Merge pull request #67 from maxplanck-ie/fix_python3

Fix python3 compatibillity of sample_qc_report_{SE,PE}.py

shared/common_functions.py

@@ -103,7 +103,7 @@ def get_sample_names(infiles, ext, reads):
         x = os.path.basename(x).replace(ext, "")
         try:
             x = x.replace(reads[0], "").replace(reads[1], "")
-        except:
+        except IndexError:
             pass
         s.append(x)
     return sorted(list(set(s)))
@@ -145,7 +145,7 @@ def get_fragment_length(infile):
                 try:
                     median = next(f).split()[0]
                     return int(median)
-                except:
+                except TypeError:
                     print("ERROR: File", infile, "is NOT a proper Picard CollectInsertSizeMetrics metrics file.\n")
                     exit(1)
     # no match in infile

shared/rules/ChIP_qc_report.snakefile

@@ -17,7 +17,7 @@ if paired:
         benchmark:
             "QC_report/.benchmark/qc_report.{sample}.benchmark"
         shell:
-            "python " + os.path.join(workflow_tools, "sample_qc_report_PE.py") + " "
+            os.path.join(workflow_tools, "sample_qc_report_PE.py") + " "
             "{input.alignment_summary_metrics} {input.mark_duplicates_metrics} {input.insert_size_metrics} {input.macs2_xls} {input.macs2_qc_txt} "
             ">{output} 2>{log} "
 else:
@@ -36,7 +36,7 @@ else:
         benchmark:
             "QC_report/.benchmark/qc_report.{sample}.benchmark"
         shell:
-            "python " + os.path.join(workflow_tools, "sample_qc_report_SE.py") + " "
+            os.path.join(workflow_tools, "sample_qc_report_SE.py") + " "
             "{input.alignment_summary_metrics} {input.mark_duplicates_metrics} {input.macs2_xls} {input.macs2_qc_txt} "
             ">{output} 2>{log} "
 

shared/tools/sample_qc_report_PE.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
 
 
 # paired-end ONLY!
@@ -19,7 +19,7 @@
 try:
     infile_MACS2_xls = sys.argv[4]              # sample_name.filtered.BAM_peaks.xls (optional)
     infile_MACS2_qc_txt = sys.argv[5]           # ample_name.filtered.BAM_peaks.qc.txt (optional)
-except:
+except IndexError:
     pass
 
 
@@ -28,7 +28,7 @@
     with open(infile_AlignmentSummaryMetrics) as f:
         lines = f.readlines()
 
-    columns = filter(lambda x: x.startswith("PAIR"), lines)[0].strip().split("\t")
+    columns = list(filter(lambda x: x.startswith("PAIR"), lines))[0].strip().split("\t")
 
     # PF_READS: The number of PF reads where PF is defined as passing Illumina's filter.
     total_reads = int(columns[2])
@@ -49,21 +49,21 @@
     fmapped_pairs = 1.0 * mapped_pairs / read_pairs
     fmapped_singletons = 1.0 * (mapped_reads - mapped_reads_in_pairs) / total_reads
 
-except:
+except OSError:
     exit("ERROR! Unable to read: {}".format(infile_AlignmentSummaryMetrics))
 
 
 # read Picard MarkDuplicates results #########################################
 try:
     with open(infile_MarkDuplicates) as f:
         lines = f.readlines()
-    columns = filter(lambda x: x.startswith("Unknown Library"), lines)[0].strip().split("\t")
+    columns = list(filter(lambda x: x.startswith("Unknown Library"), lines))[0].strip().split("\t")
 
     dup_mapped_pairs = int(columns[5])
     fdup_mapped_pairs = 1.0 * dup_mapped_pairs / mapped_pairs
     dupfree_mapped_pairs = mapped_pairs - dup_mapped_pairs
     fdupfree_mapped_pairs = 1.0 * dupfree_mapped_pairs / read_pairs
-except:
+except OSError:
     exit("ERROR! Unable to read: {}".format(infile_MarkDuplicates))
 
 
@@ -79,11 +79,11 @@
     elif os.path.isfile(infile_MACS2_xls):
         with open(infile_MACS2_xls) as f:
             lines = f.readlines()
-        columns = filter(lambda x: x.startswith("# d"), lines)[0].strip()
+        columns = list(filter(lambda x: x.startswith("# d"), lines))[0].strip()
         fragment_size = int(columns.split(" = ")[1])
     else:
         fragment_size = "NA"
-except:
+except OSError:
     fragment_size = "NA"
 
 
@@ -94,7 +94,7 @@
         peak_count = int(columns[0])
         frip = round(float(columns[1]), 3)
         peak_genome_coverage = round(columns[2], 3)
-except:
+except OSError:
     peak_count = "NA"
     frip = "NA"
     peak_genome_coverage = "NA"

shared/tools/sample_qc_report_SE.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
 
 
 # single-end ONLY!
@@ -16,15 +16,15 @@
 try:
     infile_MACS2_xls = sys.argv[3]              # sample_name.filtered.BAM_peaks.xls (optional)
     infile_MACS2_qc_txt = sys.argv[4]           # ample_name.filtered.BAM_peaks.qc.txt (optional)
-except:
+except IndexError:
     pass
 
 
 # read Picard AlignmentSummaryMetrics results ################################
 try:
     with open(infile_AlignmentSummaryMetrics) as f:
         lines = f.readlines()
-    columns = filter(lambda x: x.startswith("UNPAIRED"), lines)[0].strip().split("\t")
+    columns = list(filter(lambda x: x.startswith("UNPAIRED"), lines))[0].strip().split("\t")
 
     # PF_READS: The number of PF reads where PF is defined as passing Illumina's filter.
     total_reads = int(columns[2])
@@ -37,15 +37,15 @@
 
     # fraction of high-quality mapped reads (MAPQ >=20)
     fhq_mapped_reads = 1.0 * int(columns[8]) / total_reads
-except:
+except OSError:
     exit("ERROR! Unable to read: {}\n".format(infile_AlignmentSummaryMetrics))
 
 
 # read Picard MarkDuplicates results #########################################
 try:
     with open(infile_MarkDuplicates) as f:
         lines = f.readlines()
-    columns = filter(lambda x: x.startswith("Unknown Library"), lines)[0].strip().split("\t")
+    columns = list(filter(lambda x: x.startswith("Unknown Library"), lines))[0].strip().split("\t")
 
     # UNPAIRED_READ_DUPLICATES: The number of fragments that were marked as duplicates.
     dup_mapped_reads = int(columns[4])
@@ -58,17 +58,17 @@
 
     # fraction of duplication free mapped reads
     fdupfree_mapped_reads = 1.0 * dupfree_mapped_reads / total_reads
-except:
+except OSError:
     exit("ERROR! Unable to read: {}".format(infile_MarkDuplicates))
 
 
 # get fragment size from Picard CollectInsertSizeMetrics/MACS2 output ########
 try:
     with open(infile_MACS2_xls) as f:
         lines = f.readlines()
-    columns = filter(lambda x: x.startswith("# d"), lines)[0].strip()
+    columns = list(filter(lambda x: x.startswith("# d"), lines))[0].strip()
     fragment_size = int(columns.split(" = ")[1])
-except:
+except OSError:
     fragment_size = "NA"
 
 
@@ -79,7 +79,7 @@
         peak_count = int(columns[0])
         frip = round(float(columns[1]), 3)
         peak_genome_coverage = round(columns[2], 3)
-except:
+except OSError:
     peak_count = "NA"
     frip = "NA"
     peak_genome_coverage = "NA"