Mercurial > repos > jjohnson > qiime

comparison 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
comparison
equal deleted inserted replaced
-1:000000000000 0:e5c3175506b7
1 <tool id="pick_otus_through_otu_table" name="pick_otus_through_otu_table" version="1.2.0">
2 <description>A workflow script for picking OTUs through building OTU tables</description>
3 <requirements>
4 <requirement type="binary">pick_otus_through_otu_table.py</requirement>
5 </requirements>
6 <command interpreter="python">
7 qiime_wrapper.py
8 --galaxy_outputdir='$log.extra_files_path'
9 --galaxy_datasets='^log_\S+\.txt$:'$log,'^\S+_otus.txt$:'$seqs_otus,'^\S+_rep_set.fasta$:'$seqs_rep_set,'^\S+_rep_set_tax_assignments.txt$:'$seqs_rep_set_tax_assignments,'^\S+_otu_table.txt$:'$seqs_otu_table,'^\S+_rep_set_aligned.fasta$:'$seqs_rep_set_aligned,'^\S+_rep_set_aligned_pfiltered.fasta$:'$seqs_rep_set_aligned_pfiltered,'^\S+_rep_set.tre$:'$seqs_rep_set_tre
10 pick_otus_through_otu_table.py
11 --input_fp=$input_fp
12 #if $parameter.source == 'hist':
13 --parameter_fp=$parameter.parameter_fp
14 #else:
15 --parameter_fp=$parameter_generated
16 #end if
17 #if $denoise.choice == 'yes':
18 --sff_fp=$denoise.sff_fp
19 --mapping_fp=$denoise.mapping_fp
20 #end if
21 --output_dir='$log.extra_files_path'
22 --force
23 $parallel
24 </command>
25 <inputs>
26 <param name="input_fp" type="data" format="fasta" label="input_fp"
27 help="the input fasta file [REQUIRED]"/>
28 <conditional name="parameter">
29 <param name="source" type="select" label="Grouping Design from" help="">
30 <option value="hist">Your History</option>
31 <option value="build">Build a grouping design</option>
32 </param>
33 <when value="hist">
34 <param name="parameter_fp" type="data" format="qiimeparams" label="parameter_fp"
35 help="path to the parameter file [REQUIRED]"/>
36 </when> <!-- hist -->
37 <when value="build">
38 </when> <!-- build -->
39 </conditional> <!-- parameter -->
40 <conditional name="denoise">
41 <param name="choice" type="select" label="Denoise (requires sff flowgram and a mapping faile)" help="">
42 <option value="no">No</option>
43 <option value="yes">Yes</option>
44 </param>
45 <when value="yes">
46 <param name="sff_fp" type="data" format="ssf" label="sff_fp"
47 help="the sff flowgram file [REQUIRED for denoising]"/>
48 <param name="mapping_fp" type="data" format="qiimemapping" label="mapping_fp"
49 help="the mapping filepath [REQUIRED for denoising]"/>
50 </when> <!-- hist -->
51 <when value="no"/>
52 </conditional> <!-- denoise -->
53 <param name="parallel" type="boolean" truevalue="--parallel" falsevalue="" checked="false" label="parallel"
54 help="Run in parallel where available [default: False]"/>
55 </inputs>
56 <!-- Construct a parameter file
57 -->
58 <configfiles>
59 <configfile name="parameter_generated">
60 ##OTU picker parameters
61 pick_otus:otu_picking_method uclust
62 pick_otus:clustering_algorithm furthest
63 pick_otus:max_cdhit_memory 400
64 pick_otus:refseqs_fp
65 pick_otus:blast_db
66 pick_otus:similarity 0.97
67 pick_otus:max_e_value 1e-10
68 pick_otus:prefix_prefilter_length
69 pick_otus:trie_prefilter
70 pick_otus:prefix_length
71 pick_otus:suffix_length
72 pick_otus:optimal_uclust
73 pick_otus:exact_uclust
74 pick_otus:user_sort
75 pick_otus:suppress_presort_by_abundance_uclust
76 pick_otus:suppress_new_clusters
77 pick_otus:suppress_uclust_stable_sort
78 pick_otus:max_accepts
79 pick_otus:max_rejects
80 pick_otus:word_length
81 pick_otus:stepwords
82 ##Representative set picker parameters
83 pick_rep_set:rep_set_picking_method first
84 pick_rep_set:sort_by otu
85 ##Multiple sequence alignment parameters
86 align_seqs:template_fp
87 align_seqs:alignment_method pynast
88 align_seqs:pairwise_alignment_method uclust
89 align_seqs:blast_db
90 align_seqs:min_length 150
91 align_seqs:min_percent_id 75.0
92 ##Alignment filtering (prior to tree-building) parameters
93 filter_alignment:lane_mask_fp
94 filter_alignment:allowed_gap_frac 0.999999
95 filter_alignment:remove_outliers False
96 filter_alignment:threshold 3.0
97 ##Taxonomy assignment parameters
98 assign_taxonomy:id_to_taxonomy_fp
99 assign_taxonomy:reference_seqs_fp
100 assign_taxonomy:assignment_method rdp
101 assign_taxonomy:blast_db
102 assign_taxonomy:confidence 0.8
103 #assign_taxonomy:e_value 0.001
104 ##Phylogenetic tree building parameters
105 make_phylogeny:tree_method fasttree
106 make_phylogeny:root_method tree_method_default
107 ##align_seqs:template_fp
108 ##filter_alignment:lane_mask_fp
109 </configfile>
110 </configfiles>
111 <outputs>
112 <!--
113 This script will produce a set of cluster centroids (as a FASTA file)
114 and a cluster mapping file (from denoise.py if sff.txt and mapping file were provided),
115 an OTU mapping file (pick_otus.py),
116 a representative set of sequences (FASTA file from pick_rep_set.py),
117 a sequence alignment file (FASTA file from align_seqs.py),
118 taxonomy assignment file (from assign_taxonomy.py),
119 a filtered sequence alignment (from filter_alignment.py),
120 a phylogenetic tree (Newick file from make_phylogeny.py) and an OTU table (from make_otu_table.py).
121
122 wf_da2/log_20110305084135.txt
123 wf_da2/uclust_picked_otus/seqs_otus.txt
124 wf_da/uclust_picked_otus/rep_set/seqs_rep_set.fasta
125 wf_da/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/seqs_rep_set_tax_assignments.txt
126 wf_da/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/otu_table//seqs_otu_table.txt
127 wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned.fasta
128 wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned_pfiltered.fasta
129 wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/fasttree_phylogeny/seqs_rep_set.tre
130
131
132 wf_da2/log_20110305084135.txt
133 wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/fasttree_phylogeny/seqs_rep_set.tre
134 wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/fasttree_phylogeny/seqs_rep_set_phylogeny.log
135 wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned.fasta
136 wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned_pfiltered.fasta
137 wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_failures.fasta
138 wf_da2/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_log.txt
139 wf_da2/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/otu_table/seqs_otu_table.txt
140 wf_da2/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/seqs_rep_set_tax_assignments.log
141 wf_da2/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/seqs_rep_set_tax_assignments.txt
142 wf_da2/uclust_picked_otus/rep_set/seqs_rep_set.fasta
143 wf_da2/uclust_picked_otus/rep_set/seqs_rep_set.log
144 wf_da2/uclust_picked_otus/seqs_clusters.uc
145 wf_da2/uclust_picked_otus/seqs_otus.log
146 wf_da2/uclust_picked_otus/seqs_otus.txt
147
148 wf_da2/log_20110305084135.txt
149 wf_da2/uclust_picked_otus/seqs_otus.txt
150 wf_da/uclust_picked_otus/rep_set/seqs_rep_set.fasta
151 wf_da/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/seqs_rep_set_tax_assignments.txt
152 wf_da/uclust_picked_otus/rep_set/rdp_assigned_taxonomy/otu_table/seqs_otu_table.txt
153 wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned.fasta
154 wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/seqs_rep_set_aligned_pfiltered.fasta
155 wf_da/uclust_picked_otus/rep_set/pynast_aligned_seqs/fasttree_phylogeny/seqs_rep_set.tre
156 -->
157 <data format="txt" name="log" label="${tool.name} on ${on_string}: log" />
158 <data format="qiimeotu" name="seqs_otus" label="${tool.name} on ${on_string}: seqs_otus" />
159 <data format="fasta" name="seqs_rep_set" label="${tool.name} on ${on_string}: seqs_rep_set.fasta" />
160 <data format="seq.taxonomy" name="seqs_rep_set_tax_assignments" label="${tool.name} on ${on_string}: seqs_rep_set_tax_assignments" />
161 <data format="qiimeotutable" name="seqs_otu_table" label="${tool.name} on ${on_string}: seqs_otu_table" />
162 <data format="align" name="seqs_rep_set_aligned" label="${tool.name} on ${on_string}: seqs_rep_set_aligned.fasta" />
163 <data format="align" name="seqs_rep_set_aligned_pfiltered" label="${tool.name} on ${on_string}: seqs_rep_set_aligned_pfiltered.fasta" />
164 <data format="tre" name="seqs_rep_set_tre" label="${tool.name} on ${on_string}: seqs_rep_set.tre" />
165
166
167 </outputs>
168 <tests>
169 </tests>
170 <help>
171
172 The steps performed by this function are:
173 0) Optionally denoise the sequences (if sff_input_fp=True);
174 1) Pick OTUs;
175 2) Pick a representative set;
176 3) Align the representative set;
177 4) Assign taxonomy;
178 5) Filter the alignment prior to tree building - remove positions
179 which are all gaps, and specified as 0 in the lanemask
180 6) Build a phylogenetic tree;
181 7) Build an OTU table.
182
183
184 pick_otus_through_otu_table.py -i split_library_output/seqs.fna -p custom_parameters.txt -o wf_da --print_only
185
186 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
187
188 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
189
190 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
191
192 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
193
194 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
195
196 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
197
198 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
199
200
201 </help>
202 </tool>
203