def test_aln_to_no_gap_input(self):
try:
dh.check_sequence_matrix(["aaca", "aaa"])
except dh.sequenceNotSameLength:
pass
else:
self.fail("here should raise a exception!")
dh.aln2inputNogap("./tmp.aln","./tmp2.input")
def test_aln_to_no_gap_input(self):
try:
dh.check_sequence_matrix(["aaca", "aaa"])
except dh.sequenceNotSameLength:
pass
else:
self.fail("here should raise a exception!")
dh.aln2inputNogap("./tmp.aln", "./tmp2.input")
def main():
# main part
aln_files_folder = "d:/Workspace/Ecoli/ecoli_10_species"
#aln_files_folder = "d:/Workspace/Ecoli/test"
target_path = "d:/Workspace/Ecoli/NoGapP1"
aln_files = [
single_file for single_file in os.listdir(aln_files_folder)
if ".aln" == os.path.splitext(single_file)[-1]
]
model_gtr = "rebuild_model.mdl"
model_nest = "rna_full_length_structure.mdl"
job_ids = []
seq_length = []
for aln in aln_files:
aln_path_full = os.path.join(aln_files_folder, aln)
gene_in_aln, length_in_aln = dh.aln_info(aln_path_full)
seq_length.append(length_in_aln[0])
job_id = aln.split(".")[0]
if 10 == len(gene_in_aln): # only those gene shared in 10 species
job_ids.append(job_id)
input_file_path_full = os.path.join(target_path, job_id + ".input")
shutil.copyfile(aln_path_full, os.path.join(target_path, aln))
# write input file
dh.aln2inputNogap(aln_path_full, input_file_path_full)
# make bf file for full length no gap gtr and empirical model
os.chdir(target_path)
bf_maker_nest = BfH.HYPHYBatchFile(species_name="ecoli",
model_file=model_nest,
bf_template_file="templateNoGap")
bf_maker_gtr = BfH.HYPHYBatchFile(species_name="ecoli",
model_file=model_gtr,
bf_template_file="templateNoGap")
for job_id in job_ids:
# aln_path_full = os.path.join(aln_files_folder,aln)
# input_file_path_full = os.path.join(target_path, job_id + ".input")
# shutil.copyfile(aln_path_full, os.path.join(target_path,aln))
# # write input file
# dh.aln2inputNogap(aln_path_full, input_file_path_full)
# make bf file for full length no gap gtr and empirical model
bfgtr = job_id + "gtr.bf"
bf_maker_gtr.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id + "gtr.result",
hyphy_batch_file=bfgtr)
bfnest = job_id + "nest.bf"
bf_maker_nest.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id +
"nest.result",
hyphy_batch_file=bfnest)
bf_maker_gtr.set_partition(0, 51)
bf_maker_nest.set_partition(0, 51)
for job_id in job_ids:
bfgtr = job_id + "gtrp1.bf"
bf_maker_gtr.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id +
"gtrp1.result",
hyphy_batch_file=bfgtr)
bfnest = job_id + "nestp1.bf"
bf_maker_nest.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id +
"nestp1.result",
hyphy_batch_file=bfnest)
for indexI, job_id in enumerate(job_ids):
bf_maker_gtr.set_partition(51, seq_length[indexI])
bf_maker_nest.set_partition(51, seq_length[indexI])
bfgtr = job_id + "gtrp2.bf"
bf_maker_gtr.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id +
"gtrp2.result",
hyphy_batch_file=bfgtr)
bfnest = job_id + "nestp2.bf"
bf_maker_nest.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id +
"nestp2.result",
hyphy_batch_file=bfnest)
def main():
# main part
aln_files_folder = "d:/Workspace/Ecoli/ecoli_10_species"
#aln_files_folder = "d:/Workspace/Ecoli/test"
target_path = "d:/Workspace/Ecoli/NoGapP1"
aln_files = [single_file for single_file in os.listdir(aln_files_folder)
if ".aln" == os.path.splitext(single_file)[-1]]
model_gtr = "rebuild_model.mdl"
model_nest = "rna_full_length_structure.mdl"
job_ids = []
seq_length = []
for aln in aln_files:
aln_path_full = os.path.join(aln_files_folder, aln)
gene_in_aln, length_in_aln = dh.aln_info(aln_path_full)
seq_length.append(length_in_aln[0])
job_id = aln.split(".")[0]
if 10 == len(gene_in_aln): # only those gene shared in 10 species
job_ids.append(job_id)
input_file_path_full = os.path.join(target_path, job_id + ".input")
shutil.copyfile(aln_path_full, os.path.join(target_path, aln))
# write input file
dh.aln2inputNogap(aln_path_full, input_file_path_full)
# make bf file for full length no gap gtr and empirical model
os.chdir(target_path)
bf_maker_nest = BfH.HYPHYBatchFile(species_name="ecoli",
model_file=model_nest,
bf_template_file="templateNoGap")
bf_maker_gtr = BfH.HYPHYBatchFile(species_name="ecoli",
model_file=model_gtr,
bf_template_file="templateNoGap")
for job_id in job_ids:
# aln_path_full = os.path.join(aln_files_folder,aln)
# input_file_path_full = os.path.join(target_path, job_id + ".input")
# shutil.copyfile(aln_path_full, os.path.join(target_path,aln))
# # write input file
# dh.aln2inputNogap(aln_path_full, input_file_path_full)
# make bf file for full length no gap gtr and empirical model
bfgtr = job_id + "gtr.bf"
bf_maker_gtr.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id + "gtr.result",
hyphy_batch_file=bfgtr)
bfnest = job_id + "nest.bf"
bf_maker_nest.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id + "nest.result",
hyphy_batch_file=bfnest)
bf_maker_gtr.set_partition(0, 51)
bf_maker_nest.set_partition(0, 51)
for job_id in job_ids:
bfgtr = job_id + "gtrp1.bf"
bf_maker_gtr.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id + "gtrp1.result",
hyphy_batch_file=bfgtr)
bfnest = job_id + "nestp1.bf"
bf_maker_nest.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id + "nestp1.result",
hyphy_batch_file=bfnest)
for indexI, job_id in enumerate(job_ids):
bf_maker_gtr.set_partition(51, seq_length[indexI])
bf_maker_nest.set_partition(51, seq_length[indexI])
bfgtr = job_id + "gtrp2.bf"
bf_maker_gtr.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id + "gtrp2.result",
hyphy_batch_file=bfgtr)
bfnest = job_id + "nestp2.bf"
bf_maker_nest.write_batch_file(dot_input=job_id + ".input",
dot_aln=job_id + ".aln",
hyphy_result_file=job_id + "nestp2.result",
hyphy_batch_file=bfnest)
