changeset 0:242462fc608b draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/qiime/ commit d41cdeeec9fd0eb5612df0d5af63a979d1c9ec87
author iuc
date Mon, 10 Jul 2017 16:38:55 -0400
parents
children
files README.rst collapse_samples.xml generate_test_data.sh macros.xml test-data/collapse_samples/collapsed_first_2fields_map.txt test-data/collapse_samples/collapsed_first_2fields_table.biom test-data/collapse_samples/collapsed_sum_SampleType_map.txt test-data/collapse_samples/collapsed_sum_SampleType_table.biom test-data/collapse_samples/map.txt test-data/collapse_samples/table.biom test-data/make_otu_table/OTU_table_chimeric.biom test-data/make_otu_table/OTU_table_pynast.biom test-data/make_otu_table/chimeric_seqs.txt test-data/make_otu_table/mapping_file.txt test-data/make_otu_table/otu_map.txt test-data/make_otu_table/pynast_failures.fna test-data/make_otu_table/tax_assignments.txt
diffstat 17 files changed, 264 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/README.rst	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,7 @@
+QIIME 1.9.1 Galaxy Wrapper
+--------------------------
+
+Note: Many of these tools output html files that will not display properly
+unless sanitization is turned off in Galaxy. This can be done globally via the
+`santize_all_html` option in `galaxy.ini` or on a per tool basis using the
+`santize_whitelist_file` in `galaxy.ini`.
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/collapse_samples.xml	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,90 @@
+<tool id="qiime_collapse_samples" name="Collapse samples" version="@WRAPPER_VERSION@.0">
+    <description>Collapse samples in a BIOM table and mapping file</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <version_command>collapse_samples.py --version</version_command>
+    <command detect_errors="aggressive"><![CDATA[
+        collapse_samples.py
+            --input_biom_fp '$input_biom_fp'
+            --mapping_fp '$mapping_fp'
+            --collapse_mode '$collapse_mode'
+            $normalize
+            #set allCollapseFields = ''
+            #for $repeat in ( $collapse_fields_repeat )
+                #if $allCollapseFields == ''
+                    #set allCollapseFields += str($repeat.collapse_fields)
+                #else:
+                    #set allCollapseFields += ',' + str($repeat.collapse_fields)
+                #end if
+            #end for
+            --collapse_fields $allCollapseFields
+            --output_biom_fp '$output_biom_fp'
+            --output_mapping_fp '$output_mapping_fp'
+    ]]></command>
+    <inputs>
+        <param argument="--input_biom_fp" type="data" format="biom1" label="Input biom table" help="The biom table containing the samples to be collapsed" />
+        <param argument="--mapping_fp" type="data" format="tabular" label="Input mapping file" help="The sample metadata mapping file" />
+        <param argument="--collapse_mode" type="select" label="Collapse mode to use" help="The mechanism for collapsing counts within groups">
+            <option value="sum" selected="true">sum</option>
+            <option value="mean">mean</option>
+            <option value="random">random</option>
+            <option value="median">median</option>
+            <option value="first">first</option>
+        </param>
+        <param argument="--normalize" type="boolean" label="Do you want to normalize observation counts to relative abundances ?" truevalue="--normalize" falsevalue="" checked="False" help="When this option is used the counts within each sample sum to 1.0" />
+        <repeat name="collapse_fields_repeat" title="New field to collapse data on" help="You must specify at least one field to collapse data on" min="1" >
+            <param argument="--collapse_fields" type="text" label="Name of the field" value="" help="Enter the name of one of the column of your mapping file" />
+        </repeat>
+    </inputs>
+    <outputs>
+        <data name="output_biom_fp" format="biom1" label="${tool.name} on ${on_string}: Collapsed biom table"/>
+        <data name="output_mapping_fp" format="tabular" label="${tool.name} on ${on_string}: Collapsed mapping file"/>
+    </outputs>
+    <tests>
+        <!-- Qiime collapse_samples.py generates a binary file (Collapsed biom file) that can't be directly compared to the sample biom file using diff -->
+        <!-- The following tests on output biom files are then based on a comparison of file sizes with a maximum delta of 0 bytes instead of the classic diff-based comparison -->
+        <test>
+            <param name="input_biom_fp" value="collapse_samples/table.biom" />
+            <param name="mapping_fp" value="collapse_samples/map.txt" />
+            <param name="collapse_mode" value="sum" />
+            <repeat name="collapse_fields_repeat">
+                <param name="collapse_fields" value="SampleType" />
+            </repeat>
+            <output name="output_biom_fp" file="collapse_samples/collapsed_sum_SampleType_table.biom" compare="sim_size"/>
+            <output name="output_mapping_fp" file="collapse_samples/collapsed_sum_SampleType_map.txt" ftype="tabular" />
+        </test>
+        <test>
+            <param name="input_biom_fp" value="collapse_samples/table.biom" />
+            <param name="mapping_fp" value="collapse_samples/map.txt" />
+            <param name="collapse_mode" value="first" />
+            <param name="normalize" value="True" />
+            <repeat name="collapse_fields_repeat">
+                <param name="collapse_fields" value="subject" />
+            </repeat>
+            <repeat name="collapse_fields_repeat">
+                <param name="collapse_fields" value="year" />
+            </repeat>
+            <output name="output_biom_fp" file="collapse_samples/collapsed_first_2fields_table.biom" compare="sim_size"/>
+            <output name="output_mapping_fp" file="collapse_samples/collapsed_first_2fields_map.txt" ftype="tabular" />
+        </test>
+    </tests>
+    <help><![CDATA[
+**What it does**
+
+The script `collapse_samples.py <http://qiime.org/scripts/collapse_samples.html>`_ collapse samples in a BIOM table and mapping file.
+
+The values in the BIOM table are collapsed in one of several different ways (see possible values of the --collapse_mode parameter).
+
+The values in the mapping file are collapsed by grouping the values if they differ for the grouped samples, and by providing the single value if they don’t differ for the grouped samples.
+
+The output of `collapse_samples.py <http://qiime.org/scripts/collapse_samples.html>`_ are a collapsed `biom file <http://biom-format.org/>`_ and a collapsed mapping file.
+
+More information about this tool is available on
+`QIIME documentation <http://qiime.org/scripts/collapse_samples.html>`_.
+    ]]></help>
+    <citations>
+        <expand macro="citations"/>
+    </citations>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/generate_test_data.sh	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,50 @@
+#!/usr/bin/env bash
+
+# make_otu_table
+make_otu_table.py \
+    --otu_map_fp 'test-data/make_otu_table/otu_map.txt' \
+    --taxonomy 'test-data/make_otu_table/tax_assignments.txt' \
+    --exclude_otus_fp 'test-data/make_otu_table/chimeric_seqs.txt' \
+    --mapping_fp 'test-data/make_otu_table/mapping_file.txt' \
+    --output_biom_fp 'test-data/make_otu_table/OTU_table_chimeric.biom'
+biom convert \
+    -i 'test-data/make_otu_table/OTU_table_chimeric.biom' \
+    -o 'test-data/make_otu_table/OTU_table_chimeric.biom' \
+    --to-json
+
+make_otu_table.py \
+    --otu_map_fp 'test-data/make_otu_table/otu_map.txt' \
+    --taxonomy 'test-data/make_otu_table/tax_assignments.txt' \
+    --exclude_otus_fp 'test-data/make_otu_table/pynast_failures.fna' \
+    --mapping_fp 'test-data/make_otu_table/mapping_file.txt' \
+    --output_biom_fp 'test-data/make_otu_table/OTU_table_pynast.biom'
+biom convert \
+    -i 'test-data/make_otu_table/OTU_table_pynast.biom' \
+    -o 'test-data/make_otu_table/OTU_table_pynast.biom' \
+    --to-json
+
+# collapse_samples
+collapse_samples.py \
+    --input_biom_fp 'test-data/collapse_samples/table.biom' \
+    --mapping_fp 'test-data/collapse_samples/map.txt' \
+    --collapse_mode 'sum' \
+    --collapse_fields 'SampleType' \
+    --output_biom_fp 'test-data/collapse_samples/collapsed_sum_SampleType_table.biom' \
+    --output_mapping_fp 'test-data/collapse_samples/collapsed_sum_SampleType_map.txt'
+biom convert \
+    -i 'test-data/collapse_samples/collapsed_sum_SampleType_table.biom' \
+    -o 'test-data/collapse_samples/collapsed_sum_SampleType_table.biom' \
+    --to-json
+    
+collapse_samples.py \
+    --input_biom_fp 'test-data/collapse_samples/table.biom' \
+    --mapping_fp 'test-data/collapse_samples/map.txt' \
+    --collapse_mode 'first' \
+    --collapse_fields 'subject','year' \
+    --normalize \
+    --output_biom_fp 'test-data/collapse_samples/collapsed_first_2fields_table.biom' \
+    --output_mapping_fp 'test-data/collapse_samples/collapsed_first_2fields_map.txt'
+biom convert \
+    -i 'test-data/collapse_samples/collapsed_first_2fields_table.biom' \
+    -o 'test-data/collapse_samples/collapsed_first_2fields_table.biom' \
+    --to-json
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,70 @@
+<?xml version="1.0" ?>
+<macros>
+    <token name="@WRAPPER_VERSION@">1.9.1</token>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@WRAPPER_VERSION@">qiime</requirement>
+            <yield/>
+        </requirements>
+    </xml>
+    <xml name="citations">
+        <citation type="doi">10.1038/nmeth.f.303</citation>
+    </xml>
+    <xml name="pick_otus_reference_source">
+        <conditional name="references">
+            <param name="source_selector" type="select" label="Use reference sequences from">
+                <option value="cached">Local cache</option>
+                <option value="history">History</option>
+            </param>
+            <when value="cached">
+                <param argument="--refseqs_fp" label="Reference sequences" type="select">
+                    <options from_data_table="qiime_rep_set"/>
+                </param>
+            </when>
+            <when value="history">
+                <param argument="--refseqs_fp" type="data" format="fasta" label="Reference sequences to search against"/>
+            </when>
+        </conditional>
+    </xml>
+    <xml name="assign_taxonomy_reference_source">
+        <conditional name="references">
+            <param name="source_selector" type="select" label="Select a reference sequence file from">
+                <option value="cached">The local cache</option>
+                <option value="history">The active history</option>
+            </param>
+            <when value="cached">
+                <param argument="--reference_seqs_fp" label="Reference sequences either used to generate a blast database (Blast) or used as training sequences for the selected classifier (RDP, Mothur)" type="select">
+                    <options from_data_table="qiime_rep_set"/>
+                </param>
+            </when>
+            <when value="history">
+                <param argument="--reference_seqs_fp" type="data" format="fasta" label="Reference sequences to search against"/>
+            </when>
+        </conditional>
+    </xml>
+    <xml name="pick_otus_similarity">
+        <param argument="--similarity" type="float" value="0.97" label="Sequence similarity threshold"/>
+    </xml>
+    <xml name="pick_otus_denovo_otu_id_prefix">
+        <param argument="--denovo_otu_id_prefix" type="text" value="denovo" label="OTU identifier prefix for the de novo OTU pickers"/>
+    </xml>
+    <xml name="pick_otus_enable_rev_strand_match">
+        <param argument="--enable_rev_strand_match" type="boolean" truevalue="--enable_rev_strand_match" falsevalue="" checked="false" label="Enable reverse strand matching?" help="Will double the amount of memory used"/>
+    </xml>
+    <xml name="pick_otus_suppress_presort_by_abundance_uclust">
+        <param argument="--suppress_presort_by_abundance_uclust" type="boolean" truevalue="--suppress_presort_by_abundance_uclust" falsevalue="" checked="false" label="Suppress presorting of sequences by abundance?"/>
+    </xml>
+    <xml name="pick_otus_max">
+        <param argument="--max_accepts" type="integer" value="1" label="Max_accepts value"/>
+        <param argument="--max_rejects" type="integer" value="8" label="Max_rejects value"/>
+    </xml>
+    <xml name="pick_otus_stepwords">
+        <param argument="--stepwords" type="integer" value="8" label="Stepwords value"/>
+    </xml>
+    <xml name="pick_otus_word_length">
+        <param argument="--word_length" type="integer" value="8" label="Word length value"/>
+    </xml>
+    <xml name="pick_otus_suppress_prefilter_exact_match">
+        <param argument="--suppress_prefilter_exact_match" type="boolean" truevalue="--suppress_prefilter_exact_match" falsevalue="" checked="false" label="Don't collapse exact matches before calling?"/>
+    </xml>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/collapse_samples/collapsed_first_2fields_map.txt	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,3 @@
+#SampleID	original-sample-ids	BarcodeSequence	LinkerPrimerSequence	SampleType	month	day	replicate-group	days_since_epoch	Description
+1.2008	(f1, f2, f5, f6, p1, not16S.1)	(ACACTGTTCATG, ACCAGACGATGC, ACCAGACGATGC, ACCAGACGATGC, AACGCACGCTAG, ATACTATTGCGC)	GTGCCAGCMGCCGCGGTAA	(feces, feces, feces, feces, L_palm, Other)	10	(22, 23, 23, 23, 21, 22)	(1, 1, 2, 2, 2, 3)	(14174, 14175, 14175, 14175, 14173, 14174)	(fecal1, fecal2, derived from f3 with some changes to sequences to add one new otu, derived from f4 with some changes to sequences to add one new otu, palm1, contains one randomly generated sequence, randomly generated sequence plus some variants, these should not map to 16S)
+2.2008	(f3, f4, p2, t1, t2)	(ACCAGACGATGC, ACCAGACGATGC, ACACTGTTCATG, AGTGAGAGAAGC, ATACTATTGCGC)	GTGCCAGCMGCCGCGGTAA	(feces, feces, L_palm, Tongue, Tongue)	10	(23, 23, 22, 21, 22)	(1, 1, 2, 2, 2)	(14175, 14175, 14174, 14173, 14174)	(identical sequences to fecal2, all sequences identical, map to GG 295053 at 97 percent id, palm2, tongue1, contains one randomly generated sequence, tongue2)
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/collapse_samples/collapsed_first_2fields_table.biom	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,1 @@
+{"id": "No Table ID","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","matrix_type": "sparse","generated_by": "BIOM-Format 2.1.5","date": "2017-05-19T14:27:09.894251","type": "OTU table","matrix_element_type": "float","shape": [14, 2],"data": [[0,0,0.81818181818181823],[0,1,0.90909090909090906],[2,1,0.045454545454545456],[13,0,0.18181818181818182],[13,1,0.045454545454545456]],"rows": [{"id": "295053", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "42684", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria"]}},{"id": "None11", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None10", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None7", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None6", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None5", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None4", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None3", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None2", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None1", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "879972", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None9", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None8", "metadata": {"taxonomy": ["k__Bacteria"]}}],"columns": [{"id": "2.2008", "metadata": {"collapsed_ids": ["f3", "f4", "p2", "t1", "t2"]}},{"id": "1.2008", "metadata": {"collapsed_ids": ["f2", "f1", "p1", "not16S.1"]}}]}
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/collapse_samples/collapsed_sum_SampleType_map.txt	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,5 @@
+#SampleID	original-sample-ids	BarcodeSequence	LinkerPrimerSequence	year	month	day	subject	replicate-group	days_since_epoch	Description
+L_palm	(p1, p2)	(AACGCACGCTAG, ACACTGTTCATG)	GTGCCAGCMGCCGCGGTAA	2008	10	(21, 22)	(1, 2)	2	(14173, 14174)	(palm1, contains one randomly generated sequence, palm2)
+Other	not16S.1	ATACTATTGCGC	GTGCCAGCMGCCGCGGTAA	2008	10	22	1	3	14174	randomly generated sequence plus some variants, these should not map to 16S
+Tongue	(t1, t2)	(AGTGAGAGAAGC, ATACTATTGCGC)	GTGCCAGCMGCCGCGGTAA	2008	10	(21, 22)	2	2	(14173, 14174)	(tongue1, contains one randomly generated sequence, tongue2)
+feces	(f1, f2, f3, f4, f5, f6)	(ACACTGTTCATG, ACCAGACGATGC, ACCAGACGATGC, ACCAGACGATGC, ACCAGACGATGC, ACCAGACGATGC)	GTGCCAGCMGCCGCGGTAA	2008	10	(22, 23, 23, 23, 23, 23)	(1, 1, 2, 2, 1, 1)	(1, 1, 1, 1, 2, 2)	(14174, 14175, 14175, 14175, 14175, 14175)	(fecal1, fecal2, identical sequences to fecal2, all sequences identical, map to GG 295053 at 97 percent id, derived from f3 with some changes to sequences to add one new otu, derived from f4 with some changes to sequences to add one new otu)
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/collapse_samples/collapsed_sum_SampleType_table.biom	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,1 @@
+{"id": "No Table ID","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","matrix_type": "sparse","generated_by": "BIOM-Format 2.1.5","date": "2017-05-19T14:27:05.204426","type": "OTU table","matrix_element_type": "float","shape": [14, 4],"data": [[0,1,78.0],[0,3,4.0],[1,3,1.0],[2,1,1.0],[2,3,2.0],[3,0,1.0],[4,3,1.0],[5,2,20.0],[6,3,1.0],[7,3,2.0],[8,0,5.0],[8,3,1.0],[9,2,2.0],[10,3,1.0],[11,0,5.0],[11,3,29.0],[12,0,34.0],[12,3,3.0],[13,1,9.0]],"rows": [{"id": "295053", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "42684", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria"]}},{"id": "None11", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None10", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None7", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None6", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None5", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None4", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None3", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None2", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None1", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "879972", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None9", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None8", "metadata": {"taxonomy": ["k__Bacteria"]}}],"columns": [{"id": "Tongue", "metadata": {"collapsed_ids": ["t1", "t2"]}},{"id": "feces", "metadata": {"collapsed_ids": ["f2", "f1", "f3", "f4"]}},{"id": "Other", "metadata": {"collapsed_ids": ["not16S.1"]}},{"id": "L_palm", "metadata": {"collapsed_ids": ["p2", "p1"]}}]}
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/collapse_samples/map.txt	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,12 @@
+#SampleID	BarcodeSequence	LinkerPrimerSequence	SampleType	year	month	day	subject	replicate-group	days_since_epoch	Description
+f1	ACACTGTTCATG	GTGCCAGCMGCCGCGGTAA	feces	2008	10	22	1	1	14174	fecal1
+f2	ACCAGACGATGC	GTGCCAGCMGCCGCGGTAA	feces	2008	10	23	1	1	14175	fecal2
+f3	ACCAGACGATGC	GTGCCAGCMGCCGCGGTAA	feces	2008	10	23	2	1	14175	identical sequences to fecal2
+f4	ACCAGACGATGC	GTGCCAGCMGCCGCGGTAA	feces	2008	10	23	2	1	14175	all sequences identical, map to GG 295053 at 97 percent id
+f5	ACCAGACGATGC	GTGCCAGCMGCCGCGGTAA	feces	2008	10	23	1	2	14175	derived from f3 with some changes to sequences to add one new otu
+f6	ACCAGACGATGC	GTGCCAGCMGCCGCGGTAA	feces	2008	10	23	1	2	14175	derived from f4 with some changes to sequences to add one new otu
+p1	AACGCACGCTAG	GTGCCAGCMGCCGCGGTAA	L_palm	2008	10	21	1	2	14173	palm1, contains one randomly generated sequence
+p2	ACACTGTTCATG	GTGCCAGCMGCCGCGGTAA	L_palm	2008	10	22	2	2	14174	palm2
+t1	AGTGAGAGAAGC	GTGCCAGCMGCCGCGGTAA	Tongue	2008	10	21	2	2	14173	tongue1, contains one randomly generated sequence
+t2	ATACTATTGCGC	GTGCCAGCMGCCGCGGTAA	Tongue	2008	10	22	2	2	14174	tongue2
+not16S.1	ATACTATTGCGC	GTGCCAGCMGCCGCGGTAA	Other	2008	10	22	1	3	14174	randomly generated sequence plus some variants, these should not map to 16S
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/collapse_samples/table.biom	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,1 @@
+{"id": "None","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","type": "OTU table","generated_by": "QIIME 1.6.0-dev","date": "2013-02-09T09:30:11.550590","matrix_type": "sparse","matrix_element_type": "int","shape": [14, 9],"data": [[0,0,20],[0,1,18],[0,2,18],[0,3,22],[0,4,4],[1,4,1],[2,0,1],[2,4,1],[2,5,1],[3,6,1],[4,4,1],[5,7,20],[6,4,1],[7,4,1],[7,5,1],[8,4,1],[8,6,2],[8,8,3],[9,7,2],[10,5,1],[11,4,9],[11,5,20],[11,6,1],[11,8,4],[12,4,3],[12,6,19],[12,8,15],[13,0,1],[13,1,4],[13,2,4]],"rows": [{"id": "295053", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "42684", "metadata": {"taxonomy": ["k__Bacteria", "p__Proteobacteria"]}},{"id": "None11", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None10", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None7", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None6", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None5", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None4", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None3", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None2", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None1", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "879972", "metadata": {"taxonomy": ["k__Bacteria"]}},{"id": "None9", "metadata": {"taxonomy": ["Unclassified"]}},{"id": "None8", "metadata": {"taxonomy": ["k__Bacteria"]}}],"columns": [{"id": "f2", "metadata": null},{"id": "f1", "metadata": null},{"id": "f3", "metadata": null},{"id": "f4", "metadata": null},{"id": "p2", "metadata": null},{"id": "p1", "metadata": null},{"id": "t1", "metadata": null},{"id": "not16S.1", "metadata": null},{"id": "t2", "metadata": null}]}
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/make_otu_table/OTU_table_chimeric.biom	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,1 @@
+{"id": "No Table ID","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","matrix_type": "sparse","generated_by": "BIOM-Format 2.1.5","date": "2017-05-19T14:25:37.660678","type": "OTU table","matrix_element_type": "float","shape": [2, 2],"data": [[0,0,1.0],[1,1,3.0]],"rows": [{"id": "1", "metadata": {"taxonomy": ["A", "B", "C", "D"]}},{"id": "x", "metadata": {"taxonomy": ["A", "B", "C"]}}],"columns": [{"id": "ABC", "metadata": {"LinkerPrimerSequence": "AAAAAA", "BarcodeSequence": "ATGC", "Description": "First Sample"}},{"id": "GHI", "metadata": {"LinkerPrimerSequence": "AAAAAA", "BarcodeSequence": "CATG", "Description": "Third Sample"}}]}
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/make_otu_table/OTU_table_pynast.biom	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,1 @@
+{"id": "No Table ID","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","matrix_type": "sparse","generated_by": "BIOM-Format 2.1.5","date": "2017-05-19T14:26:19.586158","type": "OTU table","matrix_element_type": "float","shape": [2, 2],"data": [[0,0,1.0],[1,1,3.0]],"rows": [{"id": "1", "metadata": {"taxonomy": ["A", "B", "C", "D"]}},{"id": "x", "metadata": {"taxonomy": ["A", "B", "C"]}}],"columns": [{"id": "ABC", "metadata": {"LinkerPrimerSequence": "AAAAAA", "BarcodeSequence": "ATGC", "Description": "First Sample"}},{"id": "GHI", "metadata": {"LinkerPrimerSequence": "AAAAAA", "BarcodeSequence": "CATG", "Description": "Third Sample"}}]}
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/make_otu_table/chimeric_seqs.txt	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,3 @@
+0 some comment
+42 not a real otu id
+z
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/make_otu_table/mapping_file.txt	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,5 @@
+#SampleID	BarcodeSequence	LinkerPrimerSequence	Description
+ABC	ATGC	AAAAAA	First Sample
+XYZ	TGCA	AAAAAA	Fourth Sample
+GHI	CATG	AAAAAA	Third Sample
+DEF	GCAT	AAAAAA	Second Sample
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/make_otu_table/otu_map.txt	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,4 @@
+0	ABC_0	DEF_1
+1	ABC_1
+x	GHI_2	GHI_3	GHI_77
+z	DEF_3	XYZ_1
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/make_otu_table/pynast_failures.fna	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,6 @@
+>0 something
+ACCG
+>42 some comment
+CCGGTT
+>z
+CCGG
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/make_otu_table/tax_assignments.txt	Mon Jul 10 16:38:55 2017 -0400
@@ -0,0 +1,4 @@
+0	A;B;C
+1	A;B;C;D
+x	A;B;C
+z	A;B
\ No newline at end of file