def getZfrags():
zFrag = lCnt()
for i in range(1, N):
zFrag += superAtoms[N - i]
zFrag_tmp = lCnt(zFrag)
frag_type = 'z' + str(i)
if not frag_type in blockedFragments:
yield (frag_type, atomCnt2string(zFrag_tmp), i)
def getCfrags():
cFrag = lCnt({'H':1}) # Adding one extra hydrogen to meet the definition of a c fragment.
for i in range(N-1):
cFrag += superAtoms[i]
cFrag_tmp = lCnt(cFrag)
fragType = 'c'+str(i)
if not fragType in blockedFragments and not i == 0:
yield (fragType, atomCnt2string(cFrag_tmp), i)
def makeBricks():
'''Prepare the base counters of atoms.
These will be later collected into superatoms that finally make up the observed fragments.'''
AAS = AminoAcids().get()
AAS = [(aa, AAS[aa]['graph'], AAS[aa]['NalphaIDX'], AAS[aa]['CcarboIDX'])
for aa in AAS]
bricks = {}
for aa, G, N, C in AAS:
N = G.vs[N]['name']
C = G.vs[C]['name']
G.delete_edges(Roep_ne=None)
G = G.decompose()
brick = {}
if len(G) == 2:
assert aa == 'P'
brick['C'] = lCnt()
while len(G) > 0:
g = G.pop()
isN = N in g.vs['name']
isC = C in g.vs['name']
if isN or isC:
if isN:
tag = 'L'
elif isC:
tag = 'R'
else:
raise ValueError
else:
tag = 'C'
brick[tag] = elementContent(g)
bricks[aa] = brick
return bricks
def standardize(modifications):
"""Standardize modifications so that they meet the internal nomenclature scheme.
Parameters
----------
atomCnt : Counter
The chemical formula counter.
Returns
-------
out : defaultdict
The atomic modifications.
Notes
-----
It was easier for me to think of an amino acid as if it was composed out of three bricks: the left one, the center one, and the right one. The left one corresponds to the group with nitrogen, the center one - to the alpha carbon (including the side chain), and the right one - to the other carbon atom.
"""
backboneAtom2aaNomen = {'N': 'L', 'Calpha': 'C', 'C': 'R'}
R = defaultdict(lambda: defaultdict(lCnt))
for tag, atomCnt in modifications.items():
match = re.match(r"([a-z]+)([0-9]+)", tag, re.I)
if match:
aa, aa_idx = match.groups()
aa_idx = int(aa_idx) - 1
R[aa_idx][backboneAtom2aaNomen[aa]] = lCnt(atomCnt)
return R
def standardize(modifications):
'''Standardize modifications so that they meet the internal nomenclature scheme.'''
backboneAtom2aaNomen = {'N':'L', 'Calpha':'C', 'C':'R'}
R = defaultdict(lambda:defaultdict(lCnt))
for tag, atomCnt in list(modifications.items()):
R[ tag[1]-1 ][ backboneAtom2aaNomen[tag[0]] ] = lCnt(atomCnt)
return R
def make_cz_fragments(fasta, modifications):
'''Prepares the precursor and the c and z fragments atom counts.'''
bricks = makeBricks()
def getBrick(aaPart, aa):
brick = bricks[aa][aaPart] + modifications[aaNo][aaPart]
if countIsNegative(brick):
print("Attention: your modification has an unexpected effect. Part of your molecule now has negative atom count. Bear that in mind while publishing your results.")
return brick
superAtoms = []
sA = lCnt()
for aaNo, aa in enumerate(fasta):
sA += getBrick('L', aa)
superAtoms.append( sA )
sA = getBrick('C', aa) + getBrick('R', aa)
sA += lCnt({'O':1,'H':1})
superAtoms.append(sA)
superAtoms[0] += lCnt({'H':1})
N = len(superAtoms)
def getPrecursor():
precursor = sum(superAtoms)
yield ('precursor', atomCnt2string(precursor), len(fasta) )
blockedFragments = prolineBlockedFragments(fasta)
def getCfrags():
cFrag = lCnt({'H':1}) # Adding one extra hydrogen to meet the definition of a c fragment.
for i in range(N-1):
cFrag += superAtoms[i]
cFrag_tmp = lCnt(cFrag)
fragType = 'c'+str(i)
if not fragType in blockedFragments and not i == 0:
yield (fragType, atomCnt2string(cFrag_tmp), i)
#
def getZfrags():
zFrag = lCnt()
for i in range(1,N):
zFrag += superAtoms[N-i]
zFrag_tmp = lCnt(zFrag)
fragType = 'z'+str(i)
if not fragType in blockedFragments:
yield (fragType, atomCnt2string(zFrag_tmp), i)
return getPrecursor, getCfrags, getZfrags
def elementContent(G):
'''Extracts numbes of atoms of elements that make up the graph of a molecule.'''
atomNo = lCnt()
for el in G.vs['elem']:
atomNo[el] += 1
return atomNo
def make_cz_fragments(fasta, modifications):
"""Prepares the precursor and the c and z fragments atom counts.
Parameters
----------
fasta : str
The fasta of the studied molecular species.
modifications : list
A list of modifications.
Returns
-------
out : tuple
A tuple with generators of precursors, c fragments, and z fragments.
"""
data_path = pkg_resources.resource_filename('MassTodonPy', 'Data/')
bricks = pickle.load(open(data_path + 'amino_acids.txt', 'rb'))
def getBrick(aaPart, aa):
brick = bricks[aa][aaPart] + modifications[aaNo][aaPart]
if countIsNegative(brick):
print(
"Attention: your modification has an unexpected effect. Part of your molecule now has negative atom count. Bear that in mind while publishing your results."
)
return brick
superAtoms = []
sA = lCnt()
for aaNo, aa in enumerate(fasta):
sA += getBrick('L', aa)
superAtoms.append(sA)
sA = getBrick('C', aa) + getBrick('R', aa)
sA += lCnt({'O': 1, 'H': 1})
superAtoms.append(sA)
superAtoms[0] += lCnt({'H': 1})
N = len(superAtoms)
def getPrecursor():
precursor = sum(superAtoms)
yield ('precursor', atomCnt2string(precursor), len(fasta))
blockedFragments = prolineBlockedFragments(fasta)
def getCfrags():
cFrag = lCnt({
'H': 1
}) # Adding one extra hydrogen to meet the definition of a c fragment.
for i in range(N - 1):
cFrag += superAtoms[i]
cFrag_tmp = lCnt(cFrag)
frag_type = 'c' + str(i)
if not frag_type in blockedFragments and not i == 0:
yield (frag_type, atomCnt2string(cFrag_tmp), i)
def getZfrags():
zFrag = lCnt()
for i in range(1, N):
zFrag += superAtoms[N - i]
zFrag_tmp = lCnt(zFrag)
frag_type = 'z' + str(i)
if not frag_type in blockedFragments:
yield (frag_type, atomCnt2string(zFrag_tmp), i)
return getPrecursor, getCfrags, getZfrags