Mercurial > repos > bebatut > format_metaphlan2_output

changeset 0:2bfa9b200600 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/format_metaphlan2_output/ commit 36388cac89e4ffa55fe317d10cbf97346ab00a71-dirty
author bebatut
date Wed, 20 Apr 2016 07:52:41 -0400
parents
children 1e74cb2c8e67
files format_metaphlan2_output.py format_metaphlan2_output.xml test-data/all_taxo_level_abundance.txt test-data/class_abundance.txt test-data/family_abundance.txt test-data/genus_abundance.txt test-data/kingdom_abundance.txt test-data/metaphlan2_output.txt test-data/order_abundance.txt test-data/phylum_abundance.txt test-data/species_abundance.txt test-data/strains_abundance.txt
diffstat 12 files changed, 495 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/format_metaphlan2_output.py	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,97 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import sys
+import os
+import argparse
+import re
+
+taxo_level_correspondance = {}
+taxo_level_correspondance['k'] = 'kingdom'
+taxo_level_correspondance['p'] = 'phylum'
+taxo_level_correspondance['c'] = 'class'
+taxo_level_correspondance['o'] = 'order'
+taxo_level_correspondance['f'] = 'family'
+taxo_level_correspondance['g'] = 'genus'
+taxo_level_correspondance['s'] = 'species'
+taxo_level_correspondance['t'] = 'strains'
+
+def write_taxo_abundance(output_files, level, taxo, abundance):
+    if not taxo_level_correspondance.has_key(level):
+        raise ValueError(level + ' is not a know taxonomic level')
+    output_files[taxo_level_correspondance[level]].write(taxo + '\t')
+    output_files[taxo_level_correspondance[level]].write(abundance + '\n')
+
+def format_metaphlan2_output(args):
+    taxo_levels_abundance_files = {}
+    taxo_levels_abundance_files['kingdom'] = open(args.kingdom_abundance_file, 'w')
+    taxo_levels_abundance_files['phylum'] = open(args.phylum_abundance_file, 'w')
+    taxo_levels_abundance_files['class'] = open(args.class_abundance_file, 'w')
+    taxo_levels_abundance_files['order'] = open(args.order_abundance_file, 'w')
+    taxo_levels_abundance_files['family'] = open(args.family_abundance_file, 'w')
+    taxo_levels_abundance_files['genus'] = open(args.genus_abundance_file, 'w')
+    taxo_levels_abundance_files['species'] = open(args.species_abundance_file, 'w')
+    taxo_levels_abundance_files['strains'] = open(args.strains_abundance_file, 'w')
+
+    for taxo_level_file in taxo_levels_abundance_files:
+        taxo_levels_abundance_files[taxo_level_file].write(taxo_level_file + '\t')
+        taxo_levels_abundance_files[taxo_level_file].write('abundance\n')
+
+    with open(args.metaphlan2_output, 'r') as input_file:
+        with open(args.all_taxo_level_abundance_file, 'w') as output_file:
+            output_file.write("kingdom\t")
+            output_file.write("phylum\t")
+            output_file.write("class\t")
+            output_file.write("order\t")
+            output_file.write("family\t")
+            output_file.write("genus\t")
+            output_file.write("species\t")
+            output_file.write("strains\t")
+            output_file.write("abundance\n")
+            levels_number = 8
+
+            for line in input_file.readlines():
+                if line.startswith("#"):
+                    continue
+
+                split_line = line[:-1].split('\t')
+                all_taxo = split_line[0]
+                abundance = split_line[1]
+
+                split_taxo = all_taxo.split('|')
+                for level in split_taxo:
+                    taxo = level.split('__')[1]
+                    taxo = taxo.replace("_"," ")
+                    output_file.write(taxo + '\t')
+
+                for i in range(len(split_taxo), levels_number):
+                    output_file.write('\t')
+
+                output_file.write(abundance + "\n")
+
+
+                last_taxo_level = split_taxo[-1].split('__')
+                taxo = last_taxo_level[1].replace("_"," ")
+                level = last_taxo_level[0]
+                write_taxo_abundance(taxo_levels_abundance_files, level, taxo, 
+                    abundance)
+
+    for taxo_level_file in taxo_levels_abundance_files:
+        taxo_levels_abundance_files[taxo_level_file].close()
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--metaphlan2_output', required=True)
+    parser.add_argument('--all_taxo_level_abundance_file', required=True)
+    parser.add_argument('--kingdom_abundance_file', required=True)
+    parser.add_argument('--phylum_abundance_file', required=True)
+    parser.add_argument('--class_abundance_file', required=True)
+    parser.add_argument('--order_abundance_file', required=True)
+    parser.add_argument('--family_abundance_file', required=True)
+    parser.add_argument('--genus_abundance_file', required=True)
+    parser.add_argument('--species_abundance_file', required=True)
+    parser.add_argument('--strains_abundance_file', required=True)
+    
+    args = parser.parse_args()
+
+    format_metaphlan2_output(args)
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/format_metaphlan2_output.xml	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,67 @@
+<tool id="format_metaphlan2_output" name="Format MetaPhlAn2" version="0.1.0">
+    <description>output to extract abundance at different taxonomic levels</description>
+
+    <requirements>
+    </requirements>
+
+    <stdio>
+    </stdio>
+
+    <version_command></version_command>
+
+    <command><![CDATA[
+        python $__tool_directory__/format_metaphlan2_output.py
+            --metaphlan2_output $input_file
+            --all_taxo_level_abundance_file $all_taxo_level_abundance_file
+            --kingdom_abundance_file $kingdom_abundance_file
+            --phylum_abundance_file $phylum_abundance_file
+            --class_abundance_file $class_abundance_file
+            --order_abundance_file $order_abundance_file
+            --family_abundance_file $family_abundance_file
+            --genus_abundance_file $genus_abundance_file
+            --species_abundance_file $species_abundance_file
+            --strains_abundance_file $strains_abundance_file
+    ]]></command>
+
+    <inputs>
+        <param name="input_file" type="data" format="tabular,tsv,csv" label="Input file" help="Output file of MetaPhlAN with all taxonomic levels (from kingdom to strains, --metaphlan2_output)"/>
+    </inputs>
+
+    <outputs>
+        <data name="all_taxo_level_abundance_file" format="tabular" label="${tool.name} on ${on_string}: Abundances for all taxonomic levels" />
+        <data name="kingdom_abundance_file" format="tabular" label="${tool.name} on ${on_string}: Kingdom abundances" />
+        <data name="phylum_abundance_file" format="tabular" label="${tool.name} on ${on_string}: Phylum abundances" />
+        <data name="class_abundance_file" format="tabular" label="${tool.name} on ${on_string}: Class abundances" />
+        <data name="order_abundance_file" format="tabular" label="${tool.name} on ${on_string}: Order abundances" />
+        <data name="family_abundance_file" format="tabular" label="${tool.name} on ${on_string}: Family abundances" />
+        <data name="genus_abundance_file" format="tabular" label="${tool.name} on ${on_string}: Genus abundances" />
+        <data name="species_abundance_file" format="tabular" label="${tool.name} on ${on_string}: Species abundances" />
+        <data name="strains_abundance_file" format="tabular" label="${tool.name} on ${on_string}: Stain abundances" />
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="input_file" value="metaphlan2_output.txt"/>
+            <output name="all_taxo_level_abundance_file" file="all_taxo_level_abundance.txt"/>
+            <output name="kingdom_abundance_file" file="kingdom_abundance.txt"/>
+            <output name="phylum_abundance_file" file="phylum_abundance.txt"/>
+            <output name="class_abundance_file" file="class_abundance.txt"/>
+            <output name="order_abundance_file" file="order_abundance.txt"/>
+            <output name="family_abundance_file" file="family_abundance.txt"/>
+            <output name="genus_abundance_file" file="genus_abundance.txt"/>
+            <output name="species_abundance_file" file="species_abundance.txt"/>
+            <output name="strains_abundance_file" file="strains_abundance.txt"/>
+        </test>
+    </tests>
+
+    <help><![CDATA[
+**What it does**
+
+This tool format output file of MetaPhlan2 containing community content (abundance) at all taxonomic levels (from kingdom to strains).
+
+9 files are generated: one file per taxonomic levels with abundance for corresponding clades and one file combining all taxonomic levels and corresponding abundances.
+    ]]></help>
+
+    <citations>
+    </citations>
+</tool>
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/all_taxo_level_abundance.txt	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,108 @@
+kingdom	phylum	class	order	family	genus	species	strains	abundance
+Bacteria								99.20573
+Archaea								0.79427
+Bacteria	Deinococcus Thermus							45.20297
+Bacteria	Firmicutes							19.15406
+Bacteria	Proteobacteria							16.57369
+Bacteria	Actinobacteria							10.37863
+Bacteria	Bacteroidetes							7.89639
+Archaea	Euryarchaeota							0.79427
+Bacteria	Deinococcus Thermus	Deinococci						45.20297
+Bacteria	Firmicutes	Bacilli						17.33469
+Bacteria	Actinobacteria	Actinobacteria						10.37863
+Bacteria	Proteobacteria	Gammaproteobacteria						8.28554
+Bacteria	Bacteroidetes	Bacteroidia						7.89639
+Bacteria	Proteobacteria	Epsilonproteobacteria						4.03024
+Bacteria	Proteobacteria	Betaproteobacteria						3.73739
+Bacteria	Firmicutes	Clostridia						1.81937
+Archaea	Euryarchaeota	Methanobacteria						0.79427
+Bacteria	Proteobacteria	Alphaproteobacteria						0.52051
+Bacteria	Deinococcus Thermus	Deinococci	Deinococcales					45.20297
+Bacteria	Actinobacteria	Actinobacteria	Actinomycetales					10.37863
+Bacteria	Firmicutes	Bacilli	Bacillales					9.19153
+Bacteria	Firmicutes	Bacilli	Lactobacillales					8.14315
+Bacteria	Bacteroidetes	Bacteroidia	Bacteroidales					7.89639
+Bacteria	Proteobacteria	Gammaproteobacteria	Pseudomonadales					6.58945
+Bacteria	Proteobacteria	Epsilonproteobacteria	Campylobacterales					4.03024
+Bacteria	Proteobacteria	Betaproteobacteria	Neisseriales					3.73739
+Bacteria	Firmicutes	Clostridia	Clostridiales					1.81937
+Bacteria	Proteobacteria	Gammaproteobacteria	Enterobacteriales					1.6961
+Archaea	Euryarchaeota	Methanobacteria	Methanobacteriales					0.79427
+Bacteria	Proteobacteria	Alphaproteobacteria	Rhodobacterales					0.52051
+Bacteria	Deinococcus Thermus	Deinococci	Deinococcales	Deinococcaceae				45.20297
+Bacteria	Bacteroidetes	Bacteroidia	Bacteroidales	Bacteroidaceae				7.89639
+Bacteria	Firmicutes	Bacilli	Bacillales	Staphylococcaceae				7.4516
+Bacteria	Actinobacteria	Actinobacteria	Actinomycetales	Propionibacteriaceae				6.71696
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Streptococcaceae				6.43313
+Bacteria	Proteobacteria	Gammaproteobacteria	Pseudomonadales	Moraxellaceae				5.88648
+Bacteria	Proteobacteria	Epsilonproteobacteria	Campylobacterales	Helicobacteraceae				4.03024
+Bacteria	Proteobacteria	Betaproteobacteria	Neisseriales	Neisseriaceae				3.73739
+Bacteria	Actinobacteria	Actinobacteria	Actinomycetales	Actinomycetaceae				3.66166
+Bacteria	Firmicutes	Clostridia	Clostridiales	Clostridiaceae				1.81937
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Enterococcaceae				1.71002
+Bacteria	Proteobacteria	Gammaproteobacteria	Enterobacteriales	Enterobacteriaceae				1.6961
+Bacteria	Firmicutes	Bacilli	Bacillales	Listeriaceae				1.58307
+Archaea	Euryarchaeota	Methanobacteria	Methanobacteriales	Methanobacteriaceae				0.79427
+Bacteria	Proteobacteria	Gammaproteobacteria	Pseudomonadales	Pseudomonadaceae				0.70297
+Bacteria	Proteobacteria	Alphaproteobacteria	Rhodobacterales	Rhodobacteraceae				0.52051
+Bacteria	Firmicutes	Bacilli	Bacillales	Bacillaceae				0.15687
+Bacteria	Deinococcus Thermus	Deinococci	Deinococcales	Deinococcaceae	Deinococcus			45.20297
+Bacteria	Bacteroidetes	Bacteroidia	Bacteroidales	Bacteroidaceae	Bacteroides			7.89639
+Bacteria	Firmicutes	Bacilli	Bacillales	Staphylococcaceae	Staphylococcus			7.4516
+Bacteria	Actinobacteria	Actinobacteria	Actinomycetales	Propionibacteriaceae	Propionibacterium			6.71696
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Streptococcaceae	Streptococcus			6.43313
+Bacteria	Proteobacteria	Gammaproteobacteria	Pseudomonadales	Moraxellaceae	Acinetobacter			5.88648
+Bacteria	Proteobacteria	Epsilonproteobacteria	Campylobacterales	Helicobacteraceae	Helicobacter			4.03024
+Bacteria	Proteobacteria	Betaproteobacteria	Neisseriales	Neisseriaceae	Neisseria			3.73739
+Bacteria	Actinobacteria	Actinobacteria	Actinomycetales	Actinomycetaceae	Actinomyces			3.66166
+Bacteria	Firmicutes	Clostridia	Clostridiales	Clostridiaceae	Clostridium			1.81937
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Enterococcaceae	Enterococcus			1.71002
+Bacteria	Proteobacteria	Gammaproteobacteria	Enterobacteriales	Enterobacteriaceae	Escherichia			1.6961
+Bacteria	Firmicutes	Bacilli	Bacillales	Listeriaceae	Listeria			1.58307
+Archaea	Euryarchaeota	Methanobacteria	Methanobacteriales	Methanobacteriaceae	Methanobrevibacter			0.79427
+Bacteria	Proteobacteria	Gammaproteobacteria	Pseudomonadales	Pseudomonadaceae	Pseudomonas			0.70297
+Bacteria	Proteobacteria	Alphaproteobacteria	Rhodobacterales	Rhodobacteraceae	Rhodobacter			0.52051
+Bacteria	Firmicutes	Bacilli	Bacillales	Bacillaceae	Bacillus			0.15687
+Bacteria	Deinococcus Thermus	Deinococci	Deinococcales	Deinococcaceae	Deinococcus	Deinococcus radiodurans		45.20297
+Bacteria	Bacteroidetes	Bacteroidia	Bacteroidales	Bacteroidaceae	Bacteroides	Bacteroides vulgatus		7.89639
+Bacteria	Actinobacteria	Actinobacteria	Actinomycetales	Propionibacteriaceae	Propionibacterium	Propionibacterium acnes		6.71696
+Bacteria	Proteobacteria	Gammaproteobacteria	Pseudomonadales	Moraxellaceae	Acinetobacter	Acinetobacter baumannii		5.88648
+Bacteria	Firmicutes	Bacilli	Bacillales	Staphylococcaceae	Staphylococcus	Staphylococcus epidermidis		4.54517
+Bacteria	Proteobacteria	Epsilonproteobacteria	Campylobacterales	Helicobacteraceae	Helicobacter	Helicobacter pylori		4.03024
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Streptococcaceae	Streptococcus	Streptococcus mitis oralis pneumoniae		4.02995
+Bacteria	Proteobacteria	Betaproteobacteria	Neisseriales	Neisseriaceae	Neisseria	Neisseria meningitidis		3.73739
+Bacteria	Actinobacteria	Actinobacteria	Actinomycetales	Actinomycetaceae	Actinomyces	Actinomyces odontolyticus		3.66166
+Bacteria	Firmicutes	Bacilli	Bacillales	Staphylococcaceae	Staphylococcus	Staphylococcus aureus		2.90642
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Streptococcaceae	Streptococcus	Streptococcus mutans		2.35195
+Bacteria	Firmicutes	Clostridia	Clostridiales	Clostridiaceae	Clostridium	Clostridium beijerinckii		1.81937
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Enterococcaceae	Enterococcus	Enterococcus faecalis		1.71002
+Bacteria	Firmicutes	Bacilli	Bacillales	Listeriaceae	Listeria	Listeria monocytogenes		1.58307
+Bacteria	Proteobacteria	Gammaproteobacteria	Enterobacteriales	Enterobacteriaceae	Escherichia	Escherichia coli		0.89751
+Bacteria	Proteobacteria	Gammaproteobacteria	Enterobacteriales	Enterobacteriaceae	Escherichia	Escherichia unclassified		0.79859
+Bacteria	Proteobacteria	Gammaproteobacteria	Pseudomonadales	Pseudomonadaceae	Pseudomonas	Pseudomonas unclassified		0.55542
+Archaea	Euryarchaeota	Methanobacteria	Methanobacteriales	Methanobacteriaceae	Methanobrevibacter	Methanobrevibacter smithii		0.55066
+Bacteria	Proteobacteria	Alphaproteobacteria	Rhodobacterales	Rhodobacteraceae	Rhodobacter	Rhodobacter sphaeroides		0.52051
+Archaea	Euryarchaeota	Methanobacteria	Methanobacteriales	Methanobacteriaceae	Methanobrevibacter	Methanobrevibacter unclassified		0.24361
+Bacteria	Firmicutes	Bacilli	Bacillales	Bacillaceae	Bacillus	Bacillus cereus thuringiensis		0.15687
+Bacteria	Proteobacteria	Gammaproteobacteria	Pseudomonadales	Pseudomonadaceae	Pseudomonas	Pseudomonas aeruginosa		0.14755
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Streptococcaceae	Streptococcus	Streptococcus agalactiae		0.05124
+Bacteria	Deinococcus Thermus	Deinococci	Deinococcales	Deinococcaceae	Deinococcus	Deinococcus radiodurans	GCF 000008565	45.20297
+Bacteria	Bacteroidetes	Bacteroidia	Bacteroidales	Bacteroidaceae	Bacteroides	Bacteroides vulgatus	GCF 000012825	7.89639
+Bacteria	Actinobacteria	Actinobacteria	Actinomycetales	Propionibacteriaceae	Propionibacterium	Propionibacterium acnes	Propionibacterium acnes unclassified	6.71696
+Bacteria	Proteobacteria	Gammaproteobacteria	Pseudomonadales	Moraxellaceae	Acinetobacter	Acinetobacter baumannii	Acinetobacter baumannii unclassified	5.88648
+Bacteria	Firmicutes	Bacilli	Bacillales	Staphylococcaceae	Staphylococcus	Staphylococcus epidermidis	Staphylococcus epidermidis unclassified	4.54517
+Bacteria	Proteobacteria	Epsilonproteobacteria	Campylobacterales	Helicobacteraceae	Helicobacter	Helicobacter pylori	Helicobacter pylori unclassified	4.03024
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Streptococcaceae	Streptococcus	Streptococcus mitis oralis pneumoniae	Streptococcus mitis oralis pneumoniae unclassified	4.02995
+Bacteria	Proteobacteria	Betaproteobacteria	Neisseriales	Neisseriaceae	Neisseria	Neisseria meningitidis	Neisseria meningitidis unclassified	3.73739
+Bacteria	Actinobacteria	Actinobacteria	Actinomycetales	Actinomycetaceae	Actinomyces	Actinomyces odontolyticus	Actinomyces odontolyticus unclassified	3.66166
+Bacteria	Firmicutes	Bacilli	Bacillales	Staphylococcaceae	Staphylococcus	Staphylococcus aureus	Staphylococcus aureus unclassified	2.90642
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Streptococcaceae	Streptococcus	Streptococcus mutans	Streptococcus mutans unclassified	2.35195
+Bacteria	Firmicutes	Clostridia	Clostridiales	Clostridiaceae	Clostridium	Clostridium beijerinckii	Clostridium beijerinckii unclassified	1.81937
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Enterococcaceae	Enterococcus	Enterococcus faecalis	Enterococcus faecalis unclassified	1.71002
+Bacteria	Firmicutes	Bacilli	Bacillales	Listeriaceae	Listeria	Listeria monocytogenes	Listeria monocytogenes unclassified	1.58307
+Bacteria	Proteobacteria	Gammaproteobacteria	Enterobacteriales	Enterobacteriaceae	Escherichia	Escherichia coli	Escherichia coli unclassified	0.89751
+Archaea	Euryarchaeota	Methanobacteria	Methanobacteriales	Methanobacteriaceae	Methanobrevibacter	Methanobrevibacter smithii	Methanobrevibacter smithii unclassified	0.55066
+Bacteria	Proteobacteria	Alphaproteobacteria	Rhodobacterales	Rhodobacteraceae	Rhodobacter	Rhodobacter sphaeroides	Rhodobacter sphaeroides unclassified	0.52051
+Bacteria	Firmicutes	Bacilli	Bacillales	Bacillaceae	Bacillus	Bacillus cereus thuringiensis	Bacillus cereus thuringiensis unclassified	0.15687
+Bacteria	Proteobacteria	Gammaproteobacteria	Pseudomonadales	Pseudomonadaceae	Pseudomonas	Pseudomonas aeruginosa	Pseudomonas aeruginosa unclassified	0.14755
+Bacteria	Firmicutes	Bacilli	Lactobacillales	Streptococcaceae	Streptococcus	Streptococcus agalactiae	Streptococcus agalactiae unclassified	0.05124
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/class_abundance.txt	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,11 @@
+class	abundance
+Deinococci	45.20297
+Bacilli	17.33469
+Actinobacteria	10.37863
+Gammaproteobacteria	8.28554
+Bacteroidia	7.89639
+Epsilonproteobacteria	4.03024
+Betaproteobacteria	3.73739
+Clostridia	1.81937
+Methanobacteria	0.79427
+Alphaproteobacteria	0.52051
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/family_abundance.txt	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,18 @@
+family	abundance
+Deinococcaceae	45.20297
+Bacteroidaceae	7.89639
+Staphylococcaceae	7.4516
+Propionibacteriaceae	6.71696
+Streptococcaceae	6.43313
+Moraxellaceae	5.88648
+Helicobacteraceae	4.03024
+Neisseriaceae	3.73739
+Actinomycetaceae	3.66166
+Clostridiaceae	1.81937
+Enterococcaceae	1.71002
+Enterobacteriaceae	1.6961
+Listeriaceae	1.58307
+Methanobacteriaceae	0.79427
+Pseudomonadaceae	0.70297
+Rhodobacteraceae	0.52051
+Bacillaceae	0.15687
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/genus_abundance.txt	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,18 @@
+genus	abundance
+Deinococcus	45.20297
+Bacteroides	7.89639
+Staphylococcus	7.4516
+Propionibacterium	6.71696
+Streptococcus	6.43313
+Acinetobacter	5.88648
+Helicobacter	4.03024
+Neisseria	3.73739
+Actinomyces	3.66166
+Clostridium	1.81937
+Enterococcus	1.71002
+Escherichia	1.6961
+Listeria	1.58307
+Methanobrevibacter	0.79427
+Pseudomonas	0.70297
+Rhodobacter	0.52051
+Bacillus	0.15687
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/kingdom_abundance.txt	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,3 @@
+kingdom	abundance
+Bacteria	99.20573
+Archaea	0.79427
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/metaphlan2_output.txt	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,108 @@
+#SampleID	Metaphlan2_Analysis
+k__Bacteria	99.20573
+k__Archaea	0.79427
+k__Bacteria|p__Deinococcus_Thermus	45.20297
+k__Bacteria|p__Firmicutes	19.15406
+k__Bacteria|p__Proteobacteria	16.57369
+k__Bacteria|p__Actinobacteria	10.37863
+k__Bacteria|p__Bacteroidetes	7.89639
+k__Archaea|p__Euryarchaeota	0.79427
+k__Bacteria|p__Deinococcus_Thermus|c__Deinococci	45.20297
+k__Bacteria|p__Firmicutes|c__Bacilli	17.33469
+k__Bacteria|p__Actinobacteria|c__Actinobacteria	10.37863
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria	8.28554
+k__Bacteria|p__Bacteroidetes|c__Bacteroidia	7.89639
+k__Bacteria|p__Proteobacteria|c__Epsilonproteobacteria	4.03024
+k__Bacteria|p__Proteobacteria|c__Betaproteobacteria	3.73739
+k__Bacteria|p__Firmicutes|c__Clostridia	1.81937
+k__Archaea|p__Euryarchaeota|c__Methanobacteria	0.79427
+k__Bacteria|p__Proteobacteria|c__Alphaproteobacteria	0.52051
+k__Bacteria|p__Deinococcus_Thermus|c__Deinococci|o__Deinococcales	45.20297
+k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Actinomycetales	10.37863
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales	9.19153
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales	8.14315
+k__Bacteria|p__Bacteroidetes|c__Bacteroidia|o__Bacteroidales	7.89639
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales	6.58945
+k__Bacteria|p__Proteobacteria|c__Epsilonproteobacteria|o__Campylobacterales	4.03024
+k__Bacteria|p__Proteobacteria|c__Betaproteobacteria|o__Neisseriales	3.73739
+k__Bacteria|p__Firmicutes|c__Clostridia|o__Clostridiales	1.81937
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Enterobacteriales	1.6961
+k__Archaea|p__Euryarchaeota|c__Methanobacteria|o__Methanobacteriales	0.79427
+k__Bacteria|p__Proteobacteria|c__Alphaproteobacteria|o__Rhodobacterales	0.52051
+k__Bacteria|p__Deinococcus_Thermus|c__Deinococci|o__Deinococcales|f__Deinococcaceae	45.20297
+k__Bacteria|p__Bacteroidetes|c__Bacteroidia|o__Bacteroidales|f__Bacteroidaceae	7.89639
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Staphylococcaceae	7.4516
+k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Actinomycetales|f__Propionibacteriaceae	6.71696
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Streptococcaceae	6.43313
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae	5.88648
+k__Bacteria|p__Proteobacteria|c__Epsilonproteobacteria|o__Campylobacterales|f__Helicobacteraceae	4.03024
+k__Bacteria|p__Proteobacteria|c__Betaproteobacteria|o__Neisseriales|f__Neisseriaceae	3.73739
+k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Actinomycetales|f__Actinomycetaceae	3.66166
+k__Bacteria|p__Firmicutes|c__Clostridia|o__Clostridiales|f__Clostridiaceae	1.81937
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Enterococcaceae	1.71002
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Enterobacteriales|f__Enterobacteriaceae	1.6961
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Listeriaceae	1.58307
+k__Archaea|p__Euryarchaeota|c__Methanobacteria|o__Methanobacteriales|f__Methanobacteriaceae	0.79427
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Pseudomonadaceae	0.70297
+k__Bacteria|p__Proteobacteria|c__Alphaproteobacteria|o__Rhodobacterales|f__Rhodobacteraceae	0.52051
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Bacillaceae	0.15687
+k__Bacteria|p__Deinococcus_Thermus|c__Deinococci|o__Deinococcales|f__Deinococcaceae|g__Deinococcus	45.20297
+k__Bacteria|p__Bacteroidetes|c__Bacteroidia|o__Bacteroidales|f__Bacteroidaceae|g__Bacteroides	7.89639
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Staphylococcaceae|g__Staphylococcus	7.4516
+k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Actinomycetales|f__Propionibacteriaceae|g__Propionibacterium	6.71696
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Streptococcaceae|g__Streptococcus	6.43313
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Acinetobacter	5.88648
+k__Bacteria|p__Proteobacteria|c__Epsilonproteobacteria|o__Campylobacterales|f__Helicobacteraceae|g__Helicobacter	4.03024
+k__Bacteria|p__Proteobacteria|c__Betaproteobacteria|o__Neisseriales|f__Neisseriaceae|g__Neisseria	3.73739
+k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Actinomycetales|f__Actinomycetaceae|g__Actinomyces	3.66166
+k__Bacteria|p__Firmicutes|c__Clostridia|o__Clostridiales|f__Clostridiaceae|g__Clostridium	1.81937
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Enterococcaceae|g__Enterococcus	1.71002
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Enterobacteriales|f__Enterobacteriaceae|g__Escherichia	1.6961
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Listeriaceae|g__Listeria	1.58307
+k__Archaea|p__Euryarchaeota|c__Methanobacteria|o__Methanobacteriales|f__Methanobacteriaceae|g__Methanobrevibacter	0.79427
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Pseudomonadaceae|g__Pseudomonas	0.70297
+k__Bacteria|p__Proteobacteria|c__Alphaproteobacteria|o__Rhodobacterales|f__Rhodobacteraceae|g__Rhodobacter	0.52051
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Bacillaceae|g__Bacillus	0.15687
+k__Bacteria|p__Deinococcus_Thermus|c__Deinococci|o__Deinococcales|f__Deinococcaceae|g__Deinococcus|s__Deinococcus_radiodurans	45.20297
+k__Bacteria|p__Bacteroidetes|c__Bacteroidia|o__Bacteroidales|f__Bacteroidaceae|g__Bacteroides|s__Bacteroides_vulgatus	7.89639
+k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Actinomycetales|f__Propionibacteriaceae|g__Propionibacterium|s__Propionibacterium_acnes	6.71696
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Acinetobacter|s__Acinetobacter_baumannii	5.88648
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Staphylococcaceae|g__Staphylococcus|s__Staphylococcus_epidermidis	4.54517
+k__Bacteria|p__Proteobacteria|c__Epsilonproteobacteria|o__Campylobacterales|f__Helicobacteraceae|g__Helicobacter|s__Helicobacter_pylori	4.03024
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Streptococcaceae|g__Streptococcus|s__Streptococcus_mitis_oralis_pneumoniae	4.02995
+k__Bacteria|p__Proteobacteria|c__Betaproteobacteria|o__Neisseriales|f__Neisseriaceae|g__Neisseria|s__Neisseria_meningitidis	3.73739
+k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Actinomycetales|f__Actinomycetaceae|g__Actinomyces|s__Actinomyces_odontolyticus	3.66166
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Staphylococcaceae|g__Staphylococcus|s__Staphylococcus_aureus	2.90642
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Streptococcaceae|g__Streptococcus|s__Streptococcus_mutans	2.35195
+k__Bacteria|p__Firmicutes|c__Clostridia|o__Clostridiales|f__Clostridiaceae|g__Clostridium|s__Clostridium_beijerinckii	1.81937
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Enterococcaceae|g__Enterococcus|s__Enterococcus_faecalis	1.71002
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Listeriaceae|g__Listeria|s__Listeria_monocytogenes	1.58307
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Enterobacteriales|f__Enterobacteriaceae|g__Escherichia|s__Escherichia_coli	0.89751
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Enterobacteriales|f__Enterobacteriaceae|g__Escherichia|s__Escherichia_unclassified	0.79859
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Pseudomonadaceae|g__Pseudomonas|s__Pseudomonas_unclassified	0.55542
+k__Archaea|p__Euryarchaeota|c__Methanobacteria|o__Methanobacteriales|f__Methanobacteriaceae|g__Methanobrevibacter|s__Methanobrevibacter_smithii	0.55066
+k__Bacteria|p__Proteobacteria|c__Alphaproteobacteria|o__Rhodobacterales|f__Rhodobacteraceae|g__Rhodobacter|s__Rhodobacter_sphaeroides	0.52051
+k__Archaea|p__Euryarchaeota|c__Methanobacteria|o__Methanobacteriales|f__Methanobacteriaceae|g__Methanobrevibacter|s__Methanobrevibacter_unclassified	0.24361
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Bacillaceae|g__Bacillus|s__Bacillus_cereus_thuringiensis	0.15687
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Pseudomonadaceae|g__Pseudomonas|s__Pseudomonas_aeruginosa	0.14755
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Streptococcaceae|g__Streptococcus|s__Streptococcus_agalactiae	0.05124
+k__Bacteria|p__Deinococcus_Thermus|c__Deinococci|o__Deinococcales|f__Deinococcaceae|g__Deinococcus|s__Deinococcus_radiodurans|t__GCF_000008565	45.20297
+k__Bacteria|p__Bacteroidetes|c__Bacteroidia|o__Bacteroidales|f__Bacteroidaceae|g__Bacteroides|s__Bacteroides_vulgatus|t__GCF_000012825	7.89639
+k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Actinomycetales|f__Propionibacteriaceae|g__Propionibacterium|s__Propionibacterium_acnes|t__Propionibacterium_acnes_unclassified	6.71696
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Acinetobacter|s__Acinetobacter_baumannii|t__Acinetobacter_baumannii_unclassified	5.88648
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Staphylococcaceae|g__Staphylococcus|s__Staphylococcus_epidermidis|t__Staphylococcus_epidermidis_unclassified	4.54517
+k__Bacteria|p__Proteobacteria|c__Epsilonproteobacteria|o__Campylobacterales|f__Helicobacteraceae|g__Helicobacter|s__Helicobacter_pylori|t__Helicobacter_pylori_unclassified	4.03024
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Streptococcaceae|g__Streptococcus|s__Streptococcus_mitis_oralis_pneumoniae|t__Streptococcus_mitis_oralis_pneumoniae_unclassified	4.02995
+k__Bacteria|p__Proteobacteria|c__Betaproteobacteria|o__Neisseriales|f__Neisseriaceae|g__Neisseria|s__Neisseria_meningitidis|t__Neisseria_meningitidis_unclassified	3.73739
+k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Actinomycetales|f__Actinomycetaceae|g__Actinomyces|s__Actinomyces_odontolyticus|t__Actinomyces_odontolyticus_unclassified	3.66166
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Staphylococcaceae|g__Staphylococcus|s__Staphylococcus_aureus|t__Staphylococcus_aureus_unclassified	2.90642
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Streptococcaceae|g__Streptococcus|s__Streptococcus_mutans|t__Streptococcus_mutans_unclassified	2.35195
+k__Bacteria|p__Firmicutes|c__Clostridia|o__Clostridiales|f__Clostridiaceae|g__Clostridium|s__Clostridium_beijerinckii|t__Clostridium_beijerinckii_unclassified	1.81937
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Enterococcaceae|g__Enterococcus|s__Enterococcus_faecalis|t__Enterococcus_faecalis_unclassified	1.71002
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Listeriaceae|g__Listeria|s__Listeria_monocytogenes|t__Listeria_monocytogenes_unclassified	1.58307
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Enterobacteriales|f__Enterobacteriaceae|g__Escherichia|s__Escherichia_coli|t__Escherichia_coli_unclassified	0.89751
+k__Archaea|p__Euryarchaeota|c__Methanobacteria|o__Methanobacteriales|f__Methanobacteriaceae|g__Methanobrevibacter|s__Methanobrevibacter_smithii|t__Methanobrevibacter_smithii_unclassified	0.55066
+k__Bacteria|p__Proteobacteria|c__Alphaproteobacteria|o__Rhodobacterales|f__Rhodobacteraceae|g__Rhodobacter|s__Rhodobacter_sphaeroides|t__Rhodobacter_sphaeroides_unclassified	0.52051
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Bacillales|f__Bacillaceae|g__Bacillus|s__Bacillus_cereus_thuringiensis|t__Bacillus_cereus_thuringiensis_unclassified	0.15687
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Pseudomonadaceae|g__Pseudomonas|s__Pseudomonas_aeruginosa|t__Pseudomonas_aeruginosa_unclassified	0.14755
+k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Streptococcaceae|g__Streptococcus|s__Streptococcus_agalactiae|t__Streptococcus_agalactiae_unclassified	0.05124
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/order_abundance.txt	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,13 @@
+order	abundance
+Deinococcales	45.20297
+Actinomycetales	10.37863
+Bacillales	9.19153
+Lactobacillales	8.14315
+Bacteroidales	7.89639
+Pseudomonadales	6.58945
+Campylobacterales	4.03024
+Neisseriales	3.73739
+Clostridiales	1.81937
+Enterobacteriales	1.6961
+Methanobacteriales	0.79427
+Rhodobacterales	0.52051
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/phylum_abundance.txt	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,7 @@
+phylum	abundance
+Deinococcus Thermus	45.20297
+Firmicutes	19.15406
+Proteobacteria	16.57369
+Actinobacteria	10.37863
+Bacteroidetes	7.89639
+Euryarchaeota	0.79427
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/species_abundance.txt	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,24 @@
+species	abundance
+Deinococcus radiodurans	45.20297
+Bacteroides vulgatus	7.89639
+Propionibacterium acnes	6.71696
+Acinetobacter baumannii	5.88648
+Staphylococcus epidermidis	4.54517
+Helicobacter pylori	4.03024
+Streptococcus mitis oralis pneumoniae	4.02995
+Neisseria meningitidis	3.73739
+Actinomyces odontolyticus	3.66166
+Staphylococcus aureus	2.90642
+Streptococcus mutans	2.35195
+Clostridium beijerinckii	1.81937
+Enterococcus faecalis	1.71002
+Listeria monocytogenes	1.58307
+Escherichia coli	0.89751
+Escherichia unclassified	0.79859
+Pseudomonas unclassified	0.55542
+Methanobrevibacter smithii	0.55066
+Rhodobacter sphaeroides	0.52051
+Methanobrevibacter unclassified	0.24361
+Bacillus cereus thuringiensis	0.15687
+Pseudomonas aeruginosa	0.14755
+Streptococcus agalactiae	0.05124
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/strains_abundance.txt	Wed Apr 20 07:52:41 2016 -0400
@@ -0,0 +1,21 @@
+strains	abundance
+GCF 000008565	45.20297
+GCF 000012825	7.89639
+Propionibacterium acnes unclassified	6.71696
+Acinetobacter baumannii unclassified	5.88648
+Staphylococcus epidermidis unclassified	4.54517
+Helicobacter pylori unclassified	4.03024
+Streptococcus mitis oralis pneumoniae unclassified	4.02995
+Neisseria meningitidis unclassified	3.73739
+Actinomyces odontolyticus unclassified	3.66166
+Staphylococcus aureus unclassified	2.90642
+Streptococcus mutans unclassified	2.35195
+Clostridium beijerinckii unclassified	1.81937
+Enterococcus faecalis unclassified	1.71002
+Listeria monocytogenes unclassified	1.58307
+Escherichia coli unclassified	0.89751
+Methanobrevibacter smithii unclassified	0.55066
+Rhodobacter sphaeroides unclassified	0.52051
+Bacillus cereus thuringiensis unclassified	0.15687
+Pseudomonas aeruginosa unclassified	0.14755
+Streptococcus agalactiae unclassified	0.05124