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 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 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 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)
