def check_srna(input, output):
"""
Check whether the input species in the SSU rRNA database
:param input: the species names
:param output: the directory contains check result
"""
if not os.path.exists(output):
os.makedirs(output)
fw_name = "PhySpeTree_srna_checked.txt"
open_path = os.path.join(output, fw_name)
fw = open(open_path, 'wb')
input_path = checkFile(input)
input_list = readIputFile(input_path)
in_match, no_match = check_organism(input_list, "kegg_to_silva_id.txt")
if no_match.__len__() == 0:
print(print_style('INFO: ', fore='green') + "All species are match in SILVA DATABASE")
fw.write("All species are match in SILVA DATABASE")
else:
print(print_style('WARNING: ', fore='red') + "The following species are not supported by SILVA DATABASE:")
fw.write("The following species are not supported by SILVA DATABASE:\n")
for line in no_match:
print(line)
fw.write(line + "\n")
print("Checked whether the input species names in SILVA DATABASE completed.")
print("Checked result is store in {0}".format(open_path))
fw.close()
def annotatingLabels(input, output):
"""
Change labels
:param input: input a files contain abb names
:param output: output directory path
:return: None
"""
if not os.path.exists(output):
os.makedirs(output)
fw_name = "labels.txt"
open_path = os.path.join(output, fw_name)
fw = open(open_path, 'wb')
fw.write('LABELS\nSEPARATOR TAB\nDATA\n')
inputfile = checkFile(input)
input_list = readIputFile(inputfile)
tax_list = taxlist()
for i in input_list:
for j in tax_list:
if i == j[0]:
fw.write("{0}\t{1}\n".format(j[0], j[1]))
else:
pass
fw.close()
print("Change abbreviation names to full names complete")
print("change labels file was save in {0}".format(open_path))
def check_hcp(input, output):
"""
Check whether the input species in the hcp database
:param input: the species names
:param output: the directory contains check result
"""
if not os.path.exists(output):
os.makedirs(output)
fw_name = "PhySpeTree_hcp_checked.txt"
open_path = os.path.join(output, fw_name)
fw = open(open_path, 'w')
input_path = checkFile(input)
input_list = readIputFile(input_path)
in_match, no_match = check_organism(input_list, "organism_kegg_to_tax.txt")
if no_match.__len__() == 0:
print(
print_style('INFO: ', fore='green') +
"All species are match in KEGG DATABASE.")
fw.write("All species are match in KEGG DATABASE")
else:
print(
print_style('WARNING: ', fore='red') +
"The following species are not supported by KEGG DATABASE:")
fw.write("The following species are not supported by KEGG DATABASE:\n")
for line in no_match:
print(line)
fw.write(line + "\n")
print(
"Checked whether the input species names in KEGG DATABASE completed.")
print("Checked result is store in {0}".format(open_path))
fw.close()
def check_ehcp(input, output):
"""
Check the highly conserved proteins will be prepared.
:param input: the species abbreviated names
:param output: a directory contain check result
"""
# prepare a file write result
if not os.path.exists(output):
os.makedirs(output)
fw_name = "PhySpeTree_echp_extend.txt"
open_path = os.path.join(output, fw_name)
fw = open(open_path, 'wb')
# check input names
input_path = checkFile(input)
input_list = readIputFile(input_path)
colname = getcolname()
relist, match_ko = getspecies(input_list, colname)
p = 1
for line in match_ko:
hcpname = hcp_name(line.strip())
massage = "'{0}' ----------------------------------> p{1}.fasta\n".format(hcpname, str(p))
print(massage)
fw.write(massage)
p += 1
print("Checked extend highly conserved proteins is completed.")
print("Checked result was store in {0}".format(open_path))
fw.close()
def check_ehcp(input, output):
"""
Check the highly conserved proteins will be prepared.
:param input: the species abbreviated names
:param output: a directory contain check result
"""
# prepare a file write result
if not os.path.exists(output):
os.makedirs(output)
fw_name = "PhySpeTree_echp_extend.txt"
open_path = os.path.join(output, fw_name)
fw = open(open_path, 'w')
# check input names
input_path = checkFile(input)
input_list = readIputFile(input_path)
colname = getcolname()
relist, match_ko = getspecies(input_list, colname)
p = 1
for line in match_ko:
hcpname = hcp_name(line.strip())
massage = "'{0}' ----------------------------------> p{1}.fasta\n".format(
hcpname, str(p))
print(massage)
fw.write(massage)
p += 1
print("Checked extend highly conserved proteins is completed.")
print("Checked result was store in {0}".format(open_path))
fw.close()
def starting_esrna(in_put, out_put, args_muscle, args_muscle_p, args_clustalw,
args_clustalw_p, args_gblocks, args_raxml, args_raxml_p,
args_fasttree, args_fasttree_p, args_thread,
args_extenddata):
'''reconstruct phylogenetic tree by ssu rna extend method'''
extend_check = checkFile(args_extenddata)
ssu_input = checkSilvaOrganism(in_put)
out_retrieve = retrieve16srna(ssu_input, out_put)
retrieve_srna_path = os.path.join(out_retrieve, 'rna_sequence.fasta')
fw = open(retrieve_srna_path, 'ab')
with open(extend_check) as read:
for line in read:
fw.write(line)
fw.close()
# set default aligned by muscle if not specify clustalw
if args_clustalw:
out_alg = doclustalw(out_retrieve, out_put, args_clustalw_p)
elif args_muscle:
out_alg = domuscle(out_retrieve, out_put, args_muscle_p)
# gblocks
if args_gblocks is gblockspara_pro:
args_gblocks = gblockspara_dna
out_gblock = dogblocks(out_alg, args_gblocks)
out_f2p = fasta2phy(out_gblock)
# reconstruct tree
if args_fasttree:
args_fasttree_p_add = "-nt " + args_fasttree_p.lstrip()
doFastTree(out_f2p, out_put, args_fasttree_p_add, args_thread)
elif args_raxml:
if args_raxml_p is raxmlpara_pro:
args_raxml_p = raxmlpara_dna
doraxml(out_f2p, out_put, args_raxml_p, args_thread)
def colorLabel(input, output, taxon):
"""
Main function to color label
:param input: input file names
:param output: output directory path
:param taxon: choice annotation by ['kingdom', 'phylum', 'class', 'order']
:return: no
"""
if not os.path.exists(output):
os.makedirs(output)
# writ file name
fw_name = "labels_color_by_" + taxon + ".txt"
open_path = os.path.join(output, fw_name)
fw = open(open_path, 'w')
# write annotation range head
fw.write(cite_label)
fw.write('\n')
fw.write('TREE_COLORS\nSEPARATOR TAB\nDATA\n')
# check and get input list
inputfile = checkFile(input)
input_list = readIputFile(inputfile)
# get match list and annotation dict to annotation
match_list, anno_dict = matchInput(input_list, taxon)
# write to annotation to file
for line in match_list:
color = anno_dict[line[1]]
write_data = "{0}\tlabel\t{1}\n".format(line[0], color)
fw.write(write_data)
fw.close()
print("Color labels by {0} was complete.".format(taxon))
print("Color labels annotation was save in {0}".format(open_path))
def annotatingLabels(input, output):
"""
Change labels
:param input: input a files contain abb names
:param output: output directory path
:return: None
"""
if not os.path.exists(output):
os.makedirs(output)
fw_name = "labels.txt"
open_path = os.path.join(output, fw_name)
fw = open(open_path, 'w')
fw.write(cite)
fw.write('\n')
fw.write('LABELS\nSEPARATOR TAB\nDATA\n')
inputfile = checkFile(input)
input_list = readIputFile(inputfile)
if is_number(input_list[0]):
tax_list = taxlistid()
else:
tax_list = taxlist()
for i in input_list:
for j in tax_list:
if i == j[0]:
fw.write("{0}\t{1}\n".format(j[0], j[1]))
fw.close()
print("Change abbreviation names to full names complete")
print("change labels file was save in {0}".format(open_path))
def colorRange(input, output, taxon):
"""
Main function to color range
:param input: input file names
:param output: output directory path
:param taxon: choice annotation by ['kingdom', 'phylum', 'class', 'order']
:return: no
"""
if not os.path.exists(output):
os.makedirs(output)
# writ file name
fw_name = "range_color_by_" + taxon + ".txt"
open_path = os.path.join(output, fw_name)
fw = open(open_path, 'wb')
# write annotation range head
fw.write('TREE_COLORS\nSEPARATOR TAB\nDATA\n')
# check and get input list
inputfile = checkFile(input)
input_list = readIputFile(inputfile)
# get match list and annotation dict to annotation
match_list, anno_dict = matchInput(input_list, taxon)
# write to annotation to file
for line in match_list:
color = anno_dict[line[1]]
write_data = "{0}\trange\t{1}\t{2}\n".format(line[0], color, line[1])
fw.write(write_data)
fw.close()
print("Color range by {0} was complete.".format(taxon))
print("Color range annotation was save in {0}".format(open_path))
def starting_esrna(in_put, out_put, args_muscle, args_muscle_p, args_clustalw,
args_clustalw_p, args_mafft, args_mafft_p, args_gblocks,
args_gblocks_p, args_trimal, args_trimal_p, args_raxml,
args_raxml_p, args_fasttree, args_fasttree_p, args_iqtree,
args_iqtree_p, args_thread, args_extenddata, args_db):
'''reconstruct phylogenetic tree by ssu rna extend method'''
extend_check = checkFile(args_extenddata)
ssu_input, recovery_dic = checkSilvaOrganism(in_put)
start = time.time()
out_retrieve = retrieve16srna(ssu_input, out_put, args_db)
end = time.time()
auto_build_log.info(
'Retrieving SSU rRNA sequences used time: {} Seconds'.format(end -
start))
if not recovery_dic == []:
recovery_silva(out_retrieve, recovery_dic, ssu_input)
retrieve_srna_path = os.path.join(out_retrieve, 'rna_sequence.fasta')
fw = open(retrieve_srna_path, 'a')
with open(extend_check) as read:
for line in read:
fw.write(line)
fw.close()
# set default aligned by muscle if not specify clustalw
start2 = time.time()
if args_clustalw:
out_alg = doclustalw(out_retrieve, out_put, args_clustalw_p)
elif args_mafft:
out_alg = domafft(out_retrieve, out_put, args_mafft_p)
elif args_muscle:
out_alg = domuscle(out_retrieve, out_put, args_muscle_p)
# set default trim by gblocks if not specify trimal
if args_trimal:
out_f2p = dotrimal(out_alg, args_trimal_p)
elif args_gblocks:
if args_gblocks_p is gblockspara_pro:
args_gblocks_p = gblockspara_dna
out_gblock = dogblocks(out_alg, args_gblocks_p)
out_f2p = fasta2phy(out_gblock)
# reconstruct tree
if args_fasttree:
args_fasttree_p_add = "-nt " + args_fasttree_p.lstrip()
doFastTree(out_f2p, out_put, args_fasttree_p_add, args_thread)
elif args_iqtree:
doiqtree(out_f2p, out_put, args_iqtree_p, args_thread)
elif args_raxml:
if args_raxml_p is raxmlpara_pro:
args_raxml_p = raxmlpara_dna
doraxml(out_f2p, out_put, args_raxml_p, args_thread)
end2 = time.time()
auto_build_log.info(
'Constructing species tree used time: {} Seconds'.format(end2 -
start2))
def starting_esrna(in_put, out_put,
args_muscle, args_muscle_p,
args_clustalw, args_clustalw_p,
args_mafft, args_mafft_p,
args_gblocks, args_gblocks_p,
args_trimal, args_trimal_p,
args_raxml, args_raxml_p,
args_fasttree, args_fasttree_p,
args_iqtree,args_iqtree_p,
args_thread, args_extenddata):
'''reconstruct phylogenetic tree by ssu rna extend method'''
extend_check = checkFile(args_extenddata)
ssu_input,recovery_dic = checkSilvaOrganism(in_put)
out_retrieve = retrieve16srna(ssu_input, out_put)
if not recovery_dic == {}:
recovery(out_retrieve,recovery_dic)
retrieve_srna_path = os.path.join(out_retrieve, 'rna_sequence.fasta')
fw = open(retrieve_srna_path, 'ab')
with open(extend_check) as read:
for line in read:
fw.write(line)
fw.close()
# set default aligned by muscle if not specify clustalw
if args_clustalw:
out_alg = doclustalw(out_retrieve, out_put, args_clustalw_p)
elif args_mafft:
out_alg = domafft(out_retrieve, out_put, args_mafft_p)
elif args_muscle:
out_alg = domuscle(out_retrieve, out_put, args_muscle_p)
# set default trim by gblocks if not specify trimal
if args_trimal:
out_f2p = dotrimal(out_alg, args_trimal_p)
elif args_gblocks:
if args_gblocks_p is gblockspara_pro:
args_gblocks_p = gblockspara_dna
out_gblock = dogblocks(out_alg, args_gblocks_p)
out_f2p = fasta2phy(out_gblock)
# reconstruct tree
if args_fasttree:
args_fasttree_p_add = "-nt " + args_fasttree_p.lstrip()
doFastTree(out_f2p, out_put, args_fasttree_p_add, args_thread)
elif args_iqtree:
doiqtree(out_f2p, out_put, args_iqtree_p, args_thread)
elif args_raxml:
if args_raxml_p is raxmlpara_pro:
args_raxml_p = raxmlpara_dna
doraxml(out_f2p, out_put, args_raxml_p, args_thread)