Repository 'group_humann2_uniref_abundances_to_go'
hg clone https://toolshed.g2.bx.psu.edu/repos/rsajulga/group_humann2_uniref_abundances_to_go

Changeset 0:bdc077ef0cdd (2019-03-08)
Next changeset 1:fcc46fdac26b (2019-03-08)
Commit message:
planemo upload for repository https://github.com/ASaiM/galaxytools/tree/master/tools/group_humann2_uniref_abundances_to_GO
added:
group_humann2_uniref_abundances_to_go.xml
test-data/expected_biological_process_abundance.txt
test-data/expected_cellular_component_abundance.txt
test-data/expected_molecular_function_abundances.txt
test-data/go_02_22_2016.obo
test-data/goslim_metagenomics_02_22_2016.obo
test-data/humann2_gene_families.csv
test-data/map_infogo1000_uniref50_02_22_2016.txt
test-data/o_02_22_2016.obo
tool_dependencies.xml
b
diff -r 000000000000 -r bdc077ef0cdd group_humann2_uniref_abundances_to_go.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/group_humann2_uniref_abundances_to_go.xml Fri Mar 08 15:04:11 2019 -0500
[
@@ -0,0 +1,127 @@
+<tool id="group_humann2_uniref_abundances_to_go" name="Group abundances" version="1.2.3">
+    <description> of UniRef50 gene families obtained (HUMAnN2 output) to Gene Ontology (GO) slim terms</description>
+
+    <requirements>
+        <requirement type="package" version="1.9">numpy</requirement>
+        <requirement type="package" version="0.6.1">humann2</requirement>
+        <requirement type="package" version="0.6.4">goatools</requirement>
+        <requirement type="package" version="0.1.4">fisher</requirement>
+        <requirement type="package" version="1.2.0">group_humann2_uniref_abundances_to_go</requirement>
+    </requirements>
+
+    <stdio>
+        <exit_code range="1:" />
+        <regex match="IOError"
+               source="both"
+               level="fatal"
+               description="Python file error" />
+        <regex match="pkg_resources"
+               source="both"
+               level="fatal"
+               description="PKG Error" />
+    </stdio>
+
+    <version_command></version_command>
+
+    <command><![CDATA[
+        group_humann2_uniref_abundances_to_GO.sh
+            -i $humann2_gene_families_abundance 
+            -m $molecular_function_abundance
+            -b $biological_process_abundance
+            -c $cellular_component_abundance
+
+            #if $gene_ontology.gene_ontology_test:
+                -a $gene_ontology.gene_ontology_file
+            #end if
+
+            #if $slim_gene_ontology.slim_gene_ontology_test:
+                -s $slim_gene_ontology.slim_gene_ontology_file
+            #end if
+
+            #if $uniref50_go.uniref50_go_test:
+                -u $uniref50_go.uniref50_go_file
+            #end if
+
+            -g `which map_to_slim.py | xargs -n1 dirname`
+            -p `which humann2 | xargs -n1 dirname`
+    ]]></command>
+
+    <inputs>
+        <param name="humann2_gene_families_abundance" type="data" format="tabular,tsv,txt" label="HUMAnN2 output with UniRef50 gene family abundance" help="(-i)"/>
+
+        <conditional name="gene_ontology">
+            <param name='gene_ontology_test' type='boolean' checked="false" truevalue='true' falsevalue='false' label="Use a custom Gene Ontology file?" help="By default, the used Gene Ontology is the core ontology downloaded on Gene
+                Ontology website"/>
+            <when value="true">
+                <param name="gene_ontology_file" type="data" format="txt" label="Gene Ontology" help=""/>
+            </when>
+            <when value="false" />
+        </conditional>
+
+        <conditional name="slim_gene_ontology">
+            <param name='slim_gene_ontology_test' type='boolean' checked="false" truevalue='true' falsevalue='false' label="Use a custom slim Gene Ontology file?" help="By default, the used slim Gene Ontology is the metagenomics slim developed by Jane Lomax and the InterPro group"/>
+            <when value="true">
+                <param name="slim_gene_ontology_file" type="data" format="txt" label="Slim Gene Ontology" help=""/>
+            </when>
+            <when value="false" />
+        </conditional>
+
+        <conditional name="uniref50_go">
+            <param name='uniref50_go_test' type='boolean' checked="false" truevalue='true' falsevalue='false' label="Use a custom correspondance between UniRef50 and precise GO?" help="By default, the used correspondance is the one
+                proposed in HUMAnN2"/>
+            <when value="true">
+                <param name="uniref50_go_file" type="data" format="txt" label="Correspondance between UniRef50 and GO" help=""/>
+            </when>
+            <when value="false" />
+        </conditional>
+    </inputs>
+
+    <outputs>
+        <data format="tabular" name="molecular_function_abundance" label="${tool.name} on ${on_string}: Molecular function abundance"/>
+        <data format="tabular" name="biological_process_abundance" label="${tool.name} on ${on_string}: Biological process abundance"/>
+        <data format="tabular" name="cellular_component_abundance" label="${tool.name} on ${on_string}: Cellular component abundance"/>
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="humann2_gene_families_abundance" value="humann2_gene_families.csv"/>
+            <param name='gene_ontology_test' value='true'/>
+            <param name="gene_ontology_file" value="go_02_22_2016.obo" />
+            <param name='slim_gene_ontology_test' value="true"/>
+            <param name="slim_gene_ontology_file" value="goslim_metagenomics_02_22_2016.obo" />
+            <param name='uniref50_go_test' value="true"/>
+            <param name="uniref50_go_file" value="map_infogo1000_uniref50_02_22_2016.txt"/>
+            <output name="molecular_function_abundance" file="expected_molecular_function_abundances.txt"/>
+            <output name="biological_process_abundance" file="expected_biological_process_abundance.txt"/>
+            <output name="cellular_component_abundance" file="expected_cellular_component_abundance.txt"/>
+        </test>
+    </tests>
+
+    <help><![CDATA[
+**What it does**
+
+HUMAnN2 is a pipeline to profile the presence/absence and abundance of microbial pathways in community of microbiota sequencing data. One output is a file with UniRef50 gene family abundances. HUMAnN2 proposes a script to regroup Uniref50 to GO, but used GO terms are too precise to get a broad overview of the ontology content.
+
+The tool described here contains scripts to group UniRef50 abundances obtained using main HUMANn2 script (Gene families) to GO slim terms. GO slim is a subset of the terms in the whole GO. For this tool, metagenomics GO slim terms developed by Jane Lomax and the InterPro group.
+
+More information on `dedicated GitHub repository <https://github.com/ASaiM/group_humann2_uniref_abundances_to_GO>`_.
+
+**Inputs**
+
+This tool takes as input a file with UniRef50 gene family abundances generated with HUMAnN2.
+
+Several optional inputs can also be given: a custom Gene Ontology file with the core ontology, a custom slim Gene Ontology with description of slim GO terms to use and a custom mapping file which map UniRef50 gene families to GO terms.
+
+**Outputs**
+
+3 outputs are generated: abundances of GO slim terms grouped in 3 groups (molecular functions, biological processes and cellular components). 
+
+Each file is a tabular file with 3 columns: GO slim term id, name and abundance.
+    ]]></help>
+
+    <citations>
+        <citation type="doi">10.5281/zenodo.50086</citation>
+        <citation type="doi">10.5281/zenodo.31628</citation>
+        <citation type="doi">10.1371/journal.pcbi.1002358</citation>
+    </citations>
+</tool>
\ No newline at end of file
b
diff -r 000000000000 -r bdc077ef0cdd test-data/expected_biological_process_abundance.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/expected_biological_process_abundance.txt Fri Mar 08 15:04:11 2019 -0500
b
@@ -0,0 +1,47 @@
+GO id GO name Abundance
+GO:0000160 phosphorelay signal transduction system 1112.3915515778
+GO:0000746 conjugation 46.559859807600006
+GO:0000902 cell morphogenesis 1.8470267351
+GO:0002376 immune system process 23.700662623200003
+GO:0005975 carbohydrate metabolic process 2612.6970692966993
+GO:0006091 generation of precursor metabolites and energy 943.0642504650992
+GO:0006259 DNA metabolic process 2760.3666308885995
+GO:0006351 transcription, DNA-templated 0.0615114205
+GO:0006412 translation 3280.1516158372006
+GO:0006520 cellular amino acid metabolic process 3953.6382689974002
+GO:0006629 lipid metabolic process 1380.8390328801004
+GO:0006790 sulfur compound metabolic process 1012.3221601218003
+GO:0006807 nitrogen compound metabolic process 3915.4792502578994
+GO:0006810 transport 1101.0465624405
+GO:0006811 ion transport 1276.2633195375001
+GO:0006950 response to stress 954.8641672250999
+GO:0007154 cell communication 316.8910362473
+GO:0007165 signal transduction 45.3316263193
+GO:0008150 biological_process 2784.3062048235997
+GO:0009056 catabolic process 1728.292233976299
+GO:0009058 biosynthetic process 12048.508539055703
+GO:0009117 nucleotide metabolic process 2472.3435074350996
+GO:0009306 protein secretion 23.141466690899996
+GO:0009404 toxin metabolic process 9.095920561400002
+GO:0009405 pathogenesis 58.27509464559998
+GO:0015979 photosynthesis 44.73480409939999
+GO:0016032 viral process 0.7986287266
+GO:0016043 cellular component organization 1246.5641915709
+GO:0016049 cell growth 4.1997618312
+GO:0016070 RNA metabolic process 1855.2220049666994
+GO:0016310 phosphorylation 1372.0241480503992
+GO:0019538 protein metabolic process 672.0486860101004
+GO:0022900 electron transport chain 103.16706894990003
+GO:0030031 cell projection assembly 32.495419504000004
+GO:0032196 transposition 300.7048225378001
+GO:0042592 homeostatic process 306.4798266318999
+GO:0043934 sporulation 174.71346946979997
+GO:0044281 small molecule metabolic process 4445.203127840403
+GO:0045333 cellular respiration 5.518723520100001
+GO:0046034 ATP metabolic process 1002.5305430942991
+GO:0048870 cell motility 107.9960707376
+GO:0051186 cofactor metabolic process 2456.361318531299
+GO:0051301 cell division 864.5391215972995
+GO:0055114 oxidation-reduction process 215.51031499180004
+GO:0071554 cell wall organization or biogenesis 36.7500063207
+GO:0071941 nitrogen cycle metabolic process 56.684053508
b
diff -r 000000000000 -r bdc077ef0cdd test-data/expected_cellular_component_abundance.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/expected_cellular_component_abundance.txt Fri Mar 08 15:04:11 2019 -0500
b
@@ -0,0 +1,25 @@
+GO id GO name Abundance
+GO:0005575 cellular_component 4211.620011669099
+GO:0005618 cell wall 101.24244809220001
+GO:0005634 nucleus 86.82707381589996
+GO:0005694 chromosome 0.0271872006
+GO:0005727 extrachromosomal circular DNA 121.82450720269999
+GO:0005737 cytoplasm 9919.697399687224
+GO:0005739 mitochondrion 193.03667393669969
+GO:0005773 vacuole 2.2073187229999993
+GO:0005783 endoplasmic reticulum 13.858678920100003
+GO:0005794 Golgi apparatus 11.580712904300004
+GO:0005840 ribosome 1635.3364950416994
+GO:0005856 cytoskeleton 0.1781304753
+GO:0005886 plasma membrane 2956.1483673840053
+GO:0009295 nucleoid 56.116239729200025
+GO:0009579 thylakoid 16.531472969800003
+GO:0016020 membrane 76.73590696070002
+GO:0019012 virion 0.2407286574
+GO:0019867 outer membrane 502.1513331402007
+GO:0031012 extracellular matrix 0.5991089999
+GO:0031982 vesicle 81.09742051820007
+GO:0042575 DNA polymerase complex 65.46696539999999
+GO:0042597 periplasmic space 130.1736765559
+GO:0043190 ATP-binding cassette (ABC) transporter complex 271.6521785019997
+GO:0070469 respiratory chain 2.0447839356
b
diff -r 000000000000 -r bdc077ef0cdd test-data/expected_molecular_function_abundances.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/expected_molecular_function_abundances.txt Fri Mar 08 15:04:11 2019 -0500
b
@@ -0,0 +1,40 @@
+GO id GO name Abundance
+GO:0000156 phosphorelay response regulator activity 4.4347360838
+GO:0000166 nucleotide binding 11436.730254302318
+GO:0000988 transcription factor activity, protein binding 673.7839975407998
+GO:0003674 molecular_function 4087.6458012782
+GO:0003676 nucleic acid binding 3028.700666733601
+GO:0003924 GTPase activity 490.16358835940014
+GO:0004386 helicase activity 273.26291990489995
+GO:0004518 nuclease activity 708.2423017374001
+GO:0004672 protein kinase activity 626.4942495674997
+GO:0004812 aminoacyl-tRNA ligase activity 234.25362423819996
+GO:0004872 receptor activity 626.4846539767997
+GO:0005102 receptor binding 1.5301407557
+GO:0005215 transporter activity 1762.0709654024004
+GO:0008092 cytoskeletal protein binding 7.383357547800001
+GO:0008134 transcription factor binding 84.63172726779997
+GO:0008233 peptidase activity 1182.3108289962993
+GO:0016298 lipase activity 3.6081972003000002
+GO:0016301 kinase activity 937.2682550285
+GO:0016407 acetyltransferase activity 65.750125095
+GO:0016491 oxidoreductase activity 2051.3275224607996
+GO:0016740 transferase activity 2598.2115822036
+GO:0016746 transferase activity, transferring acyl groups 212.45457835869996
+GO:0016757 transferase activity, transferring glycosyl groups 319.0056774039
+GO:0016765 transferase activity, transferring alkyl or aryl (other than methyl) groups 161.48389564689995
+GO:0016787 hydrolase activity 280.95384492459993
+GO:0016788 hydrolase activity, acting on ester bonds 549.7984070913
+GO:0016791 phosphatase activity 148.29697741039996
+GO:0016798 hydrolase activity, acting on glycosyl bonds 650.9218081131
+GO:0016810 hydrolase activity, acting on carbon-nitrogen (but not peptide) bonds 428.24025912369996
+GO:0016829 lyase activity 575.0019956493999
+GO:0016853 isomerase activity 1916.3316482209
+GO:0016874 ligase activity 675.5332395482
+GO:0016887 ATPase activity 965.0511058454001
+GO:0030234 enzyme regulator activity 31.695909846600003
+GO:0034061 DNA polymerase activity 290.6773463926
+GO:0034062 RNA polymerase activity 233.7752678209
+GO:0046872 metal ion binding 4116.705081461401
+GO:0048037 cofactor binding 2930.3128404498993
+GO:0051082 unfolded protein binding 203.18389855299998
b
diff -r 000000000000 -r bdc077ef0cdd test-data/go_02_22_2016.obo
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/go_02_22_2016.obo Fri Mar 08 15:04:11 2019 -0500
[
b'@@ -0,0 +1,597223 @@\n+format-version: 1.2\n+data-version: releases/2016-02-20\n+date: 19:02:2016 13:43\n+saved-by: tanyaberardini\n+auto-generated-by: OBO-Edit 2.3.1\n+subsetdef: goantislim_grouping "Grouping classes that can be excluded"\n+subsetdef: gocheck_do_not_annotate "Term not to be used for direct annotation"\n+subsetdef: gocheck_do_not_manually_annotate "Term not to be used for direct manual annotation"\n+subsetdef: goslim_aspergillus "Aspergillus GO slim"\n+subsetdef: goslim_candida "Candida GO slim"\n+subsetdef: goslim_chembl "ChEMBL protein targets summary"\n+subsetdef: goslim_generic "Generic GO slim"\n+subsetdef: goslim_goa "GOA and proteome slim"\n+subsetdef: goslim_metagenomics "Metagenomics GO slim"\n+subsetdef: goslim_pir "PIR GO slim"\n+subsetdef: goslim_plant "Plant GO slim"\n+subsetdef: goslim_pombe "Fission yeast GO slim"\n+subsetdef: goslim_synapse "synapse GO slim"\n+subsetdef: goslim_virus "Viral GO slim"\n+subsetdef: goslim_yeast "Yeast GO slim"\n+subsetdef: gosubset_prok "Prokaryotic GO subset"\n+subsetdef: mf_needs_review "Catalytic activity terms in need of attention"\n+subsetdef: termgenie_unvetted "Terms created by TermGenie that do not follow a template and require additional vetting by editors"\n+subsetdef: virus_checked "Viral overhaul terms"\n+synonymtypedef: systematic_synonym "Systematic synonym" EXACT\n+default-namespace: gene_ontology\n+remark: cvs version: $Revision: 31531 $\n+ontology: go\n+\n+[Term]\n+id: GO:0000001\n+name: mitochondrion inheritance\n+namespace: biological_process\n+def: "The distribution of mitochondria, including the mitochondrial genome, into daughter cells after mitosis or meiosis, mediated by interactions between mitochondria and the cytoskeleton." [GOC:mcc, PMID:10873824, PMID:11389764]\n+synonym: "mitochondrial inheritance" EXACT []\n+is_a: GO:0048308 ! organelle inheritance\n+is_a: GO:0048311 ! mitochondrion distribution\n+\n+[Term]\n+id: GO:0000002\n+name: mitochondrial genome maintenance\n+namespace: biological_process\n+def: "The maintenance of the structure and integrity of the mitochondrial genome; includes replication and segregation of the mitochondrial chromosome." [GOC:ai, GOC:vw]\n+is_a: GO:0007005 ! mitochondrion organization\n+\n+[Term]\n+id: GO:0000003\n+name: reproduction\n+namespace: biological_process\n+alt_id: GO:0019952\n+alt_id: GO:0050876\n+def: "The production of new individuals that contain some portion of genetic material inherited from one or more parent organisms." [GOC:go_curators, GOC:isa_complete, GOC:jl, ISBN:0198506732]\n+subset: goslim_chembl\n+subset: goslim_generic\n+subset: goslim_pir\n+subset: goslim_plant\n+subset: gosubset_prok\n+synonym: "reproductive physiological process" EXACT []\n+xref: Wikipedia:Reproduction\n+is_a: GO:0008150 ! biological_process\n+disjoint_from: GO:0044848 ! biological phase\n+\n+[Term]\n+id: GO:0000005\n+name: obsolete ribosomal chaperone activity\n+namespace: molecular_function\n+def: "OBSOLETE. Assists in the correct assembly of ribosomes or ribosomal subunits in vivo, but is not a component of the assembled ribosome when performing its normal biological function." [GOC:jl, PMID:12150913]\n+comment: This term was made obsolete because it refers to a class of gene products and a biological process rather than a molecular function.\n+synonym: "ribosomal chaperone activity" EXACT []\n+is_obsolete: true\n+consider: GO:0042254\n+consider: GO:0044183\n+consider: GO:0051082\n+\n+[Term]\n+id: GO:0000006\n+name: high-affinity zinc uptake transmembrane transporter activity\n+namespace: molecular_function\n+def: "Enables the transfer of a solute or solutes from one side of a membrane to the other according to the reaction: Zn2+(out) = Zn2+(in), probably powered by proton motive force. In high-affinity transport the transporter is able to bind the solute even if it is only present at very low concentrations." [TC:2.A.5.1.1]\n+synonym: "high affinity zinc uptake transmembrane transporter activity" EXACT []\n+is_a: GO:0005385 ! zinc ion transmembrane transporter activity\n+\n+[Term]\n+id: G'..b' GO:2001313 ! UDP-4-deoxy-4-formamido-beta-L-arabinopyranose metabolic process\n+created_by: pr\n+creation_date: 2012-03-22T01:20:05Z\n+\n+[Term]\n+id: GO:2001316\n+name: kojic acid metabolic process\n+namespace: biological_process\n+def: "The chemical reactions and pathways involving kojic acid." [CHEBI:43572, GOC:di]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one metabolic process" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one metabolism" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 metabolic process" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 metabolism" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "kojic acid metabolism" EXACT [GOC:obol]\n+is_a: GO:0034308 ! primary alcohol metabolic process\n+is_a: GO:0042180 ! cellular ketone metabolic process\n+is_a: GO:0046483 ! heterocycle metabolic process\n+is_a: GO:1901360 ! organic cyclic compound metabolic process\n+created_by: rfoulger\n+creation_date: 2012-04-18T09:22:42Z\n+\n+[Term]\n+id: GO:2001317\n+name: kojic acid biosynthetic process\n+namespace: biological_process\n+def: "The chemical reactions and pathways resulting in the formation of kojic acid." [CHEBI:43572, GOC:di]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one anabolism" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one biosynthesis" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one biosynthetic process" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one formation" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one synthesis" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 anabolism" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 biosynthesis" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 biosynthetic process" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 formation" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 synthesis" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "kojic acid anabolism" EXACT [GOC:obol]\n+synonym: "kojic acid biosynthesis" EXACT [GOC:obol]\n+synonym: "kojic acid formation" EXACT [GOC:obol]\n+synonym: "kojic acid synthesis" EXACT [GOC:obol]\n+is_a: GO:0018130 ! heterocycle biosynthetic process\n+is_a: GO:0034309 ! primary alcohol biosynthetic process\n+is_a: GO:0042181 ! ketone biosynthetic process\n+is_a: GO:1901362 ! organic cyclic compound biosynthetic process\n+is_a: GO:2001316 ! kojic acid metabolic process\n+created_by: rfoulger\n+creation_date: 2012-04-18T09:22:46Z\n+\n+[Typedef]\n+id: ends_during\n+name: ends_during\n+namespace: external\n+xref: RO:0002093\n+\n+[Typedef]\n+id: happens_during\n+name: happens_during\n+namespace: external\n+xref: RO:0002092\n+is_transitive: true\n+is_a: ends_during ! ends_during\n+\n+[Typedef]\n+id: has_part\n+name: has_part\n+namespace: external\n+xref: BFO:0000051\n+is_transitive: true\n+\n+[Typedef]\n+id: negatively_regulates\n+name: negatively regulates\n+namespace: external\n+xref: RO:0002212\n+is_a: regulates ! regulates\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: never_in_taxon\n+name: never_in_taxon\n+namespace: external\n+xref: RO:0002161\n+expand_assertion_to: "Class: ?X DisjointWith: RO_0002162 some ?Y" []\n+is_metadata_tag: true\n+is_class_level: true\n+\n+[Typedef]\n+id: occurs_in\n+name: occurs in\n+namespace: external\n+xref: BFO:0000066\n+holds_over_chain: part_of occurs_in\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: part_of\n+name: part of\n+namespace: external\n+xref: BFO:0000050\n+is_transitive: true\n+inverse_of: has_part ! has_part\n+\n+[Typedef]\n+id: positively_regulates\n+name: positively regulates\n+namespace: external\n+xref: RO:0002213\n+holds_over_chain: negatively_regulates negatively_regulates\n+is_a: regulates ! regulates\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: regulates\n+name: regulates\n+namespace: external\n+xref: RO:0002211\n+is_transitive: true\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: starts_during\n+name: starts_during\n+namespace: external\n+xref: RO:0002091\n+\n'
b
diff -r 000000000000 -r bdc077ef0cdd test-data/goslim_metagenomics_02_22_2016.obo
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/goslim_metagenomics_02_22_2016.obo Fri Mar 08 15:04:11 2019 -0500
[
b'@@ -0,0 +1,3551 @@\n+format-version: 1.2\n+subsetdef: goantislim_grouping "Grouping classes that can be excluded"\n+subsetdef: gocheck_do_not_annotate "Term not to be used for direct annotation"\n+subsetdef: gocheck_do_not_manually_annotate "Term not to be used for direct manual annotation"\n+subsetdef: goslim_aspergillus "Aspergillus GO slim"\n+subsetdef: goslim_candida "Candida GO slim"\n+subsetdef: goslim_chembl "ChEMBL protein targets summary"\n+subsetdef: goslim_generic "Generic GO slim"\n+subsetdef: goslim_goa "GOA and proteome slim"\n+subsetdef: goslim_metagenomics "Metagenomics GO slim"\n+subsetdef: goslim_pir "PIR GO slim"\n+subsetdef: goslim_plant "Plant GO slim"\n+subsetdef: goslim_pombe "Fission yeast GO slim"\n+subsetdef: goslim_synapse "synapse GO slim"\n+subsetdef: goslim_virus "Viral GO slim"\n+subsetdef: goslim_yeast "Yeast GO slim"\n+subsetdef: gosubset_prok "Prokaryotic GO subset"\n+subsetdef: mf_needs_review "Catalytic activity terms in need of attention"\n+subsetdef: termgenie_unvetted "Terms created by TermGenie that do not follow a template and require additional vetting by editors"\n+subsetdef: virus_checked "Viral overhaul terms"\n+synonymtypedef: systematic_synonym "Systematic synonym" EXACT\n+ontology: go/subsets/goslim_metagenomics\n+\n+[Term]\n+id: GO:0000156\n+name: phosphorelay response regulator activity\n+namespace: molecular_function\n+def: "Responds to a phosphorelay sensor to initiate a change in cell state or activity. The activity of the response regulator is regulated by transfer of a phosphate from a histidine residue in the sensor, to an aspartate residue in the response regulator. Many but not all response regulators act as transcriptional regulators to elicit a response." [GOC:bf, PMID:10966457, PMID:11842140]\n+subset: goslim_metagenomics\n+subset: gosubset_prok\n+synonym: "two-component response regulator activity" NARROW []\n+is_a: GO:0003674 ! molecular_function\n+relationship: part_of GO:0000160 ! phosphorelay signal transduction system\n+\n+[Term]\n+id: GO:0000160\n+name: phosphorelay signal transduction system\n+namespace: biological_process\n+def: "A conserved series of molecular signals found in prokaryotes and eukaryotes; involves autophosphorylation of a histidine kinase and the transfer of the phosphate group to an aspartate that then acts as a phospho-donor to response regulator proteins." [PMID:9191038]\n+subset: goslim_metagenomics\n+subset: gosubset_prok\n+synonym: "histidyl-aspartyl phosphorelay" EXACT []\n+synonym: "phosphorelay signal transduction system" NARROW []\n+is_a: GO:0007165 ! signal transduction\n+relationship: occurs_in GO:0005575 ! cellular_component\n+\n+[Term]\n+id: GO:0000166\n+name: nucleotide binding\n+namespace: molecular_function\n+def: "Interacting selectively and non-covalently with a nucleotide, any compound consisting of a nucleoside that is esterified with (ortho)phosphate or an oligophosphate at any hydroxyl group on the ribose or deoxyribose." [GOC:mah, ISBN:0198547684]\n+subset: goslim_chembl\n+subset: goslim_metagenomics\n+subset: goslim_pir\n+subset: goslim_plant\n+subset: gosubset_prok\n+is_a: GO:0003674 ! molecular_function\n+\n+[Term]\n+id: GO:0000746\n+name: conjugation\n+namespace: biological_process\n+def: "The union or introduction of genetic information from compatible mating types that results in a genetically different individual. Conjugation requires direct cellular contact between the organisms." [GOC:elh]\n+subset: goslim_aspergillus\n+subset: goslim_candida\n+subset: goslim_metagenomics\n+subset: goslim_pir\n+subset: goslim_yeast\n+subset: gosubset_prok\n+xref: Wikipedia:Conjugation\n+is_a: GO:0008150 ! biological_process\n+\n+[Term]\n+id: GO:0000902\n+name: cell morphogenesis\n+namespace: biological_process\n+alt_id: GO:0007148\n+alt_id: GO:0045790\n+alt_id: GO:0045791\n+def: "The developmental process in which the size or shape of a cell is generated and organized." [GOC:clt, GOC:dph, GOC:go_curators, GOC:tb]\n+subset: goslim_chembl\n+subset: goslim_generic\n+subset: goslim_metagenomics\n+subset: goslim'..b', GOC:mlg, GOC:rph]\n+subset: goslim_metagenomics\n+subset: gosubset_prok\n+synonym: "oxidation reduction" EXACT [GOC:curators]\n+synonym: "oxidoreductase process" EXACT systematic_synonym []\n+xref: Wikipedia:Redox\n+is_a: GO:0008150 ! biological_process\n+\n+[Term]\n+id: GO:0070469\n+name: respiratory chain\n+namespace: cellular_component\n+def: "The protein complexes that form the electron transport system (the respiratory chain), associated with a cell membrane, usually the plasma membrane (in prokaryotes) or the inner mitochondrial membrane (on eukaryotes). The respiratory chain complexes transfer electrons from an electron donor to an electron acceptor and are associated with a proton pump to create a transmembrane electrochemical gradient." [GOC:ecd, GOC:mah, ISBN:0198547684]\n+subset: goslim_metagenomics\n+synonym: "membrane electron transport chain" EXACT [GOC:mah]\n+is_a: GO:0005575 ! cellular_component\n+relationship: part_of GO:0016020 ! membrane\n+\n+[Term]\n+id: GO:0071554\n+name: cell wall organization or biogenesis\n+namespace: biological_process\n+alt_id: GO:0070882\n+def: "A process that results in the biosynthesis of constituent macromolecules, assembly, arrangement of constituent parts, or disassembly of a cell wall." [GOC:mah]\n+subset: goslim_chembl\n+subset: goslim_generic\n+subset: goslim_metagenomics\n+subset: goslim_pombe\n+subset: goslim_yeast\n+subset: gosubset_prok\n+synonym: "cell wall organisation or biogenesis" EXACT [GOC:mah]\n+synonym: "cell wall organization or biogenesis at cellular level" EXACT [GOC:mah]\n+synonym: "cellular cell wall organisation or biogenesis" EXACT [GOC:mah]\n+synonym: "cellular cell wall organization or biogenesis" EXACT []\n+is_a: GO:0008150 ! biological_process\n+created_by: midori\n+creation_date: 2010-01-13T03:19:38Z\n+\n+[Term]\n+id: GO:0071941\n+name: nitrogen cycle metabolic process\n+namespace: biological_process\n+def: "A nitrogen compound metabolic process that contributes to the nitrogen cycle. The nitrogen cycle is a series of metabolic pathways by which nitrogen is converted between various forms and redox states; it encompasses pathways in which nitrogen is acted upon directly, such as nitrification, denitrification, nitrogen fixation, and mineralization." [GOC:mah, PMID:16675690, Wikipedia:Nitrogen_cycle]\n+subset: goslim_chembl\n+subset: goslim_generic\n+subset: goslim_metagenomics\n+subset: goslim_pombe\n+xref: Wikipedia:Nitrogen_cycle\n+is_a: GO:0006807 ! nitrogen compound metabolic process\n+created_by: midori\n+creation_date: 2010-09-30T05:21:03Z\n+\n+[Typedef]\n+id: ends_during\n+name: ends_during\n+namespace: external\n+xref: RO:0002093\n+\n+[Typedef]\n+id: happens_during\n+name: happens_during\n+namespace: external\n+xref: RO:0002092\n+is_transitive: true\n+is_a: ends_during ! ends_during\n+\n+[Typedef]\n+id: has_part\n+name: has_part\n+namespace: external\n+xref: BFO:0000051\n+is_transitive: true\n+\n+[Typedef]\n+id: negatively_regulates\n+name: negatively regulates\n+namespace: external\n+xref: RO:0002212\n+is_a: regulates ! regulates\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: never_in_taxon\n+name: never_in_taxon\n+namespace: external\n+xref: RO:0002161\n+expand_assertion_to: "Class: ?X DisjointWith: RO_0002162 some ?Y" []\n+is_metadata_tag: true\n+is_class_level: true\n+\n+[Typedef]\n+id: occurs_in\n+name: occurs in\n+namespace: external\n+xref: BFO:0000066\n+holds_over_chain: part_of occurs_in\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: part_of\n+name: part of\n+namespace: external\n+xref: BFO:0000050\n+is_transitive: true\n+inverse_of: has_part ! has_part\n+\n+[Typedef]\n+id: positively_regulates\n+name: positively regulates\n+namespace: external\n+xref: RO:0002213\n+holds_over_chain: negatively_regulates negatively_regulates\n+is_a: regulates ! regulates\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: regulates\n+name: regulates\n+namespace: external\n+xref: RO:0002211\n+is_transitive: true\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: starts_during\n+name: starts_during\n+namespace: external\n+xref: RO:0002091\n+\n'
b
diff -r 000000000000 -r bdc077ef0cdd test-data/humann2_gene_families.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/humann2_gene_families.csv Fri Mar 08 15:04:11 2019 -0500
b
b'@@ -0,0 +1,262359 @@\n+# Gene Family\thumann2_Abundance\n+UniRef50_R7E1K6\t222.2222222222\n+UniRef50_D4LXN4: DeoR-like helix-turn-helix domain\t141.9955898228\n+UniRef50_R5U882\t126.2459250750\n+UniRef50_R6RYK7\t119.9107463258\n+UniRef50_E2ZHI9\t105.7550666141\n+UniRef50_C9YMF5\t98.4861468757\n+UniRef50_T0TFA2: Replicon stabilization toxin\t91.2724509767\n+UniRef50_D4JQL7\t75.5654460556\n+UniRef50_C7RE67: FeoA family protein\t75.4985754986\n+UniRef50_R5T0L8: Virulence-associated protein E\t71.9409132965\n+UniRef50_Q650H0\t71.4403825339\n+UniRef50_A6LAX9\t71.0784313725\n+UniRef50_V6PDA5\t69.3344827271\n+UniRef50_R5EBI7\t68.8919070792\n+UniRef50_C4ZES3\t66.3932701473\n+UniRef50_J5HP76\t63.1040185731\n+UniRef50_R6QIA6: Conserved domain protein\t62.8530649180\n+UniRef50_R5ENA9\t61.1111111111\n+UniRef50_D4M212: Plasmid mobilization system relaxase\t58.9310137374\n+UniRef50_F5XA14\t57.7260295713\n+UniRef50_G8UJP0\t57.6806903991\n+UniRef50_D4K7K7: DNA binding domain, excisionase family\t56.7174082748\n+UniRef50_T2N9I9: Conjugative transposon TraJ protein\t56.2926525149\n+UniRef50_D4IJV6: Transposase DDE domain\t54.9704033269\n+UniRef50_D4KMS5: Phage replisome organizer, putative, N-terminal region\t54.5553630322\n+UniRef50_K1U2A7: Site-specific recombinase\t54.2371026295\n+UniRef50_R5ES84: Phage/plasmid primase P4 family C-terminal domain\t53.3548343112\n+UniRef50_A8S862\t52.6315789474\n+UniRef50_K1S5Y8: MbpA protein\t52.5091409643\n+UniRef50_E1WT29\t52.2264409692\n+UniRef50_R7NQ15: Gluconate 5-dehydrogenase\t51.8930270897\n+UniRef50_F3ZTC1: Conjugative transposon protein TraO\t51.5088800723\n+UniRef50_B2RKJ1: NAD-specific glutamate dehydrogenase\t49.2139555923\n+UniRef50_D4JXD1: Transcriptional regulator, AbrB family\t49.1071428571\n+UniRef50_E3GHU4\t48.8078418079\n+UniRef50_A0PXU8: 50S ribosomal protein L23\t48.6327864479\n+UniRef50_K1TJG9\t48.4054676726\n+UniRef50_B6YR21: Acyl carrier protein\t47.8072651986\n+UniRef50_Q832B8: TraE protein\t47.7054130069\n+UniRef50_G2T0H9\t47.3790322581\n+UniRef50_R7KL80\t46.4029585969\n+UniRef50_G2T0I6: Two-component sensor histidine kinase\t45.7085027100\n+UniRef50_R7ADB2: Addiction module toxin RelE/StbE family\t45.5804345129\n+UniRef50_R5W6Z1\t45.4545454545\n+UniRef50_W1I4R6: Uncultured bacterium extrachromosomal DNA RGI00148\t45.2443421815\n+UniRef50_K1ULX1\t45.2280269643\n+UniRef50_R5JE53: Conjugative transposon protein TraQ\t44.3998708866\n+UniRef50_C9YME1\t44.3854612028\n+UniRef50_R6TGQ5\t44.0534272173\n+UniRef50_Q30TV4: 50S ribosomal protein L14\t43.4868700458\n+UniRef50_A8SDY1\t42.8486116917\n+UniRef50_A8S9Q1\t42.8078364257\n+UniRef50_C7H7L8\t42.6069244797\n+UniRef50_C5ERA2\t42.4865831843\n+UniRef50_D4J5S0: ABC-type antimicrobial peptide transport system, ATPase component\t42.4463209958\n+UniRef50_D4L227: Site-specific recombinases, DNA invertase Pin homologs\t42.1929390402\n+UniRef50_E2ZJ16\t41.6666666667\n+UniRef50_R7JAU1\t40.7306806023\n+UniRef50_F5XD83: Conjugative transposon protein TraK\t39.8762963773\n+UniRef50_G2T5J9\t39.6249385526\n+UniRef50_F4XHT2\t39.6073055498\n+UniRef50_G2SZT6\t39.5449036812\n+UniRef50_D4L225: KaiC\t39.3801046475\n+UniRef50_C9YMH6\t39.0320000544\n+UniRef50_U2R4S5\t38.5648070389\n+UniRef50_D4JQL2: Addiction module antitoxin, RelB/DinJ family\t38.4344228379\n+UniRef50_D4JTZ5: DNA methylase\t38.3858256755\n+UniRef50_D4KAU2: Plasmid mobilization system relaxase\t38.0520202230\n+UniRef50_B0MXF7\t37.7896613191\n+UniRef50_K1RYT7\t37.7609713861\n+UniRef50_Q18AW5: DNA-methyltransferase, cytosine-N4-specific Tn1549-like, CTn4-Orf10\t37.6082436871\n+UniRef50_D4JVS1: Phosphotransferase System HPr (HPr) Family\t37.4802289674\n+UniRef50_D6SB91\t37.2126799169\n+UniRef50_G2T2N3: DNA primase\t36.7351486302\n+UniRef50_D4MIU0: ATP synthase I chain\t36.6409973671\n+UniRef50_Q8RGD7: ATP synthase subunit c\t36.5371955234\n+UniRef50_H1B5S2\t36.4120030567\n+UniRef50_R5GCS4\t36.3834762681\n+UniRef50_R7A658: Thioredoxin\t36.1646045535\n+UniRef50_I9IPG0\t35.9212948614\n+UniRef50_R6HUJ2\t35.8595551675\n+UniRef50_D4LUC5: Plasmid recombination enzyme\t35.8206068872\n+UniRef50_D4K8M3: Phage DNA replication protein (Predicted replicative helicase loader'..b'recognition domain\t0.0012020767\n+UniRef50_D8LR71\t0.0012003954\n+UniRef50_U6MSM9\t0.0011965468\n+UniRef50_F0VFF5: NLI interacting factor-like phosphatase domain-containing protein\t0.0011959757\n+UniRef50_B8FR62: Putative cell wall binding repeat 2-containing protein\t0.0011666455\n+UniRef50_U6LM67\t0.0011647859\n+UniRef50_Q0B8X3: Peptidoglycan-binding LysM\t0.0011536482\n+UniRef50_U6LQ59: Oxysterol-binding protein, putative\t0.0011517523\n+UniRef50_UPI000359AA1F\t0.0011490494\n+UniRef50_V4ZWS2\t0.0011479842\n+UniRef50_UPI000185D8BE: hypothetical protein TGME49_070730\t0.0011469376\n+UniRef50_U6GBK4\t0.0011001954\n+UniRef50_UPI000378A2B2: hypothetical protein\t0.0010981606\n+UniRef50_D7FYV2\t0.0010914836\n+UniRef50_M1GDM0\t0.0010904319\n+UniRef50_U6N0W5\t0.0010903061\n+UniRef50_X1XYJ5\t0.0010820624\n+UniRef50_UPI0001AF2BF7: hypothetical protein, partial\t0.0010488365\n+UniRef50_F0VF93: Leucine rich repeat containing protein / ankyrin repeat containing protein\t0.0010223409\n+UniRef50_F0VNR1\t0.0010214275\n+UniRef50_UPI0003631483: hypothetical protein\t0.0010189849\n+UniRef50_F0VCV6\t0.0010050266\n+UniRef50_D2E8D4: Protein ORF83\t0.0009938652\n+UniRef50_B3L8W7\t0.0009832699\n+UniRef50_UPI0004545162: PREDICTED: LOW QUALITY PROTEIN: histone-lysine N-methyltransferase 2D, partial\t0.0009680217\n+UniRef50_UPI0003A778AD: hypothetical protein\t0.0009629950\n+UniRef50_B4MT58: GK20098\t0.0009553027\n+UniRef50_U6GVJ1\t0.0009486734\n+UniRef50_L0M6B5\t0.0009363698\n+UniRef50_UPI00045725E2: PREDICTED: LOW QUALITY PROTEIN: collagen alpha-3(VI) chain\t0.0009350960\n+UniRef50_UPI0003B680A3: hypothetical protein\t0.0009303525\n+UniRef50_UPI0004561B03: hypothetical protein PFL1_03196\t0.0009273358\n+UniRef50_E6RNZ7\t0.0009165506\n+UniRef50_UPI00044441FD: PREDICTED: hemicentin-1\t0.0009152235\n+UniRef50_A0A058Z170\t0.0009134866\n+UniRef50_U3JEJ7\t0.0009005083\n+UniRef50_UPI00036A6291: hypothetical protein\t0.0008978087\n+UniRef50_F4QIB0: Outer membrane autotransporter barrel domain protein\t0.0008881072\n+UniRef50_U6GK87\t0.0008878935\n+UniRef50_UPI0003836527: PREDICTED: collagen alpha-4(VI) chain\t0.0008775396\n+UniRef50_UPI0004445290: PREDICTED: trinucleotide repeat-containing gene 18 protein\t0.0008733433\n+UniRef50_W9PH85\t0.0008632389\n+UniRef50_UPI000444A032: hypothetical protein STEHIDRAFT_170927\t0.0008621167\n+UniRef50_UPI000273C102\t0.0008557976\n+UniRef50_UPI0003F1A505: PREDICTED: spectrin beta chain, non-erythrocytic 4\t0.0008485597\n+UniRef50_Q89ZD7\t0.0008459523\n+UniRef50_B2A8V7: Podospora anserina S mat+ genomic DNA chromosome 1, supercontig 1\t0.0008342783\n+UniRef50_F0V7P3: Putative SET domain-containing protein\t0.0008127623\n+UniRef50_UPI00034F3DF3\t0.0008068023\n+UniRef50_Q18DY9: Cell surface glycoprotein\t0.0007961722\n+UniRef50_UPI00022478B3: PREDICTED: hypothetical protein LOC100679692\t0.0007839742\n+UniRef50_C1EHI5: Predicted protein\t0.0007696542\n+UniRef50_A8IXH7: Predicted protein (Fragment)\t0.0007631858\n+UniRef50_F0VMX2\t0.0007580465\n+UniRef50_UPI000350FB63: PREDICTED: tenascin-X\t0.0007536189\n+UniRef50_G0SBI6\t0.0007534253\n+UniRef50_F4W8Q4\t0.0007410022\n+UniRef50_Q0RLJ2\t0.0007364271\n+UniRef50_UPI0003EC164A: PREDICTED: titin-like\t0.0007344948\n+UniRef50_G1XEY7\t0.0007281788\n+UniRef50_E2ARB2: Titin\t0.0007131677\n+UniRef50_UPI0003D0722E: PREDICTED: LOW QUALITY PROTEIN: titin\t0.0006937288\n+UniRef50_G6D6Y2\t0.0006776634\n+UniRef50_UPI000328967C: PREDICTED: LOW QUALITY PROTEIN: tenascin-X\t0.0006549464\n+UniRef50_UPI00046BEF15: PREDICTED: titin\t0.0006449421\n+UniRef50_U6MUQ3\t0.0006155478\n+UniRef50_UPI0002B4C97A: PREDICTED: hydrocephalus-inducing protein homolog\t0.0005870219\n+UniRef50_UPI000302F3DC: hypothetical protein\t0.0005564568\n+UniRef50_E9BX32\t0.0005394883\n+UniRef50_E3GPY4: TPR repeat-containing cell adhesion protein\t0.0005228216\n+UniRef50_UPI0003316881\t0.0005073666\n+UniRef50_A5K9D5\t0.0004675759\n+UniRef50_V4Z5P5\t0.0004671084\n+UniRef50_UPI0003BBD5E2: PREDICTED: mucin-5B\t0.0004041705\n+UniRef50_D8U832\t0.0003381003\n+UniRef50_UPI0003691979: hypothetical protein\t0.0003177584\n+UniRef50_UPI0003C020B8: PREDICTED: mucin-5B\t0.0002890962\n'
b
diff -r 000000000000 -r bdc077ef0cdd test-data/map_infogo1000_uniref50_02_22_2016.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/map_infogo1000_uniref50_02_22_2016.txt Fri Mar 08 15:04:11 2019 -0500
b
b'@@ -0,0 +1,931 @@\n+GO:0006596:BP:07:polyamine biosynthetic process\tUniRef50_C4JAW3\tUniRef50_M4ZHA4\tUniRef50_W5F686\tUniRef50_E1VJ12\tUniRef50_O86509\tUniRef50_I0GIN3\tUniRef50_R7Q0M6\tUniRef50_A6QT49\tUniRef50_C4FLT0\tUniRef50_Q7MF74\tUniRef50_A2SCD1\tUniRef50_H2ZI05\tUniRef50_W7T3C1\tUniRef50_K0EGS5\tUniRef50_I7EYT7\tUniRef50_K4IGM0\tUniRef50_Q3E9D5\tUniRef50_K2RI31\tUniRef50_A7HQM2\tUniRef50_A7HQM3\tUniRef50_Q31DD8\tUniRef50_D7L5M3\tUniRef50_J9VHR5\tUniRef50_X0UVY8\tUniRef50_T0E0E3\tUniRef50_M5AGE1\tUniRef50_G9ZJ46\tUniRef50_L5LQI7\tUniRef50_M1CEP0\tUniRef50_A4SKE1\tUniRef50_A0CGS0\tUniRef50_E1C5E7\tUniRef50_M2WSS2\tUniRef50_I4B3Q2\tUniRef50_P17707\tUniRef50_D3PXR2\tUniRef50_J9GEW5\tUniRef50_W7QI45\tUniRef50_M6R5F6\tUniRef50_J1J802\tUniRef50_U4TL50\tUniRef50_G0T279\tUniRef50_B2UI25\tUniRef50_G7IU96\tUniRef50_X1MSN0\tUniRef50_H1XVU9\tUniRef50_Q814Q2\tUniRef50_A0A037UM43\tUniRef50_G6CMM1\tUniRef50_Q0FAX3\tUniRef50_Q8EAX8\tUniRef50_C4YQW7\tUniRef50_R1FI54\tUniRef50_A5D2A7\tUniRef50_E2AEC0\tUniRef50_G5BC60\tUniRef50_N8XG26\tUniRef50_P11926\tUniRef50_Q0JC10\tUniRef50_J3Q2A3\tUniRef50_I4BVN6\tUniRef50_A7C5H5\tUniRef50_E3T4R7\tUniRef50_W4X346\tUniRef50_B2B6G7\tUniRef50_R7QCH2\tUniRef50_H0Y1R7\tUniRef50_W1PX66\tUniRef50_D0L1T4\tUniRef50_Q7UFM7\tUniRef50_E9BM59\tUniRef50_B9KXN0\tUniRef50_B9KXN1\tUniRef50_B6HHR0\tUniRef50_Q9CEY4\tUniRef50_A0A037Z0X6\tUniRef50_B5YF01\tUniRef50_C0ZGF5\tUniRef50_A1HNA7\tUniRef50_O50657\tUniRef50_S2IXV0\tUniRef50_D4MAW1\tUniRef50_M5E856\tUniRef50_Q7UWD1\tUniRef50_H8GGN1\tUniRef50_J9K5H8\tUniRef50_S4PWJ9\tUniRef50_X1FR07\tUniRef50_Q8GW86\tUniRef50_D2ALU3\tUniRef50_R7J000\tUniRef50_B9HPP6\tUniRef50_F6AZM0\tUniRef50_E0I9Y6\tUniRef50_X0UMQ3\tUniRef50_W9RRH6\tUniRef50_F2USZ6\tUniRef50_J0XIK4\tUniRef50_Q2FTH8\tUniRef50_R7F4H4\tUniRef50_Q4DQQ6\tUniRef50_I2G6F8\tUniRef50_F6SUA6\tUniRef50_B7ICX1\tUniRef50_M4CQ45\tUniRef50_A9S5K0\tUniRef50_O41120\tUniRef50_R2LKI9\tUniRef50_K2EI21\tUniRef50_P91931\tUniRef50_J7S798\tUniRef50_A0A034TPS1\tUniRef50_R7X7W0\tUniRef50_A0A017S5U7\tUniRef50_K2CQ23\tUniRef50_U3JCU8\tUniRef50_G6D2E4\tUniRef50_V6M0M7\tUniRef50_M1E954\tUniRef50_O57711\tUniRef50_A0A017SKR3\tUniRef50_V5RVL3\tUniRef50_Q83Q93\tUniRef50_B7S493\tUniRef50_T1D7X0\tUniRef50_C1E5E7\tUniRef50_S3VH03\tUniRef50_I7M065\tUniRef50_Q7M7Q6\tUniRef50_C4V391\tUniRef50_B4DZ60\tUniRef50_R2RH64\tUniRef50_Q9S7X6\tUniRef50_Q2RHH3\tUniRef50_C3EB35\tUniRef50_I1PTF4\tUniRef50_A2Q277\tUniRef50_F1CJ68\tUniRef50_E8R8H2\tUniRef50_A9VDA6\tUniRef50_K1YV87\tUniRef50_H3E4S0\tUniRef50_N0ATA6\tUniRef50_I7A139\tUniRef50_D8HDI6\tUniRef50_F2J1B8\tUniRef50_A3K1Q6\tUniRef50_Q82XD3\tUniRef50_U9SYC2\tUniRef50_D7JEP6\tUniRef50_R7GRH6\tUniRef50_B4CXM3\tUniRef50_I5B6B8\tUniRef50_A0A016SLU8\tUniRef50_Q9NGA0\tUniRef50_R5GV63\tUniRef50_G8RZ76\tUniRef50_D7G474\tUniRef50_C5X700\tUniRef50_W1Y0N6\tUniRef50_Q6ZA98\tUniRef50_H9UAR7\tUniRef50_A6L012\tUniRef50_C2VJG9\tUniRef50_E9C1R0\tUniRef50_B0TE16\tUniRef50_Q2SRJ4\tUniRef50_O82147\tUniRef50_I3Z1P1\tUniRef50_A0A026W319\tUniRef50_E1ZEQ4\tUniRef50_Q82JP0\tUniRef50_C0QIV0\tUniRef50_K8LZW8\tUniRef50_I3IJ25\tUniRef50_A0A022MKT3\tUniRef50_W1A895\tUniRef50_B9H0H8\tUniRef50_M5RK53\tUniRef50_Q6SFB1\tUniRef50_K2AS85\tUniRef50_T1HB17\tUniRef50_F7A6X0\tUniRef50_P21673\tUniRef50_A2GG12\tUniRef50_P70999\tUniRef50_K1ZAR5\tUniRef50_V9TSP5\tUniRef50_A9A494\tUniRef50_A9UXX6\tUniRef50_Q3IJ29\tUniRef50_E6QN71\tUniRef50_V6KQZ9\tUniRef50_H0XPY2\tUniRef50_A9GB22\tUniRef50_B7S1R4\tUniRef50_E6Q203\tUniRef50_Q4ZTD6\tUniRef50_T0HX40\tUniRef50_O22616\tUniRef50_I3TL21\tUniRef50_K9W5N2\tUniRef50_D8GNL1\tUniRef50_Q9L091\tUniRef50_J8J8M2\tUniRef50_U4TEE5\tUniRef50_F0YCA8\tUniRef50_B8NMP2\tUniRef50_Q21LE5\tUniRef50_R0GV77\tUniRef50_C5LIP5\tUniRef50_R7QJI6\tUniRef50_Q7V558\tUniRef50_R7CS01\tUniRef50_Q80WZ9\tUniRef50_G3T163\tUniRef50_E0TFN8\tUniRef50_G5AU75\tUniRef50_R8WYE0\tUniRef50_B9HWQ8\tUniRef50_R4KAK7\tUniRef50_Q565W5\tUniRef50_A9T053\tUniRef50_H9UHJ3\tUniRef50_G7FW91\tUniRef50_Q31J03\tUniRef50_T1ABB5\tUniRef50_N9LXC8\tUniRef50_Q31J05\tUniRef50_C3N5P4\tUniRef50_I4AI80\tUniRef50_U6P2H2\tUniRef50_T3SBV6\tUniRef50_L2RHJ6\tUniRef50_U5KLN3\tUniRef50_R6P129\tUniRef50_F7EYV6\tUniRef50_X1ECY9\tUniRef50_L8D234\tUniRef50_H5SF62\tUniRef50_X1H5U8\tUniRef50_G3H1W5\tUniRef50_F5B479\tUniRef50_Q6L'..b'niRef50_F8FPN2\tUniRef50_R5LPZ4\tUniRef50_G2JB81\tUniRef50_A7FNJ8\tUniRef50_X1DEZ6\tUniRef50_R6XRE8\tUniRef50_J9YES5\tUniRef50_A1AWU7\tUniRef50_W1TWZ8\tUniRef50_E8REC7\tUniRef50_F8DWQ2\tUniRef50_Q2SR45\tUniRef50_X4Z8A6\tUniRef50_K8F8W2\tUniRef50_F8KSM3\tUniRef50_B6YRZ9\tUniRef50_A0R8V6\tUniRef50_W6AIL0\tUniRef50_W0PG51\tUniRef50_U4LIT3\tUniRef50_E8QW63\tUniRef50_U3GW19\tUniRef50_Q3A5V1\tUniRef50_R7VLR5\tUniRef50_S4XSP9\tUniRef50_D9PN24\tUniRef50_D9PN23\tUniRef50_Q5A6A4\tUniRef50_Q1MNC8\tUniRef50_A0KSR3\tUniRef50_V6P2V6\tUniRef50_D6S7E7\tUniRef50_C6XIF1\tUniRef50_P74415\tUniRef50_J9K955\tUniRef50_B0VJ23\tUniRef50_U4TLL1\tUniRef50_Q2II00\tUniRef50_C7PL98\tUniRef50_K2ESB9\tUniRef50_R7NHV0\tUniRef50_R4QZZ9\tUniRef50_A8GKG1\tUniRef50_M1RBL3\tUniRef50_R5ZDQ7\tUniRef50_E4RJ55\tUniRef50_R5HK19\tUniRef50_A5V0C9\tUniRef50_C5M1Q6\tUniRef50_D4M9S9\tUniRef50_Q4FPS7\tUniRef50_M5TEG8\tUniRef50_R6NG21\tUniRef50_B6BV16\tUniRef50_W4MAA9\tUniRef50_E8NEC3\tUniRef50_F9Y0W2\tUniRef50_V5GCA7\tUniRef50_X0T7F3\tUniRef50_Q5QXJ5\tUniRef50_E6QPX2\tUniRef50_R7L6S9\tUniRef50_A1UC21\tUniRef50_A9BF18\tUniRef50_R5BEG6\tUniRef50_K1ZTI1\tUniRef50_D3HP68\tUniRef50_A0A011P7D0\tUniRef50_Q2RZI8\tUniRef50_A0A031I959\tUniRef50_W0DG77\tUniRef50_A8LJ78\tUniRef50_C0QRA2\tUniRef50_W1QJ13\tUniRef50_K1XQE0\tUniRef50_E6UC85\tUniRef50_L0DKW2\tUniRef50_S5XYU9\tUniRef50_M1Z929\tUniRef50_Q28U32\tUniRef50_D5MFT4\tUniRef50_A0P816\tUniRef50_W7T2V7\tUniRef50_R7RQG9\tUniRef50_O05516\tUniRef50_O05515\tUniRef50_D5BU88\tUniRef50_I0XU01\tUniRef50_Q31RA0\tUniRef50_E5Z3P5\tUniRef50_F5WTM9\tUniRef50_U5F917\tUniRef50_B5JSB7\tUniRef50_E6W273\tUniRef50_L8LMX4\tUniRef50_V5E0A2\tUniRef50_Q6AD36\tUniRef50_M1TNY4\tUniRef50_U5T4I4\tUniRef50_F2RJX6\tUniRef50_K2CAS6\tUniRef50_R7G5W5\tUniRef50_J6H3N5\tUniRef50_Q5LY30\tUniRef50_U2QCN5\tUniRef50_K4KH03\tUniRef50_D4G8K6\tUniRef50_T1CX41\tUniRef50_U2IZU4\tUniRef50_K1E5Y0\tUniRef50_B1CBG3\tUniRef50_F3FDG8\tUniRef50_B1HT07\tUniRef50_B1CBG4\tUniRef50_K4LGA7\tUniRef50_M5E7M9\tUniRef50_A5UMH5\tUniRef50_R5FLW7\tUniRef50_X0YKW0\tUniRef50_S6H951\tUniRef50_D7DII7\tUniRef50_E6W157\tUniRef50_E0S0I8\tUniRef50_R5LKK3\tUniRef50_A0LJ71\tUniRef50_D3FBQ2\tUniRef50_W8GRW0\tUniRef50_D3FBQ0\tUniRef50_T0VWL2\tUniRef50_D5QJ15\tUniRef50_K1Y682\tUniRef50_U4UZL2\tUniRef50_S5ZWD1\tUniRef50_A6GSM1\tUniRef50_W4SHD2\tUniRef50_C7RFH3\tUniRef50_C7RFH4\tUniRef50_K1LLN4\tUniRef50_R9C0N5\tUniRef50_I7A6Y4\tUniRef50_E8N340\tUniRef50_E8N341\tUniRef50_S2JNQ8\tUniRef50_Q31JQ7\tUniRef50_E0XR92\tUniRef50_E0XR93\tUniRef50_B3EE73\tUniRef50_K2LZZ4\tUniRef50_F0NZ94\tUniRef50_D8UCF8\tUniRef50_Q1K333\tUniRef50_D2RBG7\tUniRef50_M5RXE1\tUniRef50_U3BPZ3\tUniRef50_B8GRE1\tUniRef50_Q6L243\tUniRef50_T0LI77\tUniRef50_K2MPZ1\tUniRef50_Q8KGA4\tUniRef50_K2ALN8\tUniRef50_U4KTG0\tUniRef50_K2EQP6\tUniRef50_Q2SL20\tUniRef50_F2NAE3\tUniRef50_R7GIH9\tUniRef50_V8CEH2\tUniRef50_K2EA40\tUniRef50_U2FKR2\tUniRef50_U0EAC9\tUniRef50_F8I138\tUniRef50_A0A010PPL1\tUniRef50_R5B7H8\tUniRef50_V1CM74\tUniRef50_A3QF11\tUniRef50_D1AW94\tUniRef50_D5V9A9\tUniRef50_D1AW95\tUniRef50_E6X254\tUniRef50_C7MKS0\tUniRef50_W8ZEL8\tUniRef50_A8ZVC3\tUniRef50_I4B0H9\tUniRef50_G4QAB1\tUniRef50_R5SCB5\tUniRef50_K9SCY7\tUniRef50_L0EFL7\tUniRef50_K7RV55\tUniRef50_B0SK27\tUniRef50_H0A7D2\tUniRef50_E0VDW1\tUniRef50_A4XNB6\tUniRef50_U1Q535\tUniRef50_D7CKV7\tUniRef50_A4FPB6\tUniRef50_K1YX61\tUniRef50_K1QKG4\tUniRef50_F4LPB2\tUniRef50_A0JZ04\tUniRef50_R6FTU3\tUniRef50_K1XE67\tUniRef50_R7FM83\tUniRef50_E3WIH3\tUniRef50_W1TRA1\tUniRef50_W8QJ88\tUniRef50_A3V587\tUniRef50_V6DHZ1\tUniRef50_Q31N80\tUniRef50_E6W4L2\tUniRef50_B8J6S5\tUniRef50_K9TIQ8\tUniRef50_B3QSE5\tUniRef50_A0A024IMR5\tUniRef50_M7P4Z2\tUniRef50_F2IBK7\tUniRef50_V4C494\tUniRef50_E7MLB4\tUniRef50_B2IIK2\tUniRef50_B8CIX1\tUniRef50_R5WHH6\tUniRef50_A9I7Z1\tUniRef50_W7CFL0\tUniRef50_C8WRZ4\tUniRef50_C8WRZ5\tUniRef50_R7HM19\tUniRef50_X1EW42\tUniRef50_C1DXN0\tUniRef50_Q73ET0\tUniRef50_S5R8I0\tUniRef50_S4YWE4\tUniRef50_B7KVD5\tUniRef50_X1IM01\tUniRef50_C9LXB7\tUniRef50_Q0FFB8\tUniRef50_D1AP17\tUniRef50_Q1WSV3\tUniRef50_R5I161\tUniRef50_K2EX75\tUniRef50_Q0A9E5\tUniRef50_F9UKL2\tUniRef50_U4KQX9\tUniRef50_U2TFV0\tUniRef50_F7XQX1\tUniRef50_K0C8W6\tUniRef50_H9BX09\tUniRef50_S5MAT2\tUniRef50_D0LLA3\tUniRef50_Q83I95\tUniRef50_D5QAK8\tUniRef50_G0GFX1\n'
b
diff -r 000000000000 -r bdc077ef0cdd test-data/o_02_22_2016.obo
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/o_02_22_2016.obo Fri Mar 08 15:04:11 2019 -0500
[
b'@@ -0,0 +1,602460 @@\n+format-version: 1.2\n+data-version: releases/2016-04-19\n+date: 18:04:2016 13:50\n+saved-by: bf\n+auto-generated-by: TermGenie 1.0\n+subsetdef: goantislim_grouping "Grouping classes that can be excluded"\n+subsetdef: gocheck_do_not_annotate "Term not to be used for direct annotation"\n+subsetdef: gocheck_do_not_manually_annotate "Term not to be used for direct manual annotation"\n+subsetdef: goslim_aspergillus "Aspergillus GO slim"\n+subsetdef: goslim_candida "Candida GO slim"\n+subsetdef: goslim_chembl "ChEMBL protein targets summary"\n+subsetdef: goslim_generic "Generic GO slim"\n+subsetdef: goslim_goa "GOA and proteome slim"\n+subsetdef: goslim_metagenomics "Metagenomics GO slim"\n+subsetdef: goslim_pir "PIR GO slim"\n+subsetdef: goslim_plant "Plant GO slim"\n+subsetdef: goslim_pombe "Fission yeast GO slim"\n+subsetdef: goslim_synapse "synapse GO slim"\n+subsetdef: goslim_virus "Viral GO slim"\n+subsetdef: goslim_yeast "Yeast GO slim"\n+subsetdef: gosubset_prok "Prokaryotic GO subset"\n+subsetdef: mf_needs_review "Catalytic activity terms in need of attention"\n+subsetdef: termgenie_unvetted "Terms created by TermGenie that do not follow a template and require additional vetting by editors"\n+subsetdef: virus_checked "Viral overhaul terms"\n+synonymtypedef: systematic_synonym "Systematic synonym" EXACT\n+default-namespace: gene_ontology\n+remark: cvs version: $Revision: 32767 $\n+ontology: go\n+\n+[Term]\n+id: GO:0000001\n+name: mitochondrion inheritance\n+namespace: biological_process\n+def: "The distribution of mitochondria, including the mitochondrial genome, into daughter cells after mitosis or meiosis, mediated by interactions between mitochondria and the cytoskeleton." [GOC:mcc, PMID:10873824, PMID:11389764]\n+synonym: "mitochondrial inheritance" EXACT []\n+is_a: GO:0048308 ! organelle inheritance\n+is_a: GO:0048311 ! mitochondrion distribution\n+\n+[Term]\n+id: GO:0000002\n+name: mitochondrial genome maintenance\n+namespace: biological_process\n+def: "The maintenance of the structure and integrity of the mitochondrial genome; includes replication and segregation of the mitochondrial chromosome." [GOC:ai, GOC:vw]\n+is_a: GO:0007005 ! mitochondrion organization\n+\n+[Term]\n+id: GO:0000003\n+name: reproduction\n+namespace: biological_process\n+alt_id: GO:0019952\n+alt_id: GO:0050876\n+def: "The production of new individuals that contain some portion of genetic material inherited from one or more parent organisms." [GOC:go_curators, GOC:isa_complete, GOC:jl, ISBN:0198506732]\n+subset: goslim_chembl\n+subset: goslim_generic\n+subset: goslim_pir\n+subset: goslim_plant\n+subset: gosubset_prok\n+synonym: "reproductive physiological process" EXACT []\n+xref: Wikipedia:Reproduction\n+is_a: GO:0008150 ! biological_process\n+disjoint_from: GO:0044848 ! biological phase\n+\n+[Term]\n+id: GO:0000005\n+name: obsolete ribosomal chaperone activity\n+namespace: molecular_function\n+def: "OBSOLETE. Assists in the correct assembly of ribosomes or ribosomal subunits in vivo, but is not a component of the assembled ribosome when performing its normal biological function." [GOC:jl, PMID:12150913]\n+comment: This term was made obsolete because it refers to a class of gene products and a biological process rather than a molecular function.\n+synonym: "ribosomal chaperone activity" EXACT []\n+is_obsolete: true\n+consider: GO:0042254\n+consider: GO:0044183\n+consider: GO:0051082\n+\n+[Term]\n+id: GO:0000006\n+name: high-affinity zinc uptake transmembrane transporter activity\n+namespace: molecular_function\n+def: "Enables the transfer of a solute or solutes from one side of a membrane to the other according to the reaction: Zn2+(out) = Zn2+(in), probably powered by proton motive force. In high-affinity transport the transporter is able to bind the solute even if it is only present at very low concentrations." [TC:2.A.5.1.1]\n+synonym: "high affinity zinc uptake transmembrane transporter activity" EXACT []\n+is_a: GO:0005385 ! zinc ion transmembrane transporter activity\n+\n+[Term]\n+id: GO:0000007\n+na'..b' GO:2001313 ! UDP-4-deoxy-4-formamido-beta-L-arabinopyranose metabolic process\n+created_by: pr\n+creation_date: 2012-03-22T01:20:05Z\n+\n+[Term]\n+id: GO:2001316\n+name: kojic acid metabolic process\n+namespace: biological_process\n+def: "The chemical reactions and pathways involving kojic acid." [CHEBI:43572, GOC:di]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one metabolic process" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one metabolism" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 metabolic process" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 metabolism" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "kojic acid metabolism" EXACT [GOC:obol]\n+is_a: GO:0034308 ! primary alcohol metabolic process\n+is_a: GO:0042180 ! cellular ketone metabolic process\n+is_a: GO:0046483 ! heterocycle metabolic process\n+is_a: GO:1901360 ! organic cyclic compound metabolic process\n+created_by: rfoulger\n+creation_date: 2012-04-18T09:22:42Z\n+\n+[Term]\n+id: GO:2001317\n+name: kojic acid biosynthetic process\n+namespace: biological_process\n+def: "The chemical reactions and pathways resulting in the formation of kojic acid." [CHEBI:43572, GOC:di]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one anabolism" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one biosynthesis" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one biosynthetic process" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one formation" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "5-hydroxy-2-(hydroxymethyl)-4H-pyran-4-one synthesis" EXACT [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 anabolism" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 biosynthesis" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 biosynthetic process" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 formation" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "C6H6O4 synthesis" RELATED [CHEBI:43572, GOC:obol]\n+synonym: "kojic acid anabolism" EXACT [GOC:obol]\n+synonym: "kojic acid biosynthesis" EXACT [GOC:obol]\n+synonym: "kojic acid formation" EXACT [GOC:obol]\n+synonym: "kojic acid synthesis" EXACT [GOC:obol]\n+is_a: GO:0018130 ! heterocycle biosynthetic process\n+is_a: GO:0034309 ! primary alcohol biosynthetic process\n+is_a: GO:0042181 ! ketone biosynthetic process\n+is_a: GO:1901362 ! organic cyclic compound biosynthetic process\n+is_a: GO:2001316 ! kojic acid metabolic process\n+created_by: rfoulger\n+creation_date: 2012-04-18T09:22:46Z\n+\n+[Typedef]\n+id: ends_during\n+name: ends_during\n+namespace: external\n+xref: RO:0002093\n+\n+[Typedef]\n+id: happens_during\n+name: happens_during\n+namespace: external\n+xref: RO:0002092\n+is_transitive: true\n+is_a: ends_during ! ends_during\n+\n+[Typedef]\n+id: has_part\n+name: has_part\n+namespace: external\n+xref: BFO:0000051\n+is_transitive: true\n+\n+[Typedef]\n+id: negatively_regulates\n+name: negatively regulates\n+namespace: external\n+xref: RO:0002212\n+is_a: regulates ! regulates\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: never_in_taxon\n+name: never_in_taxon\n+namespace: external\n+xref: RO:0002161\n+expand_assertion_to: "Class: ?X DisjointWith: RO_0002162 some ?Y" []\n+is_metadata_tag: true\n+is_class_level: true\n+\n+[Typedef]\n+id: occurs_in\n+name: occurs in\n+namespace: external\n+xref: BFO:0000066\n+holds_over_chain: part_of occurs_in\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: part_of\n+name: part of\n+namespace: external\n+xref: BFO:0000050\n+is_transitive: true\n+inverse_of: has_part ! has_part\n+\n+[Typedef]\n+id: positively_regulates\n+name: positively regulates\n+namespace: external\n+xref: RO:0002213\n+holds_over_chain: negatively_regulates negatively_regulates\n+is_a: regulates ! regulates\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: regulates\n+name: regulates\n+namespace: external\n+xref: RO:0002211\n+is_transitive: true\n+transitive_over: part_of ! part of\n+\n+[Typedef]\n+id: starts_during\n+name: starts_during\n+namespace: external\n+xref: RO:0002091\n+\n'
b
diff -r 000000000000 -r bdc077ef0cdd tool_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml Fri Mar 08 15:04:11 2019 -0500
b
@@ -0,0 +1,31 @@
+<?xml version="1.0" ?>
+<tool_dependency>
+    <package name="numpy" version="1.9">
+        <repository changeset_revision="f24fc0b630fc" name="package_python_2_7_numpy_1_9" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu"/>
+    </package>
+    <package name="fisher" version="0.1.4">
+        <repository changeset_revision="07479e0cbc5f" name="package_python_2_7_fisher_0_1_4" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu"/>
+    </package>
+    <package name="humann2" version="0.6.1">
+        <repository changeset_revision="48f412c4d0c9" name="package_humann2_0_6_1" owner="rsajulga" toolshed="https://toolshed.g2.bx.psu.edu"/>
+    </package>
+    <package name="goatools" version="0.6.4">
+        <repository changeset_revision="25b614b3491f" name="package_goatools_0_6_4" owner="bebatut" toolshed="https://toolshed.g2.bx.psu.edu"/>
+    </package>
+    <package name="group_humann2_uniref_abundances_to_go" version="1.2.0">
+        <install version="1.0">
+            <actions>
+                <action type="download_by_url">https://github.com/jraysajulga/group_humann2_uniref_abundances_to_GO/archive/master.zip</action>
+                <action type="move_directory_files">
+                    <source_directory>.</source_directory>
+                    <destination_directory>$INSTALL_DIR/</destination_directory>
+                </action>
+                <action type="set_environment">
+                    <environment_variable action="set_to" name="GROUP_UNIREF_GO_DIR">$INSTALL_DIR/</environment_variable>
+                    <environment_variable action="prepend_to" name="PATH">$INSTALL_DIR</environment_variable>
+                </action>
+            </actions>
+        </install>
+        <readme/>
+    </package>
+</tool_dependency>
\ No newline at end of file