def test_reading_from_guide_table(self):
"""Read table"""
root = Newick.Clade()
root.name = "cellular organisms"
#print(root.depths())
inf = open("./test-phyloutil/test1/Pseudozyma-antarctica-1.txt", 'r')
table = util.readTable(inf, header=True)
#print(table)
tree = phyloutil.treeFromClassificationTable(table)
inf.close()
phyloutil.printTree(tree, sys.stdout)
def test_reading_from_class_table(self):
"""Read table"""
root = Newick.Clade()
root.name = "cellular organisms"
inf = open("./test-phyloutil/test1/Pseudozyma-antarctica-1.txt", 'r')
table = util.readTable(inf, header=True)
#print(table)
tree = phyloutil.treeFromClassificationTable(table)
inf.close()
#phyloutil.printTree(root, sys.stdout)
termlist = list(tree.get_terminals())
self.assertTrue(termlist[0].name=='Moesziomyces antarcticus T-34')
def test_run(self):
"""readTable header"""
fname = "tmp_lightdataframe.txt"
inf = open(fname, "w")
inf.write("one\ttwo\tthree\n")
inf.write("a\tb\t3\n")
inf.write("a\tb\t33\n")
inf.close()
with open(fname, "r") as inf:
ldf = util.readTable(inf, header=True)
h = ldf.header
self.assertTrue(h[1] == "two")
os.remove(fname)
def test_run(self):
"""readTable header"""
fname = "tmp_lightdataframe.txt"
inf = open(fname, 'w')
inf.write("one\ttwo\tthree\n")
inf.write("a\tb\t3\n")
inf.write("a\tb\t33\n")
inf.close()
with open(fname, 'r') as inf:
ldf = util.readTable(inf, header=True)
h = ldf.header
self.assertTrue(h[1] == 'two')
os.remove(fname)
def test_run(self):
"""readTable basic"""
fname = "tmp_lightdataframe.txt"
inf = open(fname, 'w')
inf.write("one\ttwo\tthree\n")
inf.write("a\tb\t3\n")
inf.write("a\tb\t33\n")
inf.close()
inf = open(fname, 'r')
ldf = util.readTable(inf, header=True)
self.assertTrue(ldf['three'][0] == 3)
self.assertTrue(ldf['three'][1] == 33)
inf.close()
os.remove(fname)
def test_run(self):
"""readTable basic"""
fname = "tmp_lightdataframe.txt"
inf = open(fname, "w")
inf.write("one\ttwo\tthree\n")
inf.write("a\tb\t3\n")
inf.write("a\tb\t33\n")
inf.close()
inf = open(fname, "r")
ldf = util.readTable(inf, header=True)
self.assertTrue(ldf["three"][0] == 3)
self.assertTrue(ldf["three"][1] == 33)
inf.close()
os.remove(fname)
def test_run(self):
"""readTable dictrows"""
fname = "tmp_lightdataframe.txt"
inf = open(fname, 'w')
inf.write("one\ttwo\tthree\n")
inf.write("a\tb\t3\n")
inf.write("a\tb\t33\n")
inf.close()
inf = open(fname, 'r')
ldf = util.readTable(inf, header=True)
for (ri, flds) in enumerate(ldf.dictrows):
if ri == 0:
self.assertTrue(flds['three'] == 3)
if ri == 1:
self.assertTrue(flds['three'] == 33)
inf.close()
os.remove(fname)
def test_run(self):
"""readTable dictrows"""
fname = "tmp_lightdataframe.txt"
inf = open(fname, "w")
inf.write("one\ttwo\tthree\n")
inf.write("a\tb\t3\n")
inf.write("a\tb\t33\n")
inf.close()
inf = open(fname, "r")
ldf = util.readTable(inf, header=True)
for (ri, flds) in enumerate(ldf.dictrows):
if ri == 0:
self.assertTrue(flds["three"] == 3)
if ri == 1:
self.assertTrue(flds["three"] == 33)
inf.close()
os.remove(fname)
def __init__(self):
self.pKa = {'D':3.9, 'E':4.3, 'H':6.1, 'C':8.3, 'Y':10.1, 'K':10.67, 'R':12, 'N-term':8, 'C-term':3.1}
self.charges = {'D':-1, 'E':-1, 'H':1, 'C':-1, 'Y':-1, 'K':1, 'R':1, 'N-term':1, 'C-term':-1}
#self.charges = {'D':-1, 'E':-1, 'H':1, 'K':1, 'R':1, 'N-term':1, 'C-term':-1}
self.hydrophobicity_scales = {}
# Hack so that we can store scale information in a file -- need better way to store.
dir_path = os.path.dirname(os.path.realpath(__file__))
inf = open(os.path.expanduser(dir_path+"/../data/hydrophobicity-scales.txt"),'r')
tab = util.readTable(inf)
scales = tab.header[1:]
for scale in scales:
self.hydrophobicity_scales[scale.replace('.','-')] = dict(zip(tab.col('aa'), tab.col(scale)))
# Molecular weights of the amino acids in Da, not residues; subtract 18 for residue weight
self.mw = {'A': 89.09, 'C': 121.16, 'E': 147.13, 'D': 133.10, 'G': 75.07, 'F': 165.19,
'I': 131.18, 'H': 155.16, 'K': 146.19, 'M': 149.21, 'L': 131.18, 'N': 132.12, 'Q': 146.15,
'P': 115.13, 'S': 105.09, 'R': 174.20, 'T': 119.12, 'W': 204.23, 'V': 117.15, 'Y': 181.19,
'B': 132.61, 'Z': 146.64}
inf.close()
def read(self, stream, header=True): tab = util.readTable(stream, header=header) for flds in tab.dictrows: self._comp_dict[flds['aa']] = flds['proportion']
data_outs.addStream(outf)
else:
# By default, write to stdout
data_outs.addStream(sys.stdout)
# Write out parameters
data_outs.write("# Run started {}\n".format(util.timestamp()))
data_outs.write("# Command: {}\n".format(' '.join(sys.argv)))
data_outs.write("# Parameters:\n")
optdict = vars(options)
for (k,v) in optdict.items():
data_outs.write("#\t{k}: {v}\n".format(k=k, v=v))
# Read background information
aa_volumes = {}
vols = util.readTable(open(os.path.expanduser('~/research/lib/data/harpaz-aa-volumes.txt')))
#print vols['volume.a3']
aa_volumes = dict(zip(vols['aa'], [x/1000.0 for x in vols['mean.volume.a3']]))
#print aa_volumes
# Read input
if not os.path.isfile(options.in_fname):
raise IOError("# Error: file {} does not exist".format(options.in_fname))
(headers, seqs) = biofile.readFASTA(file(options.in_fname, 'r')) #, key_fxn=biofile.secondField)
if options.translate_sequences:
seqs = [translate.translate(s) for s in seqs]
zhs = [(h,s) for (h,s) in zip(headers,seqs) if not s is None]
all_keys = [biofile.firstField(h) for (h,s) in zhs]
(headers, seqs) = zip(*zhs)
prot_dict = dict([(biofile.firstField(h), s) for (h,s) in zhs])
gene_orf_dict = dict([(biofile.secondOrFirstField(h), biofile.firstField(h)) for h in headers])
# Read input
if not os.path.isfile(options.in_fname):
raise IOError("# Error: file {} does not exist".format(
options.in_fname))
with open(options.in_fname, 'r') as inf:
# Read a FASTA file?
(headers, seqs) = biofile.readFASTA(inf)
info_outs.write("# Read {:d} sequences\n".format(len(headers)))
if not options.in_names_fname is None:
if not os.path.isfile(options.in_names_fname):
raise IOError("# Error: file {} does not exist".format(
options.in_names_fname))
with open(options.in_names_fname, 'r') as inf:
species = util.readTable(inf, header=True)
species_name_lookup = dict(
zip(species['ODB_code'],
[shorten(x) for x in species['Organism']]))
new_headers = []
new_seqs = []
for (hdr, seq) in zip(headers, seqs):
odb_code = hdr.strip().split()[-1]
if len(odb_code) == 5:
try:
# Rename
species_name = species_name_lookup[odb_code]
new_headers.append('{} {}'.format(species_name, hdr))
except KeyError:
new_headers.append(hdr)
if not os.path.isfile(tree_fname):
raise IOError("# Error: file {} does not exist".format(tree_fname))
tree_string = ""
with open(tree_fname, 'r') as inf:
lines = inf.readlines()
for line in lines:
if not line.strip()[0] == '#':
tree_string += line.strip()
trees = NewickIO.parse(StringIO(tree_string))
tree = next(trees)
# Read mapping file
map_fname = os.path.expanduser(options.mapping_in_fname)
if not os.path.isfile(map_fname):
raise IOError("# Error: file {} does not exist".format(map_fname))
with open(map_fname, 'r') as inf:
map_table = util.readTable(inf, header=True)
# Create mapping
mapping_dict = dict(zip(map_table['species'],
map_table['updated.species']))
# Update the FASTA headers
#new_headers = []
#new_seqs = []
seq_dict = {}
header_dict = {}
short_species_names = {}
for (i, h) in enumerate(headers):
species_name = extractSpeciesName(h)
short_name = makeShortSpeciesName(species_name)
try:
def read(self, stream, header=True):
tab = util.readTable(stream, header=header)
for flds in tab.dictrows:
self._comp_dict[flds['aa']] = flds['proportion']
def __init__(self):
self.pKa = {
'D': 3.9,
'E': 4.3,
'H': 6.1,
'C': 8.3,
'Y': 10.1,
'K': 10.67,
'R': 12,
'N-term': 8,
'C-term': 3.1
}
self.charges = {
'D': -1,
'E': -1,
'H': 1,
'C': -1,
'Y': -1,
'K': 1,
'R': 1,
'N-term': 1,
'C-term': -1
}
#self.charges = {'D':-1, 'E':-1, 'H':1, 'K':1, 'R':1, 'N-term':1, 'C-term':-1}
self.hydrophobicity_scales = {}
# Hack so that we can store scale information in a file -- need better way to store.
dir_path = os.path.dirname(os.path.realpath(__file__))
inf = open(
os.path.expanduser(dir_path +
"/../data/hydrophobicity-scales.txt"), 'r')
tab = util.readTable(inf)
scales = tab.header[1:]
for scale in scales:
self.hydrophobicity_scales[scale.replace('.', '-')] = dict(
zip(tab.col('aa'), tab.col(scale)))
# Molecular weights of the amino acids in Da, not residues; subtract 18 for residue weight
self.mw = {
'A': 89.09,
'C': 121.16,
'E': 147.13,
'D': 133.10,
'G': 75.07,
'F': 165.19,
'I': 131.18,
'H': 155.16,
'K': 146.19,
'M': 149.21,
'L': 131.18,
'N': 132.12,
'Q': 146.15,
'P': 115.13,
'S': 105.09,
'R': 174.20,
'T': 119.12,
'W': 204.23,
'V': 117.15,
'Y': 181.19,
'B': 132.61,
'Z': 146.64
}
inf.close()
for (k,v) in optdict.items():
data_outs.write("#\t{k}: {v}\n".format(k=k, v=v))
# Read input
if not os.path.isfile(options.in_fname):
raise IOError("# Error: file {} does not exist".format(options.in_fname))
with open(options.in_fname,'r') as inf:
# Read a FASTA file?
(headers, seqs) = biofile.readFASTA(inf)
info_outs.write("# Read {:d} sequences\n".format(len(headers)))
if not options.in_names_fname is None:
if not os.path.isfile(options.in_names_fname):
raise IOError("# Error: file {} does not exist".format(options.in_names_fname))
with open(options.in_names_fname,'r') as inf:
species = util.readTable(inf, header=True)
species_name_lookup = dict(zip(species['ODB_code'], [shorten(x) for x in species['Organism']]))
new_headers = []
new_seqs = []
for (hdr, seq) in zip(headers,seqs):
odb_code = hdr.strip().split()[-1]
if len(odb_code) == 5:
try:
# Rename
species_name = species_name_lookup[odb_code]
new_headers.append('{} {}'.format(species_name, hdr))
except KeyError:
new_headers.append(hdr)
else:
new_headers.append(hdr)
optdict = vars(options)
for (k,v) in optdict.items():
data_outs.write("#\t{k}: {v}\n".format(k=k, v=v))
# Read input
if not os.path.isfile(options.in_fname):
raise IOError("# Error: file {} does not exist".format(options.in_fname))
with open(options.in_fname,'r') as inf:
# Read a FASTA file?
(headers, seqs) = biofile.readFASTA(inf)
pref_ids = {}
if not os.path.isfile(options.in_filter_fname):
raise IOError("# Error: file {} does not exist".format(options.in_filter_fname))
with open(options.in_filter_fname,'r') as inf:
tab = util.readTable(inf, header=True)
pref_ids = dict(zip(tab['species'],tab['orthodb.name']))
# Now go through headers, find multiples, and select one from each.
selected_indices = [] # index into headers and sequences
new_headers = []
new_seqs = []
orthodb_ids = [h.split()[-1] for h in headers]
species_names = [h.split()[0].split('_')[0] for h in headers]
for species_name in list(set(species_names)):
dupe_indices = [xi for (xi,spec) in enumerate(species_names) if spec==species_name]
if len(dupe_indices)==1:
# No problem, no duplicate
selected_indices.append(dupe_indices[0])
continue
data_outs.write("#\t{k}: {v}\n".format(k=k, v=v))
# Read input
if not os.path.isfile(options.in_fname):
raise IOError("# Error: file {} does not exist".format(
options.in_fname))
with open(options.in_fname, 'r') as inf:
# Read a FASTA file?
(headers, seqs) = biofile.readFASTA(inf)
pref_ids = {}
if not os.path.isfile(options.in_filter_fname):
raise IOError("# Error: file {} does not exist".format(
options.in_filter_fname))
with open(options.in_filter_fname, 'r') as inf:
tab = util.readTable(inf, header=True)
pref_ids = dict(zip(tab['species'], tab['orthodb.name']))
# Now go through headers, find multiples, and select one from each.
selected_indices = [] # index into headers and sequences
new_headers = []
new_seqs = []
orthodb_ids = [h.split()[-1] for h in headers]
species_names = [h.split()[0].split('_')[0] for h in headers]
for species_name in list(set(species_names)):
dupe_indices = [
xi for (xi, spec) in enumerate(species_names)
if spec == species_name
]
if len(dupe_indices) == 1:
parser.add_argument(dest="prot_in_fname", type=str, help="FASTA file containing protein sequences")
parser.add_argument(dest="feature_fname", type=str, help="SGD file containing sequence features")
parser.add_argument(dest="paralog_fname", type=str, help="Yeast Gene Order Browser formatted file of paralog identifications")
parser.add_argument("--aa", dest="do_aa", default=False, action="store_true", help="compute amino-acid frequencies?")
parser.add_argument("--gc", dest="do_gc", default=False, action="store_true", help="compute GC frequencies?")
parser.add_argument("--mw", dest="do_mw", default=False, action="store_true", help="compute molecular weights?")
parser.add_argument("--target-aas", dest="target_aas", type=str, default=translate.AAs(), help="amino acids (e.g. ACDEF) for frequency analysis")
parser.add_argument("-p", "--pseudo", dest="pseudocount", type=float, default=0.0, help="pseudocount to add to all frequencies")
parser.add_argument("-o", "--out", dest="out_fname", type=str, default=None, help="output filename")
options = parser.parse_args()
cdna_dict = biofile.readFASTADict(os.path.expanduser(options.cds_in_fname))
prot_dict = biofile.readFASTADict(os.path.expanduser(options.prot_in_fname))
# Read paralog data from Yeast Gene Order Browser file
ygob_data = util.readTable(file(os.path.expanduser(options.paralog_fname),'r'))
paralog_dict = {}
for flds in ygob_data.dictrows:
scer1 = flds['scer1'].strip()
scer2 = flds['scer2'].strip()
if not (na.isNA(scer1) or na.isNA(scer2)):
paralog_dict[scer1] = scer2
paralog_dict[scer2] = scer1
# Read SGD data
sgd_features = util.readTable(file(os.path.expanduser(options.feature_fname),'r'), header=False)
'''
http://downloads.yeastgenome.org/curation/chromosomal_feature/SGD_features.README
1. Primary SGDID (mandatory)
2. Feature type (mandatory)
3. Feature qualifier (optional)
if not os.path.isfile(fname):
raise IOError("# Error: file {} does not exist".format(fname))
tree_root = Newick.Clade()
tree_root.parent = None
tree_root.name = "cellular organisms"
# Get directory of guide file
path = os.path.dirname(fname)
curwd = os.getcwd()
species_names = []
with open(fname,'r') as inf:
os.chdir(path)
tab = util.readTable(inf, header=True)
rows = tab.dictrows
if options.debug:
rows = [x for x in tab.dictrows][:2]
just_started = True
for row in rows:
spec_fname = row['filename']
#print(spec_fname)
if not na.isNA(spec_fname):
spec_inf = util.readTable(open(spec_fname,'r'), header=True)
twig = phyloutil.treeFromClassificationTable(spec_inf)
added = phyloutil.mergeTrees(tree_root, twig, add_to_leaf=just_started)
if added:
just_started = False
species_names.append(row['updated.species'])
#print(spec_fname)
default=0.0,
help="pseudocount to add to all frequencies")
parser.add_argument("-o",
"--out",
dest="out_fname",
type=str,
default=None,
help="output filename")
options = parser.parse_args()
cdna_dict = biofile.readFASTADict(os.path.expanduser(options.cds_in_fname))
prot_dict = biofile.readFASTADict(os.path.expanduser(
options.prot_in_fname))
# Read paralog data from Yeast Gene Order Browser file
ygob_data = util.readTable(
file(os.path.expanduser(options.paralog_fname), 'r'))
paralog_dict = {}
for flds in ygob_data.dictrows:
scer1 = flds['scer1'].strip()
scer2 = flds['scer2'].strip()
if not (na.isNA(scer1) or na.isNA(scer2)):
paralog_dict[scer1] = scer2
paralog_dict[scer2] = scer1
# Read SGD data
sgd_features = util.readTable(file(
os.path.expanduser(options.feature_fname), 'r'),
header=False)
'''
http://downloads.yeastgenome.org/curation/chromosomal_feature/SGD_features.README
1. Primary SGDID (mandatory)