Repository 'maaslin2'
hg clone https://toolshed.g2.bx.psu.edu/repos/iuc/maaslin2

Changeset 0:c629e6de3c49 (2021-11-05)
Next changeset 1:ef2cace85809 (2024-03-13)
Commit message:
"planemo upload for repository https://github.com/biobakery/Maaslin2 commit a0d2ac51212781be1ba2ecd02f0388f6f01cba28"
added:
maaslin2.xml
macros.xml
test-data/HMP2_metadata.tsv
test-data/HMP2_taxonomy.tsv
b
diff -r 000000000000 -r c629e6de3c49 maaslin2.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/maaslin2.xml Fri Nov 05 11:24:33 2021 +0000
[
b'@@ -0,0 +1,362 @@\n+<tool id="maaslin2" name="MaAsLin 2" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">\n+    <description>Microbiome Multivariable Association with Linear Models</description>\n+    <macros>\n+        <import>macros.xml</import>\n+    </macros>\n+    <expand macro="edam_ontology"/>\n+    <expand macro="requirements"/>\n+    <command detect_errors="exit_code"><![CDATA[\n+ln -s \'$input_data\' \'input_data.tsv\'\n+&&\n+ln -s \'$input_metadata\' \'input_metadata.tsv\'\n+&&   \n+Maaslin2.R\n+#if $additional_options.min_abundance   \n+    --min_abundance \'$additional_options.min_abundance\'\n+#end if\n+#if $additional_options.min_prevalence\n+    --min_prevalence \'$additional_options.min_prevalence\'\n+#end if\n+#if $additional_options.max_significance\n+    --max_significance \'$additional_options.max_significance\'\n+#end if\n+#if $additional_options.normalization\n+    --normalization \'$additional_options.normalization\'\n+#end if\n+#if $additional_options.transform\n+    --transform \'$additional_options.transform\'\n+#end if\n+#if $additional_options.analysis_method\n+    --analysis_method \'$additional_options.analysis_method\'\n+#end if\n+#if $random_effects\n+    --random_effects \'$random_effects\'\n+#end if\n+#if $fixed_effects\n+    --fixed_effects \'$fixed_effects\'\n+#end if\n+#if $additional_options.correction\n+    --correction \'$additional_options.correction\'\n+#end if\n+    $additional_options.standardize\n+    $output.plot_heatmap\n+#if $output.heatmap_first_n\n+    --heatmap_first_n \'$output.heatmap_first_n\'\n+#end if\n+    $output.plot_scatter\n+    --cores \\${GALAXY_SLOTS:-4}\n+    \'input_data.tsv\'\n+    \'input_metadata.tsv\'\n+    \'outputFolder\'\n+&&\n+cd outputFolder && mkdir -p figures/ && cp *.pdf figures\n+    ]]></command>\n+    <inputs>\n+        <param name="input_data" type="data" format="tabular" label="Data (or features) file"/>\n+        <param name="input_metadata" type="data" format="tabular" label="Metadata file"/>\n+        <param argument="--fixed_effects" type="select" multiple="true" optional="true" label="Interactions: Fixed effects" help="The fixed effects for the model, comma-delimited for multiple effects">\n+            <option value="diagnosis" selected="true">diagnosis</option>\n+            <option value="dysbiosisnonIBD" selected="true">dysbiosisnonIBD</option>\n+            <option value="dysbiosisUC" selected="true">dysbiosisUC</option>\n+            <option value="dysbiosisCD" selected="true">dysbiosisCD</option>\n+            <option value="antibiotics" selected="true">antibiotics</option>\n+            <option value="age" selected="true">age</option>\n+        </param>        \n+        <param argument="--random_effects" type="text" multiple="true" optional="true" label="Random effects" help="The random effects for the model,  comma-delimited for multiple effects"/>        \n+        <section name="additional_options" title="Additional Options" expanded="true">\n+            <param argument="--min_abundance" type="float" value="0.0" optional="true" label="Minimum abundance" help="The minimum abundance for each feature"/>\n+            <param argument="--min_prevalence" type="float" value="0.1" optional="true" label="Minimum prevalence" help="The minimum percent of samples for which a feature is detected at minimum abundance"/>\n+            <param argument="--max_significance" type="float" value="0.25" optional="true" label="Maximum significance" help="The q-value threshold for significance"/>\n+            <param argument="--normalization" type="select" optional="true" label="The normalization method to apply">\n+                <option value="TSS" selected="true">TSS</option>\n+                <option value="CLR">CLR</option>\n+                <option value="CSS">CSS</option>\n+                <option value="NONE">NONE</option>\n+                <option value="TMM">TMM</option>\n+            </param>\n+            <param argument="--transform" type="select" optional="true" label="The transform to apply">\n+                <option value'..b'9943" delta="1000"/>\n+                </assert_contents>\n+            </output>\n+            <output name="headmap">\n+                <assert_contents>\n+                    <has_size value="6554" delta="1000" />\n+                </assert_contents>\n+            </output>\n+            <output_collection name="figures_pdfs" type="list">\n+                <element name="heatmap.pdf" ftype="pdf">\n+                    <assert_contents>\n+                        <has_size value="6554" delta="1000" />\n+                    </assert_contents>\n+                </element>\n+                <element name="diagnosis.pdf" ftype="pdf">\n+                    <assert_contents>\n+                        <has_size value="6061545" delta="1000000" />\n+                    </assert_contents>\n+                </element>\n+                <element name="dysbiosisnonIBD.pdf" ftype="pdf">\n+                    <assert_contents>\n+                        <has_size value="2599373" delta="1000000" />\n+                    </assert_contents>\n+                </element>                                                                    \n+            </output_collection>\n+        </test>   \n+    </tests>\n+    <help><![CDATA[\n+@HELP_HEADER@\n+MaAsLin 2\n+=========\n+MaAsLin2 is the next generation of MaAsLin (Microbiome Multivariable Association with Linear Models).\n+\n+Input\n+=====\n+MaAsLin2 requires two input files:\n+\n+    - Data (or features) tabular file\n+        - This file is tab-delimited.\n+        - Formatted with features as columns and samples as rows.\n+        - The transpose of this format is also okay.\n+        - Possible features in this file include taxonomy or genes.\n+    - Metadata tabular file\n+        - This file is tab-delimited.\n+        - Formatted with features as columns and samples as rows.\n+        - The transpose of this format is also okay.\n+        - Possible metadata in this file include gender or age.\n+\n+The data file can contain samples not included in the metadata file (along with the reverse case). For both cases, those samples not included in both files will be removed from the analysis. Also the samples do not need to be in the same order in the two files.\n+\n+Output\n+======\n+1- Data output files\n+    - All results ordered by increasing q-value (tabular file)\n+        - Full list of associations that pass MaAsLin2\'s significance threshold, ordered by increasing q-values\n+        - This includes the same data as the data.frame returned.\n+        - This file contains all results ordered by increasing q-value.\n+        - The first columns are the metadata and feature names.\n+        - The next two columns are the value and coefficient from the model.\n+        - The next column is the standard deviation from the model.\n+        - The N column is the total number of data points.\n+        - The N.not.zero column is the total of non-zero data points.\n+        - The pvalue from the calculation is the second to last column.\n+        - The qvalue is computed with p.adjust with the correction method.\n+    - Q-values smaller than or equal to the threshold (tabular file)\n+        - This file is a subset of the results in the first file.\n+        - It only includes associations with q-values <= to the threshold.\n+    - Data frame with residuals for each feature (R data file)\n+        - This file contains a data frame with residuals for each feature.\n+2- Visualization output files\n+    - Heatmap of the significant associations (PDF file)\n+        - This file contains a heatmap of the significant associations.\n+    - A plot for every significant association found (PDF file(s))\n+        - A plot is generated for each significant association.\n+        - Scatter plots are used for continuous metadata.\n+        - Box plots are for categorical data.\n+        - Data points plotted are after normalization, filtering, and transform.\n+\n+    ]]></help> \n+    <citations>\n+        <citation type="doi">10.1101/2021.01.20.427420</citation>\n+    </citations>\n+ </tool>\n'
b
diff -r 000000000000 -r c629e6de3c49 macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml Fri Nov 05 11:24:33 2021 +0000
b
@@ -0,0 +1,19 @@
+<?xml version="1.0"?>
+<macros>
+    <token name="@TOOL_VERSION@">0.99.12</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@PROFILE@">20.01</token>
+    <xml name="edam_ontology">
+        <edam_topics>
+            <edam_topic>topic_3941</edam_topic>
+            <edam_topic>topic_3301</edam_topic>
+            <edam_topic>topic_3305</edam_topic>
+        </edam_topics>           
+    </xml>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">maaslin2</requirement>
+            <yield/>
+        </requirements>
+    </xml>
+ </macros>
\ No newline at end of file
b
diff -r 000000000000 -r c629e6de3c49 test-data/HMP2_metadata.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/HMP2_metadata.tsv Fri Nov 05 11:24:33 2021 +0000
b
b'@@ -0,0 +1,1596 @@\n+ID\tsite\tage\tdiagnosis\tsubject\tantibiotics\tdysbiosis_binary\tdysbiosis\tdysbiosisnonIBD\tdysbiosisUC\tdysbiosisCD\tcollection\n+CSM5FZ3N_P\tCedars-Sinai\t43\tCD\tC3001\tNo\tNo\t0.792314801112388\tNo\tNo\tNo\t1\n+CSM5FZ3R_P\tCedars-Sinai\t43\tCD\tC3001\tNo\tNo\t0.837923415694291\tNo\tNo\tNo\t2\n+CSM5FZ3T_P\tCedars-Sinai\t76\tCD\tC3002\tNo\tYes\t0.924296928419748\tNo\tNo\tYes\t1\n+CSM5FZ3V_P\tCedars-Sinai\t43\tCD\tC3001\tNo\tNo\t0.830400526852384\tNo\tNo\tNo\t4\n+CSM5FZ3X_P\tCedars-Sinai\t76\tCD\tC3002\tNo\tYes\t0.910966992923041\tNo\tNo\tYes\t2\n+CSM5FZ3Z_P\tCedars-Sinai\t76\tCD\tC3002\tNo\tYes\t0.912281677355966\tNo\tNo\tYes\t3\n+CSM5FZ42_P\tCedars-Sinai\t76\tCD\tC3002\tNo\tYes\t0.903049136702093\tNo\tNo\tYes\t4\n+CSM5FZ44_P\tCedars-Sinai\t76\tCD\tC3002\tNo\tYes\t0.87825476936449\tNo\tNo\tYes\t5\n+CSM5FZ46_P\tCedars-Sinai\t76\tCD\tC3002\tNo\tYes\t0.92542872181954\tNo\tNo\tYes\t6\n+CSM5FZ4A_P\tCedars-Sinai\t47\tUC\tC3004\tNo\tNo\t0.775160480913896\tNo\tNo\tNo\t1\n+CSM5FZ4C_P\tCedars-Sinai\t43\tCD\tC3001\tNo\tNo\t0.836244630681399\tNo\tNo\tNo\t5\n+CSM5FZ4E_P\tCedars-Sinai\t43\tUC\tC3003\tYes\tNo\t0.787616535915359\tNo\tNo\tNo\t2\n+CSM5FZ4G_P\tCedars-Sinai\t43\tUC\tC3003\tNo\tNo\t0.68128445477854\tNo\tNo\tNo\t3\n+CSM5FZ4K_P\tCedars-Sinai\t43\tUC\tC3003\tYes\tNo\t0.717164790084925\tNo\tNo\tNo\t5\n+CSM5FZ4M\tCedars-Sinai\t43\tUC\tC3003\tNo\tNo\t0.761300183426806\tNo\tNo\tNo\t6\n+CSM5LLGB_P\tMGH\t30\tCD\tM2014\tNo\tNo\t0.730525895151516\tNo\tNo\tNo\t8\n+CSM5MCTZ_P\tCedars-Sinai\t32\tUC\tC3006\tNo\tNo\t0.690477602078951\tNo\tNo\tNo\t1\n+CSM5MCU4_P\tCedars-Sinai\t53\tCD\tC3008\tYes\tYes\t0.960340510520076\tNo\tNo\tYes\t1\n+CSM5MCU8_P\tCedars-Sinai\t47\tUC\tC3004\tNo\tNo\t0.7487518327033\tNo\tNo\tNo\t3\n+CSM5MCUA_P\tCedars-Sinai\t47\tUC\tC3004\tNo\tNo\t0.764756113674023\tNo\tNo\tNo\t4\n+CSM5MCUC_P\tCedars-Sinai\t47\tUC\tC3004\tNo\tNo\t0.753471972559145\tNo\tNo\tNo\t5\n+CSM5MCUE_P\tCedars-Sinai\t47\tUC\tC3004\tNo\tNo\t0.76616120085356\tNo\tNo\tNo\t6\n+CSM5MCUG_P\tCedars-Sinai\t32\tUC\tC3006\tNo\tNo\t0.631995641824807\tNo\tNo\tNo\t2\n+CSM5MCUK_P\tCedars-Sinai\t32\tUC\tC3006\tNo\tNo\t0.659833643343466\tNo\tNo\tNo\t4\n+CSM5MCUO\tCedars-Sinai\t32\tUC\tC3006\tNo\tNo\t0.632952326253226\tNo\tNo\tNo\t6\n+CSM5MCUQ_P\tCedars-Sinai\t76\tUC\tC3005\tNo\tNo\t0.727873670271853\tNo\tNo\tNo\t2\n+CSM5MCUS_P\tCedars-Sinai\t76\tUC\tC3005\tNo\tNo\t0.698587884579809\tNo\tNo\tNo\t3\n+CSM5MCUW_P\tCedars-Sinai\t76\tUC\tC3005\tNo\tNo\t0.759108845355999\tNo\tNo\tNo\t5\n+CSM5MCUY_P\tCedars-Sinai\t76\tUC\tC3005\tNo\tNo\t0.75050127138637\tNo\tNo\tNo\t6\n+CSM5MCV1_P\tCedars-Sinai\tNA\tCD\tC3007\tNo\tYes\t0.918640365469221\tNA\tNA\tNA\t2\n+CSM5MCV5_P\tCedars-Sinai\tNA\tCD\tC3007\tNo\tNo\t0.650022501781325\tNA\tNA\tNA\t4\n+CSM5MCVB_P\tCedars-Sinai\tNA\tCD\tC3007\tNo\tYes\t0.960878306358498\tNA\tNA\tNA\t1\n+CSM5MCVD_P\tCedars-Sinai\t43\tCD\tC3001\tNo\tNo\t0.790514760450371\tNo\tNo\tNo\t7\n+CSM5MCVF_P\tCedars-Sinai\t43\tCD\tC3001\tNo\tYes\t0.853225777127933\tNo\tNo\tYes\t8\n+CSM5MCVJ_P\tCedars-Sinai\t76\tCD\tC3002\tNo\tYes\t0.929706609618933\tNo\tNo\tYes\t7\n+CSM5MCVL\tCedars-Sinai\t76\tCD\tC3002\tNo\tYes\t0.912606413860137\tNo\tNo\tYes\t8\n+CSM5MCVN\tCedars-Sinai\t76\tCD\tC3002\tNo\tYes\t0.916894652604198\tNo\tNo\tYes\t9\n+CSM5MCVV_P\tCedars-Sinai\t43\tCD\tC3001\tNo\tNo\t0.817227676926419\tNo\tNo\tNo\t9\n+CSM5MCVZ_P\tCedars-Sinai\t53\tCD\tC3008\tYes\tYes\t0.971182046181404\tNo\tNo\tYes\t3\n+CSM5MCW4_P\tCedars-Sinai\t53\tCD\tC3008\tYes\tYes\t0.969989533466459\tNo\tNo\tYes\t4\n+CSM5MCW6\tCedars-Sinai\t53\tCD\tC3008\tYes\tYes\t0.962750632814143\tNo\tNo\tYes\t5\n+CSM5MCWA_P\tCedars-Sinai\t56\tCD\tC3009\tNo\tYes\t0.903461177800709\tNo\tNo\tYes\t3\n+CSM5MCWC\tCedars-Sinai\t56\tCD\tC3009\tNo\tYes\t0.937907191357036\tNo\tNo\tYes\t4\n+CSM5MCWE\tCedars-Sinai\t56\tCD\tC3009\tNo\tYes\t0.948532940759134\tNo\tNo\tYes\t5\n+CSM5MCWG\tCedars-Sinai\t56\tCD\tC3009\tYes\tYes\t0.99942109996108\tNo\tNo\tYes\t6\n+CSM5MCWI_P\tCedars-Sinai\t43\tCD\tC3001\tNo\tYes\t0.848980181450892\tNo\tNo\tYes\t10\n+CSM5MCWK_P\tCedars-Sinai\t51\tCD\tC3010\tNo\tNo\t0.673114239148449\tNo\tNo\tNo\t1\n+CSM5MCWM_P\tCedars-Sinai\t43\tUC\tC3003\tNo\tNo\t0.776204526557252\tNo\tNo\tNo\t7\n+CSM5MCWQ\tCedars-Sinai\t43\tUC\tC3003\tNo\tNo\t0.716845145951409\tNo\tNo\tNo\t9\n+CSM5MCX3\tCedars-Sinai\t32\tUC\tC3006\tNo\tNo\t0.625626559136398\tNo\tNo\tNo\t9\n+CSM5MCXB_P\tCedars-Sinai\t37\tUC\tC3011\tNo\tNo\t0.753275696580949\tNo\tNo\tNo\t1\n+CSM5MCXD\tCedars-Sinai\t43\tCD\tC3001\tNo\tNo\t0.780480175922642\tNo\tNo\tNo\t11\n+CSM5MCXF_P\tCedars-Sinai\t37\tCD\tC3012\tNo\tNo\t0.643653195375717\tNo\tNo\tNo\t1\n+CSM5MCXH\tCedars-Sinai\t47\tUC\tC300'..b'.755376258110351\tNo\tNo\tNo\t19\n+PSM7J1DF\tMGH Pediatrics\t15\tnonIBD\tP6014\tNo\tNo\t0.704783808863503\tNo\tNo\tNo\t10\n+PSM7J1DL\tMGH Pediatrics\t15\tnonIBD\tP6014\tNo\tNo\t0.670177989828438\tNo\tNo\tNo\t13\n+PSM7J4EF\tMGH Pediatrics\t15\tCD\tP6037\tNo\tNo\t0.762246179526217\tNo\tNo\tNo\t1\n+PSMA263M\tMGH Pediatrics\t16\tCD\tP6024\tNo\tYes\t0.960744939491056\tNo\tNo\tYes\t14\n+PSMA263S\tMGH Pediatrics\t16\tCD\tP6024\tNo\tYes\t0.96351706392056\tNo\tNo\tYes\t17\n+PSMA263U\tMGH Pediatrics\t16\tCD\tP6024\tNo\tYes\t0.963318746215513\tNo\tNo\tYes\t18\n+PSMA263W\tMGH Pediatrics\t16\tCD\tP6024\tNo\tYes\t0.957420077702007\tNo\tNo\tYes\t19\n+PSMA264K\tMGH Pediatrics\t17\tUC\tP6025\tNo\tNo\t0.757045633040137\tNo\tNo\tNo\t16\n+PSMA264O\tMGH Pediatrics\t16\tUC\tP6035\tNo\tNo\t0.759685483544399\tNo\tNo\tNo\t2\n+PSMA264Q\tMGH Pediatrics\t16\tUC\tP6035\tNo\tNo\t0.781380677857354\tNo\tNo\tNo\t3\n+PSMA264S\tMGH Pediatrics\t16\tUC\tP6035\tNo\tNo\t0.791531326183874\tNo\tNo\tNo\t4\n+PSMA264U\tMGH Pediatrics\t16\tUC\tP6035\tNo\tNo\t0.695267589178597\tNo\tNo\tNo\t5\n+PSMA264W\tMGH Pediatrics\t16\tUC\tP6035\tNo\tNo\t0.677308857433583\tNo\tNo\tNo\t6\n+PSMA2651_P\tMGH Pediatrics\t15\tCD\tP6033\tNo\tNo\t0.694761370950797\tNo\tNo\tNo\t8\n+PSMA2653\tMGH Pediatrics\t15\tCD\tP6033\tNo\tNo\t0.690954230738867\tNo\tNo\tNo\t9\n+PSMA2659\tMGH Pediatrics\t15\tCD\tP6033\tNo\tNo\t0.718055665585006\tNo\tNo\tNo\t12\n+PSMA265B\tMGH Pediatrics\t15\tCD\tP6033\tNo\tNo\t0.736183771002547\tNo\tNo\tNo\t13\n+PSMA265D\tMGH Pediatrics\t17\tnonIBD\tP6018\tNo\tYes\t0.842407349407832\tYes\tNo\tNo\t20\n+PSMA265F\tMGH Pediatrics\t17\tnonIBD\tP6018\tNo\tYes\t0.838859754896309\tYes\tNo\tNo\t21\n+PSMA265H\tMGH Pediatrics\t17\tnonIBD\tP6018\tNo\tNo\t0.836683871894684\tNo\tNo\tNo\t24\n+PSMA265J\tMGH Pediatrics\t17\tnonIBD\tP6018\tNo\tNo\t0.83671278205524\tNo\tNo\tNo\t23\n+PSMA265J_TR\tMGH Pediatrics\t17\tnonIBD\tP6018\tNo\tNo\t0.83671278205524\tNo\tNo\tNo\t23\n+PSMA265L\tMGH Pediatrics\t17\tnonIBD\tP6018\tNo\tNo\t0.819823743743616\tNo\tNo\tNo\t22\n+PSMA265N\tMGH Pediatrics\t16\tCD\tP6016\tNo\tNo\t0.741223648483934\tNo\tNo\tNo\t20\n+PSMA265T\tMGH Pediatrics\t16\tCD\tP6016\tNo\tNo\t0.790027868251687\tNo\tNo\tNo\t23\n+PSMA265X\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.71231836162602\tNo\tNo\tNo\t1\n+PSMA2668\tMGH Pediatrics\t9\tCD\tP6028\tNo\tYes\t0.999604254488082\tNo\tNo\tYes\t15\n+PSMA266I\tMGH Pediatrics\t15\tCD\tP6037\tNo\tNo\t0.719491155527537\tNo\tNo\tNo\t2\n+PSMA266M\tMGH Pediatrics\t15\tCD\tP6037\tYes\tNo\t0.731123627705743\tNo\tNo\tNo\t4\n+PSMA266O\tMGH Pediatrics\t15\tCD\tP6037\tYes\tNo\t0.745586402407911\tNo\tNo\tNo\t5\n+PSMA266Q\tMGH Pediatrics\t15\tCD\tP6037\tYes\tNo\t0.709162734571597\tNo\tNo\tNo\t6\n+PSMA266U\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.756402659712828\tNo\tNo\tNo\t2\n+PSMA266Y\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.71583332758601\tNo\tNo\tNo\t4\n+PSMA2671\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.702035643033747\tNo\tNo\tNo\t5\n+PSMA2675\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.653939747515284\tNo\tNo\tNo\t7\n+PSMA267D\tMGH Pediatrics\t15\tCD\tP6033\tNo\tNo\t0.742717159270931\tNo\tNo\tNo\t17\n+PSMA267F\tMGH Pediatrics\t15\tCD\tP6033\tNo\tNo\t0.771418335214622\tNo\tNo\tNo\t18\n+PSMA267H\tMGH Pediatrics\t15\tCD\tP6033\tNo\tNo\t0.747876595273697\tNo\tNo\tNo\t19\n+PSMA267J\tMGH Pediatrics\t16\tUC\tP6035\tNo\tNo\t0.731158902309119\tNo\tNo\tNo\t8\n+PSMA267P\tMGH Pediatrics\t16\tUC\tP6035\tNo\tNo\t0.801575972906687\tNo\tNo\tNo\t11\n+PSMA267R\tMGH Pediatrics\t16\tUC\tP6035\tNo\tNo\t0.770047699968093\tNo\tNo\tNo\t12\n+PSMA269G\tMGH Pediatrics\t15\tCD\tP6037\tNo\tNo\t0.775266691965913\tNo\tNo\tNo\t8\n+PSMA269O\tMGH Pediatrics\t15\tCD\tP6037\tNo\tNo\t0.718533251599801\tNo\tNo\tNo\t12\n+PSMA269S\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.663812474472784\tNo\tNo\tNo\t8\n+PSMA269W\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.709396968369554\tNo\tNo\tNo\t10\n+PSMA26A1\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.679252999929992\tNo\tNo\tNo\t12\n+PSMA26A3\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.682001418709998\tNo\tNo\tNo\t13\n+PSMB4MBI\tMGH Pediatrics\t16\tUC\tP6035\tNo\tNo\t0.749741766306635\tNo\tNo\tNo\t17\n+PSMB4MBK\tMGH Pediatrics\t16\tUC\tP6035\tNo\tNo\t0.698786574135189\tNo\tNo\tNo\t16\n+PSMB4MBS\tMGH Pediatrics\t15\tCD\tP6037\tNo\tNo\t0.732561466588752\tNo\tNo\tNo\t16\n+PSMB4MC1\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.691453182231825\tNo\tNo\tNo\t17\n+PSMB4MC3\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.719423017924537\tNo\tNo\tNo\t18\n+PSMB4MC5\tMGH Pediatrics\t16\tUC\tP6038\tNo\tNo\t0.722597079037033\tNo\tNo\tNo\t19\n+PSMB4MC7\tMGH Pediatrics\t16\tUC\tP6035\tNo\tNo\t0.699209149925812\tNo\tNo\tNo\t18\n'
b
diff -r 000000000000 -r c629e6de3c49 test-data/HMP2_taxonomy.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/HMP2_taxonomy.tsv Fri Nov 05 11:24:33 2021 +0000
b
b'@@ -0,0 +1,1009 @@\n+ID\tBifidobacterium adolescentis\tBifidobacterium bifidum\tBifidobacterium longum\tBifidobacterium pseudocatenulatum\tCollinsella aerofaciens\tBacteroides caccae\tBacteroides cellulosilyticus\tBacteroides dorei\tBacteroides eggerthii\tBacteroides faecis\tBacteroides finegoldii\tBacteroides fragilis\tBacteroides intestinalis\tBacteroides massiliensis\tBacteroides ovatus\tBacteroides salyersiae\tBacteroides stercoris\tBacteroides thetaiotaomicron\tBacteroides uniformis\tBacteroides vulgatus\tBacteroides xylanisolvens\tBacteroidales bacterium ph8\tBarnesiella intestinihominis\tCoprobacter fastidiosus\tOdoribacter splanchnicus\tParabacteroides distasonis\tParabacteroides goldsteinii\tParabacteroides merdae\tParabacteroides unclassified\tParaprevotella clara\tParaprevotella unclassified\tPrevotella copri\tAlistipes finegoldii\tAlistipes onderdonkii\tAlistipes putredinis\tAlistipes shahii\tAlistipes unclassified\tStreptococcus salivarius\tClostridium bolteae\tClostridium citroniae\tClostridium clostridioforme\tClostridium hathewayi\tClostridium leptum\tClostridium nexile\tClostridium symbiosum\tFlavonifractor plautii\tEubacterium eligens\tEubacterium hallii\tEubacterium rectale\tEubacterium siraeum\tEubacterium sp 3 1 31\tEubacterium ventriosum\tRuminococcus gnavus\tRuminococcus obeum\tRuminococcus torques\tCoprococcus comes\tDorea longicatena\tLachnospiraceae bacterium 1 1 57FAA\tLachnospiraceae bacterium 3 1 46FAA\tRoseburia hominis\tRoseburia intestinalis\tRoseburia inulinivorans\tRoseburia unclassified\tOscillibacter unclassified\tPeptostreptococcaceae noname unclassified\tFaecalibacterium prausnitzii\tRuminococcus bromii\tRuminococcus callidus\tRuminococcus lactaris\tSubdoligranulum unclassified\tCoprobacillus unclassified\tAcidaminococcus unclassified\tDialister invisus\tVeillonella atypica\tVeillonella dispar\tVeillonella parvula\tVeillonella unclassified\tBurkholderiales bacterium 1 1 47\tParasutterella excrementihominis\tSutterella wadsworthensis\tBilophila unclassified\tEscherichia coli\tEscherichia unclassified\tKlebsiella pneumoniae\tHaemophilus parainfluenzae\tAkkermansia muciniphila\tC2likevirus unclassified\n+CSM5FZ4M\t0\t0\t0\t0\t0\t2.99E-05\t0\t0.130632\t0\t0\t0\t0\t0\t0\t0.190863\t0.0090411\t0\t0.0199315\t0.325812\t3.62E-05\t0.011119\t0\t0\t0\t0\t0.0026035\t0\t0\t0.0605912\t0\t0\t0\t6.78E-05\t0.0041528\t0.0587475\t0\t0\t0\t3.69E-05\t0\t7.88E-05\t0\t0.0008177\t0\t0\t0\t0\t0.0015772\t0\t0.0028149\t0\t0\t0.0007802\t0.0016194\t0.0010076\t0.0013645\t0.00307\t0\t0\t0\t0\t0\t0\t0.0041547\t0\t0.0936191\t0.0071109\t0\t0\t0.0156577\t0\t0.0287905\t0\t0\t0\t0\t0\t0\t0\t0\t0.0004782\t0.0010136\t0\t0\t0\t0\t0\n+CSM5MCUO\t0.0002803\t0\t0.0002857\t0\t0.0002506\t0.025743\t0.0003977\t0.0057939\t0\t0.0025964\t0\t0.0062334\t0\t0\t0.0344354\t0.0129821\t0.0836427\t0.0006236\t0.0677076\t0.169157\t0.0009044\t0.0024183\t0.0195324\t0\t0.0030421\t0\t0\t0.0026058\t0\t0.0071178\t0.0203598\t0\t0\t0.0034786\t0.047193\t0.0021057\t0\t0\t6.96E-05\t4.3E-06\t0\t1.94E-05\t0\t0\t0\t7.25E-05\t0.0745387\t0.0001715\t0.0377607\t0\t0\t0\t0\t0.0012169\t0.002148\t0.0013398\t0.0081932\t0.0001191\t0.0016632\t9.11E-05\t0.067003\t0.0075671\t0\t0\t0.00194\t0.160706\t0\t0\t0.0005857\t0.0320903\t0\t0\t0\t0\t0\t2.06E-05\t4.24E-05\t0.000971\t0.0086767\t0\t0.0011601\t0.0026399\t0\t0.0044638\t0.000241\t0\t0\n+CSM5MCVL\t0\t0\t0\t0\t0.000644\t0\t0\t3.04E-05\t0\t0\t0\t0.260366\t0\t0\t2.46E-05\t0\t0\t0.129383\t0\t0.314003\t0.0232747\t0\t0\t0\t0\t0\t0\t0\t0.0001241\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0.0043222\t0\t0.0276218\t0.0071817\t0\t0.0012594\t0\t0.0047196\t0\t0\t0.0145548\t0\t0\t0\t7.3E-05\t0\t0.000822\t0\t6.43E-05\t0\t2.08E-05\t0.02246\t0\t0\t0\t0\t0\t0.0001213\t0\t0\t0\t0\t0.0005083\t0.0096519\t0.0239\t0\t0\t0\t0\t0\t0\t0\t0\t0.0112689\t0\t0.0138117\t0\t0\t0.0141917\n+CSM5MCVN\t0\t0\t0\t0\t7.9E-06\t0\t0\t6.2E-06\t0\t0\t0\t0.149041\t0\t1.25E-05\t0\t0\t0\t0.0832982\t0\t0.423798\t0.0164535\t0\t0\t0\t0\t0\t0\t0\t0.0006701\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0.001367\t0\t0.0884657\t0.0005971\t0\t0.0018467\t0\t0.0012898\t0\t0.0002252\t0.018187\t0\t0\t0\t0\t1.57E-05\t0\t0\t0.0053145\t0\t0.0010537\t0.0009666\t0\t0\t0\t0\t0\t0\t0\t0\t0\t7.68E-05\t2.18E-05\t0.122568\t0.0224342\t0\t0\t0\t0\t0\t0\t0\t0\t0.0001853\t0.0004242\t0\t0\t0\t0\n+CSM5MCW6\t0\t0\t0\t0\t0\t0\t0\t0.797928\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0.0033702\t0.0204998\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0.0387423\t0\t0.0090233\t0\t0.0157132\t0\t0\t0\t0.0032695\t0.0005009\t0.024'..b'929\t0\t0\t0\t0\t0.0051768\t0\t0\t0.0520471\t0\t0\t0\t0.0292367\t0\t0.0703022\t0.0114336\t0\t0\t0.0005963\t0\t0.0015297\t0\t0\t0.0007457\t0\t0.001502\t0\t0\t0\t0\t0\t0\t0.0030023\t0.0018862\t0.0015572\t0\t0\t0\t0.0002753\t0\t0\t0\t0.0010284\t0.0026192\t0.0014504\t0.134904\t0\t0\t0\t0.0102026\t9.87E-05\t0\t0.0341744\t0\t0\t0.0021856\t0.0005367\t0.0025325\t0.0041833\t0\t0.0031888\t0.0002023\t0.0001152\t0\t0.0462722\t0\t5.67E-05\n+MSM9VZME\t0\t0\t0\t0\t0.000108\t0\t0.191305\t0.000133\t0\t0\t0\t0.0212137\t0\t0\t0\t0\t0\t0.116593\t0.0279708\t0.151223\t0.0497393\t0\t0\t0\t0.0057036\t0.0067507\t0\t0\t0.0430962\t0\t0\t0\t0.0734549\t0\t0.0687556\t0.0100373\t0\t0\t0.0011548\t6.94E-05\t0.0023472\t7.96E-05\t0.0011102\t6.4E-05\t0\t0.0058978\t0\t0\t0\t0\t0\t0\t0.0020732\t0.0008888\t0.0047411\t0\t0\t0\t0.0001778\t0\t0\t0\t0.0004357\t0.0058538\t0\t0.052518\t0\t0\t0\t0.0537197\t0\t0\t0.0534006\t0\t0\t0\t0\t0.0046362\t0.0047355\t0\t0.0198739\t0.0001001\t0.0007056\t0\t0\t0\t0\n+MSM9VZMI\t0\t0\t0\t0\t5.03E-05\t0\t0.23942\t0.0001506\t0\t0\t0\t0.15187\t0\t0\t0\t0\t0\t0.0775714\t0.011215\t0.262249\t0.0290049\t0\t0\t0\t0.0052616\t0.0042727\t0\t0\t0.0248291\t0\t0\t0\t0.0409708\t0\t0.0770084\t0.0176112\t0\t0\t0.0002089\t2.94E-05\t0.0015217\t0.0001828\t0\t0.0002016\t0\t0.0006898\t0\t0\t0\t0\t0\t0\t0.0001476\t5.92E-05\t0\t0\t0\t0\t0\t0\t0\t0\t0.0001744\t0.0018425\t0\t0.0058649\t0\t0\t0\t0.0053152\t0\t0\t0.0179672\t0\t0\t7.2E-06\t6.67E-05\t0.0017386\t0.0018334\t0\t0.0021825\t0.0119374\t0\t0\t2.79E-05\t0\t0\n+MSM9VZMM\t0\t0\t0.0005431\t0\t0\t0.0077173\t0.105207\t0.0545479\t0\t0\t0.0507981\t0\t0\t0.0897776\t3.96E-05\t0\t0.110157\t1.86E-05\t0.229784\t0.0670108\t0.0055243\t0.001652\t0.0346675\t0\t0.0144093\t0\t0\t0.0071537\t0\t0\t0\t0\t0.0075362\t0.0124354\t0.0362555\t0.0114376\t0\t0\t0\t0\t0\t0\t0\t0\t0\t5.45E-05\t0.0037208\t3.9E-06\t0.0013245\t0.0106458\t0\t0\t0\t5.98E-05\t0.0015887\t5.2E-06\t6.93E-05\t0\t0\t0.0010407\t0.0087262\t0.0015442\t0\t0.0008608\t0\t0.0841029\t0.0006899\t0\t0.0003777\t0.0131362\t0\t0\t0\t1.61E-05\t5.18E-05\t0.0004447\t0.0004656\t0\t0\t0.0118569\t0.0012579\t7.09E-05\t0\t0\t0.0018841\t0\t0\n+MSM9VZMO\t0.0001032\t0\t0.0001227\t0\t0\t0.0051527\t0.0854059\t0.0788849\t0\t0\t0.0342483\t0\t0\t0.0742246\t0\t0\t0.0179618\t3E-05\t0.108286\t0.0216667\t0.0071065\t0.0371525\t0.0755412\t0\t0.0200019\t0\t0\t0.0083959\t0\t0\t0\t0\t0.0127808\t0.0452772\t0.0972768\t0.0196866\t0\t0.0001942\t0\t0\t0\t0\t0\t0\t0\t0\t0.0028064\t0\t0.0145985\t0.0422064\t0\t0\t0\t0.0001582\t0.0014032\t0\t2.87E-05\t0\t0\t0.0212697\t0.0090858\t0.0001764\t0\t0.0009056\t0.0008713\t0.0837065\t0.0002669\t0.000418\t2.59E-05\t0.0321593\t0\t0\t0\t0.0008068\t0.0008692\t0.0005399\t0.0030484\t0\t0\t0.0152902\t0.0003471\t0.0003364\t0.0004267\t0\t0.0099232\t0\t0\n+MSM9VZMS\t9.94E-05\t0\t0.0002625\t0\t0\t0.0061244\t0.0713364\t0.0839264\t0\t0\t0.046204\t0\t0\t0.0925901\t0\t0\t0.0271915\t7.46E-05\t0.107064\t0.0250858\t0.0035575\t0.0247351\t0.0509968\t0\t0.0187663\t0\t0\t0.0172094\t0\t0\t0\t0\t0.0109501\t0.0279867\t0.0968872\t0.0159956\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0.0025534\t0.0002755\t0.0243386\t0.0597572\t0\t0\t0\t0.0017949\t0.0009681\t0\t0.0003959\t0\t0\t0.0242507\t0.0197799\t0.0004468\t0\t0.0016974\t0\t0.0915271\t0.0022387\t0.0009456\t0.000608\t0.0187437\t0\t0\t0\t0.0003442\t0.0004414\t0.0012203\t0.0007515\t0\t7.51E-05\t0.0122227\t0.0001303\t0\t0\t0\t0.0018513\t0\t0\n+MSM9VZMU\t0.0001206\t0\t0.0001581\t0\t5.8E-05\t0.0048656\t0.0998666\t0.0645561\t0\t0\t0.0409275\t0\t0\t0.0650844\t1.56E-05\t0\t0.0378778\t0\t0.124656\t0.0236297\t0.0050342\t0.0217115\t0.0616114\t0\t0.0166771\t0\t0\t0.0169516\t0\t0\t0\t0\t0.0090507\t0.0231818\t0.0864844\t0.0141578\t0\t0\t0\t0\t0\t0\t3.68E-05\t0\t0\t0\t0.0022385\t0.0001456\t0.0174219\t0.0556441\t0\t0\t0\t0.0001221\t0.0008884\t0\t0\t0.0005516\t0\t0.0126853\t0.0202313\t0.000705\t0\t0.0011717\t0\t0.112018\t0.0026062\t0.0007356\t0.0004748\t0.0214564\t0\t0\t0\t1.66E-05\t0.0001945\t0.0005091\t0.0002599\t2.47E-05\t0.0001786\t0.0173983\t0.0004678\t0.0001086\t1.21E-05\t0\t0.0036507\t0\t0\n+MSM9VZMW\t0.0012569\t0\t0.0003438\t0\t0.0003153\t0.0033297\t0.0768685\t0.0368513\t0\t0\t0.0135074\t0\t0\t0.0717403\t0\t0\t0.0125568\t2.69E-05\t0.0940726\t0.0138323\t0.0046885\t0.0798308\t0.068879\t0\t0.0197053\t0\t0\t0.0046808\t0\t0\t0\t0\t0.0262443\t0.0557565\t0.133181\t0.0512599\t0\t0.000117\t0\t0\t0\t0\t0\t0\t0\t0\t0.0033192\t0.0001365\t0.0173356\t0.0583453\t0\t0\t0\t0.0001536\t0.0012564\t0\t0\t0.0002727\t0\t0.017555\t0.0083024\t0.000177\t0\t0.000762\t0.0036406\t0.0534358\t0.0005022\t0.0010192\t1.96E-05\t0.0112984\t0\t0\t0\t0.0002487\t0.0003399\t0.0009258\t0.0027059\t5E-06\t0.0001013\t0.0358018\t0.0006067\t0.000432\t8.04E-05\t0\t0.0023856\t0\t0\n'