Mercurial > repos > jjohnson > qiime

diff pick_otus_through_otu_table.xml @ 0:e5c3175506b7 default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Initial tool configs for qiime, most need work.
author Jim Johnson <jj@umn.edu>
date Sun, 17 Jul 2011 10:30:11 -0500
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/pick_otus_through_otu_table.xml	Sun Jul 17 10:30:11 2011 -0500
@@ -0,0 +1,203 @@
+<tool id="pick_otus_through_otu_table" name="pick_otus_through_otu_table" version="1.2.0">
+ <description>A workflow script for picking OTUs through building OTU tables</description>
+ <requirements>
+  <requirement type="binary">pick_otus_through_otu_table.py</requirement>
+ </requirements>
+ <command interpreter="python">
+  qiime_wrapper.py
+  --galaxy_outputdir='$log.extra_files_path'
+  --galaxy_datasets='^log_\S+\.txt$:'$log,'^\S+_otus.txt$:'$seqs_otus,'^\S+_rep_set.fasta$:'$seqs_rep_set,'^\S+_rep_set_tax_assignments.txt$:'$seqs_rep_set_tax_assignments,'^\S+_otu_table.txt$:'$seqs_otu_table,'^\S+_rep_set_aligned.fasta$:'$seqs_rep_set_aligned,'^\S+_rep_set_aligned_pfiltered.fasta$:'$seqs_rep_set_aligned_pfiltered,'^\S+_rep_set.tre$:'$seqs_rep_set_tre
+  pick_otus_through_otu_table.py
+  --input_fp=$input_fp
+  #if $parameter.source == 'hist':
+   --parameter_fp=$parameter.parameter_fp
+  #else:
+   --parameter_fp=$parameter_generated
+  #end if
+  #if $denoise.choice == 'yes':
+   --sff_fp=$denoise.sff_fp
+   --mapping_fp=$denoise.mapping_fp
+  #end if
+  --output_dir='$log.extra_files_path'
+  --force
+  $parallel
+ </command>
+ <inputs>
+  <param name="input_fp" type="data" format="fasta" label="input_fp"
+   help="the input fasta file [REQUIRED]"/>
+  <conditional name="parameter">
+   <param name="source" type="select" label="Grouping Design from" help="">
+    <option value="hist">Your History</option>
+    <option value="build">Build a grouping design</option>
+   </param>
+   <when value="hist">
+    <param name="parameter_fp" type="data" format="qiimeparams" label="parameter_fp"
+     help="path to the parameter file [REQUIRED]"/>
+   </when> <!-- hist -->
+   <when value="build">
+   </when> <!-- build -->
+  </conditional> <!-- parameter -->
+  <conditional name="denoise">
+   <param name="choice" type="select" label="Denoise (requires sff flowgram and a mapping faile)" help="">
+    <option value="no">No</option>
+    <option value="yes">Yes</option>
+   </param>
+   <when value="yes">
+    <param name="sff_fp" type="data" format="ssf" label="sff_fp"
+     help="the sff flowgram file [REQUIRED for denoising]"/>
+    <param name="mapping_fp" type="data" format="qiimemapping" label="mapping_fp"
+     help="the mapping filepath [REQUIRED for denoising]"/>
+   </when> <!-- hist -->
+   <when value="no"/>
+  </conditional> <!-- denoise -->
+  <param name="parallel" type="boolean" truevalue="--parallel" falsevalue="" checked="false" label="parallel"
+   help="Run in parallel where available [default: False]"/>
+ </inputs>
+  <!-- Construct a parameter file
+  -->
+ <configfiles>
+  <configfile name="parameter_generated">
+##OTU picker parameters
+pick_otus:otu_picking_method	uclust
+pick_otus:clustering_algorithm	furthest
+pick_otus:max_cdhit_memory	400
+pick_otus:refseqs_fp
+pick_otus:blast_db
+pick_otus:similarity	0.97
+pick_otus:max_e_value	1e-10
+pick_otus:prefix_prefilter_length
+pick_otus:trie_prefilter
+pick_otus:prefix_length
+pick_otus:suffix_length
+pick_otus:optimal_uclust
+pick_otus:exact_uclust
+pick_otus:user_sort
+pick_otus:suppress_presort_by_abundance_uclust
+pick_otus:suppress_new_clusters
+pick_otus:suppress_uclust_stable_sort
+pick_otus:max_accepts
+pick_otus:max_rejects
+pick_otus:word_length
+pick_otus:stepwords
+##Representative set picker parameters
+pick_rep_set:rep_set_picking_method	first
+pick_rep_set:sort_by	otu
+##Multiple sequence alignment parameters
+align_seqs:template_fp
+align_seqs:alignment_method	pynast
+align_seqs:pairwise_alignment_method	uclust
+align_seqs:blast_db
+align_seqs:min_length	150
+align_seqs:min_percent_id	75.0
+##Alignment filtering (prior to tree-building) parameters
+filter_alignment:lane_mask_fp
+filter_alignment:allowed_gap_frac	0.999999
+filter_alignment:remove_outliers	False
+filter_alignment:threshold	3.0
+##Taxonomy assignment parameters
+assign_taxonomy:id_to_taxonomy_fp
+assign_taxonomy:reference_seqs_fp
+assign_taxonomy:assignment_method	rdp
+assign_taxonomy:blast_db
+assign_taxonomy:confidence	0.8
+#assign_taxonomy:e_value	0.001
+##Phylogenetic tree building parameters
+make_phylogeny:tree_method	fasttree
+make_phylogeny:root_method	tree_method_default
+##align_seqs:template_fp
+##filter_alignment:lane_mask_fp	
+  </configfile>
+ </configfiles>
+ <outputs>
+ <!--
+This script will produce a set of cluster centroids (as a FASTA file) 
+and a cluster mapping file (from denoise.py if sff.txt and mapping file were provided), 
+an OTU mapping file (pick_otus.py), 
+a representative set of sequences (FASTA file from pick_rep_set.py), 
+a sequence alignment file (FASTA file from align_seqs.py), 
+taxonomy assignment file (from assign_taxonomy.py), 
+a filtered sequence alignment (from filter_alignment.py), 
+a phylogenetic tree (Newick file from make_phylogeny.py) and an OTU table (from make_otu_table.py).
+
+wf_da2/log_20110305084135.txt
+wf_da2/uclust_picked_otus/seqs_otus.txt
+wf_da/uclust_picked_otus/rep_set/seqs_rep_set.fasta
+wf_da/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/seqs_rep_set_tax_assignments.txt
+wf_da/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/otu_table//seqs_otu_table.txt
+wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned.fasta
+wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned_pfiltered.fasta
+wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/fasttree_phylogeny/seqs_rep_set.tre
+
+
+wf_da2/log_20110305084135.txt
+wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/fasttree_phylogeny/seqs_rep_set.tre
+wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/fasttree_phylogeny/seqs_rep_set_phylogeny.log
+wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned.fasta
+wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned_pfiltered.fasta
+wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_failures.fasta
+wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_log.txt
+wf_da2/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/otu_table/seqs_otu_table.txt
+wf_da2/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/seqs_rep_set_tax_assignments.log
+wf_da2/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/seqs_rep_set_tax_assignments.txt
+wf_da2/uclust_picked_otus/rep_set/seqs_rep_set.fasta
+wf_da2/uclust_picked_otus/rep_set/seqs_rep_set.log
+wf_da2/uclust_picked_otus/seqs_clusters.uc
+wf_da2/uclust_picked_otus/seqs_otus.log
+wf_da2/uclust_picked_otus/seqs_otus.txt
+
+wf_da2/log_20110305084135.txt
+wf_da2/uclust_picked_otus/seqs_otus.txt
+wf_da/uclust_picked_otus/rep_set/seqs_rep_set.fasta
+wf_da/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/seqs_rep_set_tax_assignments.txt
+wf_da/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/otu_table/seqs_otu_table.txt
+wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned.fasta
+wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned_pfiltered.fasta
+wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/fasttree_phylogeny/seqs_rep_set.tre
+-->
+   <data format="txt" name="log" label="${tool.name} on ${on_string}: log" />
+   <data format="qiimeotu" name="seqs_otus" label="${tool.name} on ${on_string}: seqs_otus" />
+   <data format="fasta" name="seqs_rep_set" label="${tool.name} on ${on_string}: seqs_rep_set.fasta" />
+   <data format="seq.taxonomy" name="seqs_rep_set_tax_assignments" label="${tool.name} on ${on_string}: seqs_rep_set_tax_assignments" />
+   <data format="qiimeotutable" name="seqs_otu_table" label="${tool.name} on ${on_string}: seqs_otu_table" />
+   <data format="align" name="seqs_rep_set_aligned" label="${tool.name} on ${on_string}: seqs_rep_set_aligned.fasta" />
+   <data format="align" name="seqs_rep_set_aligned_pfiltered" label="${tool.name} on ${on_string}: seqs_rep_set_aligned_pfiltered.fasta" />
+   <data format="tre" name="seqs_rep_set_tre" label="${tool.name} on ${on_string}: seqs_rep_set.tre" />
+
+  
+ </outputs>
+ <tests>
+ </tests>
+ <help>
+
+        The steps performed by this function are:
+          0) Optionally denoise the sequences (if sff_input_fp=True);
+          1) Pick OTUs;
+          2) Pick a representative set;
+          3) Align the representative set; 
+          4) Assign taxonomy;
+          5) Filter the alignment prior to tree building - remove positions
+             which are all gaps, and specified as 0 in the lanemask
+          6) Build a phylogenetic tree;
+          7) Build an OTU table.
+
+
+pick_otus_through_otu_table.py -i split_library_output/seqs.fna -p custom_parameters.txt -o wf_da --print_only
+
+python /usr/local/bin/pick_otus.py -i split_library_output/seqs.fna -o wf_da/uclust_picked_otus --max_e_value 1e-10 --clustering_algorithm furthest --similarity 0.97 --otu_picking_method uclust --max_cdhit_memory 400
+
+python /usr/local/bin/pick_rep_set.py -i wf_da/uclust_picked_otus/seqs_otus.txt -f split_library_output/seqs.fna -l wf_da/uclust_picked_otus/rep_set//seqs_rep_set.log -o wf_da/uclust_picked_otus/rep_set//seqs_rep_set.fasta --rep_set_picking_method first --sort_by otu
+
+python /usr/local/bin/assign_taxonomy.py -o wf_da/uclust_picked_otus/rep_set//rdp_assigned_taxonomy -i wf_da/uclust_picked_otus/rep_set//seqs_rep_set.fasta --confidence 0.8 --assignment_method rdp
+
+python /usr/local/bin/make_otu_table.py -i wf_da/uclust_picked_otus/seqs_otus.txt -t wf_da/uclust_picked_otus/rep_set//rdp_assigned_taxonomy/seqs_rep_set_tax_assignments.txt -o wf_da/uclust_picked_otus/rep_set//rdp_assigned_taxonomy/otu_table//seqs_otu_table.txt 
+
+python /usr/local/bin/align_seqs.py -i wf_da/uclust_picked_otus/rep_set//seqs_rep_set.fasta -o wf_da/uclust_picked_otus/rep_set//pynast_aligned_seqs --alignment_method pynast --pairwise_alignment_method uclust --min_percent_id 75.0 --min_length 150
+
+python /usr/local/bin/filter_alignment.py -o wf_da/uclust_picked_otus/rep_set//pynast_aligned_seqs -i wf_da/uclust_picked_otus/rep_set//pynast_aligned_seqs/seqs_rep_set_aligned.fasta --allowed_gap_frac 0.999999 --threshold 3.0
+
+python /usr/local/bin/make_phylogeny.py -i wf_da/uclust_picked_otus/rep_set//pynast_aligned_seqs/seqs_rep_set_aligned_pfiltered.fasta -o wf_da/uclust_picked_otus/rep_set//pynast_aligned_seqs/fasttree_phylogeny/seqs_rep_set.tre -l wf_da/uclust_picked_otus/rep_set//pynast_aligned_seqs/fasttree_phylogeny/seqs_rep_set_phylogeny.log --root_method tree_method_default --tree_method fasttree
+
+  
+ </help>
+</tool>
+