def run_yn00(input_phy, yn00_binary):
binary = yn00_binary
yn = yn00.Yn00()
yn.alignment = input_phy
yn.out_file = input_phy + ".out"
yn.working_dir = "./"
yn.set_options(commonf3x4=1)
print("Analyzing " + input_phy)
run_result = yn.run(command=binary, verbose=False)
return run_result
def run_yn00(self):
yn = yn00.Yn00()
yn.alignment = self.mrtrans
yn.out_file = self.pair_yn
yn.set_options(icode=0, commonf3x4=0, weighting=0, verbose=1)
try:
run_result = yn.run(command=self.yn00_path)
except:
run_result = None
return run_result
def RunYn00(yn_path, alignment):
"""
Run yn00 on untranslated alignment with default parameters and output to file.
"""
yn = yn00.Yn00(alignment=alignment, out_file="{0}.yn00".format(alignment))
yn.set_options(verbose=0, icode=0, weighting=0, commonf3x4=0)
try:
yn.run(ctl_file=None, command=yn_path, parse=False)
except PamlError as e:
print "{0}, {1} may have internal stop codons.".format(e, alignment)
pass
def run_yn00(input_phy,
yn00_binary="/Users/longtian/Desktop/paml4.8/bin/yn00"):
binary = yn00_binary
yn = yn00.Yn00()
yn.alignment = input_phy
yn.out_file = input_phy + ".out"
yn.working_dir = "./"
yn.set_options(commonf3x4=1)
print "Analyzing " + input_phy
run_result = yn.run(command=binary, verbose=True)
return run_result
def runYn00(ogFastaPath2, allCDSpath, wd):
Omega = {}
Dn = {}
Ds = {}
for ogFastaPath in ogFastaPath2:
OG_fasta = os.path.basename(ogFastaPath)
prefix = str(OG_fasta.split(".")[0])
PEP_aln = wd + prefix + ".pep.aln"
protein_id = []
with open(PEP_aln, "w+") as f:
for seq1 in SeqIO.parse(ogFastaPath, "fasta"):
id = seq1.id.split("_")[2] + "_" + seq1.id.split("_")[3]
protein_id.append(id)
f.write(">" + id + "\n" + str(seq1.seq) + "\n")
# generate CDS .fasta file
CDSfile = wd + prefix + ".cds"
records = (r for r in SeqIO.parse(allCDSpath, "fasta")
if r.id in protein_id)
SeqIO.write(records, CDSfile, "fasta")
## align coding regions using clustalo output .aln file
CDS_aln = CDSfile + ".aln"
cdsAlign(CDSfile=CDSfile, outfile=CDS_aln)
## generate .nuc file for yn00,
nuc_file = wd + prefix + ".nuc"
runPAL2NAL(PEP_aln=PEP_aln, CDS_aln=CDS_aln, outfile=nuc_file)
## run yn00 in PAML
yn00_res = wd + prefix + "_yn00.txt"
yn = yn00.Yn00(alignment=nuc_file, out_file=yn00_res, working_dir=wd)
yn.set_options(verbose=True)
Yn00_results = yn.run(verbose=True)
memo = []
for gene1 in Yn00_results:
memo.append(gene1)
for gene2 in Yn00_results[gene1]:
if not gene2 in memo:
Omega["{0}-{1}".format(
gene1,
gene2)] = Yn00_results[gene1][gene2]["YN00"]["omega"]
Dn["{0}-{1}".format(
gene1,
gene2)] = Yn00_results[gene1][gene2]["YN00"]["dN"]
Ds["{0}-{1}".format(
gene1,
gene2)] = Yn00_results[gene1][gene2]["YN00"]["dS"]
return Omega, Dn, Ds
def yn00():
from Bio.Phylo.PAML import yn00
tests = ["yn00"]
alignment = os.path.join("Alignments", "alignment.phylip")
for test in tests:
print test[0]
yn = yn00.Yn00()
for version in VERSIONS:
print "\t{0}".format(version.replace('_', '.'))
ctl_file = os.path.join("Control_files", "yn00",
"{0}.ctl".format(test))
yn.read_ctl_file(ctl_file)
yn.alignment = alignment
out_file = "{0}-{1}.out".format(test, version)
yn.out_file = os.path.join("Results", "yn00", out_file)
bin = "yn00{0}".format(version)
yn.run(command=bin, verbose=VERBOSE)
def yn00(vers=None, verbose=False):
from Bio.Phylo.PAML import yn00
if vers is not None:
versions = [vers]
else:
versions = VERSIONS
tests = ["yn00", "yn00_long", "yn00_dotted", "yn00_dottednum"]
for test in tests:
print(test)
yn = yn00.Yn00()
for version in versions:
print(f"\t{version.replace('_', '.')}")
ctl_file = os.path.join("Control_files", "yn00", f"{test}.ctl")
yn.read_ctl_file(ctl_file)
out_file = f"{test}-{version}.out"
yn.out_file = os.path.join("Results", "yn00", out_file)
bin = f"yn00{version}"
yn.run(command=bin, verbose=verbose, parse=False)
def yn00(vers=None, verbose=False):
from Bio.Phylo.PAML import yn00
if vers is not None:
versions = [vers]
else:
versions = VERSIONS
tests = ["yn00", "yn00_long", "yn00_dotted", "yn00_dottednum"]
for test in tests:
print(test)
yn = yn00.Yn00()
for version in versions:
print("\t{0}".format(version.replace('_', '.')))
ctl_file = (os.path.join("Control_files", "yn00",
"{0}.ctl".format(test)))
yn.read_ctl_file(ctl_file)
out_file = "{0}-{1}.out".format(test, version)
yn.out_file = os.path.join("Results", 'yn00', out_file)
bin = "yn00{0}".format(version)
yn.run(command=bin, verbose=verbose, parse=False)
def yn00(vers=None, verbose=False):
from Bio.Phylo.PAML import yn00
if vers is not None:
versions = [vers]
else:
versions = VERSIONS
tests = ["yn00"]
alignment = os.path.join("Alignments", "alignment.phylip")
for test in tests:
print(test[0])
yn = yn00.Yn00()
for version in versions:
print("\t{0}".format(version.replace('_', '.')))
ctl_file = os.path.join("Control_files", "yn00",
"{0}.ctl".format(test))
yn.read_ctl_file(ctl_file)
yn.alignment = alignment
out_file = "{0}-{1}.out".format(test, version)
yn.out_file = os.path.join("Results", "yn00", out_file)
bin = "yn00{0}".format(version)
yn.run(command=bin, verbose=verbose)
def setUp(self):
self.yn00 = yn00.Yn00()
]
if len(has_stop):
#sys.stderr.write("\nfound stop codon at {} in sequence '{}'\n".format(has_stop[0], s.id))
first_stop = has_stop[0]
fa = fa[:, 0:first_stop]
trimmed_len = len(fa[0])
with open(seq_converted, "w") as ph:
AlignIO.write(fa, ph, "phylip-sequential")
## print some diagnostics to stderr
sys.stderr.write("\nWorking directory: {}\n".format(wd))
sys.stderr.write("Input file: {} (length {})\n".format(args.sequences,
untrimmed_len))
sys.stderr.write("Converted to phylip: {} (length {})\n\n".format(
seq_converted, trimmed_len))
## run yn00
yn = yn00.Yn00(alignment=seq_converted, working_dir=wd, out_file="results.out")
rez = yn.run(verbose=False)
## get results for all sequence pairs
ph = AlignIO.read(seq_converted, "phylip-relaxed")
ids = [s.id for s in ph]
for s1, s2 in itertools.combinations(ids, 2):
omega = rez[s1][s2][args.method]["omega"]
if omega < 0 or omega > 10:
omega = "NA"
print s1, s2, omega, abs(rez[s1][s2][args.method]["dN"]), abs(
rez[s1][s2][args.method]["dS"])
#Run PAML yn00 for each PHYLIP alignment and create the final output table
output_yn00 = open(organism + "_yn00_finalresult.csv", "w")
output_yn00.write("Seq1\tSeq2\tdS\tdS SE\tdN\tdN SE\n")
for i in inparalogs_dic.keys():
if taxons[organism] in i:
copy1 = i.replace(taxons[organism], "")
copy2 = inparalogs_dic[i].replace(taxons[organism], "")
if copy1 in organism_fasta and copy2 in organism_fasta:
seq1 = organism_fasta[copy1]
seq2 = organism_fasta[copy2]
namealnphy = copy1 + "_" + copy2 + ".aln.phy"
print("Runing yn00 for", namealnphy)
#run PAML yn00 software
yn = yn00.Yn00()
yn.alignment = namealnphy
yn.out_file = "yn_out.txt"
yn.working_dir = "./"
yn.commonf3x4 = 1
yn.weighting = None
yn.icode = None
yn.ndata = None
yn.verbose = None
yn.run()
result = yn00.read("yn_out.txt")[copy1]
for uu in result.values():
ds = str(uu["YN00"]["dS"])
dsse = str(uu["YN00"]["dS SE"])
dn = str(uu["YN00"]["dN"])
dnse = str(uu["YN00"]["dN SE"])
