Merge pull request #484 from Alexanderlacuna/test-regression

Add tests for marker_regression

3 files changed, 41 insertions, 36 deletions

diff --git a/wqflask/wqflask/marker_regression/gemma_mapping.py b/wqflask/wqflask/marker_regression/gemma_mapping.py
index 68a8d5ba..02f91a32 100644
--- a/wqflask/wqflask/marker_regression/gemma_mapping.py
+++ b/wqflask/wqflask/marker_regression/gemma_mapping.py
@@ -31,16 +31,11 @@ def run_gemma(this_trait, this_dataset, samples, vals, covariates, use_loco, maf
       gwa_output_filename = this_dataset.group.name + "_GWA_" + ''.join(random.choice(string.ascii_uppercase + string.digits) for _ in range(6))
 
       this_chromosomes = this_dataset.species.chromosomes.chromosomes
-      chr_list_string = ""
-      for i in range(len(this_chromosomes)):
-          if i < (len(this_chromosomes) - 1):
-              chr_list_string += this_chromosomes[i+1].name + ","
-          else:
-              chr_list_string += this_chromosomes[i+1].name
+      this_chromosomes_name=[chromosome.name for chromosome in this_chromosomes]
 
+      chr_list_string=",".join(this_chromosomes_name)
       if covariates != "":
           gen_covariates_file(this_dataset, covariates, samples)
-
       if use_loco == "True":
           generate_k_command = GEMMA_WRAPPER_COMMAND + ' --json --loco ' + chr_list_string + ' -- ' + GEMMAOPTS + ' -g %s/%s_geno.txt -p %s/gn2/%s.txt -a %s/%s_snps.txt -gk > %s/gn2/%s.json' % (flat_files('genotype/bimbam'),
                                                                                           genofile_name,
diff --git a/wqflask/wqflask/marker_regression/plink_mapping.py b/wqflask/wqflask/marker_regression/plink_mapping.py
index fd91b6ca..5d675c38 100644
--- a/wqflask/wqflask/marker_regression/plink_mapping.py
+++ b/wqflask/wqflask/marker_regression/plink_mapping.py
@@ -9,11 +9,11 @@ import utility.logger
 logger = utility.logger.getLogger(__name__ )
 
 def run_plink(this_trait, dataset, species, vals, maf):
-    plink_output_filename = webqtlUtil.genRandStr("%s_%s_"%(dataset.group.name, this_trait.name))
+    plink_output_filename = webqtlUtil.genRandStr(f"{dataset.group.name}_{this_trait.name}_")
     gen_pheno_txt_file(dataset, vals)
 
-    plink_command = PLINK_COMMAND + ' --noweb --bfile %s/%s --no-pheno --no-fid --no-parents --no-sex --maf %s --out %s%s --assoc ' % (
-        flat_files('mapping'), dataset.group.name, maf, TMPDIR, plink_output_filename)
+    
+    plink_command = f"{PLINK_COMMAND}  --noweb --bfile {flat_files('mapping')}/{dataset.group.name} --no-pheno --no-fid --no-parents --no-sex --maf {maf} --out { TMPDIR}{plink_output_filename} --assoc "
     logger.debug("plink_command:", plink_command)
 
     os.system(plink_command)
@@ -29,12 +29,12 @@ def gen_pheno_txt_file(this_dataset, vals):
     """Generates phenotype file for GEMMA/PLINK"""
 
     current_file_data = []
-    with open("{}/{}.fam".format(flat_files('mapping'), this_dataset.group.name), "r") as outfile:
+    with open(f"{flat_files('mapping')}/{this_dataset.group.name}.fam", "r") as outfile:
         for i, line in enumerate(outfile):
             split_line = line.split()
             current_file_data.append(split_line)
 
-    with open("{}/{}.fam".format(flat_files('mapping'), this_dataset.group.name), "w") as outfile:
+    with open(f"{flat_files('mapping')}/{this_dataset.group.name}.fam","w") as outfile:
         for i, line in enumerate(current_file_data):
             if vals[i] == "x":
                 this_val = -9
@@ -44,8 +44,8 @@ def gen_pheno_txt_file(this_dataset, vals):
 
 def gen_pheno_txt_file_plink(this_trait, dataset, vals, pheno_filename = ''):
     ped_sample_list = get_samples_from_ped_file(dataset)
-    output_file = open("%s%s.txt" % (TMPDIR, pheno_filename), "wb")
-    header = 'FID\tIID\t%s\n' % this_trait.name
+    output_file = open(f"{TMPDIR}{pheno_filename}.txt", "wb")
+    header = f"FID\tIID\t{this_trait.name}\n"
     output_file.write(header)
 
     new_value_list = []
@@ -65,7 +65,7 @@ def gen_pheno_txt_file_plink(this_trait, dataset, vals, pheno_filename = ''):
     for i, sample in enumerate(ped_sample_list):
         j = i+1
         value = new_value_list[i]
-        new_line += '%s\t%s\t%s\n'%(sample, sample, value)
+        new_line += f"{sample}\t{sample}\t{value}\n"
 
         if j%1000 == 0:
             output_file.write(newLine)
@@ -78,7 +78,7 @@ def gen_pheno_txt_file_plink(this_trait, dataset, vals, pheno_filename = ''):
 
 # get strain name from ped file in order
 def get_samples_from_ped_file(dataset):
-    ped_file= open("{}{}.ped".format(flat_files('mapping'), dataset.group.name), "r")
+    ped_file= open(f"{flat_files('mapping')}{dataset.group.name}.ped","r")
     line = ped_file.readline()
     sample_list=[]
 
@@ -98,7 +98,7 @@ def parse_plink_output(output_filename, species):
 
     threshold_p_value = 1
 
-    result_fp = open("%s%s.qassoc"% (TMPDIR, output_filename), "rb")
+    result_fp = open(f"{TMPDIR}{output_filename}.qassoc","rb")
 
     line = result_fp.readline()
 
@@ -154,7 +154,7 @@ def parse_plink_output(output_filename, species):
 # function: convert line from str to list;
 # output: lineList list
 #######################################################
-def build_line_list(line=None):
+def build_line_list(line=""):
     line_list = line.strip().split(' ')# irregular number of whitespaces between columns
     line_list = [item for item in line_list if item !='']
     line_list = [item.strip() for item in line_list]
diff --git a/wqflask/wqflask/marker_regression/qtlreaper_mapping.py b/wqflask/wqflask/marker_regression/qtlreaper_mapping.py
index 78b1f7b0..505ae295 100644
--- a/wqflask/wqflask/marker_regression/qtlreaper_mapping.py
+++ b/wqflask/wqflask/marker_regression/qtlreaper_mapping.py
@@ -17,22 +17,29 @@ def run_reaper(this_trait, this_dataset, samples, vals, json_data, num_perm, boo
         else:
             genofile_name = this_dataset.group.name
 
-        trait_filename = str(this_trait.name) + "_" + str(this_dataset.name) + "_pheno"
+        trait_filename =f"{str(this_trait.name)}_{str(this_dataset.name)}_pheno"
         gen_pheno_txt_file(samples, vals, trait_filename)
 
-        output_filename = this_dataset.group.name + "_GWA_" + ''.join(random.choice(string.ascii_uppercase + string.digits) for _ in range(6))
+        output_filename = (f"{this_dataset.group.name}_GWA_"+
+            ''.join(random.choice(string.ascii_uppercase + string.digits) for _ in range(6))
+            )
         bootstrap_filename = None
         permu_filename = None
 
         opt_list = []
         if boot_check and num_bootstrap > 0:
-            bootstrap_filename = this_dataset.group.name + "_BOOTSTRAP_" + ''.join(random.choice(string.ascii_uppercase + string.digits) for _ in range(6))
+            bootstrap_filename = (f"{this_dataset.group.name}_BOOTSTRAP_" + 
+                ''.join(random.choice(string.ascii_uppercase + string.digits) for _ in range(6))
+                )
 
             opt_list.append("-b")
-            opt_list.append("--n_bootstrap " + str(num_bootstrap))
-            opt_list.append("--bootstrap_output " + webqtlConfig.GENERATED_IMAGE_DIR + bootstrap_filename + ".txt")
+            opt_list.append(f"--n_bootstrap{str(num_bootstrap)}")
+            opt_list.append(f"--bootstrap_output{webqtlConfig.GENERATED_IMAGE_DIR}{bootstrap_filename}.txt")
         if num_perm > 0:
-            permu_filename = this_dataset.group.name + "_PERM_" + ''.join(random.choice(string.ascii_uppercase + string.digits) for _ in range(6))
+            permu_filename =("{this_dataset.group.name}_PERM_" + 
+            ''.join(random.choice(string.ascii_uppercase + 
+                string.digits) for _ in range(6))
+            )
             opt_list.append("-n " + str(num_perm))
             opt_list.append("--permu_output " + webqtlConfig.GENERATED_IMAGE_DIR + permu_filename + ".txt")
         if control_marker != "" and do_control == "true":
@@ -40,13 +47,15 @@ def run_reaper(this_trait, this_dataset, samples, vals, json_data, num_perm, boo
         if manhattan_plot != True:
             opt_list.append("--interval 1")
 
-        reaper_command = REAPER_COMMAND + ' --geno {0}/{1}.geno --traits {2}/gn2/{3}.txt {4} -o {5}{6}.txt'.format(flat_files('genotype'),
-                                                                                                                genofile_name,
-                                                                                                                TEMPDIR,
-                                                                                                                trait_filename,
-                                                                                                                " ".join(opt_list),
-                                                                                                                webqtlConfig.GENERATED_IMAGE_DIR,
-                                                                                                                output_filename)
+        reaper_command = (REAPER_COMMAND + 
+        ' --geno {0}/{1}.geno --traits {2}/gn2/{3}.txt {4} -o {5}{6}.txt'.format(flat_files('genotype'),
+
+                                                                              genofile_name,
+                                                                              TEMPDIR,
+                                                                              trait_filename,
+                                                                              " ".join(opt_list),
+                                                                              webqtlConfig.GENERATED_IMAGE_DIR,
+                                                                            output_filename))
 
         logger.debug("reaper_command:" + reaper_command)
         os.system(reaper_command)
@@ -61,12 +70,13 @@ def run_reaper(this_trait, this_dataset, samples, vals, json_data, num_perm, boo
         suggestive = permu_vals[int(num_perm*0.37-1)]
         significant = permu_vals[int(num_perm*0.95-1)]
 
-    return marker_obs, permu_vals, suggestive, significant, bootstrap_vals, [output_filename, permu_filename, bootstrap_filename]
+    return (marker_obs, permu_vals, suggestive, significant, bootstrap_vals, 
+        [output_filename, permu_filename, bootstrap_filename])
 
 def gen_pheno_txt_file(samples, vals, trait_filename):
     """Generates phenotype file for GEMMA"""
 
-    with open("{}/gn2/{}.txt".format(TEMPDIR, trait_filename), "w") as outfile:
+    with open(f"{TEMPDIR}/gn2/{trait_filename}.txt","w") as outfile:
         outfile.write("Trait\t")
 
         filtered_sample_list = []
@@ -90,7 +100,7 @@ def parse_reaper_output(gwa_filename, permu_filename, bootstrap_filename):
     only_cm = False
     only_mb = False
 
-    with open("{}{}.txt".format(webqtlConfig.GENERATED_IMAGE_DIR, gwa_filename)) as output_file:
+    with open(f"{webqtlConfig.GENERATED_IMAGE_DIR}{gwa_filename}.txt") as output_file:
         for line in output_file:
             if line.startswith("ID\t"):
                 if len(line.split("\t")) < 8:
@@ -137,13 +147,13 @@ def parse_reaper_output(gwa_filename, permu_filename, bootstrap_filename):
 
     permu_vals = []
     if permu_filename:
-        with open("{}{}.txt".format(webqtlConfig.GENERATED_IMAGE_DIR, permu_filename)) as permu_file:
+        with open(f"{webqtlConfig.GENERATED_IMAGE_DIR}{permu_filename}.txt") as permu_file:
             for line in permu_file:
                 permu_vals.append(float(line))
 
     bootstrap_vals = []
     if bootstrap_filename:
-        with open("{}{}.txt".format(webqtlConfig.GENERATED_IMAGE_DIR, bootstrap_filename)) as bootstrap_file:
+        with open(f"{webqtlConfig.GENERATED_IMAGE_DIR}{bootstrap_filename}.txt") as bootstrap_file:
             for line in bootstrap_file:
                 bootstrap_vals.append(int(line))