Repository 'picrust_compare_biom'
hg clone https://toolshed.g2.bx.psu.edu/repos/iuc/picrust_compare_biom

Changeset 0:43244ad9e7ef (2018-01-20)
Next changeset 1:9c0daedfbb0f (2018-01-20)
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picrust commit 95e0878f4cbd9caadffae7b9bcff4c1795f4c739
added:
README.md
compare_biom.xml
macros.xml
test-data/16S_13_5_precalculated_minimal.tab
test-data/categorize_biom.hdf5
test-data/closed_picked_otus.biom
test-data/closed_picked_otus.tab
test-data/cog_predicted_metagenomes.L2.biom
test-data/custom_trait_table.tab
test-data/expected.biom
test-data/expected_ra.biom
test-data/normalized_otus.biom
test-data/normalized_otus.classic
test-data/observation_table.biom
test-data/observed.biom
test-data/observed_ra.biom
test-data/otu_table_for_custom_trait_table.biom
test-data/predicted_metagenomes.L3.biom
test-data/tempout.table
tool-data/picrust_precalculated.loc.sample
tool_data_table_conf.xml.sample
b
diff -r 000000000000 -r 43244ad9e7ef README.md
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/README.md Sat Jan 20 03:31:34 2018 -0500
[
@@ -0,0 +1,34 @@
+## PICRUSt Galaxy Wrapper
+
+This page is for anyone interested in installing [PICRUSt](http://picrust.github.io/picrust/) in a [galaxy instance](https://galaxyproject.org/).The below descriptions should clarify the most confusing part of the installation.
+
+The most important steps are that you need to go to the Galaxy IUC tool shed and install the 4 wrapper scripts there along with PICRUSt itself. If you install PICRUSt through this interface the precalculated files will not also be installed, you will need to download them separately (see below).
+
+Once these scripts are installed sections like the one below should be added to *galaxy/config/shed_tool_data_table_conf.xml* automatically. They will point to different *picrust_precalculated.loc* files; you only need to edit one of them since all of these files will be checked.
+
+```
+<tables>
+    <table name="picrust_precalculated" comment_char="#">
+        <columns>name, value</columns>
+        <file path="tool-data/picrust_precalculated.loc" />
+    </table>
+</tables>
+```
+
+You should download the precalculated files from http://kronos.pharmacology.dal.ca/public_files/picrust/picrust_precalculated_v1.1.1/13_5/.
+
+Most users only use the below two files (however you can also download the precalculated COG and RFAM abundances):
+```
+16S_13_5_precalculated.tab.gz
+ko_13_5_precalculated.tab.gz
+```
+
+Once you download these files we just need to point to them in a *picrust_precalculated.loc* file.
+
+An example file is shown below. Note that tabs should separate the two columns and that in the below command "16S 13_5" (separated by one space) is one example dbname.
+
+```
+<dbname>       <file_base>
+16S 13_5    /path/to/16S_13_5_precalculated.tab.gz
+ko 13_5    /path/to/ko_13_5_precalculated.tab.gz
+```
b
diff -r 000000000000 -r 43244ad9e7ef compare_biom.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/compare_biom.xml Sat Jan 20 03:31:34 2018 -0500
[
@@ -0,0 +1,130 @@
+<tool id="picrust_compare_biom" name="Compare BIOM tables" version="@WRAPPER_VERSION@.0">
+    <description>Compare the accuracy of biom files (expected and observed) either by observations (default) or by samples.</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <expand macro="version_command"/>
+    <command detect_errors="exit_code"><![CDATA[
+        compare_biom.py
+            -e '$expected'
+            -o '$outfile'
+            $not_relative_abundance_scores
+            $advanced.normalize
+            $advanced.limit_to_observed_observations
+            $advanced.limit_to_expected_observations
+            $advanced.shuffle_samples
+
+            '$observed'
+    ]]></command>
+    <inputs>
+        <param name="observed" type="data" format="biom1" label="Observed table" help="The observed table of either relative abundance or real counts"/>
+        <param name="expected" type="data" format="biom1" label="Expected table" help="The expected table of either relative abundance or real counts"/>
+        <param argument="not_relative_abundance_scores" type="boolean" truevalue="--not_relative_abundance_scores" falsevalue="" checked="false" label="Real counts instead of relative abundances?"
+               help="Round numbers (instead of taking ceil() which is used for RA) before calculating TP,FP,FN,TN"/>
+        <section name="advanced" title="Advanced parameters" expanded="false">
+            <param argument="compare_observations" type="boolean" truevalue="--compare_observations" falsevalue="" checked="false" label="Compare observations"
+                help="Calculate accuracy values by comparing between observations (instead of between samples)."/>
+            <param argument="normalize" type="boolean" truevalue="--normalize" falsevalue="" checked="false" label="Normalize?"
+                help="Convert both expected and observed tables to relative abundances (instead of observations)."/>
+            <param argument="limit_to_observed_observations" type="boolean" truevalue="--limit_to_observed_observations" falsevalue="" checked="false" label="Limit to observed observations?"
+                help="Ignore observations that are not in the observed table."/>
+            <param argument="limit_to_expected_observations" type="boolean" truevalue="--limit_to_expected_observations" falsevalue="" checked="false" label="Limit to expected observations?"
+                help="Ignore observations that are not in the expected table."/>
+            <param argument="shuffle_samples" type="boolean" truevalue="--shuffle_samples" falsevalue="" checked="false" label="Shuffle samples?"
+                help="Shuffle samples ids randomly before measuring accuracy."/>
+        </section>
+    </inputs>
+    <outputs>
+        <data format="tabular" name="outfile" label="${tool.name} on ${on_string} Comparison summary"/>
+    </outputs>
+    <tests>
+        <test><!-- relative abundance test -->
+            <param name="observed" value="observed_ra.biom" ftype="biom1"/>
+            <param name="expected" value="expected_ra.biom" ftype="biom1"/>
+            <output name="outfile" ftype="tabular">
+                <assert_contents>
+                    <has_text_matching expression="file\tlabel\taccuracy"/>
+                    <has_text text="sample1"/>
+                    <has_text text="sample3"/>
+                    <has_text text="sample2"/>
+                </assert_contents>
+            </output>
+        </test>
+        <test><!-- real counts test -->
+            <param name="observed" value="observed.biom" ftype="biom1"/>
+            <param name="expected" value="expected.biom" ftype="biom1"/>
+            <param name="not_relative_abundance_scores" value="--not_relative_abundance_scores"/>
+            <output name="outfile" ftype="tabular">
+                <assert_contents>
+                    <has_text_matching expression="file\tlabel\taccuracy"/>
+                    <has_text text="sample1"/>
+                    <has_text text="sample3"/>
+                    <has_text text="sample2"/>
+                </assert_contents>
+            </output>
+        </test>
+        <test><!-- all other switches test -->
+            <param name="observed" value="observed.biom" ftype="biom1"/>
+            <param name="expected" value="expected.biom" ftype="biom1"/>
+            <param name="not_relative_abundance_scores" value="--not_relative_abundance_scores"/>
+            <param name="compare_observations" value="--compare_observations"/>
+            <param name="normalize" value="--normalize"/>
+            <param name="limit_to_observed_observations" value="--limit_to_observed_observations"/>
+            <param name="shuffle_samples" value="--shuffle_samples"/>
+            <output name="outfile" ftype="tabular">
+                <assert_contents>
+                    <has_text_matching expression="file\tlabel\taccuracy"/>
+                    <has_text text="sample1"/>
+                    <has_text text="sample3"/>
+                    <has_text text="sample2"/>
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help>
+<![CDATA[
+@PICRUST_OVERVIEW@
+
+**Command Documentation**
+
+Compare an observed table to an expected table using either relative abundance or real counts.
+
+**Input files:**
+
+**Observed table:** A table of observed relative abundances or real counts in .biom format.
+
+**Expected table:** The expected table of relative abundances or real counts in .biom format.
+
+**Output file:** Tab delimited file with various accuracy metrics.
+
+**Optional Parameters:**
+
+*compare observations*
+
+    Calculate accuracy values by comparing between observations (instead of between samples) [default: False]
+
+*normalize*
+
+    Convert both expected and observed tables to relative abundances (instead of observations) [default: False]
+
+*limit to expected observations*
+
+    Ignore observations that are not in the expected table[default: False]
+
+*limit to observed observations*
+
+    Ignore observations that are not in the observed table[default: False]
+
+*shuffle samples*
+
+    Shuffle samples ids randomly before measuring accuracy[default: False]
+
+*not relative abundance scores*
+
+    Round numbers (instead of taking ceil() which is used for RA) before calculating TP,FP,FN,TN [default: False]
+
+]]>
+    </help>
+    <expand macro="citations"/>
+</tool>
b
diff -r 000000000000 -r 43244ad9e7ef macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml Sat Jan 20 03:31:34 2018 -0500
[
@@ -0,0 +1,97 @@
+<macros>
+    <token name="@WRAPPER_VERSION@">1.1.1</token>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="1.1.1">picrust</requirement>
+        </requirements>
+    </xml>
+
+    <xml name="version_command">
+        <version_command>predict_metagenomes.py --version | cut -d" " -f3 </version_command>
+    </xml>
+
+    <xml name="otu-reference-precalculated">
+        <!-- selection of "gg" picrust parameter reference data file -->
+        <conditional name="gg">
+           <param name="source" type="select" label="Select precalculated file from" help="">
+               <option value="ref">Cached Reference</option>
+               <option value="hist">History</option>
+           </param>
+           <when value="ref">
+               <param name="precalc" type="select" label="Precalculated input marker gene copy number predictions on per-otu basis">
+                   <options from_data_table="picrust_precalculated"/>
+               </param>
+           </when>
+           <when value="hist">
+               <param name="precalc" type="data" format="tabular" label="Precalculated input marker gene copy number predictions on per-otu basis"
+                      help="files may be downloaded from PICRUSt website (see tool help below)" />
+           </when>
+       </conditional>
+    </xml>
+
+    <xml name="biom_format_select">
+        <param name="output_type" type="select" label="Format of the output BIOM file">
+            <option value="hdf5" selected="true">HDF5</option>
+            <option value="json">JSON</option>
+            <option value="tsv">Classic (tab-separated text)</option>
+        </param>
+    </xml>
+
+    <xml name="biom_format_select_no_json">
+        <param name="output_type" type="select" label="Format of the output BIOM file">
+            <option value="hdf5" selected="true">HDF5</option>
+            <option value="tsv">Classic (tab-separated text)</option>
+        </param>
+    </xml>
+
+    <xml name="biom_output">
+        <data name="out_biom" format="tabular" label="${tool.name} on ${on_string}: Normalized OTUs">
+            <change_format>
+                <when input="output_type" value="json" format="biom1"/>
+                <when input="output_type" value="tsv" format="tabular"/>
+                <when input="output_type" value="hdf5" format="h5"/>
+            </change_format>
+        </data>
+    </xml>
+
+    <token name="@OUTPUT_CONVERSION_COMMANDS@"><![CDATA[
+        #if $output_type == "hdf5":
+            && mv tempbiom '$out_biom'
+        #elif $output_type == "tsv":
+            && biom convert -i tempbiom -o '$out_biom' --to-tsv
+        #else:
+            && biom convert -i tempbiom -o '$out_biom' --to-json
+        #end if
+    ]]></token>
+
+    <token name="@PICRUST_OVERVIEW@">
+<![CDATA[
+**PICRUSt: Phylogenetic Investigation of Communities by Reconstruction of Unobserved States**
+
+The PICRUSt project aims to support prediction of the unobserved character states in a community of
+organisms from phylogenetic information about the organisms in that community. The primary application
+is to predict gene family abundance (e.g. the metagenome) in environmental DNA samples for which only
+marker gene (e.g. 16S rRNA gene) data are available. This is an open source, international, collaborative
+bioinformatics project developed in the Huttenhower, Beiko, Langille, Vega Thurber, Knight and Caporaso labs.
+
+For more information please visit:
+
+- PICRUSt Documentation: https://picrust.github.io/picrust/
+- PICRUSt GitHub: http://picrust.github.com/
+- PICRUSt Support: https://groups.google.com/d/forum/picrust-users
+
+**Reference Data**
+
+Precalculated files: http://kronos.pharmacology.dal.ca/public_files/picrust/picrust_precalculated_v1.1.1/13_5/
+
+]]>
+    </token>
+
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1038/nbt.2676</citation>
+            <yield/>
+        </citations>
+    </xml>
+
+</macros>
b
diff -r 000000000000 -r 43244ad9e7ef test-data/16S_13_5_precalculated_minimal.tab
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/16S_13_5_precalculated_minimal.tab Sat Jan 20 03:31:34 2018 -0500
b
@@ -0,0 +1,5 @@
+#OTU_IDs 16S_rRNA_Count
+290426 10.0
+265267 5.0
+248563 4.0
+61102 4.0
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/categorize_biom.hdf5
b
Binary file test-data/categorize_biom.hdf5 has changed
b
diff -r 000000000000 -r 43244ad9e7ef test-data/closed_picked_otus.biom
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/closed_picked_otus.biom Sat Jan 20 03:31:34 2018 -0500
[
@@ -0,0 +1,1 @@
+{"id": "None","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","type": "OTU table","generated_by": "BIOM-Format 1.1.2-dev","date": "2013-08-20T16:13:50.386985","matrix_type": "sparse","matrix_element_type": "float","shape": [4, 2],"data": [[0,0,1.0],[1,0,2.0],[2,1,2.0],[3,0,1.0],[3,1,1.0]],"rows": [{"id": "290426", "metadata": null},{"id": "265267", "metadata": null},{"id": "248563", "metadata": null},{"id": "61102", "metadata": null}],"columns": [{"id": "sample1", "metadata": null},{"id": "sample2", "metadata": null}]}
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/closed_picked_otus.tab
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/closed_picked_otus.tab Sat Jan 20 03:31:34 2018 -0500
b
@@ -0,0 +1,6 @@
+# Constructed from biom file
+#OTU ID sample1 sample2
+290426 1 0
+265267 2 0
+248563 0 2
+61102 1 1
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/cog_predicted_metagenomes.L2.biom
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/cog_predicted_metagenomes.L2.biom Sat Jan 20 03:31:34 2018 -0500
[
@@ -0,0 +1,1 @@
+{"id": "None","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","type": "Gene table","generated_by": "picrust 1.0.0-dev - categorize_by_function","date": "2013-10-10T12:55:15.589322","matrix_type": "sparse","matrix_element_type": "float","shape": [25, 2],"data": [[1,0,2.0],[1,1,2.0],[2,0,275.0],[2,1,128.0],[3,0,74.0],[3,1,18.0],[4,0,577.0],[4,1,233.0],[5,0,231.0],[5,1,50.0],[6,0,540.0],[6,1,144.0],[7,0,218.0],[7,1,93.0],[8,0,196.0],[8,1,96.0],[9,0,473.0],[9,1,142.0],[10,0,566.0],[10,1,216.0],[11,0,368.0],[11,1,110.0],[12,0,353.0],[12,1,121.0],[13,0,103.0],[13,1,72.0],[14,0,213.0],[14,1,73.0],[15,0,323.0],[15,1,111.0],[16,0,100.0],[16,1,55.0],[17,0,747.0],[17,1,251.0],[18,0,500.0],[18,1,95.0],[19,0,326.0],[19,1,166.0],[20,0,134.0],[20,1,58.0],[21,0,154.0],[21,1,34.0]],"rows": [{"id": "[A] RNA processing and modification", "metadata": {"COG_Category": ["INFORMATION STORAGE AND PROCESSING", "[A] RNA processing and modification"]}},{"id": "[B] Chromatin structure and dynamics", "metadata": {"COG_Category": ["INFORMATION STORAGE AND PROCESSING", "[B] Chromatin structure and dynamics"]}},{"id": "[C] Energy production and conversion", "metadata": {"COG_Category": ["METABOLISM", "[C] Energy production and conversion"]}},{"id": "[D] Cell cycle control, cell division, chromosome partitioning", "metadata": {"COG_Category": ["CELLULAR PROCESSES AND SIGNALING", "[D] Cell cycle control, cell division, chromosome partitioning"]}},{"id": "[E] Amino acid transport and metabolism", "metadata": {"COG_Category": ["METABOLISM", "[E] Amino acid transport and metabolism"]}},{"id": "[F] Nucleotide transport and metabolism", "metadata": {"COG_Category": ["METABOLISM", "[F] Nucleotide transport and metabolism"]}},{"id": "[G] Carbohydrate transport and metabolism", "metadata": {"COG_Category": ["METABOLISM", "[G] Carbohydrate transport and metabolism"]}},{"id": "[H] Coenzyme transport and metabolism", "metadata": {"COG_Category": ["METABOLISM", "[H] Coenzyme transport and metabolism"]}},{"id": "[I] Lipid transport and metabolism", "metadata": {"COG_Category": ["METABOLISM", "[I] Lipid transport and metabolism"]}},{"id": "[J] Translation, ribosomal structure and biogenesis", "metadata": {"COG_Category": ["INFORMATION STORAGE AND PROCESSING", "[J] Translation, ribosomal structure and biogenesis"]}},{"id": "[K] Transcription", "metadata": {"COG_Category": ["INFORMATION STORAGE AND PROCESSING", "[K] Transcription"]}},{"id": "[L] Replication, recombination and repair", "metadata": {"COG_Category": ["INFORMATION STORAGE AND PROCESSING", "[L] Replication, recombination and repair"]}},{"id": "[M] Cell wall/membrane/envelope biogenesis", "metadata": {"COG_Category": ["CELLULAR PROCESSES AND SIGNALING", "[M] Cell wall/membrane/envelope biogenesis"]}},{"id": "[N] Cell motility", "metadata": {"COG_Category": ["CELLULAR PROCESSES AND SIGNALING", "[N] Cell motility"]}},{"id": "[O] Post-translational modification, protein turnover, and chaperones", "metadata": {"COG_Category": ["CELLULAR PROCESSES AND SIGNALING", "[O] Post-translational modification, protein turnover, and chaperones"]}},{"id": "[P] Inorganic ion transport and metabolism", "metadata": {"COG_Category": ["METABOLISM", "[P] Inorganic ion transport and metabolism"]}},{"id": "[Q] Secondary metabolites biosynthesis, transport, and catabolism", "metadata": {"COG_Category": ["METABOLISM", "[Q] Secondary metabolites biosynthesis, transport, and catabolism"]}},{"id": "[R] General function prediction only", "metadata": {"COG_Category": ["POORLY CHARACTERIZED", "[R] General function prediction only"]}},{"id": "[S] Function unknown", "metadata": {"COG_Category": ["POORLY CHARACTERIZED", "[S] Function unknown"]}},{"id": "[T] Signal transduction mechanisms", "metadata": {"COG_Category": ["CELLULAR PROCESSES AND SIGNALING", "[T] Signal transduction mechanisms"]}},{"id": "[U] Intracellular trafficking, secretion, and vesicular transport", "metadata": {"COG_Category": ["CELLULAR PROCESSES AND SIGNALING", "[U] Intracellular trafficking, secretion, and vesicular transport"]}},{"id": "[V] Defense mechanisms", "metadata": {"COG_Category": ["CELLULAR PROCESSES AND SIGNALING", "[V] Defense mechanisms"]}},{"id": "[W] Extracellular structures", "metadata": {"COG_Category": ["CELLULAR PROCESSES AND SIGNALING", "[W] Extracellular structures"]}},{"id": "[Y] Nuclear structure", "metadata": {"COG_Category": ["CELLULAR PROCESSES AND SIGNALING", "[Y] Nuclear structure"]}},{"id": "[Z] Cytoskeleton", "metadata": {"COG_Category": ["CELLULAR PROCESSES AND SIGNALING", "[Z] Cytoskeleton"]}}],"columns": [{"id": "staggered", "metadata": null},{"id": "even", "metadata": null}]}
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/custom_trait_table.tab
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/custom_trait_table.tab Sat Jan 20 03:31:34 2018 -0500
b
@@ -0,0 +1,5 @@
+#OTU_IDs trait1 trait2 metadata_NSTI
+A 1.0 2.0 0.0
+C 1.0 1.0 0.0
+B 1.0 0.0 0.0
+D 1.0 1.0 0.7
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/expected.biom
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/expected.biom Sat Jan 20 03:31:34 2018 -0500
[
@@ -0,0 +1,1 @@
+{"id": "None","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","type": "OTU table","generated_by": "BIOM-Format 1.1.2","date": "2013-04-16T14:39:16.483909","matrix_type": "sparse","matrix_element_type": "float","shape": [5, 3],"data": [[0,0,5.0],[0,1,4.0],[0,2,3.0],[2,0,1.0],[2,1,2.0],[2,2,3.0],[3,0,7.0],[3,1,7.0],[3,2,7.0],[4,0,2.0],[4,1,2.0],[4,2,2.0]],"rows": [{"id": "K00001", "metadata": null},{"id": "K00002", "metadata": null},{"id": "K00003", "metadata": null},{"id": "K00004", "metadata": null},{"id": "K00005", "metadata": null}],"columns": [{"id": "sample1", "metadata": null},{"id": "sample2", "metadata": null},{"id": "sample3", "metadata": null}]}
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/expected_ra.biom
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/expected_ra.biom Sat Jan 20 03:31:34 2018 -0500
[
@@ -0,0 +1,1 @@
+{"id": "None","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","type": "OTU table","generated_by": "BIOM-Format 1.1.2","date": "2013-04-16T14:42:26.823100","matrix_type": "sparse","matrix_element_type": "float","shape": [5, 3],"data": [[0,0,0.5],[0,1,0.40000000000000002],[0,2,0.29999999999999999],[2,0,1.0],[2,1,1.0],[2,2,1.0],[3,0,0.29999999999999999],[3,1,0.5],[3,2,0.69999999999999996],[4,0,1.0],[4,1,1.0],[4,2,1.0]],"rows": [{"id": "K00001", "metadata": null},{"id": "K00002", "metadata": null},{"id": "K00003", "metadata": null},{"id": "K00004", "metadata": null},{"id": "K00005", "metadata": null}],"columns": [{"id": "sample1", "metadata": null},{"id": "sample2", "metadata": null},{"id": "sample3", "metadata": null}]}
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/normalized_otus.biom
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/normalized_otus.biom Sat Jan 20 03:31:34 2018 -0500
[
@@ -0,0 +1,1 @@
+{"id": "None","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","type": "OTU table","generated_by": "BIOM-Format 1.1.2-dev","date": "2013-08-19T13:58:00.733870","matrix_type": "sparse","matrix_element_type": "float","shape": [4, 2],"data": [[0,0,0.090909090909100002],[1,0,2.5],[2,1,0.083333333333299994],[3,0,0.5],[3,1,0.5]],"rows": [{"id": "290426", "metadata": null},{"id": "265267", "metadata": null},{"id": "248563", "metadata": null},{"id": "61102", "metadata": null}],"columns": [{"id": "staggered", "metadata": null},{"id": "even", "metadata": null}]}
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/normalized_otus.classic
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/normalized_otus.classic Sat Jan 20 03:31:34 2018 -0500
b
@@ -0,0 +1,6 @@
+# Constructed from biom file
+#OTU ID sample1 sample2
+290426 0.1 0.0
+265267 0.4 0.0
+248563 0.0 0.5
+61102 0.25 0.25
b
diff -r 000000000000 -r 43244ad9e7ef test-data/observation_table.biom
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/observation_table.biom Sat Jan 20 03:31:34 2018 -0500
[
@@ -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","date": "2013-05-16T01:50:26.488550","matrix_type": "sparse","matrix_element_type": "int","shape": [4, 3],"data": [[0,0,1],[1,1,1],[2,2,1],[3,0,1]],"rows": [{"id": "651338519", "metadata": {"taxonomy": ["None"]}},{"id": "644273636", "metadata": {"taxonomy": ["Environmental Information Processing", " Membrane Transport", " Transporters", " K09686"]}},{"id": "644269307", "metadata": {"taxonomy": ["None"]}},{"id": "644228691", "metadata": {"taxonomy": ["None"]}}],"columns": [{"id": "121.PD", "metadata": null},{"id": "124.PD", "metadata": null},{"id": "123.PD", "metadata": null}]}
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/observed.biom
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/observed.biom Sat Jan 20 03:31:34 2018 -0500
[
@@ -0,0 +1,1 @@
+{"id": "None","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","type": "OTU table","generated_by": "BIOM-Format 1.1.2","date": "2013-04-16T14:39:11.550319","matrix_type": "sparse","matrix_element_type": "float","shape": [5, 3],"data": [[0,0,3.0],[0,1,3.0],[0,2,1.0],[1,2,1.0],[2,0,1.0],[2,1,2.0],[2,2,2.0],[3,0,2.0],[3,1,10.0],[3,2,7.0],[4,0,2.0],[4,1,1.0],[4,2,2.0]],"rows": [{"id": "K00001", "metadata": null},{"id": "K00002", "metadata": null},{"id": "K00003", "metadata": null},{"id": "K00004", "metadata": null},{"id": "K00005", "metadata": null}],"columns": [{"id": "sample1", "metadata": null},{"id": "sample2", "metadata": null},{"id": "sample3", "metadata": null}]}
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/observed_ra.biom
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/observed_ra.biom Sat Jan 20 03:31:34 2018 -0500
[
@@ -0,0 +1,1 @@
+{"id": "None","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","type": "OTU table","generated_by": "BIOM-Format 1.1.2","date": "2013-04-16T14:42:20.632211","matrix_type": "sparse","matrix_element_type": "float","shape": [5, 3],"data": [[0,0,0.5],[0,1,0.20000000000000001],[1,2,0.10000000000000001],[2,0,0.25],[2,1,1.0],[2,2,1.0],[3,0,0.29999999999999999],[3,1,0.5],[3,2,0.69999999999999996],[4,1,1.0],[4,2,0.80000000000000004]],"rows": [{"id": "K00001", "metadata": null},{"id": "K00002", "metadata": null},{"id": "K00003", "metadata": null},{"id": "K00004", "metadata": null},{"id": "K00005", "metadata": null}],"columns": [{"id": "sample1", "metadata": null},{"id": "sample2", "metadata": null},{"id": "sample3", "metadata": null}]}
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/otu_table_for_custom_trait_table.biom
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/otu_table_for_custom_trait_table.biom Sat Jan 20 03:31:34 2018 -0500
[
@@ -0,0 +1,1 @@
+{"id": "None","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","matrix_type": "sparse","generated_by": "picrust","date": "2015-03-07T11:40:42.151151","type": "OTU table","matrix_element_type": "float","shape": [3, 4],"data": [[0,0,1.0],[0,1,2.0],[0,2,3.0],[0,3,5.0],[1,0,5.0],[1,1,1.0],[1,3,2.0],[2,2,1.0],[2,3,4.0]],"rows": [{"id": "A", "metadata": null},{"id": "B", "metadata": null},{"id": "C", "metadata": null}],"columns": [{"id": "Sample1", "metadata": {"pH": 7.0}},{"id": "Sample2", "metadata": {"pH": 8.0}},{"id": "Sample3", "metadata": {"pH": 7.0}},{"id": "Sample4", "metadata": {"pH": NaN}}]}
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef test-data/predicted_metagenomes.L3.biom
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/predicted_metagenomes.L3.biom Sat Jan 20 03:31:34 2018 -0500
[
b'@@ -0,0 +1,1 @@\n+{"id": "None","format": "Biological Observation Matrix 1.0.0","format_url": "http://biom-format.org","type": "Gene table","generated_by": "picrust 0.9.1-dev - categorize_by_function","date": "2013-05-27T13:45:53.337575","matrix_type": "sparse","matrix_element_type": "float","shape": [333, 2],"data": [[0,0,4.0],[0,1,520.0],[1,0,11253380.0],[1,1,14766313.0],[3,0,40038.0],[3,1,207872.0],[4,0,8251.0],[4,1,7424.0],[5,0,2629787.0],[5,1,3843593.0],[7,0,273619.0],[7,1,349797.0],[8,0,782585.0],[8,1,1617459.0],[9,0,3877219.0],[9,1,5825383.0],[10,0,3487288.0],[10,1,4801487.0],[11,0,3208588.0],[11,1,4558273.0],[12,0,810978.0],[12,1,1433244.0],[13,0,31993.0],[13,1,62805.0],[14,0,139406.0],[14,1,291752.0],[15,0,10913.0],[15,1,27859.0],[16,0,37461.0],[16,1,18670.0],[17,0,191152.0],[17,1,224917.0],[18,0,3230253.0],[18,1,5657091.0],[20,0,408582.0],[20,1,543762.0],[21,0,260597.0],[21,1,398834.0],[23,0,705213.0],[23,1,740153.0],[24,0,30921.0],[24,1,11673.0],[25,0,1469523.0],[25,1,2186655.0],[26,0,1736700.0],[26,1,2233662.0],[27,0,247913.0],[27,1,477448.0],[28,0,2365.0],[28,1,9296.0],[29,0,1304315.0],[29,1,1830933.0],[30,0,957684.0],[30,1,2017640.0],[31,0,4.0],[31,1,2.0],[32,0,73103.0],[32,1,56023.0],[33,0,117478.0],[33,1,247280.0],[35,0,144022.0],[35,1,234998.0],[36,0,189245.0],[36,1,154809.0],[37,0,1410.0],[37,1,2666.0],[39,0,460516.0],[39,1,1004204.0],[40,0,58390.0],[40,1,149415.0],[41,0,351690.0],[41,1,543670.0],[42,0,266238.0],[42,1,377057.0],[43,0,15305.0],[43,1,55903.0],[44,0,2544556.0],[44,1,3874762.0],[45,0,116850.0],[45,1,157739.0],[46,0,1111533.0],[46,1,1439049.0],[47,0,62.0],[47,1,57.0],[48,0,2508.0],[48,1,85400.0],[49,0,36.0],[49,1,36.0],[50,0,233621.0],[50,1,887598.0],[51,0,42238.0],[51,1,46679.0],[52,0,426106.0],[52,1,672681.0],[53,0,1564477.0],[53,1,2069862.0],[54,0,3423917.0],[54,1,5415852.0],[55,0,27563.0],[55,1,109603.0],[56,0,207772.0],[56,1,319028.0],[58,0,170.0],[58,1,16.0],[59,0,1215970.0],[59,1,1657997.0],[61,0,146237.0],[61,1,241917.0],[62,0,307968.0],[62,1,608632.0],[63,0,119063.0],[63,1,246046.0],[64,0,6818.0],[64,1,4746.0],[65,0,2096405.0],[65,1,3376677.0],[66,0,1019609.0],[66,1,1117023.0],[67,0,58307.0],[67,1,179414.0],[69,0,3929087.0],[69,1,5661716.0],[72,0,2512.0],[72,1,85417.0],[73,0,2787766.0],[73,1,3646434.0],[74,0,1408.0],[74,1,2666.0],[75,0,18666.0],[75,1,2000.0],[76,0,6169.0],[76,1,658.0],[77,0,429275.0],[77,1,710029.0],[78,0,2700365.0],[78,1,3443871.0],[79,0,1.0],[82,0,447622.0],[82,1,1002838.0],[84,0,652223.0],[84,1,623437.0],[85,0,78674.0],[85,1,55663.0],[86,0,366805.0],[86,1,559930.0],[87,0,7983105.0],[87,1,10379144.0],[88,0,1879891.0],[88,1,2390086.0],[89,0,3255430.0],[89,1,3917884.0],[91,0,176058.0],[91,1,163412.0],[92,0,543218.0],[92,1,662487.0],[93,0,841415.0],[93,1,1197648.0],[94,0,26.0],[94,1,21.0],[95,0,86670.0],[95,1,105638.0],[96,0,1.0],[96,1,2.0],[97,0,6171.0],[97,1,658.0],[98,0,1339496.0],[98,1,2028140.0],[99,0,211712.0],[99,1,323256.0],[101,0,11525.0],[101,1,11642.0],[102,0,256598.0],[102,1,477181.0],[104,0,1807371.0],[104,1,2216964.0],[105,0,20326.0],[105,1,100307.0],[106,0,1419270.0],[106,1,2825371.0],[108,0,6170.0],[108,1,658.0],[109,0,709835.0],[109,1,395878.0],[110,0,6750.0],[110,1,10854.0],[111,0,20472.0],[111,1,96330.0],[112,0,36705.0],[112,1,118595.0],[113,0,26.0],[113,1,21.0],[114,0,1735901.0],[114,1,2251484.0],[115,0,2469292.0],[115,1,3037468.0],[116,0,4687776.0],[116,1,6566679.0],[119,0,1677847.0],[119,1,1937822.0],[121,0,11928288.0],[121,1,16604102.0],[122,0,336947.0],[122,1,1168819.0],[123,0,5706.0],[123,1,8734.0],[125,0,174485.0],[125,1,291743.0],[126,0,932339.0],[126,1,1175246.0],[128,0,72026.0],[128,1,63015.0],[129,0,1457117.0],[129,1,1817000.0],[130,0,1758852.0],[130,1,2144456.0],[131,0,2894248.0],[131,1,3765864.0],[132,0,4587003.0],[132,1,5451627.0],[135,0,20867.0],[135,1,133848.0],[136,0,11417.0],[136,1,105441.0],[137,0,22269.0],[137,1,140299.0],[140,0,1300662.0],[140,1,1516986.0],[141,0,1673703.0],[141,1,2550245.0],[142,0,6170.0],[142,1,658.0],[145,0,170.0]'..b's", "metadata": {"KEGG_Pathways": ["Human Diseases", "Infectious Diseases", "Tuberculosis"]}},{"id": "Two-component system", "metadata": {"KEGG_Pathways": ["Environmental Information Processing", "Signal Transduction", "Two-component system"]}},{"id": "Type I diabetes mellitus", "metadata": {"KEGG_Pathways": ["Human Diseases", "Metabolic Diseases", "Type I diabetes mellitus"]}},{"id": "Type II diabetes mellitus", "metadata": {"KEGG_Pathways": ["Human Diseases", "Metabolic Diseases", "Type II diabetes mellitus"]}},{"id": "Tyrosine metabolism", "metadata": {"KEGG_Pathways": ["Metabolism", "Amino Acid Metabolism", "Tyrosine metabolism"]}},{"id": "Ubiquinone and other terpenoid-quinone biosynthesis", "metadata": {"KEGG_Pathways": ["Metabolism", "Metabolism of Cofactors and Vitamins", "Ubiquinone and other terpenoid-quinone biosynthesis"]}},{"id": "Ubiquitin system", "metadata": {"KEGG_Pathways": ["Genetic Information Processing", "Folding, Sorting and Degradation", "Ubiquitin system"]}},{"id": "VEGF signaling pathway", "metadata": {"KEGG_Pathways": ["Environmental Information Processing", "Signal Transduction", "VEGF signaling pathway"]}},{"id": "Valine, leucine and isoleucine biosynthesis", "metadata": {"KEGG_Pathways": ["Metabolism", "Amino Acid Metabolism", "Valine, leucine and isoleucine biosynthesis"]}},{"id": "Valine, leucine and isoleucine degradation", "metadata": {"KEGG_Pathways": ["Metabolism", "Amino Acid Metabolism", "Valine, leucine and isoleucine degradation"]}},{"id": "Various types of N-glycan biosynthesis", "metadata": {"KEGG_Pathways": ["Metabolism", "Glycan Biosynthesis and Metabolism", "Various types of N-glycan biosynthesis"]}},{"id": "Vascular smooth muscle contraction", "metadata": {"KEGG_Pathways": ["Organismal Systems", "Circulatory System", "Vascular smooth muscle contraction"]}},{"id": "Vasopressin-regulated water reabsorption", "metadata": {"KEGG_Pathways": ["Organismal Systems", "Excretory System", "Vasopressin-regulated water reabsorption"]}},{"id": "Vibrio cholerae infection", "metadata": {"KEGG_Pathways": ["Human Diseases", "Infectious Diseases", "Vibrio cholerae infection"]}},{"id": "Vibrio cholerae pathogenic cycle", "metadata": {"KEGG_Pathways": ["Human Diseases", "Infectious Diseases", "Vibrio cholerae pathogenic cycle"]}},{"id": "Viral myocarditis", "metadata": {"KEGG_Pathways": ["Human Diseases", "Cardiovascular Diseases", "Viral myocarditis"]}},{"id": "Vitamin B6 metabolism", "metadata": {"KEGG_Pathways": ["Metabolism", "Metabolism of Cofactors and Vitamins", "Vitamin B6 metabolism"]}},{"id": "Wnt signaling pathway", "metadata": {"KEGG_Pathways": ["Environmental Information Processing", "Signal Transduction", "Wnt signaling pathway"]}},{"id": "Xylene degradation", "metadata": {"KEGG_Pathways": ["Metabolism", "Xenobiotics Biodegradation and Metabolism", "Xylene degradation"]}},{"id": "Zeatin biosynthesis", "metadata": {"KEGG_Pathways": ["Metabolism", "Metabolism of Terpenoids and Polyketides", "Zeatin biosynthesis"]}},{"id": "alpha-Linolenic acid metabolism", "metadata": {"KEGG_Pathways": ["Metabolism", "Lipid Metabolism", "alpha-Linolenic acid metabolism"]}},{"id": "beta-Alanine metabolism", "metadata": {"KEGG_Pathways": ["Metabolism", "Metabolism of Other Amino Acids", "beta-Alanine metabolism"]}},{"id": "beta-Lactam resistance", "metadata": {"KEGG_Pathways": ["Metabolism", "Biosynthesis of Other Secondary Metabolites", "beta-Lactam resistance"]}},{"id": "mRNA surveillance pathway", "metadata": {"KEGG_Pathways": ["Genetic Information Processing", "Translation", "mRNA surveillance pathway"]}},{"id": "mTOR signaling pathway", "metadata": {"KEGG_Pathways": ["Environmental Information Processing", "Signal Transduction", "mTOR signaling pathway"]}},{"id": "p53 signaling pathway", "metadata": {"KEGG_Pathways": ["Cellular Processes", "Cell Growth and Death", "p53 signaling pathway"]}}],"columns": [{"id": "staggered", "metadata": null},{"id": "even", "metadata": null}]}\n\\ No newline at end of file\n'
b
diff -r 000000000000 -r 43244ad9e7ef test-data/tempout.table
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/tempout.table Sat Jan 20 03:31:34 2018 -0500
b
@@ -0,0 +1,45 @@
+# Constructed from biom file
+#OTU ID staggered even KEGG_Pathways
+Amino Acid Metabolism 28955185.0 45374765.0 Metabolism; Amino Acid Metabolism
+Biosynthesis of Other Secondary Metabolites 1737365.0 2923945.0 Metabolism; Biosynthesis of Other Secondary Metabolites
+Cancers 282088.0 393993.0 Human Diseases; Cancers
+Carbohydrate Metabolism 33779735.0 44900117.0 Metabolism; Carbohydrate Metabolism
+Cardiovascular Diseases 18668.0 2002.0 Human Diseases; Cardiovascular Diseases
+Cell Communication 26.0 21.0 Cellular Processes; Cell Communication
+Cell Growth and Death 1340246.0 1728222.0 Cellular Processes; Cell Growth and Death
+Cell Motility 3332193.0 4325524.0 Cellular Processes; Cell Motility
+Cellular Processes and Signaling 12376427.0 16085447.0 Unclassified; Cellular Processes and Signaling
+Circulatory System 27563.0 109603.0 Organismal Systems; Circulatory System
+Development 0.0 0.0 Organismal Systems; Development
+Digestive System 205590.0 268235.0 Organismal Systems; Digestive System
+Endocrine System 311963.0 901422.0 Organismal Systems; Endocrine System
+Energy Metabolism 16483126.0 22914670.0 Metabolism; Energy Metabolism
+Environmental Adaptation 263572.0 488829.0 Organismal Systems; Environmental Adaptation
+Enzyme Families 5457311.0 7759696.0 Metabolism; Enzyme Families
+Excretory System 36303.0 100424.0 Organismal Systems; Excretory System
+Folding, Sorting and Degradation 6690470.0 9464060.0 Genetic Information Processing; Folding, Sorting and Degradation
+Genetic Information Processing 7466411.0 10678653.0 Unclassified; Genetic Information Processing
+Glycan Biosynthesis and Metabolism 5153604.0 6993096.0 Metabolism; Glycan Biosynthesis and Metabolism
+Immune System 38800.0 75125.0 Organismal Systems; Immune System
+Immune System Diseases 141292.0 225122.0 Human Diseases; Immune System Diseases
+Infectious Diseases 1734917.0 1799045.0 Human Diseases; Infectious Diseases
+Lipid Metabolism 9430513.0 14243639.0 Metabolism; Lipid Metabolism
+Membrane Transport 40619910.0 51257841.0 Environmental Information Processing; Membrane Transport
+Metabolic Diseases 245399.0 327300.0 Human Diseases; Metabolic Diseases
+Metabolism 7818926.0 11548413.0 Unclassified; Metabolism
+Metabolism of Cofactors and Vitamins 13332788.0 18431813.0 Metabolism; Metabolism of Cofactors and Vitamins
+Metabolism of Other Amino Acids 5175074.0 6958034.0 Metabolism; Metabolism of Other Amino Acids
+Metabolism of Terpenoids and Polyketides 5806434.0 9500869.0 Metabolism; Metabolism of Terpenoids and Polyketides
+Nervous System 174485.0 291743.0 Organismal Systems; Nervous System
+Neurodegenerative Diseases 660119.0 1222484.0 Human Diseases; Neurodegenerative Diseases
+Nucleotide Metabolism 11770630.0 16309025.0 Metabolism; Nucleotide Metabolism
+Poorly Characterized 16616064.0 23170781.0 Unclassified; Poorly Characterized
+RNA family 0.0 0.0 Genetic Information Processing; RNA family
+Replication and Repair 23845775.0 31340489.0 Genetic Information Processing; Replication and Repair
+Sensory System 0.0 0.0 Organismal Systems; Sensory System
+Signal Transduction 6054447.0 7820067.0 Environmental Information Processing; Signal Transduction
+Signaling Molecules and Interaction 503602.0 917661.0 Environmental Information Processing; Signaling Molecules and Interaction
+Transcription 7071835.0 8709955.0 Genetic Information Processing; Transcription
+Translation 14940935.0 19978123.0 Genetic Information Processing; Translation
+Transport and Catabolism 585366.0 1330052.0 Cellular Processes; Transport and Catabolism
+Xenobiotics Biodegradation and Metabolism 7799254.0 12542712.0 Metabolism; Xenobiotics Biodegradation and Metabolism
\ No newline at end of file
b
diff -r 000000000000 -r 43244ad9e7ef tool-data/picrust_precalculated.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/picrust_precalculated.loc.sample Sat Jan 20 03:31:34 2018 -0500
b
@@ -0,0 +1,11 @@
+#This is a sample file distributed with Galaxy.
+#
+# PICRUSt supplied files: http://kronos.pharmacology.dal.ca/public_files/picrust/picrust_precalculated_v1.1.1/13_5/
+#
+# files may be in gzipped format or unzipped
+#
+#<dbname> <file_base>
+#16S 13_5 /path/to/file/16S_13_5_precalculated.tab.gz
+#cog 13_5 /path/to/file/cog_13_5_precalculated.tab
+#ko 13_5 /path/to/file/ko_13_5_precalculated.tab.gz
+#rfam 13_5 /path/to/file/rfam_13_5_precalculated.tab.gz
b
diff -r 000000000000 -r 43244ad9e7ef tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Sat Jan 20 03:31:34 2018 -0500
b
@@ -0,0 +1,6 @@
+<tables>
+    <table name="picrust_precalculated" comment_char="#">
+        <columns>name, value</columns>
+        <file path="tool-data/picrust_precalculated.loc" />
+    </table>
+</tables>