def mouse_prepare():
parent_path = "/home/zerodel/GitProject"
work_path = "/home/zerodel/Workspace/mouse"
source_path = "/home/zerodel/Workspace/mouse/mouse_rnasnp"
output_path = "/home/zerodel/Workspace/mouse/cpd"
single_codon_file_path = os.path.join(work_path, "codon_codon_lst")
cc_significant_file_path = os.path.join(work_path, "codon_all.lst")
rnasnp_files, snppathname = RNAsnp.snp_dir_list(source_path)
# # step 1 , set up .cpd files
# RNAsnp.snp_dir_traversal(rnasnp_files, snppathname, output_path, True)
# # # step 2 , print each codon lst file
# for codon in gc.codon_list_hypothesis:
# codon_with_direction = codon + "_"
# print "--->", codon_with_direction
# RNAsnp.cpd_dir_traversal(codon_with_direction, output_path, single_codon_file_path)
RNAsnp.group_divide(single_codon_file_path, cc_significant_file_path)
gu_model_file = "/home/zerodel/GitProjects/python-rna-structure/gu_model.mdl"
rebuild_model_file = "/home/zerodel/GitProjects/python-rna-structure/rebuild_model.mdl"
nested_model_file = os.path.join(work_path, "rna_structure_full_mouse.mdl")
# matrixh.degenerate(gu_model_file,
# rebuild_model_file)
matrixh.nest_export(rebuild_model_file, nested_model_file,
cc_significant_file_path)
def make_model():
work_path = "d:/Workspace/Ecoli"
source_path = "d:/Workspace/Ecoli/ecoli_snp"
output_path = "d:/Workspace/Ecoli/cpd_full"
single_codon_file_path = os.path.join(work_path, "codon_lst")
cc_significant_file_path = os.path.join(work_path, "codon_all.lst")
#step 1 , set up .cpd files
gu_model_file = "d:/Home/GitProject/python-rna-structure/gu_model.mdl"
rebuild_model_file = "d:/Workspace/Ecoli/rebuild_model_full_length.mdl"
nested_model_file = "d:/Workspace/Ecoli/rna_full_length_structure.mdl"
rnasnp_files, snppathname = RNAsnp.snp_dir_list(source_path)
RNAsnp.snp_dir_traversal(rnasnp_files, snppathname, output_path, True,
True)
###step 2 , print each codon lst file
for codon in gc.codon_list_hypothesis:
codon_with_direction = codon + "_"
print "--->", codon_with_direction
RNAsnp.cpd_dir_traversal(codon_with_direction, output_path,
single_codon_file_path)
RNAsnp.group_divide(single_codon_file_path, cc_significant_file_path)
matrixh.degenerate(gu_model_file, rebuild_model_file)
matrixh.nest_export(rebuild_model_file, nested_model_file,
cc_significant_file_path)
def test_nest_export(self):
pyMatrix.degenerate(gtr_nested_file="gu_model.mdl",
gtr_mdl_file="rebuilt_gtr.mdl")
model_your = pyMatrix.nest_export(gtr_mdl="rebuilt_gtr.mdl",
gtr_nested="rna_structure.mdl",
ccl_file="../50CCl.lst")
print len(re.findall("\*psi", model_your)), "psi in model_your"
self.assertTrue(os.path.exists("rna_structure.mdl"))
index_codon = gc.codon_list_hypothesis
mg2 = pyMH.ModelHYPHY()
tuple_list = mg2.read_lst("../50CCl.lst")
zero_psi = True
with open(name="rna_structure.mdl", mode="r") as readerG:
model_nest = [line for line in readerG]
print len(model_nest), " lines in model"
for line_num, line in enumerate(model_nest):
entry_in_line = line.split(",")
for entry_index, single_entry in enumerate(entry_in_line):
if "psi" in single_entry:
zero_psi = False
self.assertIn(
(index_codon[line_num], index_codon[entry_index]),
tuple_list)
self.assertFalse(zero_psi)
def mouse_prepare():
parent_path = "/home/zerodel/GitProject"
work_path = "/home/zerodel/Workspace/mouse"
source_path = "/home/zerodel/Workspace/mouse/mouse_rnasnp"
output_path = "/home/zerodel/Workspace/mouse/cpd"
single_codon_file_path = os.path.join(work_path, "codon_codon_lst")
cc_significant_file_path = os.path.join(work_path, "codon_all.lst")
rnasnp_files, snppathname = RNAsnp.snp_dir_list(source_path)
# # step 1 , set up .cpd files
# RNAsnp.snp_dir_traversal(rnasnp_files, snppathname, output_path, True)
# # # step 2 , print each codon lst file
# for codon in gc.codon_list_hypothesis:
# codon_with_direction = codon + "_"
# print "--->", codon_with_direction
# RNAsnp.cpd_dir_traversal(codon_with_direction, output_path, single_codon_file_path)
RNAsnp.group_divide(single_codon_file_path, cc_significant_file_path)
gu_model_file = "/home/zerodel/GitProjects/python-rna-structure/gu_model.mdl"
rebuild_model_file = "/home/zerodel/GitProjects/python-rna-structure/rebuild_model.mdl"
nested_model_file = os.path.join(work_path, "rna_structure_full_mouse.mdl")
# matrixh.degenerate(gu_model_file,
# rebuild_model_file)
matrixh.nest_export(rebuild_model_file, nested_model_file, cc_significant_file_path)
def make_model():
work_path = "d:/Workspace/Ecoli"
source_path = "d:/Workspace/Ecoli/ecoli_snp"
output_path = "d:/Workspace/Ecoli/cpd_full"
single_codon_file_path = os.path.join(work_path, "codon_lst")
cc_significant_file_path = os.path.join(work_path, "codon_all.lst")
#step 1 , set up .cpd files
gu_model_file = "d:/Home/GitProject/python-rna-structure/gu_model.mdl"
rebuild_model_file = "d:/Workspace/Ecoli/rebuild_model_full_length.mdl"
nested_model_file = "d:/Workspace/Ecoli/rna_full_length_structure.mdl"
rnasnp_files, snppathname = RNAsnp.snp_dir_list(source_path)
RNAsnp.snp_dir_traversal(rnasnp_files, snppathname, output_path, True, True)
###step 2 , print each codon lst file
for codon in gc.codon_list_hypothesis:
codon_with_direction = codon + "_"
print "--->", codon_with_direction
RNAsnp.cpd_dir_traversal(codon_with_direction, output_path, single_codon_file_path)
RNAsnp.group_divide(single_codon_file_path, cc_significant_file_path)
matrixh.degenerate(gu_model_file,
rebuild_model_file)
matrixh.nest_export(rebuild_model_file, nested_model_file, cc_significant_file_path)
def built_model():
parent_path = "/home/zerodel/GitProject"
work_path = "/home/zerodel/Workspace"
source_path = "/home/zerodel/Workspace/ecoli_snp"
output_path = "/home/zerodel/Workspace/cpd_store_site"
single_codon_file_path = os.path.join(work_path, "codon_lst")
cc_significant_file_path = os.path.join(work_path, "codon_all.lst")
rnasnp_files, snppathname = RNAsnp.snp_dir_list(source_path)
#step 1 , set up .cpd files
# RNAsnp.snp_dir_traversal(rnasnp_files, snppathname, output_path, True)
# # step 2 , print each codon lst file
# for codon in gc.codon_list_hypothesis:
# codon_with_direction = codon + "_"
# print "--->", codon_with_direction
# RNAsnp.cpd_dir_traversal(codon_with_direction, output_path, single_codon_file_path, 60)
# kmeans meet some problem here 20140912
# # R kmeans part ******
# print "kmeans of cluster"
# kmeans_script_path = os.path.join(parent_path,"kmeans.R")
# cc_significant_file_path = os.path.join(work_path, "codon20.lst")
# cmd_line = "Rscript " + kmeans_script_path + " " + single_codon_file_path + " > " + cc_significant_file_path
# os.system(cmd_line)
# here we choose a new way to infer the group 20140912
# read the result of R process
cc_significant_raw = RNAsnp.get_large_codon_group(cc_significant_file_path)
cc_significant = [x for x in cc_significant_raw]
print len(cc_significant)
gu_model_file = "/home/zerodel/GitProjects/python-rna-structure/gu_model.mdl"
rebuild_model_file = "/home/zerodel/GitProjects/python-rna-structure/rebuild_model.mdl"
nested_model_file = "/home/zerodel/GitProjects/python-rna-structure/rna_structure.mdl"
matrixh.degenerate(gu_model_file,
rebuild_model_file)
matrixh.nest_export(rebuild_model_file, nested_model_file, cc_significant_file_path)
def make_model():
single_codon_file_path = os.path.join(work_path, "codon_lst")
cc_significant_file_path = os.path.join(work_path, "codon_all.lst")
#step 1 , set up .cpd files
rnasnp_files, snppathname = RNAsnp.snp_dir_list(source_path)
RNAsnp.snp_dir_traversal(rnasnp_files, snppathname, output_path, True, True)
# step 2 , print each codon lst file
for codon in gc.codon_list_hypothesis:
codon_with_direction = codon + "_"
print "--->", codon_with_direction
RNAsnp.cpd_dir_traversal(codon_with_direction, output_path, single_codon_file_path)
# RNAsnp.group_divide(single_codon_file_path, cc_significant_file_path)
matrixh.degenerate(gu_model_file,
rebuild_model_file)
matrixh.nest_export(rebuild_model_file, nested_model_file, cc_significant_file_path)
def built_model():
parent_path = "/home/zerodel/GitProject"
work_path = "/home/zerodel/Workspace"
source_path = "/home/zerodel/Workspace/ecoli_snp"
output_path = "/home/zerodel/Workspace/cpd_store_site"
single_codon_file_path = os.path.join(work_path, "codon_lst")
cc_significant_file_path = os.path.join(work_path, "codon_all.lst")
rnasnp_files, snppathname = RNAsnp.snp_dir_list(source_path)
#step 1 , set up .cpd files
# RNAsnp.snp_dir_traversal(rnasnp_files, snppathname, output_path, True)
# # step 2 , print each codon lst file
# for codon in gc.codon_list_hypothesis:
# codon_with_direction = codon + "_"
# print "--->", codon_with_direction
# RNAsnp.cpd_dir_traversal(codon_with_direction, output_path, single_codon_file_path, 60)
# kmeans meet some problem here 20140912
# # R kmeans part ******
# print "kmeans of cluster"
# kmeans_script_path = os.path.join(parent_path,"kmeans.R")
# cc_significant_file_path = os.path.join(work_path, "codon20.lst")
# cmd_line = "Rscript " + kmeans_script_path + " " + single_codon_file_path + " > " + cc_significant_file_path
# os.system(cmd_line)
# here we choose a new way to infer the group 20140912
# read the result of R process
cc_significant_raw = RNAsnp.get_large_codon_group(cc_significant_file_path)
cc_significant = [x for x in cc_significant_raw]
print len(cc_significant)
gu_model_file = "/home/zerodel/GitProjects/python-rna-structure/gu_model.mdl"
rebuild_model_file = "/home/zerodel/GitProjects/python-rna-structure/rebuild_model.mdl"
nested_model_file = "/home/zerodel/GitProjects/python-rna-structure/rna_structure.mdl"
matrixh.degenerate(gu_model_file, rebuild_model_file)
matrixh.nest_export(rebuild_model_file, nested_model_file,
cc_significant_file_path)
def make_model():
single_codon_file_path = os.path.join(work_path, "codon_lst")
cc_significant_file_path = os.path.join(work_path, "codon_all.lst")
#step 1 , set up .cpd files
rnasnp_files, snppathname = RNAsnp.snp_dir_list(source_path)
RNAsnp.snp_dir_traversal(rnasnp_files, snppathname, output_path, True,
True)
# step 2 , print each codon lst file
for codon in gc.codon_list_hypothesis:
codon_with_direction = codon + "_"
print "--->", codon_with_direction
RNAsnp.cpd_dir_traversal(codon_with_direction, output_path,
single_codon_file_path)
# RNAsnp.group_divide(single_codon_file_path, cc_significant_file_path)
matrixh.degenerate(gu_model_file, rebuild_model_file)
matrixh.nest_export(rebuild_model_file, nested_model_file,
cc_significant_file_path)
def test_nest_export(self):
pyMatrix.degenerate(gtr_nested_file="gu_model.mdl", gtr_mdl_file="rebuilt_gtr.mdl")
model_your = pyMatrix.nest_export(gtr_mdl="rebuilt_gtr.mdl", gtr_nested="rna_structure.mdl", ccl_file="../50CCl.lst")
print len(re.findall("\*psi", model_your)), "psi in model_your"
self.assertTrue(os.path.exists("rna_structure.mdl"))
index_codon = gc.codon_list_hypothesis
mg2 = pyMH.ModelHYPHY()
tuple_list = mg2.read_lst("../50CCl.lst")
zero_psi = True
with open(name="rna_structure.mdl", mode="r") as readerG:
model_nest = [line for line in readerG ]
print len(model_nest), " lines in model"
for line_num, line in enumerate(model_nest):
entry_in_line = line.split(",")
for entry_index, single_entry in enumerate(entry_in_line):
if "psi" in single_entry:
zero_psi = False
self.assertIn((index_codon[line_num], index_codon[entry_index]), tuple_list)
self.assertFalse(zero_psi)