def test005():
print "** Test 005 **"
(headers,seqs) = biofile.readFASTA("test-paml/paml-test-seqfile-0001.txt")
tree = newick.tree.parseTree(file("test-paml/paml-test-treefile-0001.txt", 'r').readlines()[1])
cm = paml.CodeML("codon", paml.CodeML.FMutSel_F_options)
cm.loadSequences(seqs, headers, str(tree))
cm.run()
cm.putBranchRatesOnTree(headers, tree)
cm.cleanUp()
def test005():
print "** Test 005 **"
(headers, seqs) = biofile.readFASTA("test-paml/paml-test-seqfile-0001.txt")
tree = newick.tree.parseTree(
file("test-paml/paml-test-treefile-0001.txt", 'r').readlines()[1])
cm = paml.CodeML("codon", paml.CodeML.FMutSel_F_options)
cm.loadSequences(seqs, headers, str(tree))
cm.run()
cm.putBranchRatesOnTree(headers, tree)
cm.cleanUp()
optdict = vars(options)
for (k,v) in sorted(optdict.items()):
data_outs.write("#\t{k}: {v}\n".format(k=k, v=v))
def secondField(h):
f = None
try:
f = biofile.secondField(h)
except:
f = biofile.firstField(h)
return f
# 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]
if not options.dont_align_sequences:
aligned_seqs = muscle.alignSequences(seqs)
seqs = aligned_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([(secondField(h), biofile.firstField(h)) for h in headers])
orf_gene_dict = dict([(v,k) for (k,v) in gene_orf_dict.items()])
# Write output
n_written = 0
data_outs.write("header\n")
# 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 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(seqs)))
new_headers = headers
new_seqs = seqs
for append_fname in options.append_fasta:
if not os.path.isfile(append_fname):
raise IOError(
"# Error: file {} does not exist".format(append_fname))
with open(append_fname, 'r') as inf:
# Read a FASTA file?
(app_headers, app_seqs) = biofile.readFASTA(inf)
info_outs.write("# Read {:d} sequences\n".format(len(app_seqs)))
assert len(app_seqs) == len(new_seqs)
if options.check_headers:
for (h1, h2) in zip(headers, app_headers):
random.seed(options.seed)
# Start up output
info_outs = util.OutStreams([sys.stdout])
data_outs = util.OutStreams()
multi_outs = util.OutStreams([info_outs, data_outs])
if not options.out_fname is None:
outf = file(options.out_fname, 'w')
data_outs.addStream(outf)
else:
data_outs.addStream(sys.stdout)
# Read sequences from a FASTA file?
fname = os.path.expanduser(seq)
if os.path.isfile(fname):
(headers, seq_list) = biofile.readFASTA(fname)
seqs = zip(headers, seq_list)
info_outs.write("# Read {0:d} sequences from {1}\n".format(
len(seqs), fname))
else:
seqs = [("command-line input", seq.upper())]
info_outs.write("# Read sequence L={:d} from standard input\n".format(
len(seqs[0][1])))
# If reverse-translation is desired, do it.
if options.reverse_translate:
new_seqs = []
for (h, s) in seqs:
rev_trans_seq = translate.reverseTranslate(s)
new_seqs.append((h, rev_trans_seq))
seqs = new_seqs
aas = None
if not options.aas is None:
if options.aas.lower() == 'all':
aas = translate.AAs()
else:
aas = [aa for aa in options.aas]
# Single sequence?
if not options.sequence is None:
headers = ['Input']
seqs = [options.sequence]
else:
if not options.in_fname is None:
fname = os.path.expanduser(options.in_fname)
#print(fname)
(headers, seqs) = biofile.readFASTA(open(fname, 'r'))
else:
info_outs.write("# No sequence or file provided; exiting\n")
sys.exit()
#print("# Found", len(seqs), "sequences")
#print("# Found", len(headers), "headers")
'''
if options.report: # Write a long report per protein
for (hdr, seq) in zip(headers,seqs):
if options.degap:
seq = seq.replace('-','')
if not options.end_aa is None and options.end_aa<= len(seq):
seq = seq[0:options.end_aa]
#print options.end_aa, options.begin_aa
seq = seq[options.begin_aa:]
outs.write("length = {:d}\n".format(pp.getLength(seq)))
random.seed(options.seed)
# Start up output
info_outs = util.OutStreams([sys.stdout])
data_outs = util.OutStreams()
multi_outs = util.OutStreams([info_outs, data_outs])
if not options.out_fname is None:
outf = file(options.out_fname,'w')
data_outs.addStream(outf)
else:
data_outs.addStream(sys.stdout)
# Read sequences from a FASTA file?
fname = os.path.expanduser(seq)
if os.path.isfile(fname):
(headers, seq_list) = biofile.readFASTA(fname)
seqs = zip(headers,seq_list)
info_outs.write("# Read {0:d} sequences from {1}\n".format(len(seqs), fname))
else:
seqs = [("command-line input",seq.upper())]
info_outs.write("# Read sequence L={:d} from standard input\n".format(len(seqs[0][1])))
# If reverse-translation is desired, do it.
if options.reverse_translate:
new_seqs = []
for (h,s) in seqs:
rev_trans_seq = translate.reverseTranslate(s)
new_seqs.append((h,rev_trans_seq))
seqs = new_seqs
# Obtain gene sequence using only optimal codons
if local_fname is None:
local_fname = "tmp{:d}".format(random.randint(0, 1e20))
# Fetch file from OrthoDB
if not options.orthodb_id is None:
#local_fname = "uniprot-yeast.txt"
remote_fname = "http://cegg.unige.ch/orthodb7/fasta.fasta?ogs={:s}".format(
options.orthodb_id)
urllib.urlretrieve(remote_fname, local_fname)
print "# Downloaded {} to {}".format(remote_fname, local_fname)
info_outs.write("# Downloaded {} to {}\n".format(
remote_fname, local_fname))
# Read input
if not os.path.isfile(local_fname):
raise IOError("# Error: file {} does not exist".format(local_fname))
with open(local_fname, 'r') as inf:
# Read a FASTA file?
(headers, seqs) = biofile.readFASTA(inf)
if options.fasta_out_fname is None:
# Write data
biofile.writeFASTA(seqs, fasta_outs, headers=headers)
# Write out stopping time
info_outs.write("# Run finished {}\n".format(util.timestamp()))
# Shut down output
if not options.fasta_out_fname is None:
info_outs.write("# Fetched {} sequences to {}\n".format(
len(headers), options.fasta_out_fname))
outf.close()
import sys, os, math, string
import biofile
if __name__ == '__main__':
(h, s) = biofile.readFASTA('test-biofile/test-biofile-001.fa')
assert len(h) == 143
cd = biofile.readFASTADict(
os.path.expanduser('test-biofile/test-biofile-001.fa'))
assert len(cd.keys()) == len(h)
frags = digestWithEnzyme(seq, "trypsin", 1)
assert set(frags) == set(["VR", "VRK", "KT", "K", "T"])
print "\ttest006 passed"
if __name__ == '__main__':
fname = sys.argv[1]
if fname == "__test__":
print "Running tests..."
test001()
test002()
test003()
test004()
test005()
test006()
print "All tests passed"
sys.exit()
patterns = sys.argv[2].split("/")
complete = True
if os.path.isfile(os.path.expanduser(fname)):
(headers, seqs) = biofile.readFASTA(os.path.expanduser(fname))
else:
seqs = [fname]
for seq in seqs:
frags = digest(seq, patterns, complete)
#print "\n%s\n---" % seq
for f in frags:
print len(f), f
if complete:
assert ''.join(frags) == seq
aas = None
if not options.aas is None:
if options.aas.lower() == 'all':
aas = translate.AAs()
else:
aas = [aa for aa in options.aas]
# Single sequence?
if not options.sequence is None:
headers = ['Input']
seqs = [options.sequence]
else:
if not options.in_fname is None:
fname = os.path.expanduser(options.in_fname)
#print(fname)
(headers,seqs) = biofile.readFASTA(open(fname, 'r'))
else:
info_outs.write("# No sequence or file provided; exiting\n")
sys.exit()
#print("# Found", len(seqs), "sequences")
#print("# Found", len(headers), "headers")
'''
if options.report: # Write a long report per protein
for (hdr, seq) in zip(headers,seqs):
if options.degap:
seq = seq.replace('-','')
if not options.end_aa is None and options.end_aa<= len(seq):
seq = seq[0:options.end_aa]
#print options.end_aa, options.begin_aa
seq = seq[options.begin_aa:]
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 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)
for fname in options.other_fasta_fnames:
if not os.path.isfile(fname):
raise IOError("# Error: file {} does not exist".format(fname))
with open(fname,'r') as inf:
# Read a FASTA file?
(new_headers, new_seqs) = biofile.readFASTA(inf)
headers = headers + new_headers
seqs = seqs + new_seqs
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)
def shorten(x):
import sys, os, math, string
import biofile
if __name__=='__main__':
(h,s) = biofile.readFASTA('test-biofile/test-biofile-001.fa')
assert len(h) == 143
cd = biofile.readFASTADict(os.path.expanduser('test-biofile/test-biofile-001.fa'))
assert len(cd.keys()) == len(h)
optdict = vars(options)
for (k,v) in sorted(optdict.items()):
data_outs.write("#\t{k}: {v}\n".format(k=k, v=v))
def secondField(h):
f = None
try:
f = biofile.secondField(h)
except:
f = biofile.firstField(h)
return f
prot_dict = {}
# Read input
if not os.path.isfile(options.in_fasta_fname):
raise IOError("# Error: file {} does not exist".format(options.in_fasta_fname))
(headers, seqs) = biofile.readFASTA(file(options.in_fasta_fname, 'r'))
all_keys = [biofile.firstField(h) for h in headers]
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]
(headers, seqs) = zip(*zhs)
prot_dict = dict([(biofile.firstField(h), s) for (h,s) in zhs])
gene_orf_dict = dict([(secondField(h), biofile.firstField(h)) for h in headers])
orf_gene_dict = dict([(o,g) for (g,o) in gene_orf_dict.items()])
query_keys = []
if not options.query_orf is []:
# Specific ORF(s)
query_keys += options.query_orf
if not options.query_gene is []:
# Specific gene(s)
# Set up some output
info_outs = util.OutStreams(sys.stdout)
outs = util.OutStreams()
params_outs = util.OutStreams([outs])
if not options.out_fname is None:
outf = open(os.path.expanduser(options.out_fname),'w')
outs.addStream(outf)
else:
outs.addStream(sys.stdout)
orf_dict = None
gene_orf_map = None
if not options.fasta_fname is None:
fname = os.path.expanduser(options.fasta_fname)
(headers, sequences) = biofile.readFASTA(fname)
orf_dict = dict(zip([biofile.firstField(h) for h in headers], sequences))
gene_orf_map = dict([(biofile.secondField(h), biofile.firstField(h)) for h in headers])
# Set the weight matrix
try:
matrix = motif.weight_matrices[options.pssm_name]
except KeyError as ke:
outs.write("# Unable to find weight matrix {}; try one of {}\n".format(options.pssm_name, ','.join(motif.weight_matrices.keys())))
window_size = len(matrix['A']) #len(matrix.values()[0])
# for associating windows with residues, center them
mid_window = int(math.floor(window_size/2.0))
# Write out parameters
params_outs.write("# Run started {}\n".format(util.timestamp()))
assert set(frags) == set(["VR","VRK","KT","K","T"])
print "\ttest006 passed"
if __name__ == '__main__':
fname = sys.argv[1]
if fname == "__test__":
print "Running tests..."
test001()
test002()
test003()
test004()
test005()
test006()
print "All tests passed"
sys.exit()
patterns = sys.argv[2].split("/")
complete = True
if os.path.isfile(os.path.expanduser(fname)):
(headers, seqs) = biofile.readFASTA(os.path.expanduser(fname))
else:
seqs = [fname]
for seq in seqs:
frags = digest(seq, patterns, complete)
#print "\n%s\n---" % seq
for f in frags:
print len(f), f
if complete:
assert ''.join(frags) == seq
if not options.isolate_out_fname is None:
isolate_outf = file(options.isolate_out_fname,'w')
isolate_outs.addStream(isolate_outf)
# Write out parameters
params_outs.write("# Run started {}\n".format(util.timestamp()))
params_outs.write("# Command: {}\n".format(' '.join(sys.argv)))
params_outs.write("# Parameters:\n")
optdict = vars(options)
for (k,v) in optdict.items():
params_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))
(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])
orf_gene_dict = dict([(v,k) for (k,v) in gene_orf_dict.items()])
# Select which genes to process
query_keys = []
if not options.query_orf is []:
# Specific ORF(s)
query_keys += options.query_orf
if not options.query_gene is []:
fasta_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 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(seqs)))
new_headers = headers
new_seqs = seqs
for append_fname in options.append_fasta:
if not os.path.isfile(append_fname):
raise IOError("# Error: file {} does not exist".format(append_fname))
with open(append_fname,'r') as inf:
# Read a FASTA file?
(app_headers, app_seqs) = biofile.readFASTA(inf)
info_outs.write("# Read {:d} sequences\n".format(len(app_seqs)))
assert len(app_seqs) == len(new_seqs)
if options.check_headers:
for (h1, h2) in zip(headers, app_headers):
assert h1==h2, "# Error: headers do not match:\n\t{}\n\t{}".format(h1,h2)
fasta_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 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(seqs)))
# Find query sequence(s)
query_ids = []
for (xi, h) in enumerate(headers):
if options.query in h:
query_ids.append(xi)
if len(query_ids) == 0:
info_outs.write("# Could not find sequences '{}'; exiting\n".format(options.query))
sys.exit()
if len(query_ids) > 1:
info_outs.write("# Found more than one sequence matching '{}'; using the first one: \n#\t{}\n".format(options.query, headers[xi]))
# Pick the first one
query_id = query_ids[0]
parser.add_argument("in_fname", help="input filename")
parser.add_argument("-p", "--path", dest="muscle_path", default=const_default_muscle_exepath, help="path to Muscle binary")
parser.add_argument("-t", "--translate", dest="translate", action="store_true", default=False, help="translate the input sequences?")
parser.add_argument("-o", "--out", dest="out_fname", default=None, help="output filename")
options = parser.parse_args()
outs = util.OutStreams()
if not options.out_fname is None:
fname = os.path.expanduser(options.out_fname)
#print fname
outf = open(fname,'w')
outs.addStream(outf)
else:
outs.addStream(sys.stdout)
(headers, seqs) = biofile.readFASTA(open(options.in_fname,'r'))
seqs_to_align = seqs
if options.translate:
seqs_to_align = [translate.translate(s) for s in seqs]
alseqs = alignSequences(seqs_to_align, exepath=options.muscle_path)
#print alseqs
if options.translate:
alseqs = [alignGeneFromProtein(g, s) for (g,s) in zip(seqs,alseqs)]
for (h,s) in zip(headers,alseqs):
outs.write(">{}\n{}\n".format(h,s))
if not options.out_fname is None:
outf.close()
data_outs.write("#\t{k}: {v}\n".format(k=k, v=v))
def secondField(h):
f = None
try:
f = biofile.secondField(h)
except:
f = biofile.firstField(h)
return f
prot_dict = {}
# Read input
if not os.path.isfile(options.in_fasta_fname):
raise IOError("# Error: file {} does not exist".format(
options.in_fasta_fname))
(headers, seqs) = biofile.readFASTA(file(options.in_fasta_fname, 'r'))
all_keys = [biofile.firstField(h) for h in headers]
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]
(headers, seqs) = zip(*zhs)
prot_dict = dict([(biofile.firstField(h), s) for (h, s) in zhs])
gene_orf_dict = dict([(secondField(h), biofile.firstField(h))
for h in headers])
orf_gene_dict = dict([(o, g) for (g, o) in gene_orf_dict.items()])
query_keys = []
if not options.query_orf is []:
# Specific ORF(s)
query_keys += options.query_orf
if not options.query_gene is []:
