Repository 'compare_humann2_output'
hg clone https://toolshed.g2.bx.psu.edu/repos/bebatut/compare_humann2_output

Changeset 2:05766022dfc4 (2020-09-14)
Previous changeset 1:c1aca37cb1fc (2016-04-20) Next changeset 3:eaa95ea1195c (2022-10-19)
Commit message:
"planemo upload for repository https://github.com/asaim/galaxytools/tree/master/tools/compare_humann2_output commit dc55dc3b5275d1d6aac390698c0c6e0ab8fbf2f7"
modified:
compare_humann2_output.py
compare_humann2_output.xml
added:
more_abundant_output_file
similar_output_file
specific_to_sample1.txt
specific_to_sample2.txt
removed:
test-data/more_abundant_pathways.tabular
test-data/sample_1_specific_pathways.txt
test-data/sample_2_specific_pathways.txt
test-data/sample_similar_pathways.tabular
b
diff -r c1aca37cb1fc -r 05766022dfc4 compare_humann2_output.py
--- a/compare_humann2_output.py Wed Apr 20 09:15:27 2016 -0400
+++ b/compare_humann2_output.py Mon Sep 14 13:50:30 2020 +0000
[
b'@@ -1,17 +1,15 @@\n #!/usr/bin/env python\n # -*- coding: utf-8 -*-\n \n-import sys\n-import os\n import argparse\n-import re\n+\n \n-def extract_abundances(filepath, nb_charact_to_extract):\n+def extract_abundances(fp, nb_charact_to_extract):\n     abundances = {}\n     more_abund_charact = []\n     abund_sum = 0\n-    with open(filepath, \'r\') as abundance_file:\n-        for line in abundance_file.readlines()[1:]:\n+    with open(fp, \'r\') as abundance_f:\n+        for line in abundance_f.readlines()[1:]:\n             split_line = line[:-1].split(\'\\t\')\n             charact_id = split_line[0]\n             abund = float(split_line[1])\n@@ -22,117 +20,134 @@\n                 more_abund_charact.append(charact_id)\n             else:\n                 best_pos = None\n-                for i in range(len(more_abund_charact)-1,-1,-1):\n+                for i in range(len(more_abund_charact)-1, -1, -1):\n                     if abundances[more_abund_charact[i]] < abund:\n                         best_pos = i\n                     else:\n                         break\n-                if best_pos != None:\n+                if best_pos is not None:\n                     tmp_more_abund_charact = more_abund_charact\n                     more_abund_charact = tmp_more_abund_charact[:best_pos]\n                     more_abund_charact += [charact_id]\n                     more_abund_charact += tmp_more_abund_charact[best_pos:-1]\n     return abundances, more_abund_charact\n \n+\n def format_characteristic_name(all_name):\n     if all_name.find(\':\') != -1:\n         charact_id = all_name.split(\':\')[0]\n-        charact_name = all_name.split(\':\')[1][1:]\n+        char_name = all_name.split(\':\')[1][1:]\n     else:\n         charact_id = all_name\n-        charact_name = \'\'\n+        char_name = \'\'\n \n-    charact_name = charact_name.replace(\'/\',\' \')\n-    charact_name = charact_name.replace(\'-\',\' \')\n-    charact_name = charact_name.replace("\'",\'\')\n-    if charact_name.find(\'(\') != -1 and charact_name.find(\')\') != -1:\n-        open_bracket = charact_name.find(\'(\')\n-        close_bracket = charact_name.find(\')\')+1\n-        charact_name = charact_name[:open_bracket] + charact_name[close_bracket:]\n-    return charact_id,charact_name\n+    char_name = char_name.replace(\'/\', \' \')\n+    char_name = char_name.replace(\'-\', \' \')\n+    char_name = char_name.replace("\'", \'\')\n+    if char_name.find(\'(\') != -1 and char_name.find(\')\') != -1:\n+        open_bracket = char_name.find(\'(\')\n+        close_bracket = char_name.find(\')\')+1\n+        char_name = char_name[:open_bracket] + char_name[close_bracket:]\n+    return charact_id, char_name\n \n-def write_more_abundant_charat(abundances,more_abund_charact, output_filepath):\n-    with open(output_filepath,\'w\') as output_file:\n-        output_file.write(\'id\\tname\\t\')\n-        output_file.write(\'\\t\'.join(abundances.keys()) + \'\\n\')\n+\n+def write_more_abundant_charat(abundances, more_abund_charact, output_fp):\n+    with open(output_fp, \'w\') as output_f:\n+        output_f.write(\'id\\tname\\t%s\\n\' % \'\\t\'.join(abundances.keys()))\n \n         for mac in more_abund_charact:\n-            charact_id,charact_name = format_characteristic_name(mac)\n-            output_file.write(charact_id + \'\\t\' + charact_name)\n+            charact_id, charact_name = format_characteristic_name(mac)\n+            output_f.write(\'%s\\t%s\' % (charact_id, charact_name))\n             for sample in abundances:\n                 abund = abundances[sample].get(mac, 0)\n-                output_file.write(\'\\t\' + str(abund))\n-            output_file.write(\'\\n\')\n+                output_f.write(\'\\t%s\' % (abund))\n+            output_f.write(\'\\n\')\n+\n \n-def extract_similar_characteristics(abundances, sim_output_filepath,\n-    specific_output_files):\n-    sim_characteristics = set(abundances[abundances.keys()[0]].keys())\n-    for sample in abundances.keys()[1:]:\n-        sim_characteristics.intersection_update(abundances[sample].keys())\n-    print \'Similar between all samples:\', len(sim_characteristics)\n+def extract_'..b'put_file:\n-            output_file.write(\'id\\tname\\tabundances\\n\')\n-            for charact in list(diff_characteristics[sample]):\n-                charact_id,charact_name = format_characteristic_name(charact)\n-                output_file.write(charact_id + \'\\t\' + charact_name + \'\\t\')\n-                output_file.write(str(abundances[sample][charact]) + \'\\n\')\n-                relative_abundance += abundances[sample][charact]\n-        print \'    Relative abundance of specific characteristics(%):\', relative_abundance\n+        with open(output_files[i], \'w\') as output_f:\n+            output_f.write(\'id\\tname\\tabundances\\n\')\n+            for charact in list(diff_char[sample]):\n+                charact_id, charact_name = format_characteristic_name(charact)\n+                output_f.write(\'%s\\t%s\' % (charact_id, charact_name))\n+                output_f.write(\'%s\\n\' % abund[sample][charact])\n+                relative_abundance += abund[sample][charact]\n+        print(\'    Relative abundance of specific characteristics: %s\' % relative_abundance)\n \n     return sim_characteristics\n \n+\n def compare_humann2_output(args):\n-    abundances = {}\n+    abund = {}\n     more_abund_charact = []\n \n     for i in range(len(args.sample_name)):\n-        abundances[args.sample_name[i]], mac = extract_abundances(args.charact_input_file[i],\n+        abund[args.sample_name[i]], mac = extract_abundances(\n+            args.charact_input_fp[i],\n             args.most_abundant_characteristics_to_extract)\n         more_abund_charact += mac\n \n-    write_more_abundant_charat(abundances, list(set(more_abund_charact)), \n-        args.more_abundant_output_file)\n-    sim_characteristics = extract_similar_characteristics(abundances, \n-        args.similar_output_file, args.specific_output_file)\n+    write_more_abundant_charat(\n+        abund,\n+        list(set(more_abund_charact)),\n+        args.more_abundant_output_fp)\n+    extract_similar_characteristics(\n+        abund,\n+        args.similar_output_fp,\n+        args.specific_output_fp)\n+\n \n if __name__ == \'__main__\':\n     parser = argparse.ArgumentParser()\n     parser.add_argument(\'--sample_name\', required=True, action=\'append\')\n-    parser.add_argument(\'--charact_input_file\', required=True, action=\'append\')\n-    parser.add_argument(\'--most_abundant_characteristics_to_extract\', required=True,\n-        type = int)\n-    parser.add_argument(\'--more_abundant_output_file\', required=True)\n-    parser.add_argument(\'--similar_output_file\', required=True)\n-    parser.add_argument(\'--specific_output_file\', required=True,action=\'append\')\n+    parser.add_argument(\'--charact_input_fp\', required=True, action=\'append\')\n+    parser.add_argument(\n+        \'--most_abundant_characteristics_to_extract\',\n+        required=True,\n+        type=int)\n+    parser.add_argument(\'--more_abundant_output_fp\', required=True)\n+    parser.add_argument(\'--similar_output_fp\', required=True)\n+    parser.add_argument(\n+        \'--specific_output_fp\',\n+        required=True,\n+        action=\'append\')\n     args = parser.parse_args()\n \n-    if len(args.sample_name) != len(args.charact_input_file):\n-        raise ValueError("Same number of values (in same order) are expected for --sample_name and --charact_input_file")\n-    if len(args.sample_name) != len(args.specific_output_file):\n-        raise ValueError("Same number of values (in same order) are expected for --sample_name and --specific_output_file")\n+    if len(args.sample_name) != len(args.charact_input_fp):\n+        string = "Same number of values (in same order) are expected for "\n+        string += "--sample_name and --charact_input_fp"\n+        raise ValueError(string)\n+    if len(args.sample_name) != len(args.specific_output_fp):\n+        string = "Same number of values (in same order) are expected for "\n+        string += "--sample_name and --specific_output_fp"\n+        raise ValueError(string)\n \n-    compare_humann2_output(args)\n\\ No newline at end of file\n+    compare_humann2_output(args)\n'
b
diff -r c1aca37cb1fc -r 05766022dfc4 compare_humann2_output.xml
--- a/compare_humann2_output.xml Wed Apr 20 09:15:27 2016 -0400
+++ b/compare_humann2_output.xml Mon Sep 14 13:50:30 2020 +0000
[
@@ -1,73 +1,93 @@
-<tool id="compare_humann2_output" name="Compare outputs of HUMAnN2 for several samples" version="0.1.0">
+<tool id="compare_humann2_output" name="Compare outputs of HUMAnN2 for several samples" version="0.2.0">
     <description>and extract similar and specific information</description>
-
-    <requirements>
-    </requirements>
-
-    <stdio>
-        <exit_code range="1:" />
-        <exit_code range=":-1" />
-    </stdio>
-
-    <version_command></version_command>
-
-    <command><![CDATA[
+    <command detect_errors="exit_code"><![CDATA[
         mkdir specifics 
         &&
 
         python $__tool_directory__/compare_humann2_output.py
-            #for $sample in $samples:
-                --sample_name "${sample.sample_name}"
-                --charact_input_file "${sample.input}"
-                --specific_output_file "specifics/specific_to_${sample.sample_name}.txt"
+            #for $sample in $samples
+                --sample_name '$sample.sample_name'
+                --charact_input_fp '$sample.charact_input_fp'
+                --specific_output_fp 'specifics/specific_to_${sample.sample_name}.txt'
             #end for
-
-            --most_abundant_characteristics_to_extract $charact_nb
-            --more_abundant_output_file $more_abundant_output_file
-            --similar_output_file $similar_output_file
+            --most_abundant_characteristics_to_extract $most_abundant_characteristics_to_extract
+            --more_abundant_output_fp '$more_abundant_output_file'
+            --similar_output_fp '$similar_output_file'
             > $log
-                
     ]]></command>
-
     <inputs>
         <repeat name="samples" title="Add sample and input file (HUMAnN2 output after normalization)" >
-            <param name="sample_name" type="text" label="Name of the sample" help="(--sample_name)"/>
-            <param name="input" format="txt,tabular" type="data" label="Input file corresponding to HUMAnN2 output" help="The HUMAnN2 output file contains relative abundance of gene families or pathways (after normalization, --charact_input_file)"/>
+            <param argument="sample_name" type="text" label="Name of the sample"/>
+            <param argument="charact_input_fp" format="txt,tabular" type="data" label="Input file corresponding to HUMAnN2 output" help="The HUMAnN2 output file contains relative abundance of gene families or pathways (after normalization"/>
         </repeat>
-
-        <param name="charact_nb" type="integer" value="10" label="Number of most abundant characteristics to extract for each sample" help="(--most_abundant_characteristics_to_extract)"/>
+        <param argument="most_abundant_characteristics_to_extract" type="integer" value="10" label="Number of most abundant characteristics to extract for each sample"/>
     </inputs>
-
     <outputs>
         <data name="more_abundant_output_file" format="tabular"
             label="${tool.name} on ${on_string}: More abundant characteristics for each sample" />
         <data name="similar_output_file" format="tabular"
             label="${tool.name} on ${on_string}: Similar characteristics and the relative abundances for all samples" />
         <data name="log" format="txt"
-            label="${tool.name} on ${on_string}: Log" />
+            label="${tool.name} on ${on_string}: Log" hidden="true"/>
         <collection name="specific_files" type="list">
             <discover_datasets pattern="__designation_and_ext__" directory="specifics"/>
         </collection>
-
     </outputs>
-
     <tests>
         <test>
-            <param name="samples_0|sample_name" value="sample1"/>
-            <param name="samples_0|input" value="sample_1_pathway_abundances.tabular"/>
-            <param name="samples_1|sample_name" value="sample2"/>
-            <param name="samples_1|input" value="sample_2_pathway_abundances.tabular"/>
-            <param name="charact_nb" value="10"/>
-            <output name="more_abundant_output_file" file="more_abundant_pathways.tabular"/>
-            <output name="similar_output_file" file="sample_similar_pathways.tabular"/>
-            <output name="log" file="sample_comparison_log.txt"/>
+            <repeat name="samples">
+                <param name="sample_name" value="sample1"/>
+                <param name="charact_input_fp" value="sample_1_pathway_abundances.tabular"/>
+            </repeat>
+            <repeat name="samples">
+                <param name="sample_name" value="sample2"/>
+                <param name="charact_input_fp" value="sample_2_pathway_abundances.tabular"/>
+            </repeat>
+            <param name="most_abundant_characteristics_to_extract" value="10"/>
+            <output name="more_abundant_output_file">
+                <assert_contents>
+                    <has_n_columns n="4"/>
+                    <has_n_lines n="16"/>
+                    <has_text text="aerobic respiration I |g__Rhodobacter.s__Rhodobacter_sphaeroides"/>
+                    <has_text text="phytol degradation|g__Staphylococcus.s__Staphylococcus_aureus"/>
+                </assert_contents>
+            </output>
+            <output name="similar_output_file">
+                <assert_contents>
+                    <has_n_columns n="4"/>
+                    <has_n_lines n="1921"/>
+                    <has_text text="superpathway of sulfur amino acid biosynthesis |g__Staphylococcus.s__Staphylococcus_epidermidis"/>
+                    <has_text text="tetrapyrrole biosynthesis I |g__Pseudomonas.s__Pseudomonas_aeruginosa"/>
+                </assert_contents>
+            </output>
+            <output name="log">
+                <assert_contents>
+                    <has_n_lines n="12"/>
+                    <has_line line="Similar between all samples: 1920"/>
+                    <has_line line="    Number of specific characteristics: 392"/>
+                    <has_line line="    Number of specific characteristics: 1335"/>
+                </assert_contents>
+            </output>
             <output_collection name="specific_files" type="list">
-                <element name="specific_to_sample1" file="sample_1_specific_pathways.txt" />
-                <element name="specific_to_sample2" file="sample_2_specific_pathways.txt" />
+                <element name="specific_to_sample1">
+                    <assert_contents>
+                        <has_n_columns n="3"/>
+                        <has_n_lines n="393"/>
+                        <has_text text="GLUCOSE1PMETAB-PWY"/>
+                        <has_text text="inosine 5 phosphate biosynthesis III|g__Staphylococcus.s__Staphylococcus_aureus"/>
+                    </assert_contents>
+                </element>
+                <element name="specific_to_sample2">
+                    <assert_contents>
+                        <has_n_columns n="3"/>
+                        <has_n_lines n="1336"/>
+                        <has_text text="PEPTIDOGLYCANSYN-PWY"/>
+                        <has_text text="nitrate reduction V |g__Deinococcus.s__Deinococcus_radiodurans"/>
+                    </assert_contents>
+                </element>
             </output_collection>
         </test>
     </tests>
-
     <help><![CDATA[
 **What it does**
 
@@ -80,7 +100,4 @@
   * Specific gene families and pathways for each samples and the relative abundances of these specific characteristics
 
     ]]></help>
-
-    <citations>
-    </citations>
 </tool>
\ No newline at end of file
b
diff -r c1aca37cb1fc -r 05766022dfc4 more_abundant_output_file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/more_abundant_output_file Mon Sep 14 13:50:30 2020 +0000
b
@@ -0,0 +1,16 @@
+id name sample1 sample2
+PWY-3781 aerobic respiration I |g__Rhodobacter.s__Rhodobacter_sphaeroides 45855.05069573 7356.870952820001
+PWY-3781 aerobic respiration I |g__Staphylococcus.s__Staphylococcus_epidermidis 29048.52870919 8522.11671136
+PWY-3781 aerobic respiration I |g__Escherichia.s__Escherichia_coli 11428.460877009999 3504.5920137499998
+PWY66-389 phytol degradation|g__Staphylococcus.s__Staphylococcus_aureus 31048.84820709 3743.72936189
+PWY-3781 aerobic respiration I |g__Acinetobacter.s__Acinetobacter_baumannii 0 10661.254254039999
+PWY66-389 phytol degradation 97948.05701095 126799.82204952001
+PWY-3781 aerobic respiration I |g__Deinococcus.s__Deinococcus_radiodurans 243.95473535000002 51964.068130520005
+PWY-3781 aerobic respiration I |g__Neisseria.s__Neisseria_meningitidis 142.20887338999998 6845.43838944
+PWY-3781 aerobic respiration I |unclassified 3699.6275521400003 1118.9863796
+PWY-3781 aerobic respiration I |g__Pseudomonas.s__Pseudomonas_aeruginosa 7491.56572789 2317.68361723
+PWY-3781 aerobic respiration I  146949.34957509 137931.17561632
+PWY-3781 aerobic respiration I |g__Staphylococcus.s__Staphylococcus_aureus 31496.03040367 2108.46546528
+PWY-3781 aerobic respiration I |g__Helicobacter.s__Helicobacter_pylori 475.85206385000004 7486.51278743
+PWY-3781 aerobic respiration I |g__Propionibacterium.s__Propionibacterium_acnes 307.60781448 14416.040401769998
+PWY-3781 aerobic respiration I |g__Actinomyces.s__Actinomyces_odontolyticus 0 2772.58262062
b
diff -r c1aca37cb1fc -r 05766022dfc4 similar_output_file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/similar_output_file Mon Sep 14 13:50:30 2020 +0000
b
b'@@ -0,0 +1,1921 @@\n+id\tname\tsample1\tsample2\n+PWY-821\tsuperpathway of sulfur amino acid biosynthesis |g__Staphylococcus.s__Staphylococcus_epidermidis\t10880.14677635\t2695.08502543\n+PWY-6318\tL phenylalanine degradation IV |g__Streptococcus.s__Streptococcus_mutans\t1598.93459295\t477.28733176000003\n+P105-PWY\tTCA cycle IV |unclassified\t417.22426747\t298.08991033\n+HOMOSER-METSYN-PWY\tL methionine biosynthesis I|g__Escherichia.s__Escherichia_coli\t3776.83864118\t695.70708218\n+POLYISOPRENSYN-PWY\tpolyisoprenoid biosynthesis |g__Staphylococcus.s__Staphylococcus_epidermidis\t12410.21918677\t3402.87724422\n+PWY-3841\tfolate transformations II|g__Rhodobacter.s__Rhodobacter_sphaeroides\t4568.53278951\t242.13420068999997\n+DTDPRHAMSYN-PWY\tdTDP L rhamnose biosynthesis I|g__Rhodobacter.s__Rhodobacter_sphaeroides\t25871.992567709996\t3493.0071529899997\n+PWY-5345\tsuperpathway of L methionine biosynthesis \t45016.41648231\t40305.835161430005\n+MET-SAM-PWY\tsuperpathway of S adenosyl L methionine biosynthesis|g__Pseudomonas.s__Pseudomonas_aeruginosa\t452.55553718000004\t238.97560409\n+PWY-7228\tsuperpathway of guanosine nucleotides de novo biosynthesis I|g__Deinococcus.s__Deinococcus_radiodurans\t187.59460807\t21248.594380040002\n+REDCITCYC\tTCA cycle VIII \t48658.12042871\t30732.22044426\n+PWYG-321\tmycolate biosynthesis|g__Rhodobacter.s__Rhodobacter_sphaeroides\t20343.72192787\t3516.1051310700004\n+PWY-7196\tsuperpathway of pyrimidine ribonucleosides salvage\t40398.22784233\t41832.91851937\n+PWY-6606\tguanosine nucleotides degradation II|g__Rhodobacter.s__Rhodobacter_sphaeroides\t2736.23201469\t471.84886441\n+PWY-5897\tsuperpathway of menaquinol 11 biosynthesis|g__Escherichia.s__Escherichia_coli\t3694.00663281\t527.00700198\n+PWY-4981\tL proline biosynthesis II |g__Staphylococcus.s__Staphylococcus_epidermidis\t15181.20229661\t2233.73828052\n+PWY-5173\tsuperpathway of acetyl CoA biosynthesis|g__Staphylococcus.s__Staphylococcus_aureus\t15599.502940190001\t1720.86327384\n+METSYN-PWY\tL homoserine and L methionine biosynthesis\t42751.19552667\t32239.21002944\n+PWY-6737\tstarch degradation V|unclassified\t48.21577448\t239.03206251000003\n+PWY-7013\tL 1,2 propanediol degradation\t4148.3920522299995\t10375.048369639999\n+COA-PWY-1\tcoenzyme A biosynthesis II |g__Staphylococcus.s__Staphylococcus_epidermidis\t9071.2442565\t580.96446474\n+PWY-821\tsuperpathway of sulfur amino acid biosynthesis |g__Pseudomonas.s__Pseudomonas_aeruginosa\t605.30096054\t321.46343092\n+PWY-6891\tthiazole biosynthesis II |unclassified\t32.229173779999996\t74.15115623\n+PWY66-400\tglycolysis VI |g__Streptococcus.s__Streptococcus_mutans\t6043.58140287\t848.32486235\n+PWY-7117\tC4 photosynthetic carbon assimilation cycle, PEPCK type|unclassified\t22.263231910000002\t367.15187651\n+PWY-6386\tUDP N acetylmuramoyl pentapeptide biosynthesis II |g__Pseudomonas.s__Pseudomonas_aeruginosa\t606.94449313\t145.93585417\n+PWY-7663\tgondoate biosynthesis |unclassified\t623.9800982\t867.35110658\n+UDPNAGSYN-PWY\tUDP N acetyl D glucosamine biosynthesis I|g__Methanobrevibacter.s__Methanobrevibacter_smithii\t5123.88198898\t554.81214991\n+PENTOSE-P-PWY\tpentose phosphate pathway|g__Staphylococcus.s__Staphylococcus_epidermidis\t9462.89698214\t1831.25439958\n+PWY-6282\tpalmitoleate biosynthesis I  dodec 5 enoate)|g__Escherichia.s__Escherichia_coli\t5235.734033500001\t1550.00566836\n+NONOXIPENT-PWY\tpentose phosphate pathway |g__Acinetobacter.s__Acinetobacter_baumannii\t207.44599457\t5015.152257039999\n+3-HYDROXYPHENYLACETATE-DEGRADATION-PWY\t4 hydroxyphenylacetate degradation\t5939.43167638\t13973.278780050001\n+PWY66-391\tfatty acid &beta; oxidation VI |unclassified\t82.70659416000001\t143.2949423\n+PWY-6313\tserotonin degradation|g__Propionibacterium.s__Propionibacterium_acnes\t257.91056362\t3253.85903121\n+PWY-6125\tsuperpathway of guanosine nucleotides de novo biosynthesis II|unclassified\t257.44739331\t1093.60424306\n+SULFATE-CYS-PWY\tsuperpathway of sulfate assimilation and cysteine biosynthesis|g__Pseudomonas.s__Pseudomonas_aeruginosa\t1206.06770903\t368.86227068\n+P221-PWY\toctane oxidation|g__Acinetobacter.s__Acinetoba'..b'us\t13369.976352750002\t1138.58445146\n+P42-PWY\tincomplete reductive TCA cycle|g__Propionibacterium.s__Propionibacterium_acnes\t125.05394405000001\t4360.80925658\n+PANTOSYN-PWY\tpantothenate and coenzyme A biosynthesis I|g__Escherichia.s__Escherichia_coli\t2299.31537269\t337.86673042\n+PWY-6562\tnorspermidine biosynthesis\t218.86041799\t4624.32885997\n+FASYN-INITIAL-PWY\tsuperpathway of fatty acid biosynthesis initiation |g__Staphylococcus.s__Staphylococcus_aureus\t9743.57817824\t879.08031243\n+PWY-6124\tinosine 5 phosphate biosynthesis II|g__Streptococcus.s__Streptococcus_agalactiae\t341.08923605\t79.05367387\n+P42-PWY\tincomplete reductive TCA cycle|g__Staphylococcus.s__Staphylococcus_aureus\t13936.750358750001\t1191.4175682\n+PWY-7400\tL arginine biosynthesis IV |g__Staphylococcus.s__Staphylococcus_aureus\t15354.11940315\t2495.26566885\n+PWY-7664\toleate biosynthesis IV |g__Staphylococcus.s__Staphylococcus_aureus\t6208.22400634\t1214.56040809\n+PWY-6628\tsuperpathway of L phenylalanine biosynthesis|g__Escherichia.s__Escherichia_coli\t3493.26437899\t774.5820243\n+PWY-3801\tsucrose degradation II |g__Staphylococcus.s__Staphylococcus_aureus\t9958.965535970001\t1227.63555655\n+PWY-6803\tphosphatidylcholine acyl editing|g__Neisseria.s__Neisseria_meningitidis\t92.76437848\t2398.33809012\n+PWY-2942\tL lysine biosynthesis III|g__Methanobrevibacter.s__Methanobrevibacter_smithii\t2684.68361975\t271.52394734\n+PWY66-367\tketogenesis\t20586.77550017\t11739.88053451\n+GLUTORN-PWY\tL ornithine biosynthesis|unclassified\t341.67654023\t569.7612764099999\n+PWY-7208\tsuperpathway of pyrimidine nucleobases salvage|g__Streptococcus.s__Streptococcus_mutans\t7465.08545776\t1650.49554073\n+PWY66-389\tphytol degradation|g__Propionibacterium.s__Propionibacterium_acnes\t427.17229621\t4830.73518595\n+PWY0-1586\tpeptidoglycan maturation |g__Staphylococcus.s__Staphylococcus_aureus\t12323.38519243\t1001.6705746199999\n+PWY-5910\tsuperpathway of geranylgeranyldiphosphate biosynthesis I \t37359.01700251\t11927.378765090001\n+METHGLYUT-PWY\tsuperpathway of methylglyoxal degradation|unclassified\t112.17208644\t110.92868734000001\n+PWY-7111\tpyruvate fermentation to isobutanol |g__Acinetobacter.s__Acinetobacter_baumannii\t580.74819003\t16585.03150303\n+PWY-6630\tsuperpathway of L tyrosine biosynthesis|g__Streptococcus.s__Streptococcus_mutans\t3646.835713\t285.14604184\n+PWY-7391\tisoprene biosynthesis II \t30738.87869861\t8400.52258056\n+GLYCOLYSIS\tglycolysis I \t42940.06802303\t57491.91524327\n+PWY-6122\t5 aminoimidazole ribonucleotide biosynthesis II|g__Rhodobacter.s__Rhodobacter_sphaeroides\t1759.45401497\t633.23408091\n+PWY-5347\tsuperpathway of L methionine biosynthesis |g__Escherichia.s__Escherichia_coli\t5535.9622291900005\t1122.03662727\n+PWY-6353\tpurine nucleotides degradation II |g__Escherichia.s__Escherichia_coli\t8709.22987767\t981.44226721\n+PWY-7431\taromatic biogenic amine degradation |unclassified\t9.98055831\t58.30332417\n+PWY0-42\t2 methylcitrate cycle I|g__Pseudomonas.s__Pseudomonas_aeruginosa\t608.37208118\t118.40719672\n+PWY66-389\tphytol degradation\t97948.05701095\t126799.82204952001\n+PWY-7400\tL arginine biosynthesis IV |g__Streptococcus.s__Streptococcus_mutans\t7613.585259209999\t1319.31787361\n+PWY-7221\tguanosine ribonucleotides de novo biosynthesis|g__Deinococcus.s__Deinococcus_radiodurans\t159.71379076\t19876.46520516\n+SER-GLYSYN-PWY\tsuperpathway of L serine and glycine biosynthesis I|unclassified\t360.41633729\t196.35650766999998\n+PWY-6277\tsuperpathway of 5 aminoimidazole ribonucleotide biosynthesis|g__Pseudomonas.s__Pseudomonas_aeruginosa\t1056.89034552\t272.35544024\n+PWY-5659\tGDP mannose biosynthesis|g__Rhodobacter.s__Rhodobacter_sphaeroides\t4117.82806788\t694.21044438\n+NAD-BIOSYNTHESIS-II\tNAD salvage pathway II|g__Escherichia.s__Escherichia_coli\t6399.36784439\t1081.15882603\n+TRIGLSYN-PWY\tdiacylglycerol and triacylglycerol biosynthesis\t459.46669737999997\t5730.57246545\n+PWY-6823\tmolybdenum cofactor biosynthesis|unclassified\t34.30203548\t84.75362593\n+PWY-5188\ttetrapyrrole biosynthesis I |g__Pseudomonas.s__Pseudomonas_aeruginosa\t658.20873845\t335.98771892\n'
b
diff -r c1aca37cb1fc -r 05766022dfc4 specific_to_sample1.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/specific_to_sample1.txt Mon Sep 14 13:50:30 2020 +0000
b
b'@@ -0,0 +1,393 @@\n+id\tname\tabundances\n+PWY-7208\tsuperpathway of pyrimidine nucleobases salvage|g__Pseudomonas.s__Pseudomonas_aeruginosa2355.2977619499998\n+PWY0-1061\tsuperpathway of L alanine biosynthesis|g__Streptococcus.s__Streptococcus_agalactiae629.81986142\n+ORNARGDEG-PWY\tsuperpathway of L arginine and L ornithine degradation|unclassified67.59290738\n+PENTOSE-P-PWY\tpentose phosphate pathway|g__Pseudomonas.s__Pseudomonas_aeruginosa232.40561581\n+PWY-7222\tguanosine deoxyribonucleotides de novo biosynthesis II|g__Streptococcus.s__Streptococcus_agalactiae705.67950476\n+PWY-7210\tpyrimidine deoxyribonucleotides biosynthesis from CTP|g__Escherichia.s__Escherichia_coli623.1847142400001\n+PWY-6612\tsuperpathway of tetrahydrofolate biosynthesis|g__Pseudomonas.s__Pseudomonas_aeruginosa320.96477039\n+P4-PWY\tsuperpathway of L lysine, L threonine and L methionine biosynthesis I|g__Pseudomonas.s__Pseudomonas_aeruginosa677.11766653\n+PWY-6700\tqueuosine biosynthesis|g__Rhodobacter.s__Rhodobacter_sphaeroides447.95699647999993\n+PWY-6527\tstachyose degradation|unclassified53.551283819999995\n+PWY-4221\tpantothenate and coenzyme A biosynthesis II |g__Rhodobacter.s__Rhodobacter_sphaeroides935.46980828\n+PWY-6703\tpreQ0 biosynthesis|g__Pseudomonas.s__Pseudomonas_aeruginosa796.0549075700001\n+PWY-6147\t6 hydroxymethyl dihydropterin diphosphate biosynthesis I|g__Rhodobacter.s__Rhodobacter_sphaeroides600.7633936799999\n+PWY-5079\tL phenylalanine degradation III|unclassified6.5206192\n+1CMET2-PWY\tN10 formyl tetrahydrofolate biosynthesis|g__Pseudomonas.s__Pseudomonas_aeruginosa752.81237337\n+PWY-561\tsuperpathway of glyoxylate cycle and fatty acid degradation|g__Pseudomonas.s__Pseudomonas_aeruginosa395.39499627\n+PWY0-781\taspartate superpathway|unclassified35.58050169\n+PWY0-1277\t3 phenylpropanoate and 3 propanoate degradation|g__Escherichia.s__Escherichia_coli2473.1533402\n+PWY-7184\tpyrimidine deoxyribonucleotides de novo biosynthesis I|g__Streptococcus.s__Streptococcus_agalactiae502.26578072\n+ARGININE-SYN4-PWY\tL ornithine de novo  biosynthesis|g__Streptococcus.s__Streptococcus_agalactiae186.2324897\n+PWY-6317\tgalactose degradation I |unclassified27.43425146\n+PWY-7539\t6 hydroxymethyl dihydropterin diphosphate biosynthesis III |g__Staphylococcus.s__Staphylococcus_aureus1142.2860582\n+1CMET2-PWY\tN10 formyl tetrahydrofolate biosynthesis|g__Escherichia.s__Escherichia_coli2980.83193002\n+PWY-7219\tadenosine ribonucleotides de novo biosynthesis|g__Streptococcus.s__Streptococcus_agalactiae381.06191748\n+COMPLETE-ARO-PWY\tsuperpathway of aromatic amino acid biosynthesis|g__Rhodobacter.s__Rhodobacter_sphaeroides603.00195694\n+PWY-6123\tinosine 5 phosphate biosynthesis I|g__Pseudomonas.s__Pseudomonas_aeruginosa869.41608143\n+PWY-7409\tphospholipid remodeling |g__Escherichia.s__Escherichia_coli2324.0578138\n+PWY-2201\tfolate transformations I207.35386067000002\n+PWY-5690\tTCA cycle II |g__Methanobrevibacter.s__Methanobrevibacter_smithii2245.54201886\n+PWY-5860\tsuperpathway of demethylmenaquinol 6 biosynthesis I|g__Escherichia.s__Escherichia_coli1639.5406975899998\n+PWY-7209\tsuperpathway of pyrimidine ribonucleosides degradation|unclassified14.160067660000001\n+PWY-6562\tnorspermidine biosynthesis|unclassified70.22305715\n+PWY-2201\tfolate transformations I|unclassified115.80586462\n+FOLSYN-PWY\tsuperpathway of tetrahydrofolate biosynthesis and salvage|g__Staphylococcus.s__Staphylococcus_aureus5666.17436329\n+ARGDEG-IV-PWY\tL arginine degradation VIII 413.14165668999993\n+PWY-7663\tgondoate biosynthesis |g__Streptococcus.s__Streptococcus_agalactiae495.11402348\n+PWY-5850\tsuperpathway of menaquinol 6 biosynthesis I|g__Escherichia.s__Escherichia_coli2086.15005453\n+ARGSYNBSUB-PWY\tL arginine biosynthesis II |g__Rhodobacter.s__Rhodobacter_sphaeroides2860.34862539\n+NONOXIPENT-PWY\tpentose phosphate pathway |g__Streptococcus.s__Streptococcus_agalactiae1256.57046857\n+SALVADEHYPOX-PWY\tadenosine nucleotides degradation II|g__Staphylococcus.s__Staphylococcus_aureus796.46617638\n+PWY-5695\turate biosynthesis inosine 5 phosp'..b'6904313\n+PWY-7221\tguanosine ribonucleotides de novo biosynthesis|g__Streptococcus.s__Streptococcus_agalactiae263.18388651000004\n+TRNA-CHARGING-PWY\ttRNA charging|g__Staphylococcus.s__Staphylococcus_aureus1635.82224797\n+ARO-PWY\tchorismate biosynthesis I|g__Rhodobacter.s__Rhodobacter_sphaeroides531.17556088\n+PWY-621\tsucrose degradation III |g__Streptococcus.s__Streptococcus_agalactiae112.79225549\n+PYRIDNUCSAL-PWY\tNAD salvage pathway I|g__Pseudomonas.s__Pseudomonas_aeruginosa314.33071124\n+PWY-1541\tsuperpathway of taurine degradation|unclassified58.7739116\n+GLYCOLYSIS\tglycolysis I |g__Streptococcus.s__Streptococcus_agalactiae246.23941276000002\n+PWY-5121\tsuperpathway of geranylgeranyl diphosphate biosynthesis II |g__Pseudomonas.s__Pseudomonas_aeruginosa505.74692227\n+PWY-7200\tsuperpathway of pyrimidine deoxyribonucleoside salvage|g__Escherichia.s__Escherichia_coli524.75222768\n+COA-PWY\tcoenzyme A biosynthesis I|g__Streptococcus.s__Streptococcus_agalactiae323.6348991\n+P105-PWY\tTCA cycle IV |g__Pseudomonas.s__Pseudomonas_aeruginosa346.96109280999997\n+PWY-7200\tsuperpathway of pyrimidine deoxyribonucleoside salvage|g__Staphylococcus.s__Staphylococcus_aureus9664.74077711\n+PWY-6519\t8 amino 7 oxononanoate biosynthesis I|unclassified37.58644825\n+PWY-6386\tUDP N acetylmuramoyl pentapeptide biosynthesis II |unclassified47.18774207\n+PWY-4041\t&gamma; glutamyl cycle|g__Streptococcus.s__Streptococcus_agalactiae357.22684804\n+PWY-6117\tspermine and spermidine degradation I|unclassified9.97625171\n+CALVIN-PWY\tCalvin Benson Bassham cycle|g__Pseudomonas.s__Pseudomonas_aeruginosa263.3999058\n+PWY-7208\tsuperpathway of pyrimidine nucleobases salvage|g__Streptococcus.s__Streptococcus_agalactiae301.65285339999997\n+PWY-7282\t4 amino 2 methyl 5 phosphomethylpyrimidine biosynthesis |unclassified125.63136519\n+PWY0-166\tsuperpathway of pyrimidine deoxyribonucleotides de novo biosynthesis |g__Pseudomonas.s__Pseudomonas_aeruginosa2909.69565583\n+PWY-7184\tpyrimidine deoxyribonucleotides de novo biosynthesis I|g__Escherichia.s__Escherichia_coli708.4604707699999\n+NONMEVIPP-PWY\tmethylerythritol phosphate pathway I|g__Pseudomonas.s__Pseudomonas_aeruginosa580.3736268499999\n+PWY-6565\tsuperpathway of polyamine biosynthesis III|unclassified65.06157163\n+OANTIGEN-PWY\tO antigen building blocks biosynthesis |g__Rhodobacter.s__Rhodobacter_sphaeroides617.65804587\n+KETOGLUCONMET-PWY\tketogluconate metabolism|g__Rhodobacter.s__Rhodobacter_sphaeroides2086.77560891\n+PWY-5484\tglycolysis II |g__Streptococcus.s__Streptococcus_agalactiae230.80642089999998\n+RUMP-PWY\tformaldehyde oxidation I|g__Staphylococcus.s__Staphylococcus_aureus10207.43071166\n+HCAMHPDEG-PWY\t3 phenylpropanoate and 3 propanoate degradation to 2 oxopent 4 enoate|g__Escherichia.s__Escherichia_coli1403.43643815\n+PWY-5417\tcatechol degradation III |g__Rhodobacter.s__Rhodobacter_sphaeroides211.99234581000002\n+PWY-7198\tpyrimidine deoxyribonucleotides de novo biosynthesis IV|g__Staphylococcus.s__Staphylococcus_aureus11389.66331209\n+PWY66-422\tD galactose degradation V |g__Streptococcus.s__Streptococcus_agalactiae254.63203563\n+PWY3O-19\tubiquinol 6 biosynthesis from 4 hydroxybenzoate |g__Rhodobacter.s__Rhodobacter_sphaeroides2645.8359955700003\n+PYRIDOXSYN-PWY\tpyridoxal 5 phosphate biosynthesis I|g__Pseudomonas.s__Pseudomonas_aeruginosa869.1164710900001\n+PWY-6387\tUDP N acetylmuramoyl pentapeptide biosynthesis I |g__Streptococcus.s__Streptococcus_agalactiae324.2241648\n+PWY-7199\tpyrimidine deoxyribonucleosides salvage|g__Staphylococcus.s__Staphylococcus_aureus10064.13020033\n+CATECHOL-ORTHO-CLEAVAGE-PWY\tcatechol degradation to &beta; ketoadipate|g__Rhodobacter.s__Rhodobacter_sphaeroides480.71275029000003\n+TEICHOICACID-PWY\tteichoic acid  biosynthesis|g__Staphylococcus.s__Staphylococcus_epidermidis7484.93061203\n+PWY-7229\tsuperpathway of adenosine nucleotides de novo biosynthesis I|g__Pseudomonas.s__Pseudomonas_aeruginosa1554.97187132\n+PWY-6124\tinosine 5 phosphate biosynthesis II|g__Methanobrevibacter.s__Methanobrevibacter_smithii3405.18193479\n'
b
diff -r c1aca37cb1fc -r 05766022dfc4 specific_to_sample2.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/specific_to_sample2.txt Mon Sep 14 13:50:30 2020 +0000
[
b'@@ -0,0 +1,1336 @@\n+id\tname\tabundances\n+PWY0-1298\tsuperpathway of pyrimidine deoxyribonucleosides degradation|g__Deinococcus.s__Deinococcus_radiodurans11045.646771369999\n+THRESYN-PWY\tsuperpathway of L threonine biosynthesis|g__Actinomyces.s__Actinomyces_odontolyticus869.8459622199999\n+PWY-6122\t5 aminoimidazole ribonucleotide biosynthesis II|g__Listeria.s__Listeria_monocytogenes957.31899135\n+P221-PWY\toctane oxidation|g__Clostridium.s__Clostridium_beijerinckii451.02308636000004\n+PWY-3841\tfolate transformations II|g__Listeria.s__Listeria_monocytogenes825.20149758\n+GLUTORN-PWY\tL ornithine biosynthesis|g__Acinetobacter.s__Acinetobacter_baumannii6249.9626888\n+PWY-5345\tsuperpathway of L methionine biosynthesis |g__Acinetobacter.s__Acinetobacter_baumannii5138.44802921\n+RHAMCAT-PWY\tL rhamnose degradation I|g__Bacteroides.s__Bacteroides_vulgatus2720.4624286400003\n+P185-PWY\tformaldehyde assimilation III |g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae2799.70889862\n+PYRIDNUCSAL-PWY\tNAD salvage pathway I|unclassified48.01244259\n+FASYN-ELONG-PWY\tfatty acid elongation    saturated|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae2326.16249888\n+ANAEROFRUCAT-PWY\thomolactic fermentation|g__Listeria.s__Listeria_monocytogenes1159.5063759500001\n+PWY-4242\tpantothenate and coenzyme A biosynthesis III|g__Neisseria.s__Neisseria_meningitidis1177.5189052\n+PWY-7185\tUTP and CTP dephosphorylation I95.19614057\n+PWY4FS-8\tphosphatidylglycerol biosynthesis II |g__Enterococcus.s__Enterococcus_faecalis264.06357646\n+HISTSYN-PWY\tL histidine biosynthesis|g__Listeria.s__Listeria_monocytogenes622.7921232799999\n+PWY-841\tsuperpathway of purine nucleotides de novo biosynthesis I|g__Acinetobacter.s__Acinetobacter_baumannii3027.23954619\n+PWY0-321\tphenylacetate degradation I |unclassified95.84027976\n+PWY-6387\tUDP N acetylmuramoyl pentapeptide biosynthesis I |g__Deinococcus.s__Deinococcus_radiodurans819.0181925499999\n+PWY-5667\tCDP diacylglycerol biosynthesis I|g__Neisseria.s__Neisseria_meningitidis1978.55815874\n+PWY-724\tsuperpathway of L lysine, L threonine and L methionine biosynthesis II|g__Acinetobacter.s__Acinetobacter_baumannii4876.52400545\n+PWY0-1586\tpeptidoglycan maturation |g__Bacillus.s__Bacillus_cereus_thuringiensis2488.88961105\n+PWY-5103\tL isoleucine biosynthesis III|g__Actinomyces.s__Actinomyces_odontolyticus640.50375917\n+PWY-5686\tUMP biosynthesis|g__Actinomyces.s__Actinomyces_odontolyticus1155.0252265\n+PWY-7338\t10 trans heptadecenoyl CoA degradation |unclassified44.864782240000004\n+PWY-4242\tpantothenate and coenzyme A biosynthesis III|g__Helicobacter.s__Helicobacter_pylori1193.87628964\n+NAD-BIOSYNTHESIS-II\tNAD salvage pathway II|g__Bacteroides.s__Bacteroides_vulgatus1561.82848783\n+MET-SAM-PWY\tsuperpathway of S adenosyl L methionine biosynthesis|g__Bacteroides.s__Bacteroides_vulgatus2904.45909841\n+FASYN-INITIAL-PWY\tsuperpathway of fatty acid biosynthesis initiation |g__Propionibacterium.s__Propionibacterium_acnes3524.4272528899996\n+NONMEVIPP-PWY\tmethylerythritol phosphate pathway I|g__Acinetobacter.s__Acinetobacter_baumannii3071.89162094\n+PWY-4981\tL proline biosynthesis II |g__Bacteroides.s__Bacteroides_vulgatus2337.74199143\n+PWY66-400\tglycolysis VI |g__Propionibacterium.s__Propionibacterium_acnes2923.04364527\n+METHGLYUT-PWY\tsuperpathway of methylglyoxal degradation|g__Enterococcus.s__Enterococcus_faecalis807.63764403\n+ALLANTOINDEG-PWY\tsuperpathway of allantoin degradation in yeast|g__Enterococcus.s__Enterococcus_faecalis362.21552207999997\n+P185-PWY\tformaldehyde assimilation III |g__Bacillus.s__Bacillus_cereus_thuringiensis189.13084629000002\n+PWY0-1586\tpeptidoglycan maturation |g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae6858.429670869999\n+PWY-5973\tcis vaccenate biosynthesis|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae2600.36043229\n+PWY-6527\tstachyose degradation|g__Actinomyces.s__Actinomyces_odontolyticus711.43422479\n+PWY-7282\t4 amino 2 methyl 5 phosphomethylpyrimidine biosynthesis |g__Deinococcus.s__Deinococcus_radi'..b'PWY-7388\toctanoyl [acyl carrier protein] biosynthesis |g__Listeria.s__Listeria_monocytogenes507.22180871999996\n+PWY-6147\t6 hydroxymethyl dihydropterin diphosphate biosynthesis I|g__Neisseria.s__Neisseria_meningitidis947.77913253\n+HEMESYN2-PWY\theme biosynthesis II |g__Bacillus.s__Bacillus_cereus_thuringiensis322.00293305\n+PWY-6123\tinosine 5 phosphate biosynthesis I|g__Acinetobacter.s__Acinetobacter_baumannii3746.82815929\n+HEMESYN2-PWY\theme biosynthesis II |g__Listeria.s__Listeria_monocytogenes369.10390205\n+PWY-7118\tchitin degradation to ethanol|g__Bacillus.s__Bacillus_cereus_thuringiensis400.33401129000003\n+DTDPRHAMSYN-PWY\tdTDP L rhamnose biosynthesis I|g__Listeria.s__Listeria_monocytogenes187.61090748\n+PWY-6125\tsuperpathway of guanosine nucleotides de novo biosynthesis II|g__Propionibacterium.s__Propionibacterium_acnes3194.01708626\n+PWY-7663\tgondoate biosynthesis |g__Enterococcus.s__Enterococcus_faecalis1735.8151961\n+PWY-3781\taerobic respiration I |g__Bacillus.s__Bacillus_cereus_thuringiensis740.84156305\n+KETOGLUCONMET-PWY\tketogluconate metabolism|g__Propionibacterium.s__Propionibacterium_acnes3498.2123751000004\n+PWY-7220\tadenosine deoxyribonucleotides de novo biosynthesis II|g__Helicobacter.s__Helicobacter_pylori4205.54671787\n+PWY-7211\tsuperpathway of pyrimidine deoxyribonucleotides de novo biosynthesis|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae2318.0237892600003\n+PWY-7185\tUTP and CTP dephosphorylation I|unclassified86.86345616999999\n+PWY-2942\tL lysine biosynthesis III|g__Acinetobacter.s__Acinetobacter_baumannii4184.39331209\n+DTDPRHAMSYN-PWY\tdTDP L rhamnose biosynthesis I|g__Actinomyces.s__Actinomyces_odontolyticus1602.39397488\n+PWY-7388\toctanoyl [acyl carrier protein] biosynthesis |g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae1522.60994915\n+PWY-7400\tL arginine biosynthesis IV |g__Neisseria.s__Neisseria_meningitidis2661.7116863\n+PWY0-1061\tsuperpathway of L alanine biosynthesis|g__Deinococcus.s__Deinococcus_radiodurans17207.619728309997\n+PWY-6151\tS adenosyl L methionine cycle I|g__Acinetobacter.s__Acinetobacter_baumannii3884.9562603800005\n+BRANCHED-CHAIN-AA-SYN-PWY\tsuperpathway of branched amino acid biosynthesis|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae3873.13594163\n+PWY-6703\tpreQ0 biosynthesis|g__Clostridium.s__Clostridium_beijerinckii456.48187263000005\n+PWY-6307\tL tryptophan degradation X |g__Bacteroides.s__Bacteroides_vulgatus1665.5719701100002\n+PWY-5103\tL isoleucine biosynthesis III|g__Neisseria.s__Neisseria_meningitidis2998.96553709\n+PWY-7220\tadenosine deoxyribonucleotides de novo biosynthesis II|g__Enterococcus.s__Enterococcus_faecalis1253.1079087\n+VALSYN-PWY\tL valine biosynthesis|g__Propionibacterium.s__Propionibacterium_acnes3111.11632972\n+PWY-5910\tsuperpathway of geranylgeranyldiphosphate biosynthesis I |g__Listeria.s__Listeria_monocytogenes465.60089664\n+PWY-6123\tinosine 5 phosphate biosynthesis I|g__Clostridium.s__Clostridium_beijerinckii293.81784981\n+GLYCOGENSYNTH-PWY\tglycogen biosynthesis I |g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae3029.53758634\n+PWY-6608\tguanosine nucleotides degradation III|g__Bacteroides.s__Bacteroides_vulgatus1761.75460692\n+PWY-7197\tpyrimidine deoxyribonucleotide phosphorylation|g__Listeria.s__Listeria_monocytogenes430.81396281\n+PWY-7111\tpyruvate fermentation to isobutanol |g__Helicobacter.s__Helicobacter_pylori1895.1322225\n+PWY-6859\tall trans farnesol biosynthesis|g__Listeria.s__Listeria_monocytogenes514.9571508500001\n+PWY0-781\taspartate superpathway|g__Acinetobacter.s__Acinetobacter_baumannii5029.55209128\n+GLUCUROCAT-PWY\tsuperpathway of &beta; D glucuronide and D glucuronate degradation|g__Propionibacterium.s__Propionibacterium_acnes3236.09786158\n+PWY-6385\tpeptidoglycan biosynthesis III |g__Bacillus.s__Bacillus_cereus_thuringiensis504.30027838000007\n+PWY0-1296\tpurine ribonucleosides degradation|g__Deinococcus.s__Deinococcus_radiodurans19916.5017068\n+PWY-5659\tGDP mannose biosynthesis|g__Listeria.s__Listeria_monocytogenes632.43764388\n'
b
diff -r c1aca37cb1fc -r 05766022dfc4 test-data/more_abundant_pathways.tabular
--- a/test-data/more_abundant_pathways.tabular Wed Apr 20 09:15:27 2016 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
b
@@ -1,16 +0,0 @@
-id name sample1 sample2
-PWY-3781 aerobic respiration I |g__Escherichia.s__Escherichia_coli 11428.460877 3504.59201375
-PWY-3781 aerobic respiration I |g__Neisseria.s__Neisseria_meningitidis 142.20887339 6845.43838944
-PWY-3781 aerobic respiration I |g__Staphylococcus.s__Staphylococcus_aureus 31496.0304037 2108.46546528
-PWY-3781 aerobic respiration I |g__Acinetobacter.s__Acinetobacter_baumannii 0 10661.254254
-PWY-3781 aerobic respiration I |g__Deinococcus.s__Deinococcus_radiodurans 243.95473535 51964.0681305
-PWY66-389 phytol degradation|g__Staphylococcus.s__Staphylococcus_aureus 31048.8482071 3743.72936189
-PWY-3781 aerobic respiration I |g__Helicobacter.s__Helicobacter_pylori 475.85206385 7486.51278743
-PWY66-389 phytol degradation 97948.0570109 126799.82205
-PWY-3781 aerobic respiration I |unclassified 3699.62755214 1118.9863796
-PWY-3781 aerobic respiration I |g__Actinomyces.s__Actinomyces_odontolyticus 0 2772.58262062
-PWY-3781 aerobic respiration I |g__Pseudomonas.s__Pseudomonas_aeruginosa 7491.56572789 2317.68361723
-PWY-3781 aerobic respiration I |g__Rhodobacter.s__Rhodobacter_sphaeroides 45855.0506957 7356.87095282
-PWY-3781 aerobic respiration I |g__Staphylococcus.s__Staphylococcus_epidermidis 29048.5287092 8522.11671136
-PWY-3781 aerobic respiration I |g__Propionibacterium.s__Propionibacterium_acnes 307.60781448 14416.0404018
-PWY-3781 aerobic respiration I  146949.349575 137931.175616
b
diff -r c1aca37cb1fc -r 05766022dfc4 test-data/sample_1_specific_pathways.txt
--- a/test-data/sample_1_specific_pathways.txt Wed Apr 20 09:15:27 2016 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
[
b'@@ -1,393 +0,0 @@\n-id\tname\tabundances\n-GLUCOSE1PMETAB-PWY\tglucose and glucose 1 phosphate degradation|g__Streptococcus.s__Streptococcus_agalactiae\t1410.06644622\n-PWY-621\tsucrose degradation III |g__Streptococcus.s__Streptococcus_agalactiae\t112.79225549\n-PWY-7282\t4 amino 2 methyl 5 phosphomethylpyrimidine biosynthesis |g__Rhodobacter.s__Rhodobacter_sphaeroides\t478.21587188\n-GLUCOSE1PMETAB-PWY\tglucose and glucose 1 phosphate degradation|unclassified\t179.77462326\n-PWY-6731\tstarch degradation III|g__Escherichia.s__Escherichia_coli\t2025.33248781\n-PWY-6897\tthiamin salvage II|g__Staphylococcus.s__Staphylococcus_epidermidis\t6943.50315533\n-PWY-7388\toctanoyl [acyl carrier protein] biosynthesis |g__Pseudomonas.s__Pseudomonas_aeruginosa\t3608.12319483\n-PWY-5860\tsuperpathway of demethylmenaquinol 6 biosynthesis I|g__Escherichia.s__Escherichia_coli\t1639.54069759\n-PWY-1861\tformaldehyde assimilation II |g__Streptococcus.s__Streptococcus_agalactiae\t839.53086925\n-PWY-7208\tsuperpathway of pyrimidine nucleobases salvage|g__Streptococcus.s__Streptococcus_agalactiae\t301.6528534\n-ARGORNPROST-PWY\targinine, ornithine and proline interconversion|unclassified\t119.95840721\n-PWY-7208\tsuperpathway of pyrimidine nucleobases salvage|g__Pseudomonas.s__Pseudomonas_aeruginosa\t2355.29776195\n-PWY-7229\tsuperpathway of adenosine nucleotides de novo biosynthesis I|g__Streptococcus.s__Streptococcus_agalactiae\t361.12670274\n-P4-PWY\tsuperpathway of L lysine, L threonine and L methionine biosynthesis I|g__Pseudomonas.s__Pseudomonas_aeruginosa\t677.11766653\n-PWY-6277\tsuperpathway of 5 aminoimidazole ribonucleotide biosynthesis|g__Streptococcus.s__Streptococcus_agalactiae\t384.06128551\n-GLCMANNANAUT-PWY\tsuperpathway of N acetylglucosamine, N acetylmannosamine and N acetylneuraminate degradation|unclassified\t42.89806203\n-PWY-7234\tinosine 5 phosphate biosynthesis III|g__Staphylococcus.s__Staphylococcus_aureus\t8533.03496704\n-PWY-621\tsucrose degradation III |g__Escherichia.s__Escherichia_coli\t3150.29450022\n-PWY-7413\tdTDP 6 deoxy &alpha; D allose biosynthesis\t12.26474527\n-PWY-5345\tsuperpathway of L methionine biosynthesis |g__Escherichia.s__Escherichia_coli\t837.30529432\n-PWY-5154\tL arginine biosynthesis III |g__Pseudomonas.s__Pseudomonas_aeruginosa\t386.2629909\n-PWY-6690\tcinnamate and 3 hydroxycinnamate degradation to 2 oxopent 4 enoate|unclassified\t1.42686388\n-COMPLETE-ARO-PWY\tsuperpathway of aromatic amino acid biosynthesis|g__Rhodobacter.s__Rhodobacter_sphaeroides\t603.00195694\n-HCAMHPDEG-PWY\t3 phenylpropanoate and 3 propanoate degradation to 2 oxopent 4 enoate|g__Escherichia.s__Escherichia_coli\t1403.43643815\n-PWY-6859\tall trans farnesol biosynthesis|g__Streptococcus.s__Streptococcus_agalactiae\t318.54192069\n-PWY66-400\tglycolysis VI |g__Streptococcus.s__Streptococcus_agalactiae\t303.79411134\n-PWY-5973\tcis vaccenate biosynthesis|g__Streptococcus.s__Streptococcus_agalactiae\t447.83907364\n-PWY-6672\tcis genanyl CoA degradation|g__Pseudomonas.s__Pseudomonas_aeruginosa\t246.74381202\n-P105-PWY\tTCA cycle IV |g__Pseudomonas.s__Pseudomonas_aeruginosa\t346.96109281\n-PWY-4702\tphytate degradation I|unclassified\t88.68668132\n-PWY-7242\tD fructuronate degradation|g__Streptococcus.s__Streptococcus_agalactiae\t202.56826561\n-PWY-6609\tadenine and adenosine salvage III|g__Pseudomonas.s__Pseudomonas_aeruginosa\t492.9281104\n-PWY-6124\tinosine 5 phosphate biosynthesis II|g__Methanobrevibacter.s__Methanobrevibacter_smithii\t3405.18193479\n-PWY-6562\tnorspermidine biosynthesis|unclassified\t70.22305715\n-NAGLIPASYN-PWY\tlipid IVA biosynthesis|unclassified\t25.03978499\n-PWY0-1277\t3 phenylpropanoate and 3 propanoate degradation|g__Escherichia.s__Escherichia_coli\t2473.1533402\n-GLYCOL-GLYOXDEG-PWY\tsuperpathway of glycol metabolism and degradation|g__Pseudomonas.s__Pseudomonas_aeruginosa\t675.72913268\n-PWY-6969\tTCA cycle V (2 oxoglutarate\t7590.86231693\n-PWY-5686\tUMP biosynthesis|g__Methanobrevibacter.s__Methanobrevibacter_smithii\t2597.42400205\n-PWY-7294\txylose degradation IV\t3457.02196873\n-PWY-7187\tpyrimidine deoxyribonucleot'..b' ornithine degradation|unclassified\t67.59290738\n-PWY-6168\tflavin biosynthesis III |g__Escherichia.s__Escherichia_coli\t1076.61192214\n-PWY-7228\tsuperpathway of guanosine nucleotides de novo biosynthesis I|g__Streptococcus.s__Streptococcus_agalactiae\t339.2748428\n-PWY-6123\tinosine 5 phosphate biosynthesis I|g__Staphylococcus.s__Staphylococcus_aureus\t8629.38522048\n-PWY-7664\toleate biosynthesis IV |g__Pseudomonas.s__Pseudomonas_aeruginosa\t2728.84413265\n-DAPLYSINESYN-PWY\tL lysine biosynthesis I|g__Pseudomonas.s__Pseudomonas_aeruginosa\t780.13280579\n-ALLANTOINDEG-PWY\tsuperpathway of allantoin degradation in yeast|unclassified\t184.58699889\n-P125-PWY\tsuperpathway of  butanediol biosynthesis|unclassified\t50.56326117\n-PWY-7118\tchitin degradation to ethanol|unclassified\t179.48569416\n-PWY-6167\tflavin biosynthesis II \t4728.07707794\n-PWY-841\tsuperpathway of purine nucleotides de novo biosynthesis I|g__Staphylococcus.s__Staphylococcus_aureus\t11184.2607862\n-HCAMHPDEG-PWY\t3 phenylpropanoate and 3 propanoate degradation to 2 oxopent 4 enoate|unclassified\t1.42686388\n-PWY-5850\tsuperpathway of menaquinol 6 biosynthesis I|g__Escherichia.s__Escherichia_coli\t2086.15005453\n-PWY-7409\tphospholipid remodeling \t2857.98178304\n-FOLSYN-PWY\tsuperpathway of tetrahydrofolate biosynthesis and salvage|g__Pseudomonas.s__Pseudomonas_aeruginosa\t415.68053269\n-PWY-6969\tTCA cycle V (2 oxoglutarate\t346.96109281\n-SALVADEHYPOX-PWY\tadenosine nucleotides degradation II|g__Staphylococcus.s__Staphylococcus_aureus\t796.46617638\n-PWY66-409\tsuperpathway of purine nucleotide salvage|g__Escherichia.s__Escherichia_coli\t1182.85263435\n-PWY-6147\t6 hydroxymethyl dihydropterin diphosphate biosynthesis I|g__Rhodobacter.s__Rhodobacter_sphaeroides\t600.76339368\n-URSIN-PWY\tureide biosynthesis|g__Pseudomonas.s__Pseudomonas_aeruginosa\t346.33151921\n-PENTOSE-P-PWY\tpentose phosphate pathway|g__Pseudomonas.s__Pseudomonas_aeruginosa\t232.40561581\n-PWY0-1061\tsuperpathway of L alanine biosynthesis|g__Streptococcus.s__Streptococcus_agalactiae\t629.81986142\n-PWY-7234\tinosine 5 phosphate biosynthesis III|g__Streptococcus.s__Streptococcus_agalactiae\t388.54431864\n-ARGDEG-PWY\tsuperpathway of L arginine, putrescine, and 4 aminobutanoate degradation|g__Pseudomonas.s__Pseudomonas_aeruginosa\t792.37856895\n-PWY4FS-8\tphosphatidylglycerol biosynthesis II |g__Pseudomonas.s__Pseudomonas_aeruginosa\t366.47566208\n-OANTIGEN-PWY\tO antigen building blocks biosynthesis |g__Methanobrevibacter.s__Methanobrevibacter_smithii\t3062.91191006\n-3-HYDROXYPHENYLACETATE-DEGRADATION-PWY\t4 hydroxyphenylacetate degradation|g__Escherichia.s__Escherichia_coli\t1868.56730475\n-ARO-PWY\tchorismate biosynthesis I|g__Rhodobacter.s__Rhodobacter_sphaeroides\t531.17556088\n-PWY-5079\tL phenylalanine degradation III\t7.14741288\n-PWY-6305\tputrescine biosynthesis IV|g__Methanobrevibacter.s__Methanobrevibacter_smithii\t1780.01452698\n-CATECHOL-ORTHO-CLEAVAGE-PWY\tcatechol degradation to &beta; ketoadipate|g__Rhodobacter.s__Rhodobacter_sphaeroides\t480.71275029\n-PWY-7184\tpyrimidine deoxyribonucleotides de novo biosynthesis I|g__Staphylococcus.s__Staphylococcus_aureus\t11346.2826023\n-PWY-5857\tubiquinol 10 biosynthesis |g__Pseudomonas.s__Pseudomonas_aeruginosa\t1649.4470132\n-PWY-4702\tphytate degradation I|g__Staphylococcus.s__Staphylococcus_aureus\t666.66666667\n-PWY-6703\tpreQ0 biosynthesis|g__Pseudomonas.s__Pseudomonas_aeruginosa\t796.05490757\n-PWY-6507\t4 deoxy L threo hex 4 enopyranuronate degradation|g__Streptococcus.s__Streptococcus_agalactiae\t223.47351181\n-PWY-6435\t4 hydroxybenzoate biosynthesis V|g__Staphylococcus.s__Staphylococcus_aureus\t9409.37733628\n-PWY-7199\tpyrimidine deoxyribonucleosides salvage|g__Staphylococcus.s__Staphylococcus_aureus\t10064.1302003\n-CALVIN-PWY\tCalvin Benson Bassham cycle|g__Streptococcus.s__Streptococcus_agalactiae\t616.19648266\n-PWY-5855\tubiquinol 7 biosynthesis |g__Pseudomonas.s__Pseudomonas_aeruginosa\t1649.4470132\n-PWY0-845\tsuperpathway of pyridoxal 5 phosphate biosynthesis and salvage|g__Rhodobacter.s__Rhodobacter_sphaeroides\t779.91889375\n'
b
diff -r c1aca37cb1fc -r 05766022dfc4 test-data/sample_2_specific_pathways.txt
--- a/test-data/sample_2_specific_pathways.txt Wed Apr 20 09:15:27 2016 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
[
b'@@ -1,1336 +0,0 @@\n-id\tname\tabundances\n-PWY-6123\tinosine 5 phosphate biosynthesis I|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae\t3694.54369841\n-PWY-7111\tpyruvate fermentation to isobutanol |g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae\t7136.11057394\n-PWY-7187\tpyrimidine deoxyribonucleotides de novo biosynthesis II|g__Bacteroides.s__Bacteroides_vulgatus\t1482.08811185\n-PWY-5392\treductive TCA cycle II|unclassified\t13.94276095\n-PWY-6126\tsuperpathway of adenosine nucleotides de novo biosynthesis II|g__Neisseria.s__Neisseria_meningitidis\t1351.86626275\n-PWY-5855\tubiquinol 7 biosynthesis |g__Acinetobacter.s__Acinetobacter_baumannii\t3461.49933469\n-PWY0-1061\tsuperpathway of L alanine biosynthesis|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae\t2801.26577532\n-ARGORNPROST-PWY\targinine, ornithine and proline interconversion|g__Enterococcus.s__Enterococcus_faecalis\t229.86451776\n-PWY-841\tsuperpathway of purine nucleotides de novo biosynthesis I|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae\t3239.55702033\n-PWY-6125\tsuperpathway of guanosine nucleotides de novo biosynthesis II|g__Neisseria.s__Neisseria_meningitidis\t1264.65018972\n-PWY-5918\tsuperpathay of heme biosynthesis from glutamate|g__Acinetobacter.s__Acinetobacter_baumannii\t3739.74164481\n-PWY-5189\ttetrapyrrole biosynthesis II |g__Deinococcus.s__Deinococcus_radiodurans\t939.65853472\n-PWY-1042\tglycolysis IV |g__Propionibacterium.s__Propionibacterium_acnes\t4307.94946602\n-HISDEG-PWY\tL histidine degradation I|g__Propionibacterium.s__Propionibacterium_acnes\t3254.94984635\n-PWY-5173\tsuperpathway of acetyl CoA biosynthesis|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae\t2519.87744949\n-FOLSYN-PWY\tsuperpathway of tetrahydrofolate biosynthesis and salvage|g__Propionibacterium.s__Propionibacterium_acnes\t1675.37062714\n-PWY-6895\tsuperpathway of thiamin diphosphate biosynthesis II|unclassified\t64.56529023\n-PWY-7388\toctanoyl [acyl carrier protein] biosynthesis |g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae\t1522.60994915\n-PEPTIDOGLYCANSYN-PWY\tpeptidoglycan biosynthesis I |g__Bacteroides.s__Bacteroides_vulgatus\t2160.13104462\n-PWY-4984\turea cycle|g__Bacteroides.s__Bacteroides_vulgatus\t2013.67758619\n-3-HYDROXYPHENYLACETATE-DEGRADATION-PWY\t4 hydroxyphenylacetate degradation|g__Deinococcus.s__Deinococcus_radiodurans\t11558.1286712\n-PWY-5695\turate biosynthesis inosine 5 phosphate degradation|g__Enterococcus.s__Enterococcus_faecalis\t256.90178056\n-BRANCHED-CHAIN-AA-SYN-PWY\tsuperpathway of branched amino acid biosynthesis|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae\t3873.13594163\n-PEPTIDOGLYCANSYN-PWY\tpeptidoglycan biosynthesis I |g__Listeria.s__Listeria_monocytogenes\t724.9534439\n-SER-GLYSYN-PWY\tsuperpathway of L serine and glycine biosynthesis I|g__Bacteroides.s__Bacteroides_vulgatus\t2896.52791818\n-PWY-7219\tadenosine ribonucleotides de novo biosynthesis|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae\t3526.58041039\n-PWY-6151\tS adenosyl L methionine cycle I|g__Acinetobacter.s__Acinetobacter_baumannii\t3884.95626038\n-COA-PWY\tcoenzyme A biosynthesis I|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae\t2145.77462112\n-PWY-6387\tUDP N acetylmuramoyl pentapeptide biosynthesis I |g__Enterococcus.s__Enterococcus_faecalis\t413.84697579\n-PWY0-162\tsuperpathway of pyrimidine ribonucleotides de novo biosynthesis|g__Bacteroides.s__Bacteroides_vulgatus\t2788.62370201\n-PWY0-1296\tpurine ribonucleosides degradation|g__Listeria.s__Listeria_monocytogenes\t1662.84626817\n-PWY0-162\tsuperpathway of pyrimidine ribonucleotides de novo biosynthesis|g__Helicobacter.s__Helicobacter_pylori\t2256.50698827\n-PWY-6386\tUDP N acetylmuramoyl pentapeptide biosynthesis II |g__Acinetobacter.s__Acinetobacter_baumannii\t5271.876702\n-PWY-6317\tgalactose degradation I |g__Listeria.s__Listeria_monocytogenes\t918.92772969\n-PWY-5910\tsuperpathway of geranylgeranyldiphosphate biosynthesis I |g__Enterococcus.s__Enterococcus_faecalis\t406.73179148\n-PWY-6168\tflavin biosynthesis III'..b'esis I|g__Neisseria.s__Neisseria_meningitidis\t1703.07371128\n-PWY-7229\tsuperpathway of adenosine nucleotides de novo biosynthesis I|g__Actinomyces.s__Actinomyces_odontolyticus\t1047.3630038\n-PWY-7221\tguanosine ribonucleotides de novo biosynthesis|g__Listeria.s__Listeria_monocytogenes\t602.0224203\n-PWY-7184\tpyrimidine deoxyribonucleotides de novo biosynthesis I|g__Neisseria.s__Neisseria_meningitidis\t1063.82344404\n-PWY-7220\tadenosine deoxyribonucleotides de novo biosynthesis II|g__Listeria.s__Listeria_monocytogenes\t943.08991771\n-PWYG-321\tmycolate biosynthesis|g__Listeria.s__Listeria_monocytogenes\t727.33694636\n-PWY-6588\tpyruvate fermentation to acetone|g__Helicobacter.s__Helicobacter_pylori\t1842.02586387\n-PWY-6628\tsuperpathway of L phenylalanine biosynthesis|g__Neisseria.s__Neisseria_meningitidis\t2325.31672002\n-ARGSYNBSUB-PWY\tL arginine biosynthesis II |g__Acinetobacter.s__Acinetobacter_baumannii\t5640.53034458\n-HSERMETANA-PWY\tL methionine biosynthesis III|g__Bacteroides.s__Bacteroides_vulgatus\t3812.82018369\n-PWY-7539\t6 hydroxymethyl dihydropterin diphosphate biosynthesis III |g__Neisseria.s__Neisseria_meningitidis\t1016.73003305\n-PWY-7198\tpyrimidine deoxyribonucleotides de novo biosynthesis IV|g__Propionibacterium.s__Propionibacterium_acnes\t3089.26224286\n-PWY-7539\t6 hydroxymethyl dihydropterin diphosphate biosynthesis III |g__Propionibacterium.s__Propionibacterium_acnes\t640.34891279\n-PWY-5872\tubiquinol 10 biosynthesis \t47.19209027\n-PWY-6936\tseleno amino acid biosynthesis|g__Enterococcus.s__Enterococcus_faecalis\t575.37669038\n-PWY-5910\tsuperpathway of geranylgeranyldiphosphate biosynthesis I |g__Listeria.s__Listeria_monocytogenes\t465.60089664\n-PWY-7222\tguanosine deoxyribonucleotides de novo biosynthesis II|g__Streptococcus.s__Streptococcus_mitis_oralis_pneumoniae\t4569.16166358\n-PWY66-400\tglycolysis VI |g__Listeria.s__Listeria_monocytogenes\t824.96499562\n-FASYN-ELONG-PWY\tfatty acid elongation    saturated|g__Enterococcus.s__Enterococcus_faecalis\t1735.8151961\n-PWY-3781\taerobic respiration I |g__Bacteroides.s__Bacteroides_vulgatus\t2372.93286574\n-PWY-6126\tsuperpathway of adenosine nucleotides de novo biosynthesis II|g__Helicobacter.s__Helicobacter_pylori\t3229.2140178\n-PWY-6703\tpreQ0 biosynthesis|g__Clostridium.s__Clostridium_beijerinckii\t456.48187263\n-PWY-6121\t5 aminoimidazole ribonucleotide biosynthesis I|g__Actinomyces.s__Actinomyces_odontolyticus\t656.48352888\n-DAPLYSINESYN-PWY\tL lysine biosynthesis I|g__Neisseria.s__Neisseria_meningitidis\t1713.17916266\n-PWY-5100\tpyruvate fermentation to acetate and lactate II|g__Actinomyces.s__Actinomyces_odontolyticus\t711.05039042\n-PWY-5659\tGDP mannose biosynthesis|g__Bacteroides.s__Bacteroides_vulgatus\t5067.97426256\n-PWY-7373\tsuperpathway of demethylmenaquinol 6 biosynthesis II|g__Helicobacter.s__Helicobacter_pylori\t1006.81238724\n-PWY-7663\tgondoate biosynthesis |g__Neisseria.s__Neisseria_meningitidis\t4680.40950351\n-ARO-PWY\tchorismate biosynthesis I|g__Acinetobacter.s__Acinetobacter_baumannii\t5469.17722481\n-PWY-841\tsuperpathway of purine nucleotides de novo biosynthesis I|g__Acinetobacter.s__Acinetobacter_baumannii\t3027.23954619\n-P108-PWY\tpyruvate fermentation to propanoate I|unclassified\t80.78380624\n-UDPNAGSYN-PWY\tUDP N acetyl D glucosamine biosynthesis I|g__Bacillus.s__Bacillus_cereus_thuringiensis\t271.55477416\n-PWY-6891\tthiazole biosynthesis II |g__Bacillus.s__Bacillus_cereus_thuringiensis\t290.80786445\n-PWY-4041\t&gamma; glutamyl cycle|g__Enterococcus.s__Enterococcus_faecalis\t813.17944374\n-PWY-6163\tchorismate biosynthesis from 3 dehydroquinate|g__Listeria.s__Listeria_monocytogenes\t913.1636705\n-PWY66-389\tphytol degradation|g__Listeria.s__Listeria_monocytogenes\t853.87077686\n-OANTIGEN-PWY\tO antigen building blocks biosynthesis |g__Clostridium.s__Clostridium_beijerinckii\t485.31186564\n-PWY-7392\ttaxadiene biosynthesis |g__Propionibacterium.s__Propionibacterium_acnes\t2628.10374094\n-PWY-6125\tsuperpathway of guanosine nucleotides de novo biosynthesis II|g__Deinococcus.s__Deinococcus_radiodurans\t18402.8474421\n'
b
diff -r c1aca37cb1fc -r 05766022dfc4 test-data/sample_similar_pathways.tabular
--- a/test-data/sample_similar_pathways.tabular Wed Apr 20 09:15:27 2016 -0400
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000
[
b'@@ -1,1921 +0,0 @@\n-id\tname\tsample1\tsample2\n-PWY-6527\tstachyose degradation|g__Streptococcus.s__Streptococcus_mutans\t9089.59894354\t1696.97295223\n-PWY-6471\tpeptidoglycan biosynthesis IV \t46455.865627\t30449.8634207\n-PWY-7208\tsuperpathway of pyrimidine nucleobases salvage|g__Rhodobacter.s__Rhodobacter_sphaeroides\t12559.4677571\t1282.55432956\n-PWY-7288\tfatty acid &beta; oxidation \t12818.3639901\t25828.6507825\n-PWY-3841\tfolate transformations II|g__Escherichia.s__Escherichia_coli\t3007.20583149\t217.72486044\n-PWY-6737\tstarch degradation V|unclassified\t48.21577448\t239.03206251\n-PWY0-1297\tsuperpathway of purine deoxyribonucleosides degradation|g__Staphylococcus.s__Staphylococcus_epidermidis\t9039.67328714\t1589.30574604\n-PWY-5659\tGDP mannose biosynthesis|g__Acinetobacter.s__Acinetobacter_baumannii\t172.93621006\t4543.25980432\n-PWY-2942\tL lysine biosynthesis III|g__Streptococcus.s__Streptococcus_mutans\t4710.2025552\t708.88601201\n-PWY-6151\tS adenosyl L methionine cycle I\t45554.1733597\t42591.852733\n-SALVADEHYPOX-PWY\tadenosine nucleotides degradation II\t88803.4244676\t102915.149017\n-PWY-6596\tadenosine nucleotides degradation I\t7817.66872493\t696.2294504\n-PWY4LZ-257\tsuperpathway of fermentation \t44732.9715391\t35196.3430939\n-ILEUDEG-PWY\tL isoleucine degradation I\t33.8421746\t6967.21446351\n-PWY0-1261\tanhydromuropeptides recycling|g__Escherichia.s__Escherichia_coli\t5164.50768682\t671.73572925\n-PANTOSYN-PWY\tpantothenate and coenzyme A biosynthesis I|g__Staphylococcus.s__Staphylococcus_epidermidis\t10239.9838748\t583.91715667\n-PWY-5686\tUMP biosynthesis|g__Streptococcus.s__Streptococcus_mutans\t6754.11537711\t798.00767542\n-PWY-5384\tsucrose degradation IV \t12240.4968895\t9746.7324837\n-PWY-6277\tsuperpathway of 5 aminoimidazole ribonucleotide biosynthesis|g__Staphylococcus.s__Staphylococcus_aureus\t13369.9763528\t1138.58445146\n-PWY-7357\tthiamin formation from pyrithiamine and oxythiamine |g__Staphylococcus.s__Staphylococcus_epidermidis\t7605.96092233\t1506.9159832\n-PWY-5676\tacetyl CoA fermentation to butanoate II|g__Clostridium.s__Clostridium_beijerinckii\t834.72187681\t2820.816865\n-GLUTORN-PWY\tL ornithine biosynthesis|g__Rhodobacter.s__Rhodobacter_sphaeroides\t2679.42319429\t806.11037888\n-PWY-5676\tacetyl CoA fermentation to butanoate II|unclassified\t293.27344931\t313.4611172\n-PWY-6107\tchlorosalicylate degradation\t4990.49166626\t3707.99522741\n-PWY-5514\tUDP N acetyl D galactosamine biosynthesis II\t211.99921193\t8344.45133876\n-HEMESYN2-PWY\theme biosynthesis II |g__Rhodobacter.s__Rhodobacter_sphaeroides\t13472.0925007\t1713.65799734\n-SER-GLYSYN-PWY\tsuperpathway of L serine and glycine biosynthesis I|g__Acinetobacter.s__Acinetobacter_baumannii\t165.52210569\t5261.09986526\n-PWY-6467\tKdo transfer to lipid IVA III \t1326.69762557\t332.28938386\n-PWY-5971\tpalmitate biosynthesis II |unclassified\t328.78037799\t707.87369542\n-PWY-6313\tserotonin degradation|g__Propionibacterium.s__Propionibacterium_acnes\t257.91056362\t3253.85903121\n-PWY-5897\tsuperpathway of menaquinol 11 biosynthesis\t21209.4938493\t15529.8979214\n-PWY-2942\tL lysine biosynthesis III|g__Clostridium.s__Clostridium_beijerinckii\t372.91948736\t1644.65015852\n-PWY-6305\tputrescine biosynthesis IV|g__Rhodobacter.s__Rhodobacter_sphaeroides\t2264.19577283\t409.21191468\n-HEMESYN2-PWY\theme biosynthesis II |g__Neisseria.s__Neisseria_meningitidis\t160.47842097\t2460.45875987\n-PWY-6305\tputrescine biosynthesis IV\t19202.9873681\t14135.5882465\n-PWY-7219\tadenosine ribonucleotides de novo biosynthesis|unclassified\t316.23278205\t406.96069748\n-HEME-BIOSYNTHESIS-II\theme biosynthesis I |g__Rhodobacter.s__Rhodobacter_sphaeroides\t13109.3800959\t1763.21900128\n-ANAEROFRUCAT-PWY\thomolactic fermentation|g__Clostridium.s__Clostridium_beijerinckii\t604.47752551\t1298.26997095\n-PWY-6307\tL tryptophan degradation X |g__Propionibacterium.s__Propionibacterium_acnes\t209.13755224\t2687.36440723\n-PWY-6606\tguanosine nucleotides degradation II|g__Rhodobacter.s__Rhodobacter_sphaeroides\t2736.23201469\t471.84886441\n-PWY-5189\ttetrapyrrole biosynthesis II |g__Staphylococcus.s__Staphylococcus'..b'_baumannii\t311.86743823\t5092.62189788\n-PWY-7198\tpyrimidine deoxyribonucleotides de novo biosynthesis IV|unclassified\t497.58534601\t921.96101244\n-PWY0-1479\ttRNA processing|unclassified\t53.90015148\t65.20708513\n-PWY-5103\tL isoleucine biosynthesis III|g__Staphylococcus.s__Staphylococcus_aureus\t12414.2746766\t1786.69711145\n-PWY-4041\t&gamma; glutamyl cycle\t30349.4757439\t14586.7772214\n-COLANSYN-PWY\tcolanic acid building blocks biosynthesis|unclassified\t16.96524789\t206.11126006\n-PWY-7357\tthiamin formation from pyrithiamine and oxythiamine |g__Clostridium.s__Clostridium_beijerinckii\t367.13964071\t1248.77414621\n-PWY-5791\t1,4 dihydroxy 2 naphthoate biosynthesis II |g__Staphylococcus.s__Staphylococcus_aureus\t8931.57710009\t1036.87621513\n-PWY0-1586\tpeptidoglycan maturation |g__Escherichia.s__Escherichia_coli\t18753.0219821\t2866.53948432\n-PWY-5181\ttoluene degradation III  (via p cresol)\t947.6822035\t8800.26352918\n-PWY-5659\tGDP mannose biosynthesis|g__Escherichia.s__Escherichia_coli\t2998.91987725\t599.8717343\n-PWY-5861\tsuperpathway of demethylmenaquinol 8 biosynthesis|g__Escherichia.s__Escherichia_coli\t3430.13320251\t441.24808359\n-PWY-7220\tadenosine deoxyribonucleotides de novo biosynthesis II|g__Streptococcus.s__Streptococcus_mutans\t8808.69286571\t979.81451315\n-THISYNARA-PWY\tsuperpathway of thiamin diphosphate biosynthesis III |unclassified\t27.4597085\t4.34882378\n-PWY0-862\t dodec 5 enoate biosynthesis|g__Rhodobacter.s__Rhodobacter_sphaeroides\t15969.8171928\t2909.26805533\n-PWY-4242\tpantothenate and coenzyme A biosynthesis III|g__Streptococcus.s__Streptococcus_mutans\t1835.16841428\t1235.31350955\n-PWY-7389\tsuperpathway of anaerobic energy metabolism \t1843.01379918\t11881.3874654\n-SER-GLYSYN-PWY\tsuperpathway of L serine and glycine biosynthesis I|g__Escherichia.s__Escherichia_coli\t3369.37968613\t610.39579238\n-PWY-5138\tunsaturated, even numbered fatty acid &beta; oxidation|g__Rhodobacter.s__Rhodobacter_sphaeroides\t11928.9247442\t3378.73427795\n-PWY-7388\toctanoyl [acyl carrier protein] biosynthesis |unclassified\t188.12545302\t274.49677967\n-PWY-724\tsuperpathway of L lysine, L threonine and L methionine biosynthesis II\t41547.2317349\t36974.2649936\n-PWY-5347\tsuperpathway of L methionine biosynthesis |g__Streptococcus.s__Streptococcus_mutans\t6303.81343752\t1187.03506311\n-POLYAMSYN-PWY\tsuperpathway of polyamine biosynthesis I|unclassified\t91.63013862\t13.26838762\n-PWY-5188\ttetrapyrrole biosynthesis I |g__Escherichia.s__Escherichia_coli\t3934.45905699\t738.40173753\n-DENITRIFICATION-PWY\tnitrate reduction I \t9285.14991359\t6301.73393977\n-HISDEG-PWY\tL histidine degradation I\t21504.3758787\t24267.6604905\n-PWY-6467\tKdo transfer to lipid IVA III |g__Escherichia.s__Escherichia_coli\t919.96428358\t332.28938386\n-PWY-5989\tstearate biosynthesis II |g__Staphylococcus.s__Staphylococcus_aureus\t6689.02064509\t1275.28632006\n-NONMEVIPP-PWY\tmethylerythritol phosphate pathway I\t21604.2127381\t41467.563069\n-PWY-6595\tsuperpathway of guanosine nucleotides degradation \t63659.5681895\t24658.3886983\n-PWY-7400\tL arginine biosynthesis IV \t59561.9426266\t54069.712201\n-PWY0-1061\tsuperpathway of L alanine biosynthesis|g__Clostridium.s__Clostridium_beijerinckii\t469.04005117\t1041.74348067\n-LEU-DEG2-PWY\tL leucine degradation I|g__Pseudomonas.s__Pseudomonas_aeruginosa\t292.84136182\t209.12320819\n-BIOTIN-BIOSYNTHESIS-PWY\tbiotin biosynthesis I\t38795.0783858\t31607.4904903\n-ARG+POLYAMINE-SYN\tsuperpathway of arginine and polyamine biosynthesis|g__Escherichia.s__Escherichia_coli\t3860.50746504\t701.87663984\n-PWY-5028\tL histidine degradation II\t7261.31861705\t8974.70796842\n-ASPASN-PWY\tsuperpathway of L aspartate and L asparagine biosynthesis|unclassified\t135.51257994\t180.94686582\n-HEME-BIOSYNTHESIS-II\theme biosynthesis I |g__Escherichia.s__Escherichia_coli\t4444.06370581\t1229.13243631\n-PWY-6565\tsuperpathway of polyamine biosynthesis III\t307.24774533\t5432.67232731\n-PWY-4221\tpantothenate and coenzyme A biosynthesis II \t6446.80589887\t3651.48403549\n-PWY-6282\tpalmitoleate biosynthesis I  dodec 5 enoate)\t54100.9348987\t54847.3411852\n'