def get_molecule_type(prefix, ext='.ent'):
'''
will get the download .extension file (either ent or pdb) and parse the molecule type out into
a file
'''
d = parse_equivalencesFile(prefix)
outf=open(prefix+'.moltype','w')
l=[]
for k,v in d.iteritems():
q = Popen("cat pdb%s.ent | grep 'COMPND 2 MOLECULE'"%(transform_lowercase([k])[0]),shell=True, stdout=PIPE)
out=q.communicate()[0].split('COMPND 2 MOLECULE:')[1].strip().strip(';')
l.append(out+'\t'+k+'\t'+v)
l.sort()
for e in l:
outf.write(e)
from numpy import median
filename = sys.argv[1]
col = int(sys.argv[2]) #number of columns
f = open(filename).read().split('\n')
#parse the equivalences file
sps = {}
for e in f:
if e == '' or e == '\t\t':
continue
else:
bline = e.split('\t')
sp = bline[0].split('_')[0]
sp = sp.split()
if 'SP.' in bline[0]:
sp = transform_sentence_case([sp[0]])[0]+' '+transform_lowercase([sp[1]])[0]
else:
sp = ' '.join(sp)#sp[0][0]+'. '+transform_lowercase([sp[1]])[0]
pdb=bline[1]
ind=bline[2]
if not sp in sps:
sps[sp]= []
sps[sp].append((pdb,ind))
else:
sps[sp].append((pdb,ind))
#create the table
t = open(filename[:filename.rfind('.')]+'.latextable','w')
header ='\\begin{table}[ht]\n\t\\tiny\n\t\\caption{}\n\t\\begin{center}\n\\begin{tabular}{ ccc'+' cc'*(col-1)
header += '}\n\t\\toprule\n\t Species'+ '& PDB & Plot'*col +'\\\\\n'
filename = sys.argv[1]
col = int(sys.argv[2]) #number of columns
f = open(filename).read().split('\n')
#parse the equivalences file
sps = {}
for e in f:
if e == '' or e == '\t\t':
continue
else:
bline = e.split('\t')
sp = bline[0].split('_')[0]
sp = sp.split()
if 'SP.' in bline[0]:
sp = transform_sentence_case(
[sp[0]])[0] + ' ' + transform_lowercase([sp[1]])[0]
else:
sp = ' '.join(sp) #sp[0][0]+'. '+transform_lowercase([sp[1]])[0]
pdb = bline[1]
ind = bline[2]
if not sp in sps:
sps[sp] = []
sps[sp].append((pdb, ind))
else:
sps[sp].append((pdb, ind))
#create the table
t = open(filename[:filename.rfind('.')] + '.latextable', 'w')
header = '\\begin{table}[ht]\n\t\\tiny\n\t\\caption{}\n\t\\begin{center}\n\\begin{tabular}{ ccc' + ' cc' * (
col - 1)