def get_features(seq):
p = PyPro()
try:
p.ReadProteinSequence(seq)
features = list(p.GetALL().values())
return features
except:
return ''
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 get_features(self, seq, smi):
p = PyPro()
try:
p.ReadProteinSequence(seq)
features = list(p.GetALL().values())
smi_features = self.get_smi_features(smi)
smi_features2 = list(
np.array([f for f in smi_features], dtype=np.float32))
total_features = np.array(features + smi_features2)[np.newaxis, :]
# total_features = np.array(smi_features2+features)[np.newaxis, :] # does not work...!
return total_features
except Exception as e:
print(str(e))
return None
def uniprot_converter(self, ps, ido, L2):
try:
dpi = pydpi.PyDPI()
# print prot
# ps=dpi.GetProteinSequenceFromID(prot)
# print ps
dpi.ReadProteinSequence(ps)
protein = PyPro()
protein.ReadProteinSequence(ps)
allp = protein.GetALL()
allp["ID"] = ido
L2.append(allp)
# print(smi)
except:
logger.info("Unable to convert the sequence into features")
return False
res=AAComposition.CalculateAAComposition(seq)
k_list1=','.join(c for c in res.keys())
v_list1=','.join(str(c) for c in res.values())
#CTD calculates 147 descriptors
ctd = CTD.CalculateCTD(seq)
k_list2=','.join(c for c in ctd.keys())
v_list2=','.join(str(c) for c in ctd.values())
#pseudo amino acid composition descriptors total 30
protein=PyPro() #protein object
protein.ReadProteinSequence(seq)
paac = protein.GetPAAC(lamda=10,weight=0.05)
k_list3=','.join(c for c in paac.keys())
v_list3=','.join(str(c) for c in paac.values())
#all protein descriptors total 2049
allp=protein.GetALL()
k_list4=','.join(c for c in allp.keys())
v_list4=','.join(str(c) for c in allp.values())
except:
print "\nerror while calculation of features in:\t",f
continue
#fp.write(str(key+"_"+f.replace(".pdb",""))+","+str((line[0])[:locSlash(line[0])-1])+","+str((line[1])[:locSlash(line[1])-1])+","+str((line[2])[:(locSlash(line[2])-1)])+","+str(f15)+","+str(v_list1)+","+str(v_list2)+"\n")
fp.write(str(key+"_"+f.replace(".pdb",""))+","+str((line[0])[:locSlash(line[0])-1])+","+str((line[1])[:locSlash(line[1])-1])+","+str((line[2])[:(locSlash(line[2])-1)])+","+str(f15)+","+str(v_list1)+","+str(v_list2)+","+str(v_list3)+","+str(v_list4)+"\n")
fileTime=time.time()-time1
print "\ntime for file\t"+f+"is\t",fileTime
folderTime=time.time()-time1
print "\ncompletion time for folder\t"+key+"is\t",folderTime
fp.close()
print "done\n"