Mercurial > repos > mvdbeek > size_distribution

changeset 4:f1eeaf42144b draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bardin-lab/smallRNA_tools commit c8e0a703fcdff580ba0a0c5806a37c088c03ab7b-dirty
author mvdbeek
date Mon, 20 Aug 2018 14:46:57 -0400
parents 21b5a9170b90
children
files size_distributions.py
diffstat 1 files changed, 5 insertions(+), 4 deletions(-) [+]
line wrap: on
line diff
--- a/size_distributions.py	Mon Aug 20 14:27:49 2018 -0400
+++ b/size_distributions.py	Mon Aug 20 14:46:57 2018 -0400
@@ -29,13 +29,14 @@
                     reference_counters[reference]['sense'][readlength] += 1
     df = pd.Panel(reference_counters).to_frame()
     df.index.names = ['readlength', 'orientation']
-    return df
+    return i, df
 
 
-def to_long(df):
+def to_long(df, total_count):
     df = df.reset_index()
     df = df.melt(id_vars=('readlength', 'orientation'))
     df.columns = ['readlength', 'orientation', 'reference', 'count']
+    df['TPM'] = df['count'] / total_count * 10 ** 6
     return df
 
 
@@ -52,9 +53,9 @@
 def size_dist(alignment_path, minimum_size=18, maximum_size=30, output="/dev/stdout", wide=False):
     """Calculate size distribution and orientation"""
     with pysam.AlignmentFile(alignment_path) as alignment_file:
-        df = global_size_distribution(alignment_file, minimum_size, maximum_size)
+        total_count, df = global_size_distribution(alignment_file, minimum_size, maximum_size)
         if not wide:
-            df = to_long(df)
+            df = to_long(df, total_count)
         write_table(df, output)