Merge branch '23-rename_output' into 24-astrocyte

workflow/scripts/call_peaks_macs.py

@@ -125,11 +125,12 @@ def call_peaks_macs(experiment, xcor, control, prefix, genome_size, chrom_sizes)
     # MACS2 sometimes calls features off the end of chromosomes.
     # Remove coordinates outside chromosome sizes
 
-    narrowpeak_fn = '%s.narrowPeak' % (prefix)
+    int_narrowpeak_fn = '%s_peaks.narrowPeak' % (prefix)
+    narrowpeak_fn = '%s_peaks.narrowPeak' % (prefix)
     clipped_narrowpeak_fn = 'clipped-%s' % (narrowpeak_fn)
 
 
-    steps = ['slopBed -i %s -g %s -b 0' % (narrowpeak_fn, chrom_sizes),
+    steps = ['slopBed -i %s -g %s -b 0' % (int_narrowpeak_fn, chrom_sizes),
              'bedClip stdin %s %s' % (chrom_sizes, clipped_narrowpeak_fn)]
 
     out, err = utils.run_pipe(steps)

workflow/scripts/experiment_qc.py

@@ -174,7 +174,7 @@ def main():
 
     # Run enrichment
     new_design_df = update_controls(design_df)
-    for row in new_design_df.iterrows():
+    for index, row in new_design_df.iterrows():
         check_enrichment(
             row['sample_id'],
             row['control_id'],

workflow/scripts/map_qc.py

@@ -153,7 +153,7 @@ def dedup_mapped(bam, bam_basename, paired):
     '''Use sambamba and samtools to remove duplicates.'''
 
     # Markduplicates
-    dup_file_qc_filename = bam_basename + ".dup.qc"
+    dup_file_qc_filename = bam_basename + ".dedup.qc"
     tmp_dup_mark_filename = bam_basename + ".dupmark.bam"
     sambamba_params = "--hash-table-size=17592186044416" + \
                     " --overflow-list-size=20000000 --io-buffer-size=256"

workflow/scripts/motif_search.py

@@ -84,13 +84,18 @@ def motif_search(filename, genome, experiment, peak):
 
     file_basename = os.path.basename(
         utils.strip_extensions(filename, STRIP_EXTENSIONS))
-    sorted_fn = '%s.%d.narrowPeak' % (file_basename, peak)
+
     out_fa = '%s.fa' % (experiment)
     out_motif = '%s_memechip' % (experiment)
 
     # Sort Bed file and limit number of peaks
     if peak == -1:
         peak = utils.count_lines(filename)
+        peak_no = 'all'
+    else:
+        peak_no = peak
+
+    sorted_fn = '%s.%s.narrowPeak' % (file_basename, peak)
 
     out, err = utils.run_pipe([
         'sort -k %dgr,%dgr %s' % (5, 5, filename),

workflow/scripts/pool_and_psuedoreplicate.py

@@ -25,7 +25,7 @@ logger.setLevel(logging.INFO)
 # strip_extensions strips from the right inward, so
 # the expected right-most extensions should appear first (like .gz)
 # Modified from J. Seth Strattan
-STRIP_EXTENSIONS = ['.gz', '.tagAlign', '.bedse', 'bedpe']
+STRIP_EXTENSIONS = ['.gz', '.tagAlign', '.bedse', '.bedpe']
 
 
 def get_args():
@@ -93,7 +93,10 @@ def pool(tag_files, outfile, paired):
     else:
         file_extension = '.bedse.gz'
 
-    pooled_filename = outfile + file_extension
+    pool_basename = os.path.basename(
+        utils.strip_extensions(outfile, STRIP_EXTENSIONS))
+
+    pooled_filename = pool_basename + file_extension
 
     # Merge files
     out, err = utils.run_pipe([
@@ -106,7 +109,7 @@ def pool(tag_files, outfile, paired):
 def bedpe_to_tagalign(tag_file, outfile):
     '''Convert read pairs to reads into standard tagAlign file.'''
 
-    se_tag_filename = outfile + "tagAlign.gz"
+    se_tag_filename = outfile + ".tagAlign.gz"
 
     # Convert read pairs to reads into standard tagAlign file
     tag_steps = ["zcat -f %s" % (tag_file)]

workflow/scripts/xcor.py

@@ -26,7 +26,7 @@ logger.setLevel(logging.INFO)
 # strip_extensions strips from the right inward, so
 # the expected right-most extensions should appear first (like .gz)
 # Modified from J. Seth Strattan
-STRIP_EXTENSIONS = ['.gz', '.tagAlign', '.bedse', 'bedpe']
+STRIP_EXTENSIONS = ['.gz', '.tagAlign', '.bedse', '.bedpe']
 
 
 def get_args():
@@ -113,6 +113,8 @@ def xcor(tag, paired):
          cc_plot_filename, cc_scores_filename)
     ])
 
+    return cc_scores_filename
+
 
 
 def main():