def do_astral(input, output):
astralpath = getlocalpath()
if not os.path.exists(output):
os.mkdir(output)
out_name = "combine.tree"
consensuseCmd = "java -jar " + astralpath + "/astral.5.6.3.jar" + " -i " + input + " -o " + output + "/" + out_name
subprocess.call(consensuseCmd, shell=True)
def do_supertree(input, output):
supertreepath = getlocalpath()
if not os.path.exists(output):
os.mkdir(output)
out_name = "spr_supertree.tree"
consensuseCmd = supertreepath + "/spr_supertree" + " < " + input + " > " + output + "/" + out_name
subprocess.call(consensuseCmd, shell=True)
def domuscle_file(indata_files, outdata, musclepara):
"""
call muscle software to do align
:param indata_files: a directory contain more than one file
:param outdata: out file after alignment
:return: path
"""
muscleparas = musclepara.lstrip()
mupath = getlocalpath()
out_path = os.path.dirname(outdata)
timeformat = '%Y%m%d%H%M%S'
timeinfo = str(time.strftime(timeformat))
subdir = 'temp/alignment' + timeinfo
muscle_dir = os.path.join(out_path, subdir)
# muscle_dir = os.path.join(indata_files, 'muscle_alignment')
pro_name = os.listdir(indata_files)
if not os.path.exists(muscle_dir):
os.makedirs(muscle_dir)
for i in pro_name:
out_alg = os.path.join(muscle_dir, i.split('.')[0])
each_pro = os.path.join(indata_files, i)
cmd = mupath + "/muscle -in " + each_pro + " -out " + out_alg + " " + muscleparas
subprocess.call(cmd, shell=True)
logdomuscle.info("Multiple sequence alignment by Muscle was completed.")
return muscle_dir
def domafft_file(indata_files, outdata, mafftparas, thread):
"""
call mafft software to do align
:param indata_files: a directory contain more than one file
:param outdata: out file after alignment
:return: path
"""
mafftparas = mafftparas.lstrip()
mapath = getlocalpath()
out_path = os.path.dirname(outdata)
timeformat = '%Y%m%d%H%M%S'
timeinfo = str(time.strftime(timeformat))
subdir = 'temp/alignment' + timeinfo
mafft_dir = os.path.join(out_path, subdir)
# mafft_dir = os.path.join(indata_files, 'muscle_alignment')
pro_name = os.listdir(indata_files)
if not os.path.exists(mafft_dir):
os.makedirs(mafft_dir)
all_cmd = []
for i in pro_name:
out_alg = os.path.join(mafft_dir, i.split('.')[0])
each_pro = os.path.join(indata_files, i)
cmd = mapath + "/mafft " + mafftparas + " " + each_pro + " > " + out_alg
# subprocess.call(cmd, shell=True)
all_cmd.append(cmd)
pool = multiprocessing.Pool(processes=thread)
# method 1: map
pool.map(run_cmd, all_cmd)
logmafft.info("Multiple sequence alignment by mafft was completed.")
return mafft_dir
def dogblocks(indata, gblockpara):
"""
do gblocks after muslce and concatenate
:param indata: a fasta file input after gblock
:param gblockpara: the gblocks para
:return: a file path of gblocks result
"""
# Deal with outdata name
gblockparas = gblockpara.lstrip()
gblockparalist = gblockparas.split(" ")
regex = '-e='
for i in range(0, len(gblockparalist)):
if re.search(regex, gblockparalist[i]):
index = i
break
outnamepara = gblockparalist[index]
outdata = outnamepara.split('=')[1]
gblockpath = getlocalpath()
alg_name = os.path.basename(indata)
out_path = os.path.dirname(indata)
gblock_name = alg_name + outdata
gblock_data = os.path.join(out_path, gblock_name)
cmd = gblockpath + "/Gblocks " + indata + " " + gblockparas
subprocess.call(cmd, shell=True)
loggblocks.info('Select conserved blocks by Gblocks was completed')
loggblocks.debug('Gblocks path:{0}'.format(gblock_data))
return gblock_data
def domafft_file(indata_files, outdata, mafftparas):
"""
call mafft software to do align
:param indata_files: a directory contain more than one file
:param outdata: out file after alignment
:return: path
"""
mafftparas = mafftparas.lstrip()
mapath = getlocalpath()
out_path = os.path.dirname(outdata)
timeformat = '%Y%m%d%H%M%S'
timeinfo = str(time.strftime(timeformat))
subdir = 'temp/alignment' + timeinfo
mafft_dir = os.path.join(out_path, subdir)
# mafft_dir = os.path.join(indata_files, 'muscle_alignment')
pro_name = os.listdir(indata_files)
if not os.path.exists(mafft_dir):
os.makedirs(mafft_dir)
for i in pro_name:
out_alg = os.path.join(mafft_dir, i.split('.')[0])
each_pro = os.path.join(indata_files, i)
cmd = mapath + "/mafft " + mafftparas + " " + each_pro + " > " + out_alg
subprocess.call(cmd, shell=True)
logmafft.info("Multiple sequence alignment by mafft was completed.")
return mafft_dir
def doraxml(inputfile, outputfile, raxmlpara, thread):
"""
call RAxML method to construct species tree
:param inputfile: abs path of .phy format files
:param outputfile: a file contain RAxML result
"""
raxmlparas = raxmlpara.lstrip()
raxmlparalist = raxmlparas.split(" ")
tpara = '-T'
if tpara in raxmlparalist:
index = raxmlparalist.index(tpara)
raxmlparalist.remove(raxmlparalist[index])
raxmlparalist.remove(raxmlparalist[index])
raxmlpararet = ' '.join(raxmlparalist)
else:
raxmlpararet = raxmlpara
threadtostr = str(thread)
raxmlpath = getlocalpath()
if not os.path.exists(outputfile):
os.mkdir(outputfile)
strs = raxmlpath + "/raxmlHPC-PTHREADS-AVX " + "-T " + threadtostr + " " + raxmlpararet
# cmd command
cmd = strs + " -s " + inputfile + " -w " + outputfile
subprocess.call(cmd, shell=True)
logdoraxml.info("Phylogenetic species tree reconstructed by RAxML was completed")
def doclustalw_file(indata_files, outdata, clustalwpara):
"""
Call clustalw software to do align
:param indata_files: a directory contain more than one file
:param outdata: out file after alignment
:return: path
"""
type = "-TYPE=PROTEIN"
if clustalwpara is None:
clustalwparas = type
else:
clustalwparas = type + " " + clustalwpara.lstrip()
clu_path = getlocalpath()
out_path = os.path.dirname(outdata)
doclu_subdir = str(timeformat('temp/hcp_alignment'))
clustalw_dir = os.path.join(out_path, doclu_subdir)
pro_name = os.listdir(indata_files)
if not os.path.exists(clustalw_dir):
os.makedirs(clustalw_dir)
for i in pro_name:
each_pro = os.path.join(indata_files, i)
out_file = "-OUTFILE=" + os.path.join(clustalw_dir, i)
cmd = clu_path + "/clustalw2 " + "-INFILE=" + each_pro + " -OUTPUT=FASTA -ALIGN " + out_file + " " + clustalwparas
subprocess.call(cmd, shell=True)
logdoclustalw.info("Multiple sequence alignment by Clustalw2 was completed.")
return clustalw_dir
def dotrimal(indata, trimalpara):
"""
do trimal after muslce and concatenate
:param indata: a fasta file input to do trimal
:param outdata: append name after
:return: a file path of trimal result
"""
# Deal with outdata name
trimalparas = trimalpara.lstrip()
trimalpath = getlocalpath()
out_path = os.path.dirname(indata)
trimal_name = "trimal.phy"
trimal_data = os.path.join(out_path, trimal_name)
cmd = trimalpath + "/trimal " + " -in " + indata + " -out " + trimal_data + " " + trimalparas + " -phylip"
subprocess.call(cmd, shell=True)
# support fasttree software
trimal_data2 = trimal_data.replace('.phy', '')
cmd2 = trimalpath + "/trimal " + " -in " + indata + " -out " + trimal_data2 + " " + trimalparas + " -fasta"
subprocess.call(cmd2, shell=True)
loggtrimal.info('Select conserved blocks by trimal was completed')
loggtrimal.debug('trimal path:{0}'.format(trimal_data))
return trimal_data
def doclustalw_file(indata_files, outdata, clustalwpara):
"""
Call clustalw software to do align
:param indata_files: a directory contain more than one file
:param outdata: out file after alignment
:return: path
"""
type = "-TYPE=PROTEIN"
if clustalwpara is None:
clustalwparas = type
else:
clustalwparas = type + " " + clustalwpara.lstrip()
clu_path = getlocalpath()
out_path = os.path.dirname(outdata)
doclu_subdir = str(timeformat('temp/hcp_alignment'))
clustalw_dir = os.path.join(out_path, doclu_subdir)
pro_name = os.listdir(indata_files)
if not os.path.exists(clustalw_dir):
os.makedirs(clustalw_dir)
for i in pro_name:
each_pro = os.path.join(indata_files, i)
out_file = "-OUTFILE=" + os.path.join(clustalw_dir, i)
cmd = clu_path + "/clustalw2 " + "-INFILE=" + each_pro + " -OUTPUT=FASTA -ALIGN " + out_file + " " + clustalwparas
subprocess.call(cmd, shell=True)
logdoclustalw.info(
"Multiple sequence alignment by Clustalw2 was completed.")
return clustalw_dir
def docontree(input, output, rule):
"""
Combine tree
:param input: input files
:param output: output directory
"""
# get raxml path
raxmlpath = getlocalpath()
# run
# prepare a dir store result
if not os.path.exists(output):
os.mkdir(output)
consensuseCmd = raxmlpath + "/raxmlHPC-PTHREADS-AVX " + " -J " + rule + " -m GTRCAT -z " + input + " -w " + output + " -n T1"
subprocess.call(consensuseCmd, shell=True)
def docontree(input, output, rule):
"""
Combine tree
:param input: input files
:param output: output directory
"""
# get raxml path
raxmlpath = getlocalpath()
# run
# prepare a dir store result
if not os.path.exists(output):
os.mkdir(output)
consensuseCmd = raxmlpath + "/raxmlHPC-PTHREADS-AVX " + " -J " + rule + " -m GTRCAT -z " + input + " -w " + output + " -n T1"
subprocess.call(consensuseCmd, shell=True)
def doiqtree(inputfile, outputfile, iqtreepara, thread):
# Use FASTA format build tree
# input_fasta = inputfile.replace('.phy', '')
iqtreePath = getlocalpath()
thread_to_str = str(thread)
out_tree_name = os.path.join(outputfile, "iqtree.tree")
if not os.path.exists(outputfile):
os.mkdir(outputfile)
if thread_to_str is '1':
cmd = iqtreePath + "/iqtree " + "-s " + inputfile + " -pre " + out_tree_name + iqtreepara
subprocess.call(cmd, shell=True)
else:
# set the threads
cmd = iqtreePath + "/iqtree " + "-s " + inputfile + " -pre " + out_tree_name + " -nt " + thread_to_str + iqtreepara
subprocess.call(cmd, shell=True)
logdoiqtree.info("Phylogenetic species tree reconstructed by iqtree was completed")
def doFastTree(inputfile, outputfile, FastTreepara, thread):
# Use FASTA format build tree
input_fasta = inputfile.replace('.phy', '')
FastTreePath = getlocalpath()
thread_to_str = str(thread)
out_tree_name = os.path.join(outputfile, "FastTree.tree")
if not os.path.exists(outputfile):
os.mkdir(outputfile)
if thread_to_str is '1':
cmd = FastTreePath + "/FastTree " + FastTreepara + input_fasta + " >" + out_tree_name
subprocess.call(cmd, shell=True)
else:
# set the threads
os.environ["OMP_NUM_THREADS"] = thread_to_str
cmd = FastTreePath + "/FastTreeMP " + FastTreepara + input_fasta + " >" + out_tree_name
subprocess.call(cmd, shell=True)
logdofasttree.info("Phylogenetic species tree reconstructed by FastTree was completed")
def doiqtree(inputfile, outputfile, iqtreepara, thread):
# Use FASTA format build tree
# input_fasta = inputfile.replace('.phy', '')
iqtreePath = getlocalpath()
thread_to_str = str(thread)
out_tree_name = os.path.join(outputfile, "iqtree.tree")
if not os.path.exists(outputfile):
os.mkdir(outputfile)
if thread_to_str is '1':
cmd = iqtreePath + "/iqtree " + "-s " + inputfile + " -pre " + out_tree_name + iqtreepara
subprocess.call(cmd, shell=True)
else:
# set the threads
cmd = iqtreePath + "/iqtree " + "-s " + inputfile + " -pre " + out_tree_name + " -nt " + thread_to_str + iqtreepara
subprocess.call(cmd, shell=True)
logdoiqtree.info(
"Phylogenetic species tree reconstructed by iqtree was completed")
def doFastTree(inputfile, outputfile, FastTreepara, thread):
# Use FASTA format build tree
input_fasta = inputfile.replace('.phy', '')
FastTreePath = getlocalpath()
thread_to_str = str(thread)
out_tree_name = os.path.join(outputfile, "FastTree.tree")
if not os.path.exists(outputfile):
os.mkdir(outputfile)
if thread_to_str is '1':
cmd = FastTreePath + "/FastTree " + FastTreepara + " " + input_fasta + " >" + out_tree_name
subprocess.call(cmd, shell=True)
else:
# set the threads
os.environ["OMP_NUM_THREADS"] = thread_to_str
cmd = FastTreePath + "/FastTreeMP " + FastTreepara + " " + input_fasta + " >" + out_tree_name
subprocess.call(cmd, shell=True)
logdofasttree.info(
"Phylogenetic species tree reconstructed by FastTree was completed")
def doclustalw(indata, outdata, clustalwpara):
"""
Call clustalw software to do align
:param indata: a director contain a fasta format file or a fasta format file
:param outdata: the out is abs path with a file name
:return: outdata path
"""
logdoclustalw.debug("clustalw input data:{0}".format(indata))
type = "-TYPE=DNA"
if clustalwpara is None:
clustalwparas = type
else:
clustalwparas = type + " " + clustalwpara.lstrip()
clu_path = getlocalpath()
out_path = os.path.dirname(outdata)
doclu_subdir = str(timeformat('temp/rna_sequence'))
clustalw_dir = os.path.join(out_path, doclu_subdir)
# check indata type is dir or files?
if os.path.isdir(indata):
pro_name = os.listdir(indata)
if not os.path.exists(clustalw_dir):
os.makedirs(clustalw_dir)
out_file = "-OUTFILE=" + os.path.join(clustalw_dir, pro_name[0])
infile = os.path.join(indata, pro_name[0])
cmd = clu_path + "/clustalw2 " + "-INFILE=" + infile + " -OUTPUT=FASTA -ALIGN " + out_file + " " + clustalwparas
subprocess.call(cmd, shell=True)
logdoclustalw.info(
"Multiple sequence alignment by Clustalw2 was completed.")
out_alg = os.path.join(clustalw_dir, pro_name[0])
return out_alg
# indata is a file
elif os.path.isfile(indata):
pro_name = indata
if not os.path.exists(clustalw_dir):
os.makedirs(clustalw_dir)
out_file = "-OUTFILE=" + os.path.join(clustalw_dir, pro_name)
cmd = clu_path + "/clustalw2 " + "-INFILE=" + pro_name + " -OUTPUT=FASTA -ALIGN " + out_file + " " + clustalwparas
subprocess.call(cmd, shell=True)
logdoclustalw.info(
"Multiple sequence alignment by Clustalw2 was completed.")
out_alg = os.path.join(clustalw_dir, pro_name)
return out_alg
def doclustalw(indata, outdata, clustalwpara):
"""
Call clustalw software to do align
:param indata: a director contain a fasta format file or a fasta format file
:param outdata: the out is abs path with a file name
:return: outdata path
"""
logdoclustalw.debug("clustalw input data:{0}".format(indata))
type = "-TYPE=DNA"
if clustalwpara is None:
clustalwparas = type
else:
clustalwparas = type + " " + clustalwpara.lstrip()
clu_path = getlocalpath()
out_path = os.path.dirname(outdata)
doclu_subdir = str(timeformat('temp/rna_sequence'))
clustalw_dir = os.path.join(out_path, doclu_subdir)
# check indata type is dir or files?
if os.path.isdir(indata):
pro_name = os.listdir(indata)
if not os.path.exists(clustalw_dir):
os.makedirs(clustalw_dir)
out_file = "-OUTFILE=" + os.path.join(clustalw_dir, pro_name[0])
infile = os.path.join(indata,pro_name[0])
cmd = clu_path + "/clustalw2 " + "-INFILE=" + infile + " -OUTPUT=FASTA -ALIGN " + out_file + " " + clustalwparas
subprocess.call(cmd, shell=True)
logdoclustalw.info("Multiple sequence alignment by Clustalw2 was completed.")
out_alg = os.path.join(clustalw_dir, pro_name[0])
return out_alg
# indata is a file
elif os.path.isfile(indata):
pro_name = indata
if not os.path.exists(clustalw_dir):
os.makedirs(clustalw_dir)
out_file = "-OUTFILE=" + os.path.join(clustalw_dir, pro_name)
cmd = clu_path + "/clustalw2 " + "-INFILE=" + pro_name + " -OUTPUT=FASTA -ALIGN " + out_file + " " + clustalwparas
subprocess.call(cmd, shell=True)
logdoclustalw.info("Multiple sequence alignment by Clustalw2 was completed.")
out_alg = os.path.join(clustalw_dir, pro_name)
return out_alg
def domuscle(indata, outdata, musclepara):
"""
call muscle software to do align
:param indata: a director contain a fasta format file or a fasta format file
:param outdata: the out is abs path with a file name
:return: outdata path
"""
muscleparas = musclepara.lstrip()
mupath = getlocalpath()
out_path = os.path.dirname(outdata)
timeformat = '%Y%m%d%H%M%S'
timeinfo = str(time.strftime(timeformat))
subdir = 'temp/rna_alignment' + timeinfo
muscle_dir = os.path.join(out_path, subdir)
# check indata type
if os.path.isdir(indata):
pro_name = os.listdir(indata)
if not os.path.exists(muscle_dir):
os.makedirs(muscle_dir)
out_alg = os.path.join(muscle_dir, pro_name[0])
each_pro = os.path.join(indata, pro_name[0])
cmd = mupath + "/muscle -in " + each_pro + " -out " + out_alg + " " + muscleparas
subprocess.call(cmd, shell=True)
logdomuscle.debug('muscle result path:{0}'.format(out_alg))
logdomuscle.info(
"Multiple sequence alignment by Muscle was completed.")
return out_alg
elif os.path.isfile(indata):
pro_name = indata
if not os.path.exists(muscle_dir):
os.makedirs(muscle_dir)
out_alg = os.path.join(muscle_dir, pro_name)
each_pro = pro_name
cmd = mupath + "/muscle -in " + each_pro + " -out " + out_alg + " " + muscleparas
subprocess.call(cmd, shell=True)
logdomuscle.debug('muscle result path:{0}'.format(out_alg))
logdomuscle.info(
"Multiple sequence alignment by Muscle was completed.")
return out_alg
def domafft(indata, outdata, mafftparas):
"""
call mafft software to do align
:param indata: a director contain a fasta format file or a fasta format file
:param outdata: the out is abs path with a file name
:return: outdata path
"""
mafftparas = mafftparas.lstrip()
mapath = getlocalpath()
out_path = os.path.dirname(outdata)
timeformat = '%Y%m%d%H%M%S'
timeinfo = str(time.strftime(timeformat))
subdir = 'temp/rna_alignment' + timeinfo
mafft_dir = os.path.join(out_path, subdir)
# check indata type
if os.path.isdir(indata):
pro_name = os.listdir(indata)
if not os.path.exists(mafft_dir):
os.makedirs(mafft_dir)
out_alg = os.path.join(mafft_dir, pro_name[0])
each_pro = os.path.join(indata, pro_name[0])
cmd = mapath + "/mafft " + mafftparas + " " + each_pro + " > " + out_alg
subprocess.call(cmd, shell=True)
logmafft.debug('mafft result path:{0}'.format(out_alg))
logmafft.info("Multiple sequence alignment by mafft was completed.")
return out_alg
elif os.path.isfile(indata):
pro_name = indata
if not os.path.exists(mafft_dir):
os.makedirs(mafft_dir)
out_alg = os.path.join(mafft_dir, pro_name)
each_pro = pro_name
cmd = mapath + "/mafft " + mafftparas + " " + each_pro + " > " + out_alg
subprocess.call(cmd, shell=True)
logmafft.debug('mafft result path:{0}'.format(out_alg))
logmafft.info("Multiple sequence alignment by mafft was completed.")
return out_alg