def run(column_length, diameter, pore_size, conca, concb, flow_rate,
gradientstart, gradientstop, gradientlength, input_type, peptide):
"""See biolccc documentation"""
if len(peptide) == 0:
raise ValueError('Must supply at least 1 peptide')
if input_type == 'file':
peptide = [x for y in [open(x).read().split() for x in peptide] for x in y]
chroma = biolccc.ChromoConditions()
chroma['columnLength'] = column_length
chroma['columnDiameter'] = diameter
chroma['columnPoreSize'] = pore_size
chroma['secondSolventConcentrationA'] = conca
chroma['secondSolventConcentrationB'] = concb
chroma['gradient'] = biolccc.Gradient(gradientstart, gradientstop, gradientlength)
chroma['flowRate'] = flow_rate
results = dict()
for p in peptide:
RT = biolccc.calculateRT(str(p),
biolccc.rpAcnFaRod,
chroma
)
results[p] = RT
print('Peptide', '\t', 'RTmin')
for p, rt in results.items():
print(p, '\t', rt)
from pyteomics import biolccc peptide = 'Ac-PEPTIDE-NH2' myChromoConditions = biolccc.ChromoConditions() myGradient = biolccc.Gradient() myGradient.addPoint(0.0, 5.0) myGradient.addPoint(20.0, 5.0) myGradient.addPoint(60.0, 45.0) myGradient.addPoint(65.0, 100.0) myGradient.addPoint(85.0, 100.0) myChromoConditions.setGradient(myGradient) RT = biolccc.calculateRT(peptide, biolccc.rpAcnFaRod, myChromoConditions) print 'The retention time of', peptide, 'in the custom gradient is', RT
print('Calculating retention times...')
# Designating BioLCCC model to use:
if model_type == 'TFA':
model_to_use = biolccc.rpAcnTfaChain
elif model_type == 'FA':
model_to_use = biolccc.rpAcnFaRod
peptide_rts = []
i = 0
print('Calculating retention times...')
for tryp_pep in mod_pep:
rt_temp = biolccc.calculateRT(tryp_pep,
model_to_use,
myChromoConditions)
peptide_rts.append(rt_temp)
i += 1
# Combining the sequences, times, and physicochemical characteristics.
peptides_pd = pd.Series(z_removed_peps, name = 'peptide_sequence')
peptide_rts = pd.Series(peptide_rts, name = 'rts')
iso_electric_points_pd = pd.Series(iso_electric_points, name = 'iso_point')
pep_charges_pd = pd.Series(pep_charges, name = 'charge')
pep_mass_pd = pd.Series(pep_mass, name = 'mass')
contig_pd = pd.Series(contig_vec_no_x, name = 'contig')
peptide_dataframe = pd.concat([peptides_pd,
peptide_rts,
from pyteomics import biolccc
peptide = 'Ac-PEPTIDE-NH2'
RT = biolccc.calculateRT(peptide, biolccc.rpAcnFaRod,
biolccc.standardChromoConditions)
print 'The retention time of', peptide, 'is', RT
from pyteomics import biolccc
print biolccc.calculateRT('QWERTYIPASDFGHKLCVNM', biolccc.rpAcnTfaChain,
biolccc.standardChromoConditions)
# Using 21 interpolating points.
print biolccc.calculateRT('QWERTYIPASDFGHKLCVNM', biolccc.rpAcnTfaChain,
biolccc.standardChromoConditions, 21)
def executeBioLCCC(tool):
##wenn fehler, dann print fehler
general = Util.readConfigFile(Util.TOOL_CONFIG, "General")
paramToValue = Util.readConfigFile(Util.TOOL_CONFIG, tool)
fobjOut = open(general["outputDirectory"]+paramToValue["ioFile"], 'w')
# read values from configfile
# myChromoConditions
myChromoConditions = biolccc.standardChromoConditions
if ("columnLength" in paramToValue):
myChromoConditions['columnLength'] = float("%(columnLength)s" % paramToValue)
elif("columnDiameter"in paramToValue):
myChromoConditions['columnDiameter'] = float("%(columnDiameter)s" % paramToValue)
elif("columnPoreSize"in paramToValue):
myChromoConditions['columnPoreSize'] = float("%(columnPoreSize)s" % paramToValue)
elif("secondSolventConcentrationA"in paramToValue):
myChromoConditions['secondSolventConcentrationA'] = float("%(secondSolventConcentrationA)s" % paramToValue)
elif("secondSolventConcentrationB"in paramToValue):
myChromoConditions['secondSolventConcentrationB'] = float("%(secondSolventConcentrationB)s" % paramToValue)
elif("gradient"in paramToValue):
myChromoConditions['gradient'] = biolccc.Gradient("%initialConcentrationB", "%finalConcentrationB", "%time" % paramToValue)
elif("flowRate"in paramToValue):
myChromoConditions['flowRate'] = float("%(flowRate)s" % paramToValue)
#myGradient settings
myGradient = biolccc.Gradient()
addPointList=()
strList = paramToValue["myGradient.addPoint"]
addPointList = ast.literal_eval(strList)
for key in addPointList:
myGradient.addPoint(float(key[0]), float(key[1]))
myChromoConditions.setGradient(myGradient)
# calculateRT
continueGradient=bool("%(continuegradient)s" % paramToValue)
numinterpolationspoints=int("%(numinterpolationspoints)s" % paramToValue)
chem_basis_map = {}
chem_basis_map["rpAcnFaRod"] = biolccc.rpAcnFaRod
chem_basis_map["rpAcnTfaChain"] = biolccc.rpAcnTfaChain
chemBasis = chem_basis_map["%(chembasis)s" %paramToValue]
# print "BioLCCC starts calculating"
# calculate RT and write tmp_output
with open(general["testDirectory"]+paramToValue["ioFile"], 'r') as output:
content = output.readlines()
for fileLine in content:
sequence = fileLine.strip()
retentionTime = biolccc.calculateRT(sequence, chemBasis, myChromoConditions)
fobjOut.write(sequence + "\t" + str(retentionTime) + "\n")
fobjOut.close()
# print "BioLCCC finished calculating"
# take output and connect with input rt
output_RT_fh = open(Util.TOOLS_OUTPUT+"BioLCCC.txt", 'r')
content = output_RT_fh.readlines()
output_RT = content
output_RT_fh.close()
output_set = {}
for seq in output_RT:
seq = seq.strip()
data = re.split('\t', seq)
if len(data) != 2:
print "ERROR in len data", data
exit(-1)
unimod = data[0]
rt = data[1]
output_set[unimod] = rt
testRef_RT = open(Util.PATH_TO_TMP+"BioLCCC_test_reference.txt", 'r')
test_set = {}
# verknuepfe mir meine zwei sachen modseq : rt fuer output
for line in testRef_RT:
sseq = line.split('\t')[1]
sseq = sseq.strip()
unimod = line.split('\t')[0] #key: toolinput
unimod = unimod.strip()
test_set[unimod] = sseq #returns value
testRef_RT.close()
os.unlink(Util.TOOLS_OUTPUT+"BioLCCC.txt")
# write Tooloutput
biolc = open(Util.TOOLS_OUTPUT+"BioLCCC.txt", 'w')
for key in output_set.keys():
#rt = output_set[key]
seq = test_set[key]
seq = "-"+ seq + "-" # for PredictionToolReader.getSequence
key = key.strip()
biolc.write("\t".join(( str(seq), str(output_set[key])) )) #Ausgabe: value testRef_RT = modSeq mit phosphos, RT Zeit
biolc.write("\n")
peptides = []
random.seed()
for i in [5] * 5 + [10] * 5 + [20] * 5 + [40] * 5:
peptides.append(''.join(
[random.choice("QWERTYIPASDFGHKLCVNM") for j in range(i)]))
pylab.figure(figsize=(9, 4))
pylab.subplots_adjust(top=0.85, hspace=0.30, wspace=0.30, right=0.96)
pylab.suptitle('The difference of RT calculated by the fast and standard '
'algorithm for 20 random peptides')
for chembasis, subplot_num, title in [(biolccc.rpAcnTfaChain, 121,
'rpAcnTfaChain'),
(biolccc.rpAcnFaRod, 122, 'rpAcnFaRod')]:
pylab.subplot(subplot_num)
for peptide in peptides:
x = range(5, 31, 1)
RTs = [
biolccc.calculateRT(peptide, chembasis,
biolccc.standardChromoConditions, i) for i in x
]
ref_RT = biolccc.calculateRT(peptide, chembasis,
biolccc.standardChromoConditions)
y = [(RT / ref_RT) * 100.0 - 100.0 for RT in RTs]
pylab.plot(x, y, label=peptide)
pylab.title(title)
pylab.xlabel('Number of interpolating points')
pylab.ylabel('$\Delta RT, \; \%$')
pylab.rcParams['legend.fontsize'] = 10
#pylab.legend(loc='upper right')
#pylab.legend(loc='lower right')
pylab.show()
# Changing the bind energy of a chemical group.
myChemicalBasis.chemicalGroups()['E'].setBindEnergy(0.0)
myChemicalBasis.chemicalGroups()['-NH2'].setBindEnergy(0.0)
print "The bind energy of E is", \
myChemicalBasis.chemicalGroups()['E'].bindEnergy()
print "The bind energy of -NH2 is", \
myChemicalBasis.chemicalGroups()['-NH2'].bindEnergy()
# Adding a new chemical group. The energy is not valid.
myChemicalBasis.addChemicalGroup(
biolccc.ChemicalGroup(
'Hydroxyproline', # full name
'hoP', # label
0.40, # bind energy
97.1167 + 15.9994, # average mass
97.05276 + 15.9994915)) # monoisotopic mass
# Setting a new type of model. Without a massive recalibration
# it will ruin the accuracy of prediction.
myChemicalBasis.setModel(biolccc.CHAIN)
peptide = "Ac-PEhoPTIDE-NH2"
RT = biolccc.calculateRT(peptide, myChemicalBasis,
biolccc.standardChromoConditions)
monoisotopicMass = biolccc.calculateMonoisotopicMass(peptide, myChemicalBasis)
print 'The retention time of', peptide, 'is', RT
print 'The monoisotopic mass of', peptide, 'is', monoisotopicMass, 'Da'
[random.choice("QWERTYIPASDFGHKLCVNM") for j in range(i)]))
pylab.figure(figsize=(9, 8))
pylab.subplots_adjust(top=0.9, hspace=0.30, wspace=0.30, right=0.96)
pylab.suptitle('The effect of changing dV for ten random peptides'
' of different length')
for chembasis, chromoconditions, subplot_num, title in [
(biolccc.rpAcnTfaChain, nanocolumn, 221, 'Nanocolumn, rpAcnTfaChain'),
(biolccc.rpAcnFaRod, nanocolumn, 222, 'Nanocolumn, rpAcnFaRod'),
(biolccc.rpAcnTfaChain, macrocolumn, 223, 'Macrocolumn, rpAcnTfaChain'),
(biolccc.rpAcnFaRod, macrocolumn, 224, 'Macrocolumn, rpAcnFaRod')
]:
pylab.subplot(subplot_num)
for peptide in peptides:
divisors = [(2.0**i) for i in range(11)]
chromoconditions['dV'] = chromoconditions['flowRate'] / divisors[-1]
reference_time = (biolccc.calculateRT(peptide, chembasis,
chromoconditions))
y = []
for divisor in divisors:
chromoconditions['dV'] = chromoconditions['flowRate'] / divisor
y.append(
(biolccc.calculateRT(peptide, chembasis, chromoconditions) /
reference_time - 1.0) * 100.0)
pylab.plot(divisors, y, label=peptide)
pylab.title(title)
pylab.xlabel('Flow rate divisor')
pylab.ylabel('$\Delta RT, \; \%$')
pylab.gca().set_xscale('log')
pylab.rcParams['legend.fontsize'] = 10
#pylab.legend(loc='upper right')
#pylab.legend(loc='lower right')
pylab.show()
