def get_para_1004():
# get parameters from fly data . model : gtr, nest, parameter: likelihood, aic, w, psi
print "---- "
dsh.extract_parameter(dot_result_folder, para_path, ["gtr"], gtr_list_para)
dsh.extract_parameter(dot_result_folder, para_path, ["nest"],
nest_list_para)
def test_gap_check_traversal(self):
folder_input = os.path.abspath(os.curdir)
output_gap_lst = "gap_report.txt"
try:
dsh.gap_check_traversal(folder_input, output_gap_lst)
except dsh.idSequenceUnKnow:
print "ok , exception raisen"
else:
self.fail("nope , no exception when there should have some ")
def test_available_traversal(self):
folder_input = os.path.abspath(os.curdir)
output_gap_lst = "available_sites.txt"
job_ids = ["tmp"]
try:
dsh.report_traversal_available_site(input_folder=folder_input,output_file=output_gap_lst)
except dsh.idSequenceUnKnow:
pass
else:
self.fail("id unknow")
dsh.report_traversal_available_site(input_folder=folder_input,output_file=output_gap_lst,
jobids=job_ids)
self.assertTrue(os.path.exists(output_gap_lst))
def main1():
paras = ["likelihood", "aic", "w"]
path_working = "/home/zerodel/Workspace/former10"
mid = "10"
gene_all = dsh.transfer_for_r("gtr", mid, paras, path_working)
gene_all_tmp = dsh.transfer_for_r("gu", mid, paras, path_working)
if not gene_all == gene_all_tmp:
print "not same length"
gene_all_tmp = dsh.transfer_for_r("nest", mid, paras, path_working)
if not gene_all == gene_all_tmp:
print "not same length"
def gap_check_traversal(input_folder, output_file, given_sequence_file=""):
"""
check gap proportion on all files in "input_folder", and export as lst file to "output_file"
with (optional) given_sequence_file
:param input_folder:
:param output_file:
:param given_sequence:
:return:
"""
curdir_abs = os.path.abspath(os.curdir)
if not given_sequence_file:
jobids = dsh.get_gene_id_sequnce_from_lst(os.path.join(given_sequence_file))
else:
raise dsh.idSequenceUnKnow
#jobids = sorted([file_input for file_input in os.listdir(input_folder) if ".input" == os.path.splitext(file_input)[-1]])
with open(output_file, "w") as writer:
writer.write("gaps\tfull\n")
for jobid in jobids:
input_name = os.path.join(input_folder, jobid + ".input")
aln_name = os.path.join(input_folder, jobid + ".aln")
if os.path.exists(input_name):
num_gap, full_nt_length = gap_counting_input(input_name)
elif os.path.exists(aln_name):
num_gap, full_nt_length = gap_counting_input(aln_name)
else:
raise dsh.WrongFileTypeForGapCheck
writer.write("%s\t%s\n" % (str(num_gap), str(full_nt_length)))
os.chdir(curdir_abs)
def snp_count_species(lst_file, folder_rnasnp_file):
# read gene id sequence
path_dir = os.path.dirname(os.path.abspath(lst_file))
lst_name_bare = os.path.splitext(lst_file)[0]
jobids = dsh.get_gene_id_sequnce_from_lst(lst_file)
file_name_vector = [
os.path.join(folder_rnasnp_file, ".".join([jobid, "rnasnp"]))
for jobid in jobids
]
is_greater_than = False
data_criterion = "pvalue2"
threshold = 0.1
gene_snp_count = []
for single_file in file_name_vector:
if os.path.exists(single_file):
gene_snp_count.append(
str(
count_snp_per_file(single_file, is_greater_than, threshold,
data_criterion) / 3.0))
else:
gene_snp_count.append("NA")
# writer a new lst file for snp count in some species
with open(os.path.join(path_dir, lst_name_bare + "SnpCount.lst"),
"w") as exporter:
exporter.write("geneid\tsnpCountPerGene\n")
for index_g, jobid in enumerate(jobids):
line_to_export = "%s\t%s\n" % (jobid, gene_snp_count[index_g])
exporter.write(line_to_export)
def main1():
## get the gaps number and full_length .
aln_path = "/home/zerodel/Workspace/Yeast/result/main_full_length"
os.chdir(aln_path)
aln_files = [file1 for file1 in os.listdir(aln_path) if ".aln" == os.path.splitext(file1)[-1]]
jobids = dsh.get_gene_id_sequnce_from_lst(os.path.join("/home/zerodel/Workspace/Yeast/result/ExtractedParameter", "gtr.lst"))
with open("/home/zerodel/Workspace/Yeast/result/ExtractedParameter/gapyeast.lst", "w") as writer:
writer.write("gaps\tfull\n")
for jobid in jobids:
num_gap, full_nt_length = gap_counting_aln(jobid + ".aln")
writer.write("%s\t%s\n" % (str(num_gap), str(full_nt_length)))
def main3():
## get the gaps number and full_length .
aln_path = "/home/zerodel/Workspace/sp2"
os.chdir(aln_path)
aln_files = [file1 for file1 in os.listdir(aln_path) if ".aln" == os.path.splitext(file1)[-1]]
jobids = dsh.get_gene_id_sequnce_from_lst(os.path.join("/home/zerodel/GitProjects/python-rna-structure/data/para", "nest2.lst"))
with open("/home/zerodel/GitProjects/python-rna-structure/data/para/gap10.lst", "w") as writer:
writer.write("gaps\tfull\n")
for jobid in jobids:
num_gap, full_nt_length = gap_counting_input(jobid + ".input")
writer.write("%s\t%s\n" % (str(num_gap), str(full_nt_length)))
def main3():
path_result = "/home/zerodel/Workspace/merge0914/2sp"
dir_now = os.path.abspath(os.curdir)
os.chdir(path_result)
para = "psi"
model = "nest"
mid = "2"
system_order = "grep -i " + para + " *" + model + ".result >" + "../" + model + mid + para + ".txt"
os.system(system_order)
path_working = "/home/zerodel/Workspace/merge0914"
gene_all = dsh.transfer_for_r("nest", mid, ["psi"], path_working)
def snp_count_species(lst_file, folder_rnasnp_file):
# read gene id sequence
path_dir = os.path.dirname(os.path.abspath(lst_file))
lst_name_bare = os.path.splitext(lst_file)[0]
jobids = dsh.get_gene_id_sequnce_from_lst(lst_file)
file_name_vector = [os.path.join(folder_rnasnp_file, ".".join([jobid, "rnasnp"])) for jobid in jobids]
is_greater_than = False
data_criterion = "pvalue2"
threshold = 0.1
gene_snp_count = []
for single_file in file_name_vector:
if os.path.exists(single_file):
gene_snp_count.append(str(count_snp_per_file(single_file, is_greater_than, threshold, data_criterion)/3.0))
else:
gene_snp_count.append("NA")
# writer a new lst file for snp count in some species
with open(os.path.join(path_dir, lst_name_bare + "SnpCount.lst"), "w") as exporter:
exporter.write("geneid\tsnpCountPerGene\n")
for index_g, jobid in enumerate(jobids):
line_to_export = "%s\t%s\n" % (jobid, gene_snp_count[index_g])
exporter.write(line_to_export)
def prepare4r():
dsh.transfer_for_r("gtr", "", gtr_list_para,
"/home/zerodel/Workspace/Fly/ExtractedParameters")
dsh.transfer_for_r("nest", "", nest_list_para,
"/home/zerodel/Workspace/Fly/ExtractedParameters")
def test_aln():
aln_path = "/home/zerodel/Workspace/Fly/align_fly/fly_12_species"
given_genes = "dyak,dere,dpse,dper,dgri,dmoj,dvir,dwil,dana,dsec,dsim,dmel".split(",")
dsh.test_gene_species_match(aln_path, given_genes)
def get_para_1004():
# get parameters from fly data . model : gtr, nest, parameter: likelihood, aic, w, psi
print "---- "
dsh.extract_parameter(dot_result_folder, para_path, ["gtr"], gtr_list_para)
dsh.extract_parameter(dot_result_folder, para_path, ["nest"], nest_list_para)
def prepare4r():
dsh.transfer_for_r("gtr", "", gtr_list_para, "/home/zerodel/Workspace/Fly/ExtractedParameters")
dsh.transfer_for_r("nest", "", nest_list_para, "/home/zerodel/Workspace/Fly/ExtractedParameters")
def test_aln():
aln_path = "/home/zerodel/Workspace/mouse/mouse_8_species"
given_genes = "macaque,chimp,human,dog,cow,horse,rat,mouse".split(",")
dsh.test_gene_species_match(aln_path, given_genes)
def test_aln():
aln_path = "/home/zerodel/Workspace/Fly/align_fly/fly_12_species"
given_genes = "dyak,dere,dpse,dper,dgri,dmoj,dvir,dwil,dana,dsec,dsim,dmel".split(
",")
dsh.test_gene_species_match(aln_path, given_genes)
def test_gap(self):
file_hyphy_input = "./tmp.aln"
availble_sites,full_length = dsh.sum_available_sites(file_hyphy_input)
self.assertEqual(full_length, 4)
self.assertEqual(availble_sites,3)
def test_gap_traversal2(self):
folder_input = os.path.abspath(os.curdir)
output_gap_lst = "gap_report.txt"
jobids = ["tmp"]
dsh.gap_check_traversal(input_folder=folder_input, output_file=output_gap_lst,jobids=jobids)
self.assertTrue(os.path.exists(output_gap_lst))
def test_aln():
aln_path = "/home/zerodel/Workspace/mouse/mouse_8_species"
given_genes = "macaque,chimp,human,dog,cow,horse,rat,mouse".split(",")
dsh.test_gene_species_match(aln_path, given_genes)
