fixed

aft_pipelines_analysis/aft_pipelines_main.py

@@ -25,7 +25,7 @@
 ## 18/03/23
 ## absoulte path
 
-script_path = __file__
+script_path = os.path.abspath(__file__)
 dir_script = os.path.dirname(script_path)
 
 if len(sys.argv) == 3 and '/' in sys.argv[1]:
@@ -230,8 +230,9 @@ def draw_coverage_depths():
             else:
                 normal_name = each_pair + NORMAL_SIG
                 tumor_name = each_pair + TUMOR_SIG
-            cmdline = 'python %s/extracted_pos_from_vcf.py %s %s %s %s' % (
+            cmdline = 'python %s/extracted_pos_from_vcf.py %s %s %s %s %s' % (
                 dir_script,
+                server_setting_path,
                 bed_file,
                 '%s/%s.mt2.vcf' % (vcf_path, each_pair),
                 '%s/%s.mt2.vcf' % (vcf_path, tumor_name),

aft_pipelines_analysis/extracted_pos_from_vcf.py

@@ -1,15 +1,16 @@
 import os
 
+bcftools_path = '/home/liaoth/tools/bcftools-1.3.1/bcftools'
 
 def prepare_vcf(vcf_path):
     if not vcf_path.endswith('.gz'):
         os.system('`which bgzip` %s' % vcf_path)
         vcf_path += '.gz'
         print vcf_path
-        os.system('/home/liaoth/tools/bcftools-1.3.1/bcftools index %s' % vcf_path)
+        os.system('%s index %s' % (bcftools_path,vcf_path))
     else:
         if not os.path.isfile(vcf_path + '.csi'):
-            os.system('/home/liaoth/tools/bcftools-1.3.1/bcftools index %s' % vcf_path)
+            os.system('%s index %s' % (bcftools_path,vcf_path))
 
 
 def merge_two_vcf(pair_vcf, bed, single_vcf, output_vcf):
@@ -19,7 +20,7 @@ def merge_two_vcf(pair_vcf, bed, single_vcf, output_vcf):
     single_sample_name = os.popen("zgrep '^#C' %s | cut -f 10-" % single_vcf).read().replace('\n', '').replace('\t',
                                                                                                                ',')
 
-    formatted_line = '''/home/liaoth/tools/bcftools-1.3.1/bcftools view {vcf} -R {bed} -s ^{SM} --force-samples | vcf-sort > {output}'''
+    formatted_line = '''%s view {vcf} -R {bed} -s ^{SM} --force-samples | vcf-sort > {output}''' % bcftools_path
     cmdline1 = formatted_line.format(vcf=pair_vcf.replace('.gz', '') + '.gz', bed=bed, output=output_vcf + '1',
                                      SM=pair_sample_name)
     cmdline2 = formatted_line.format(vcf=single_vcf.replace('.gz', '') + '.gz', bed=bed, output=output_vcf + '2',
@@ -31,7 +32,8 @@ def merge_two_vcf(pair_vcf, bed, single_vcf, output_vcf):
     prepare_vcf(output_vcf + '1');
     prepare_vcf(output_vcf + '2');
 
-    formatted_line2 = """/home/liaoth/tools/bcftools-1.3.1/bcftools concat {o1} {o2} -a -d all > {output}""".format(
+    formatted_line2 = """{bcftools} concat {o1} {o2} -a -d all > {output}""".format(
+        bcftools = bcftools_path,
         o1=output_vcf + '1.gz',
         o2=output_vcf + '2.gz',
         output=output_vcf)
@@ -43,10 +45,11 @@ def merge_two_vcf(pair_vcf, bed, single_vcf, output_vcf):
 if __name__ == '__main__':
     import sys
 
-    bed_f = sys.argv[1]
-    pairedvcf = sys.argv[2]
-    single_vcf = sys.argv[3]
-    output_vcf = sys.argv[4]
+    setting_f = sys.argv[1]
+    bed_f = sys.argv[2]
+    pairedvcf = sys.argv[3]
+    single_vcf = sys.argv[4]
+    output_vcf = sys.argv[5]
     # merge_two_vcf('/home/liaoth/project/180104_XK/gpz_server/vcf_storge/XK-25.mt2.vcf',
     #               '/home/liaoth/project/180104_XK/gpz_server/analysis_result/filtered_somatic/XK-25_filtered_somatic.bed'
     #               , '/home/liaoth/project/180104_XK/gpz_server/vcf_storge/XK-25T.mt2.vcf',

aft_pipelines_analysis/filter_pipelines.py

@@ -1,6 +1,5 @@
 from __future__ import print_function
 from genes_list import snp_138_common_init,formatt_col
-from filters import *
 import pandas,time
 import argparse
 import os, sys, glob
@@ -150,6 +149,7 @@ def filter_pipelines2(normal_germline,normal_somatic, tumor_somatic,pair_somatic
     import_path = os.path.dirname(setting_file)
     sys.path.insert(0, import_path)
     from setting import *
+    from filters import *
     ############################################################
     samples_ids = [os.path.basename(i).split('.mt2.merged.')[0] for i in glob.glob(os.path.join(csv_output_dir, 'somatic', '*.csv'))]
     pair_name = [i for i in samples_ids if NORMAL_SIG not in i and TUMOR_SIG not in i]

aft_pipelines_analysis/filters.py

@@ -3,7 +3,7 @@
 import pandas as pd
 import tqdm
 
-BED_INFO = pd.read_csv('/home/liaoth/data2/project/XK_WES/Sureselect_V6_COSMIC_formal.bed', sep='\t', header=None,
+BED_INFO = pd.read_csv(local_bed_file, sep='\t', header=None,
                        index_col=None)
 range_list = []
 for idx in tqdm.tqdm(range(BED_INFO.shape[0])):

setting.py

@@ -32,6 +32,7 @@
 local_vt_pro = '/home/liaoth/tools/vt/vt'
 pcgr_pro = '/home/liaoth/data2/pcgr-0.5.3'
 local_hg19_ref_db = '/home/liaoth/data2/hg19/ucsc.hg19.fasta'
+local_bed_file = '/home/liaoth/data2/project/XK_WES/Sureselect_V6_COSMIC_formal.bed'
 #####Paired format.
 PE1_fmt = '{input}_R1'
 PE2_fmt = '{input}_R2'