coupling number 60
res = protein.GetSOCN(30)
elif jj == '10': #quasi-sequence order descriptors 100
res = protein.GetQSO()
elif jj == '11': #pseudo amino acid composition 50
res = protein.GetPAAC(30)
keys.extend(res.keys())
values.extend(res.values())
if ii == 0:
HP_list = keys
D_list.append(values)
else:
D_list.append(values)
D_Pro = np.zeros((len(D_list), len(HP_list)), dtype=float)
for k in range(len(D_list)):
D_Pro[k, :] = D_list[k]
#Variance threshold std > 0.01
import Descriptors_Selection as DesSe
ind_var = DesSe.VarinceThreshold(D_Pro)
D_Pro = D_Pro[:, ind_var]
HP_list = np.array(HP_list)[ind_var]
H_Pro = np.reshape(HP_list, (1, len(HP_list)))
Array_Pro = np.append(H_Pro, D_Pro, axis=0)
return Array_Pro
def Decriptor_generator(self, ps):
protein = PyPro()
protein.ReadProteinSequence(ps)
moran = protein.GetPAAC(lamda=5,weight=0.5)
DS_1 = protein.GetAPAAC(lamda=5,weight=0.5)
DS_2 = protein.GetCTD()
DS_3 = protein.GetDPComp()
DS_4 = protein.GetGearyAuto()
DS_5 = protein.GetMoranAuto()
DS_6 = protein.GetMoreauBrotoAuto()
DS_7 = protein.GetQSO()
DS_8 = protein.GetSOCN()
DS_9 = protein.GetTPComp()
DS_ALL = {}
for DS in (DS_1,DS_2,DS_3,DS_4,DS_5,DS_6,DS_7,DS_8,DS_9,moran):
DS_ALL.update(DS)
return DS_ALL
def Decriptor_generator(infile, lamda, weight, maxlag, destype, out_file):
list_pep_name = []
f = open(infile)
lines = f.readlines()
for line in lines:
if ">" in line:
pass
else:
list_pep_name.append(line.strip('\n'))
out_df = pd.DataFrame()
for seq in list_pep_name:
protein = PyPro()
protein.ReadProteinSequence(seq)
if destype == "GetAAComp":
DS = protein.GetAAComp()
df = pd.DataFrame(DS, index=[0])
elif destype == "GetDPComp":
DS = protein.GetDPComp()
df = pd.DataFrame(DS, index=[0])
elif destype == "GetTPComp":
DS = protein.GetTPComp()
df = pd.DataFrame(DS, index=[0])
elif destype == "GetMoreauBrotoAuto":
DS = protein.GetMoreauBrotoAuto()
df = pd.DataFrame(DS, index=[0])
elif destype == "GetMoranAuto":
DS = protein.GetMoranAuto()
df = pd.DataFrame(DS, index=[0])
elif destype == "GetGearyAuto":
DS = protein.GetGearyAuto()
df = pd.DataFrame(DS, index=[0])
elif destype == "GetCTD":
DS = protein.GetCTD()
df = pd.DataFrame(DS, index=[0])
elif destype == "GetPAAC":
DS = protein.GetPAAC(lamda=int(lamda), weight=float(weight))
df = pd.DataFrame(DS, index=[0])
elif destype == "GetAPAAC":
DS = protein.GetAPAAC(lamda=int(lamda), weight=float(weight))
df = pd.DataFrame(DS, index=[0])
elif destype == "GetSOCN":
DS = protein.GetSOCN(maxlag=int(maxlag))
df = pd.DataFrame(DS, index=[0])
elif destype == "GetQSO":
DS = protein.GetQSO(maxlag=int(maxlag), weight=float(weight))
df = pd.DataFrame(DS, index=[0])
elif destype == "GetTriad":
DS = protein.GetTriad()
df = pd.DataFrame(DS, index=[0])
elif destype == "All":
DS1 = protein.GetAAComp()
DS2 = protein.GetDPComp()
DS3 = protein.GetTPComp()
DS4 = protein.GetMoreauBrotoAuto()
DS5 = protein.GetMoranAuto()
DS6 = protein.GetGearyAuto()
DS7 = protein.GetCTD()
DS8 = protein.GetPAAC(lamda=int(lamda), weight=float(weight))
DS9 = protein.GetAPAAC(lamda=int(lamda), weight=float(weight))
DS10 = protein.GetSOCN(maxlag=int(maxlag))
DS11 = protein.GetQSO(maxlag=int(maxlag), weight=float(weight))
DS12 = protein.GetTriad()
DS = {}
for D in (DS1, DS2, DS3, DS4, DS5, DS6, DS7, DS8, DS9, DS10, DS11,
DS12):
print(D)
DS.update(D)
df = pd.DataFrame(DS, index=[0])
if destype == 'BinaryDescriptor':
out_df = BinaryDescriptor(list_pep_name)
else:
out_df = pd.concat([out_df, df], axis=0)
out_df.to_csv(out_file, index=False, sep='\t')