Merge branch 'ha_work' of github.com:ngs-docs/2016-metagenomics-sio

gather-counts.py

@@ -0,0 +1,59 @@
+#! /usr/bin/env python
+"""
+This script gathers & converts Salmon output counts into something that
+edgeR can read ("counts files").
+
+Run it in a directory above all of your Salmon output directories, and
+it will create a bunch of '.counts' files that you can load into R.
+
+See https://github.com/ngs-docs/2015-nov-adv-rna/ for background info.
+
+C. Titus Brown, 11/2015
+"""
+import os, os.path
+import sys
+import csv
+
+def process_quant_file(root, filename, outname):
+    """
+    Convert individual quant.sf files into .counts files (transcripts\tcount).
+    """
+    print >>sys.stderr, 'Loading counts from:', root, filename
+    outfp = open(outname, 'w')
+    print >>outfp, "transcript\tcount"
+
+    d = {}
+    full_file = os.path.join(root, filename)
+    for line in open(full_file):
+        if line.startswith('Name'):
+            continue
+        name, length, eff_length, tpm, count = line.strip().split('\t')
+
+        print >>outfp, "%s\t%s" % (name, float(tpm))
+
+
+def main():
+    """
+    Find all the quant.sf files, convert them into properly named .counts
+    files.
+
+    Here, "proper name" means "directory.counts".
+    """
+    quantlist = []
+
+    start_dir = '.'
+    print >>sys.stderr, 'Starting in:', os.path.abspath(start_dir)
+    for root, dirs, files in os.walk('.'):
+        for filename in files:
+            if filename.endswith('quant.sf'):
+                dirname = os.path.basename(root)
+                outname = dirname + '.counts'
+                process_quant_file(root, filename, dirname + '.counts')
+                quantlist.append(outname)
+
+                break
+
+    print ",\n".join([ "\"%s\"" % i for i in sorted(quantlist)])
+
+if __name__ == '__main__':
+    main()

prokka_tutorial.rst

@@ -39,9 +39,9 @@ Make a new directory for the annotation:
     mkdir annotation
     cd annotation
 
-Gunzip the metagenome assembly file into this directory:
+Link the metagenome assembly file into this directory:
 ::
-    gunzip subset_assembly.fa.gz
+    ln -fs /mnt/assembly/combined/final.contigs.fa
 
 Now it is time to run Prokka! There are tons of different ways to specialize the running of Prokka. We are going to keep it simple for now, though. It will take a little bit to run.
 ::

salmon_tutorial.rst

@@ -40,7 +40,7 @@ Create the salmon index:
 
 Salmon requires that paired reads be separated into two files. We can split the reads using the XXX script XXX: *CHECK ME!*
 ::
-  for file in *.abundtrim.subset.pe.fq.gz
+  for file in *.abundtrim.subset.pe.fq
   do
     split-reads.py $file
   done
@@ -74,6 +74,7 @@ Download the gather-counts.py script:
 and run it:
 
   python ./gather-counts.py
+
 This will give you a bunch of .counts files, which are processed from the quant.sf files and named for the directory from which they emanate.
 
 References