Mercurial > repos > pjbriggs > amplicon_analysis_pipeline

changeset 5:bbfc9638ba84 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
First version with (partial) bioconda deps.
author pjbriggs
date Wed, 13 Jun 2018 08:39:26 -0400
parents 013bf1e2cc8f
children 45db1f97795c
files README.rst amplicon_analysis_pipeline.xml relabel_fasta.py
diffstat 3 files changed, 84 insertions(+), 14 deletions(-) [+]
line wrap: on
line diff
--- a/README.rst	Wed Jun 13 07:43:57 2018 -0400
+++ b/README.rst	Wed Jun 13 08:39:26 2018 -0400
@@ -194,19 +194,16 @@
  - bioawk 1.0
  - fastqc 0.11.3
  - R 3.2.0
-
-Some dependencies are available but with the "wrong" versions:
-
- - spades (need 3.5.0)
- - qiime (need 1.8.0)
- - blast (need 2.2.26)
- - vsearch (need 1.1.3)
+ - spades 3.5.0
+ - qiime 1.8.0
+ - blast-legacy 2.2.26
+ - vsearch 1.1.3
+ - fasta-splitter 0.2.4
+ - rdp_classifier 2.2
 
 The following dependencies are currently unavailable:
 
  - fasta_number (need 02jun2015)
- - fasta-splitter (need 0.2.4)
- - rdp_classifier (need 2.2)
  - microbiomeutil (need r20110519)
 
 (NB usearch 6.1.544 and 8.0.1623 are special cases which must be
@@ -218,6 +215,7 @@
 ========== ======================================================================
 Version    Changes
 ---------- ----------------------------------------------------------------------
+1.2.2.1    Update to get dependencies from bioconda
 1.2.2.0    Updated to Amplicon_Analysis_Pipeline version 1.2.2 (removes
            jackknifed analysis which is not captured by Galaxy tool)
 1.2.1.0    Updated to Amplicon_Analysis_Pipeline version 1.2.1 (adds
--- a/amplicon_analysis_pipeline.xml	Wed Jun 13 07:43:57 2018 -0400
+++ b/amplicon_analysis_pipeline.xml	Wed Jun 13 08:39:26 2018 -0400
@@ -1,20 +1,24 @@
-<tool id="amplicon_analysis_pipeline" name="Amplicon Analysis Pipeline" version="1.2.2.0">
+<tool id="amplicon_analysis_pipeline" name="Amplicon Analysis Pipeline" version="1.2.2.1">
   <description>analyse 16S rRNA data from Illumina Miseq paired-end reads</description>
   <requirements>
+    <!-- amplicon_analysis_pipeline not available in bioconda -->
     <requirement type="package" version="1.2.2">amplicon_analysis_pipeline</requirement>
+    <requirement type="package" version="2.7">python</requirement>
     <requirement type="package" version="1.11">cutadapt</requirement>
-    <requirement type="package" version="1.33">sickle</requirement>
-    <requirement type="package" version="27-08-2013">bioawk</requirement>
+    <requirement type="package" version="1.33">sickle-trim</requirement>
+    <requirement type="package" version="1.0">bioawk</requirement>
     <requirement type="package" version="2.8.1">pandaseq</requirement>
     <requirement type="package" version="3.5.0">spades</requirement>
     <requirement type="package" version="0.11.3">fastqc</requirement>
     <requirement type="package" version="1.8.0">qiime</requirement>
-    <requirement type="package" version="2.2.26">blast</requirement>
+    <requirement type="package" version="2.2.26">blast-legacy</requirement>
     <requirement type="package" version="0.2.4">fasta-splitter</requirement>
-    <requirement type="package" version="2.2">rdp-classifier</requirement>
+    <requirement type="package" version="2.2">rdp_classifier</requirement>
     <requirement type="package" version="3.2.0">R</requirement>
     <requirement type="package" version="1.1.3">vsearch</requirement>
+    <!-- microbiomeutil not available in bioconda -->
     <requirement type="package" version="2010-04-29">microbiomeutil</requirement>
+    <!-- fastq_number not available in bioconda -->
     <requirement type="package">fasta_number</requirement>
   </requirements>
   <stdio>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/relabel_fasta.py	Wed Jun 13 08:39:26 2018 -0400
@@ -0,0 +1,68 @@
+#!/usr/bin/env python
+
+"""
+Replace FASTA labels with new labels <PREFIX>1, <PREFIX>2,
+<PREFIX>3 etc (where <PREFIX> is a user-provided argument).
+
+Can be used to label OTUs as OTU_1, OTU_2 etc.
+
+This is a reimplementation of the fasta_number.py script from
+https://drive5.com/python/fasta_number_py.html
+"""
+
+import argparse
+
+def relabel_fasta(fp,prefix,include_size=False):
+    """
+    """
+    # Iterate over lines in file
+    nlabel = 0
+    for line in fp:
+        # Strip trailing newlines
+        line = line.rstrip('\n')
+        if not line:
+            # Skip blank lines
+            continue
+        elif line.startswith('>'):
+            # 
+            nlabel += 1
+            label = line[1:].strip()
+            if args.needsize:
+                # Extract size from the label
+                try:
+                    size = filter(
+                        lambda x: x.startswith("size="),
+                        label.split(';'))[0]
+                except Exception as ex:
+                    raise Exception("Couldn't locate 'size' in "
+                                    "label: %s" % label)
+                yield ">%s%d;%s" % (args.prefix,
+                                    nlabel,
+                                    size)
+            else:
+                yield ">%s%d" % (args.prefix,
+                                 nlabel)
+        else:
+            # Echo the line to output
+            yield line
+
+if __name__ == "__main__":
+
+    # Set up command line parser
+    p = argparse.ArgumentParser()
+    p.add_argument("--needsize",action="store_true")
+    p.add_argument("--nosize",action="store_true")
+    p.add_argument("fasta")
+    p.add_argument("prefix")
+    
+    # Process command line
+    args = p.parse_args()
+
+    # Relabel FASTA
+    with open(args.fasta,'rU') as fasta:
+        for line in relabel_fasta(fasta,
+                                  args.prefix,
+                                  include_size=args.needsize):
+            print line
+
+