def make_bf_TIR(): workpath = "d:\Workspace\Ecoli\combinedP1" os.chdir(workpath) model_gtr = "rebuild_model.mdl" model_nest = "rna_full_length_structure.mdl" 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") bf_maker_gtr.set_tree_from_outside(SS.ecoli()) bf_maker_nest.set_tree_from_outside(SS.ecoli()) for window_width_offset in range(15): length_window = 30 + 5*window_width_offset aln_files = "d:\Workspace\Ecoli\ecoli_10_species" extracted_input_file = workpath + "\TIR" + str(length_window) + ".input" gene_conjunction(aln_files, extracted_input_file, length_window) bf_maker_gtr.write_batch_file(dot_input="TIR%d.input" % length_window, dot_aln="", hyphy_batch_file="TIR%dgtr.bf" % length_window, hyphy_result_file="TIR%dgtr.result" % length_window) bf_maker_nest.write_batch_file(dot_input="TIR%d.input" % length_window, dot_aln="", hyphy_batch_file="TIR%dnest.bf" % length_window, hyphy_result_file="TIR%dnest.result" % length_window)
def make_bf_p2(): workpath = "d:\Workspace\Ecoli\P2" os.chdir(workpath) model_gtr = "rebuild_model.mdl" model_nest = "rna_full_length_structure.mdl" bf_maker_gtr = BfH.HYPHYBatchFile(species_name="ecoli", model_file=model_gtr, bf_template_file="templateNoGap") bf_maker_nest = BfH.HYPHYBatchFile(species_name="ecoli", model_file=model_nest, bf_template_file="templateNoGap") bf_maker_gtr.set_tree_from_outside(SS.ecoli()) bf_maker_nest.set_tree_from_outside(SS.ecoli()) aln_file_folder = "d:\Workspace\Ecoli\ecoli_10_species" aln_files = [file_single for file_single in os.listdir(aln_file_folder) if ".aln" == os.path.splitext(file_single)[-1]] for single_aln in aln_files: aln_full_path = os.path.join(aln_file_folder, single_aln) genes, lengths = DH.aln_info(aln_full_path) gene_full_length = lengths[0] jobid = single_aln.split(".")[0] input_file_name = "%s.input" % jobid DH.aln2input(aln_full_path, input_file_name) if gene_full_length < 52: print "%s too short ---" % single_aln continue bf_maker_gtr.set_partition(51, gene_full_length) bf_maker_nest.set_partition(51, gene_full_length) bf_maker_gtr.write_batch_file(dot_input=input_file_name, dot_aln="", hyphy_batch_file="%sp2gtr.bf" % jobid, hyphy_result_file="%sp2gtr.result" % jobid) bf_maker_nest.write_batch_file(dot_input=input_file_name, dot_aln="", hyphy_batch_file="%sp2nest.bf" % jobid, hyphy_result_file="%sp2nest.result" % jobid)
def test_bf(): bf1 = bf.HYPHYBatchFile(species_name="ecoli", model_file="../rebuild_model.mdl", bf_template_file="../pyHYPHY/templateNoGap") bf1.use_given_tree = True bf1.tree_definition_external = "(g1,g2)" bf1.write_batch_file("./tmp2.input", "./tmp.aln", "xxx.bf", "xxx.result")
def sliding_window(): workpath = "d:\Workspace\Ecoli\slidingWindow" os.chdir(workpath) model_gtr = "rebuild_model.mdl" model_nest = "rna_full_length_structure.mdl" 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") bf_maker_gtr.set_tree_from_outside(SS.ecoli()) bf_maker_nest.set_tree_from_outside(SS.ecoli()) step_num = 15 step_width_step = 5 window_width_min = 30 site_start_point = 0 site_shift_step = 5 for window_start_offset in range(step_num): for window_width_offset in range(step_num): start_site = site_shift_step*window_start_offset + site_start_point length_window = step_width_step*window_width_offset + window_width_min aln_files = "d:\Workspace\Ecoli\ecoli_10_species" # extracted_input_file = workpath + "\TIR" + str(length_window) + ".input" job_description = "w%ds%d" % (length_window, start_site) extracted_input_file = "%s\\TIR%s.input" % (workpath, job_description) print extracted_input_file gene_conjunction(aln_files, extracted_input_file, length_window, start_site) bf_maker_gtr.write_batch_file(dot_input="TIR%s.input" % job_description, dot_aln="", hyphy_batch_file="TIR%sgtr.bf" % job_description, hyphy_result_file="TIR%sgtr.result" % job_description) bf_maker_nest.write_batch_file(dot_input="TIR%s.input" % job_description, dot_aln="", hyphy_batch_file="TIR%snest.bf" % job_description, hyphy_result_file="TIR%snest.result" % job_description)
def batch_for_batch(): os.chdir("/home/zerodel/Workspace/mouse/FullLengthMouse") model_gtr = "rebuild_model.mdl" model_nest = "rna_structure_full_mouse.mdl" aln_path = "/home/zerodel/Workspace/mouse/mouse_8_species" bf_maker_nest = BfH.HYPHYBatchFile(species_name="mouse", model_file=model_nest, bf_template_file="template_global") bf_maker_gtr = BfH.HYPHYBatchFile(species_name="mouse", model_file=model_gtr, bf_template_file="template_global") jobids = [ file1.split(".")[0] for file1 in os.listdir(aln_path) if ".aln" == file1[-4:] ] for job_id in jobids: aln_file_path_full = os.path.join(aln_path, job_id + ".aln") input_file = os.path.join(os.curdir, job_id + ".input") if not os.path.exists(input_file): DH.aln2input(aln_file_path_full, input_file) bfgtr = job_id + "gtr.bf" bf_maker_gtr.write_batch_file(dot_input=job_id + ".input", dot_aln=aln_file_path_full, 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=aln_file_path_full, hyphy_result_file=job_id + "nest.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)
def aln_folder_traversal(folder_name): """ """ built_in_gy94mdl = "/usr/lib/hyphy/TemplateBatchFiles/TemplateModels/GY94.mdl" gy94bf = bfHYPHY.HYPHYBatchFile(species_name="ecoli", model_file=built_in_gy94mdl, bf_template_file="partition.bf") own_model = "nest_gy.mdl" nested_model = bfHYPHY.HYPHYBatchFile(species_name="ecoli", model_file=own_model, bf_template_file="partition.bf") nt_nest_model = "nt_nest_gy.mdl" bf_nt_nest = bfHYPHY.HYPHYBatchFile(species_name="ecoli", model_file=nt_nest_model, bf_template_file="partition.bf") gu_model = "myCodonMatrix.def" gu_bf = bfHYPHY.HYPHYBatchFile(species_name="ecoli", model_file=gu_model, bf_template_file="synAlphaWPsiModelP.bf") pwd = os.path.abspath(folder_name) os.chdir(folder_name) aln_files = [file1 for file1 in os.listdir(pwd) if "aln" == file1.split(".")[-1]] for index, aln_name in enumerate(aln_files): # write batch file for each aln gene_id = aln_name.split(".")[0] genes, gene_len = dataHYPHY.aln_info(aln_name) len_gene = max(gene_len) gy94bf1 = "%sgy94.bf" % gene_id input_filename = "%s.input" % gene_id # input file here dataHYPHY.aln2input(dot_aln_file=aln_name, hyphy_input_file=input_filename) # gy model , full length gy94bf.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_batch_file=gy94bf1, hyphy_result_file="gy94%s_%s.result" % (gene_id, "")) # gy model , part 1 gy94p1_name = "%sgy94p1.bf" % gene_id gy94bf.set_partition(0, 60) gy94bf.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_batch_file=gy94p1_name, hyphy_result_file="gy94p1%s_%s.result" % (gene_id, "")) # gy model , part 2 gy94p2_name = "%sgy94p2.bf" % gene_id gy94bf.set_partition(60, len_gene) gy94bf.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_batch_file=gy94p2_name, hyphy_result_file="gy94p2%s_%s.result" % (gene_id, "")) # nested model , full length nested_model.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_result_file="nest_gy%s.result" % gene_id, hyphy_batch_file="%snest_gy.bf" % gene_id) # nested model , part 1 nested_model.set_partition(0, 60) nested_model.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_result_file="nest_gy%s_p1.result" % gene_id, hyphy_batch_file="%snest_gyp1.bf" % gene_id) # nested model , part 2 nested_model.set_partition(60, len_gene) nested_model.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_result_file="nest_gy%s_p2.result" % gene_id, hyphy_batch_file="%snest_gyp2.bf" % gene_id) # nt nested ,full bf_nt_nest.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_result_file="%snt_nest.result" % gene_id, hyphy_batch_file="%snt_nest.bf" % gene_id) # nt nested , part1 bf_nt_nest.set_partition(0, 60) bf_nt_nest.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_result_file="%snt_nest_p1.result" % gene_id, hyphy_batch_file="%snt_nest_p1.bf" % gene_id) # nt nested , part2 bf_nt_nest.set_partition(60, len_gene) bf_nt_nest.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_result_file="%snt_nest_p2.result" % gene_id, hyphy_batch_file="%snt_nest_p2.bf" % gene_id) # gu model . full length gu_bf.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_result_file="%sgu.result" % gene_id, hyphy_batch_file="%sgu.bf" % gene_id) gu_bf.set_partition(0, 60) gu_bf.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_result_file="%sgup1.result" % gene_id, hyphy_batch_file="%sgup1.bf" % gene_id) gu_bf.set_partition(60 ,len_gene) gu_bf.write_batch_file(dot_aln=aln_name, dot_input=input_filename, hyphy_result_file="%sgup2.result" % gene_id, hyphy_batch_file="%sgup2.bf" % gene_id)
def sliding_window(): """perform a sliding window analysis over sequence alignment """ workpath = "/Users/zerodel/WorkSpace/test/test_slidingWindow" # important here, has changed path. os.chdir(workpath) model_gtr = "rebuild_model.mdl" model_nest = "rna_full_length_structure.mdl" aln_files = "/Users/zerodel/WorkSpace/ecoli_aln" 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") bf_maker_gtr.set_tree_from_outside(SS.ecoli()) bf_maker_nest.set_tree_from_outside(SS.ecoli()) step_num = 21 step_width_step = 15 window_width_min = 30 site_start_point = 0 site_shift_step = 15 window_axis = [0,2] start_axis = range(step_num) for window_width_offset in window_axis: for window_start_offset in start_axis: start_site = site_shift_step*window_start_offset + site_start_point length_window = step_width_step*window_width_offset + window_width_min # extracted_input_file = workpath + "\TIR" + str(length_window) + ".input" job_description = "w%ds%d" % (length_window, start_site) extracted_input_file = "TIR%s.input" % job_description extracted_input_no_gap = "TIR%sN.input" % job_description gene_conjunction(aln_files, os.path.join(workpath, extracted_input_file), length_window, start_site) gene_conjunction(aln_files, os.path.join(workpath, extracted_input_no_gap), length_window, start_site, False) bf_maker_gtr.write_batch_file(dot_input=extracted_input_file, dot_aln="", hyphy_batch_file="TIR%sgtr.bf" % job_description, hyphy_result_file="TIR%sgtr.result" % job_description) bf_maker_nest.write_batch_file(dot_input=extracted_input_file, dot_aln="", hyphy_batch_file="TIR%snest.bf" % job_description, hyphy_result_file="TIR%snest.result" % job_description) # no gap bf_maker_gtr.write_batch_file(dot_input=extracted_input_no_gap, dot_aln="", hyphy_batch_file="TIR%sgtrN.bf" % job_description, hyphy_result_file="TIR%sgtrN.result" % job_description) bf_maker_nest.write_batch_file(dot_input=extracted_input_no_gap, dot_aln="", hyphy_batch_file="TIR%snestN.bf" % job_description, hyphy_result_file="TIR%snestN.result" % job_description)