def getDict(fname = 'data/mitochondrion.txt'):
ids = ['NC_000845.1',
'NC_004299.1',
'AC_000022.2',
'NC_002083.1',
'NC_001643.1',
'NC_011137.1',
'NC_012920.1',
'NC_001645.1',
'NC_002008.4',
'NC_006580.1',
'NC_012420.1',
'NC_011391.1',
'NC_012061.1',
'NC_001640.1']
a = []
for i in ids:
r = functions.get_sequence(i)
d = { 'seq' : r,
'id' : i,
'latin' : r.annotations['source'].split('(')[0].replace('mitochondrion','').strip(),
'english' : r.annotations['source'].split('(')[1].replace(')','').strip(),
'COX3' : [f.qualifiers['translation'][0] for f in r.features if f.type == 'CDS' and f.qualifiers['gene'][0] == "COX3"][0]
}
a.append(d)
return a
#AllChains[file][chain][chain_object_id] = functions.get_backbone_atoms_nucleicacids(chaincheck) <<< incase i need this (superimposer does it)
i += 1
""" in order to avoid calculating the sequences multiple times
I am just going place the sequences and their identifiers in a list of tuples to be used
in the Alignment"""
if options.verbose:
print("Saving sequences...\n\n")
forAlignmentlist = []
for file in AllChains:
i = 0
for chain in AllChains[file]:
for new_id in AllChains[file][chain]:
addtuple = (file + "_" + chain,
functions.get_sequence(AllChains[file][chain][new_id]))
forAlignmentlist.append(addtuple)
i += 1
############# #############
############# Dealing with H**o-mers #############
############# #############
""" If the protein is a H**o-mer we will only have a single file to deal with
in that case the user has to provide us with an integer of the amount of repeating chains
of that homomer in the end structure."""
###
### The method of growing the model here is the same as the original which will occur
### Further on (if no stoichiometry was provided). The process is explained there
###
l = sorted([(f.location.end.position - f.location.start.position) / 3 for f in cds])
print "number of orfs: %5d" % (len(cds))
print "average length: %7.2f" % (float(sum(l)) / len(l))
print "mean length: %5d" % (l[len(l) / 2])
if __name__ == "__main__":
seq_id = 'NC_006058'
start_c = {'NC_006058' : set(["ATG"]),
'NC_007346' : set(["ATG", "TTG", "CTG"]) }
stop_c = {'NC_006058' : set(["TGA"]),
'NC_007346' : set(["TAA", "TAG", "TGA"]) }
rec = functions.get_sequence(seq_id)
rf_pred = get_reading_frames(rec, start_c[seq_id], stop_c[seq_id]);
rf_orig = [{'start': f.location.start.position,
'end': f.location.end.position,
'length': (f.location.end.position - f.location.start.position) / 3,
'strand':-f.strand}
for f in rec.features if f.type == "CDS"]
cds = [f for f in rec.features if f.type == "CDS"]
l = sorted([i['length'] for i in rf_orig])
print "number of orfs: %5d" % (len(cds))
print "average length: %7.2f" % (float(sum(l)) / len(l))
print "mean length: %5d" % (l[len(l) / 2])