This document contains a brief analysis of the OBO ontology repository. The corpus version is a snapshot from December 2016, available from Zenodo.

Parse Errors (OWL API 4.2.8)

kable(plyr::count(corpus_md_failed$error_cat))
x freq
UnloadableImportException 9
UnparsableOntologyException 1
kable(corpus_md_failed[!is.na(corpus_md_failed$error_cat),c("filename","error_cat","exception_message")])
filename error_cat exception_message
aero.owl UnloadableImportException java.lang.RuntimeException: org.semanticweb.owlapi.model.UnloadableImportException: Could not load imported ontology: http://purl.obolibrary.org/obo/aero/OMREAEROImport.owl Cause: http://ogms.googlecode.com/svn/trunk/src/ontology/omre/OMREAEROImport.owl
flu.owl UnloadableImportException java.lang.RuntimeException: org.semanticweb.owlapi.model.UnloadableImportException: Could not load imported ontology: http://www.obofoundry.org/ro/ro.owl Cause: http://www.obofoundry.org/ro/ro.owl
foodon.owl UnloadableImportException java.lang.RuntimeException: org.semanticweb.owlapi.model.UnloadableImportException: Could not load imported ontology: http://purl.obolibrary.org/obo/foodon/imports/bfoimport.owl Cause: https://raw.githubusercontent.com/FoodOntology/foodon/master/imports/bfoimport.owl
MFOMD.owl UnloadableImportException java.lang.RuntimeException: org.semanticweb.owlapi.model.UnloadableImportException: Could not load imported ontology: http://ogms.googlecode.com/svn/trunk/src/ontology/ogms.owl Cause: http://ogms.googlecode.com/svn/trunk/src/ontology/ogms.owl
miapa.owl UnloadableImportException java.lang.RuntimeException: org.semanticweb.owlapi.model.UnloadableImportException: Could not load imported ontology: http://www.w3.org/ns/prov-aq Cause: Ontology already exists. OntologyID(OntologyIRI(http://www.w3.org/ns/prov VersionIRI(null
omit.owl UnloadableImportException java.lang.RuntimeException: org.semanticweb.owlapi.model.UnloadableImportException: Could not load imported ontology: http://purl.obolibrary.org/obo/ncro/2015-12-10/ncro-combined.owl Cause: https://raw.githubusercontent.com/OmniSearch/ncro/release-2015-12-10/src/ontology/ncro-combined.owl
omrse.owl UnloadableImportException java.lang.RuntimeException: org.semanticweb.owlapi.model.UnloadableImportException: Could not load imported ontology: http://purl.obofoundry.org/obo/iao/d-acts/20150916/d-acts.owl Cause: http://purl.obofoundry.org/obo/iao/d-acts/20150916/d-acts.owl
pro_reasoned.owl UnparsableOntologyException java.lang.RuntimeException: org.semanticweb.owlapi.io.UnparsableOntologyException: Problem parsing file:/D:/000/obo/files/proreasoned.owlCould not parse ontology. Either a suitable parser could not be found or parsing failed. See parser logs below for explanation.The following parsers were tried:1 org.semanticweb.owlapi.rdf.rdfxml.parser.RDFXMLParser3b95d6412 org.semanticweb.owlapi.owlxml.parser.OWLXMLParser2372b0543 org.semanticweb.owlapi.functional.parser.OWLFunctionalSyntaxOWLParser2b3eb65c4 org.semanticweb.owlapi.rio.RioParserImpl : org.semanticweb.owlapi.formats.RioTurtleDocumentFormatFactory95fd655c5 org.semanticweb.owlapi.manchestersyntax.parser.ManchesterOWLSyntaxOntologyParser1688873b6 org.semanticweb.owlapi.rio.RioParserImpl : org.semanticweb.owlapi.formats.NQuadsDocumentFormat […RESTCUTOFF]
rnao.owl UnloadableImportException java.lang.RuntimeException: org.semanticweb.owlapi.model.UnloadableImportException: Could not load imported ontology: http://www.obofoundry.org/ro/ro.owl Cause: http://www.obofoundry.org/ro/ro.owl
sep.owl UnloadableImportException java.lang.RuntimeException: org.semanticweb.owlapi.model.UnloadableImportException: Could not load imported ontology: http://obo.cvs.sourceforge.net/checkout/obo/obo/ontology/phenotype/unit.obo Cause: Problem parsing http://obo.cvs.sourceforge.net/checkout/obo/obo/ontology/phenotype/unit.oboCould not parse ontology. Either a suitable parser could not be found or parsing failed. See parser logs below for explanation.The following parsers were tried:1 org.semanticweb.owlapi.rdf.rdfxml.parser.RDFXMLParser103105472 org.semanticweb.owlapi.owlxml.parser.OWLXMLParser4b58b4ea3 org.semanticweb.owlapi.functional.parser.OWLFunctionalSyntaxOWLParser778d30aa4 org.semanticweb.owlapi.rio.RioParserImpl : org.semanticweb.owlapi.formats.RioTurtleDocumentFormatFactory95fd655c5 org.semanticweb.owlapi.manche […RESTCUTOFF]

Corpus Description

table_o<-corpus_md[c("filename.x","o","ax_o_logical_axiom_count","ax_o_logical_axiom_count_incl","cat_main","cat_prof","expressivity.y","expressivity_incl.y")]
names(table_o)<-c("filename","Ontology","Axiom count","Axiom count (incl)","OWL 2","Profile Category","Expressivity","Expressivity (incl)")

options(scipen = 1000)
ggplot(corpus_md,aes(x=corpus_md$logical_axiom_count_incl)) + geom_histogram() + scale_x_log10() + ggtitle("Distribution of logical axiom counts")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(corpus_md,aes(x=corpus_md$tboxrbox_size_incl)) + geom_histogram() + scale_x_log10()+ ggtitle("Distribution of TBox size")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(corpus_md,aes(x=corpus_md$abox_size_incl)) + geom_histogram() + scale_x_log10()+ ggtitle("Distribution of ABox size")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(corpus_md,aes(x=corpus_md$sizebin)) + geom_bar() + ggtitle("Distribution across size bins")

p<-generateDLProfileBarchart(corpus_md)
## [1] "Warning, fixing wrong RDFS (DL Pure + RDFS = DL Pure + Not RDFS)"
grid::grid.draw(p$plot_1)

kable(table_o[order(-table_o$`Axiom count (incl)`),])
filename Ontology Axiom count Axiom count (incl) OWL 2 Profile Category Expressivity Expressivity (incl)
75 ncbitaxon.owl ncbitaxon 1507562 1507562 Profiled EL+QL+RL AL AL
45 gaz.owl gaz 898145 908023 OWL Full NA ALRI+ SRIQ
27 dron-full.owl dron-full 0 874966 OWL Full NA AL SHOI(D)
74 nbo.owl nbo 1402 383488 Pure DL NA ALC SRIQ
76 NCITNCBO.owl NCITNCBO 281421 281421 OWL Full NA SH SH
12 chebi.owl chebi 224955 224955 Pure DL NA ALE+ ALE+
24 DINTO_1.2.owl DINTO_1 173859 173859 OWL Full NA ALCRIQ(D) ALCRIQ(D)
43 fma.owl fma 121712 121712 Profiled EL ALEH+ ALEH+
17 clo_merged.owl clo_merged 117057 117057 OWL Full NA SHOI(D) SHOI(D)
125 vto.owl vto 106944 106944 Pure DL NA AL AL
48 go.owl go 106492 106492 Pure DL NA SRI SRI
83 ogg-merged.owl ogg-merged 70116 70116 OWL Full NA SRIQ SRIQ
79 oba.owl oba 36448 63389 OWL Full NA ALERI+ SRI
119 uberon.owl uberon 53169 53169 OWL Full NA SRIQ SRIQ
70 mp.owl mp 22776 52002 OWL Full NA ALC SRI
51 hp.owl hp 21326 51165 OWL Full NA ALCR SRI
121 upheno.owl upheno 41179 41179 OWL Full NA AL AL
118 tto.owl tto 38639 38639 Profiled RL AL AL
37 fbbt.owl fbbt 33282 33282 Pure DL NA SRI SRI
44 fypo.owl fypo 33040 33040 Pure DL NA SH SH
42 flopo.owl flopo 23504 28754 OWL Full NA SR(D) SRI(D)
63 MicrO.owl MicrO 5441 24114 OWL Full NA SROIQ(D) SROIQ(D)
31 emapa.owl emapa 21772 21772 Pure DL NA ALE+ ALE+
30 emap.owl emap 21723 21723 Profiled EL ALE+ ALE+
16 cl.owl cl 7976 19845 OWL Full NA ALCR SRI
96 PDRO.owl PDRO 204 17372 OWL Full NA ALCQ(D) SROIQ(D)
126 wbbt.owl wbbt 15187 15187 Pure DL NA S S
29 ehdaa2.owl ehdaa2 13369 13369 Pure DL NA ALE+ ALE+
132 zfa.owl zfa 11750 11750 Pure DL NA SRI SRI
78 oae.owl oae 6681 11329 OWL Full NA ALCH SRIQ
123 VO.owl VO 9673 10481 OWL Full NA ALCHOQ SROIQ
49 hao.owl hao 10171 10171 Pure DL NA SR SR
32 envo.owl envo 9896 9896 OWL Full NA SRIQ SRIQ
116 to.owl to 6406 8254 OWL Full NA ALE SRI
25 doid.owl doid 7892 7892 Profiled RL ALC ALC
111 swo_merged.owl swo_merged 7683 7683 OWL Full NA SHOIQ(D) SHOIQ(D)
8 bto.owl bto 6884 6884 Pure DL NA ALE ALE
81 obi.owl obi 6316 6316 OWL Full NA SROIQ(D) SROIQ(D)
104 rs.owl rs 5922 5922 Pure DL NA ALE ALE
129 xao.owl xao 5887 5887 Pure DL NA ALE+ ALE+
77 ncro-all-in-one.owl ncro-all-in-one 5471 5471 OWL Full NA SROI SROI
46 genepio.owl genepio 3147 5118 OWL Full NA SIQ(D) SROIQ(D)
33 ero.owl ero 4892 4892 OWL Full NA SHOIF(D) SHOIF(D)
93 ovae_merged.owl ovae_merged 4701 4701 OWL Full NA SROIQ(D) SROIQ(D)
4 bcgo_merged_inferred.owl bcgo_merged_inferred 4514 4514 OWL Full NA SROIN(D) SROIN(D)
65 miro.owl miro 4457 4457 Pure DL NA ALE+ ALE+
58 ma.owl ma 4104 4104 Pure DL NA ALE+ ALE+
69 mop.owl mop 3809 3809 Pure DL NA ALCH ALCH
124 vt.owl vt 3757 3757 OWL Full NA AL AL
68 mod.owl mod 3581 3581 Pure DL NA ALE+ ALE+
56 idomal.owl idomal 3468 3468 Pure DL NA ALERI+ ALERI+
14 chmo.owl chmo 3417 3417 Pure DL NA ALCH ALCH
18 cmo.owl cmo 3299 3299 Pure DL NA ALE+ ALE+
101 pw.owl pw 3253 3253 Pure DL NA ALE ALE
99 po.owl po 3152 3152 Pure DL NA SRI SRI
72 mro.owl mro 3098 3098 OWL Full NA ALEH ALEH
108 so-xp.owl so-xp 3096 3096 Pure DL NA SHI SHI
90 ontoneo.owl ontoneo 430 3086 OWL Full NA ALCHIQ(D) SRIQ(D)
73 ms.owl ms 2949 2949 Pure DL NA ALE+ ALE+
38 fbcv.owl fbcv 2836 2836 Pure DL NA SRIF(D) SRIF(D)
128 wbphenotype.owl wbphenotype 2777 2777 Profiled RL AL AL
115 tgma.owl tgma 2733 2733 Profiled EL ALE+ ALE+
95 pco_merged_inferred.owl pco_merged_inferred 2600 2600 OWL Full NA SROIQ SROIQ
11 ceph.owl ceph 604 2598 OWL Full NA SRI SRI
94 pato.owl pato 2384 2384 Pure DL NA SH SH
89 omp.owl omp 1998 1998 Pure DL NA ALER+ ALER+
110 stato.owl stato 1875 1875 OWL Full NA SROIQ(D) SROIQ(D)
28 eco.owl eco 1811 1811 Pure DL NA ALCI ALCI
41 fix.owl fix 1684 1684 OWL Full NA ALE ALE
13 cheminf.owl cheminf 485 1583 OWL Full NA SRIF(D) SROIN(D)
19 cteno.owl cteno 999 1560 OWL Full NA ALCQ SRIQ
100 poro.owl poro 1211 1520 OWL Full NA ALCRQ SRIQ
40 feed.owl feed 353 1497 OWL Full NA ALCHIQ SRIQ
80 obcs_merged_inferred.owl obcs_merged_inferred 1438 1438 OWL Full NA SROIQ(D) SROIQ(D)
62 mi.owl mi 1424 1424 Pure DL NA ALE+ ALE+
127 wbls.owl wbls 1424 1424 Pure DL NA ALEH+ ALEH+
105 rxno.owl rxno 1328 1328 Pure DL NA ALCH ALCH
82 obib_merged_inferred.owl obib_merged_inferred 1291 1291 Pure DL NA SROIQ(D) SROIQ(D)
26 dpo.owl dpo 1265 1265 Pure DL NA SRIF(D) SRIF(D)
103 ro.owl ro 830 1130 OWL Full NA SRIF SRIF
107 sibo.owl sibo 1106 1106 Pure DL NA ALE+ ALE+
61 MFOEM.owl MFOEM 289 1096 OWL Full NA ALEI SROIQ
86 ogsf-merged.owl ogsf-merged 1056 1089 OWL Full NA SROIQ(D) SROIQ(D)
22 ddpheno.owl ddpheno 1080 1080 Profiled RL AL AL
55 ido-merged.owl ido-merged 1064 1064 OWL Full NA SROI SROI
88 omiabis_merged.owl omiabis_merged 990 990 OWL Full NA SROIQ(D) SROIQ(D)
2 agro.owl agro 986 986 Pure DL NA SROIN(D) SROIN(D)
113 tads.owl tads 948 948 Profiled EL ALE+ ALE+
71 mpath.owl mpath 941 941 Pure DL NA ALE+ ALE+
92 opl_inferred.owl opl_inferred 885 885 Pure DL NA SHOIF SHOIF
57 kisao_full.owl kisao_full 50 844 OWL Full NA ALC ALCRIQ(D)
109 spd.owl spd 840 840 Pure DL NA ALE+ ALE+
112 symp.owl symp 840 840 Profiled RL AL AL
23 dideo.owl dideo 442 838 OWL Full NA SROIQ(D) SROIQ(D)
60 MF.owl MF 21 807 OWL Full NA ALE SROIQ
64 mirnao.owl mirnao 764 764 OWL Full NA ALEI ALEI
102 rex.owl rex 730 730 Profiled EL+QL ALE ALE
39 fbdv.owl fbdv 719 719 Pure DL NA SRI SRI
54 ico_merged.owl ico_merged 705 705 OWL Full NA SHOIN(D) SHOIN(D)
52 hsapdv.owl hsapdv 698 698 Pure DL NA ALEH+ ALEH+
91 oostt.owl oostt 175 677 OWL Full NA ALCH SROIN(D)
106 sbo.owl sbo 671 671 Profiled RL AL AL
66 mmo.owl mmo 642 642 Profiled RL AL AL
20 cvdo.owl cvdo 580 632 OWL Full NA ALCR ALCR
130 xco.owl xco 607 607 Pure DL NA ALE+ ALE+
36 fbbi.owl fbbi 596 596 Pure DL NA S S
98 plant-environment-ontology.obo.owl plant-environment-ontology 558 558 OWL Full NA AL AL
7 bspo.owl bspo 473 473 Pure DL NA ALERI+ ALERI+
10 cdao.owl cdao 421 456 OWL Full NA SROIQ(D) SROIQ(D)
84 OGI.owl OGI 372 424 OWL Full NA ALCHIQ(D) ALCHIQ(D)
122 vario.owl vario 405 405 Profiled EL ALER+ ALER+
120 uo.owl uo 389 389 Pure DL NA ALE ALE
53 iao.owl iao 383 383 OWL Full NA SROIN(D) SROIN(D)
1 aeo.owl aeo 366 366 Pure DL NA ALE ALE
21 ddanat.owl ddanat 347 347 Pure DL NA ALE+ ALE+
9 caro.owl caro 163 307 OWL Full NA ALCQ SRIQ
67 mmusdv.owl mmusdv 307 307 Pure DL NA ALEH+ ALEH+
3 apo.owl apo 306 306 Profiled RL AL AL
5 bco.owl bco 304 304 OWL Full NA SROIF(D) SROIF(D)
47 geo.owl geo 104 244 OWL Full NA SROIQ(D) SROIQ(D)
85 ogms.owl ogms 79 165 OWL Full NA AL ALCO
59 mamo-xml.owl mamo-xml 164 164 OWL Full NA ALCR ALCR
15 cio.owl cio 160 160 Pure DL NA SHQ SHQ
131 zeco.owl zeco 152 152 OWL Full NA AL+ AL+
133 zfs.owl zfs 148 148 Profiled EL ALEH+ ALEH+
35 fao.owl fao 116 116 Pure DL NA ALE+ ALE+
34 exo.owl exo 101 101 Profiled EL ALER+ ALER+
87 olatdv.owl olatdv 91 91 Profiled EL ALEH+ ALEH+
50 hom.owl hom 83 83 Profiled RL ALC ALC
114 taxrank.owl taxrank 61 61 Pure DL NA AL AL
6 bfo.owl bfo 52 52 Profiled EL+QL+RL ALC ALC
97 pdumdv.owl pdumdv 42 42 Profiled EL ALEH+ ALEH+
117 trans.owl trans 24 24 Profiled RL AL AL

OWL 2 DL Violations

violations<-names(corpus_md[grepl("viol_",names(corpus_md))])
plotViolationBin(corpus_md,violations,"ProfileViolations")

kable(corpus_md[corpus_md$owl2dl_profile_violation!="",c("filename.x","owl2dl_profile_violation")])
filename.x owl2dl_profile_violation
4 bcgo_merged_inferred.owl IllegalPunning:6
5 bco.owl IllegalPunning:188
9 caro.owl IllegalPunning:3 OntologyVersionIRINotAbsolute:12
10 cdao.owl UseOfNonSimplePropertyInCardinalityRestriction:2
11 ceph.owl OntologyVersionIRINotAbsolute:5
13 cheminf.owl IllegalPunning:2 UseOfReservedVocabularyForObjectPropertyIRI:3 OntologyVersionIRINotAbsolute:5 UseOfReservedVocabularyForAnnotationPropertyIRI:2 UseOfUnknownDatatype:1
16 cl.owl OntologyVersionIRINotAbsolute:8
17 clo_merged.owl OntologyVersionIRINotAbsolute:1
19 cteno.owl OntologyVersionIRINotAbsolute:7 UseOfNonSimplePropertyInCardinalityRestriction:1
20 cvdo.owl OntologyVersionIRINotAbsolute:1
23 dideo.owl OntologyVersionIRINotAbsolute:5 UseOfUnknownDatatype:1
24 DINTO_1.2.owl OntologyVersionIRINotAbsolute:1
27 dron-full.owl OntologyVersionIRINotAbsolute:8
32 envo.owl UseOfNonSimplePropertyInCardinalityRestriction:1
33 ero.owl UseOfReservedVocabularyForObjectPropertyIRI:3 OntologyVersionIRINotAbsolute:1 UseOfReservedVocabularyForClassIRI:8
40 feed.owl OntologyVersionIRINotAbsolute:10
41 fix.owl OntologyVersionIRINotAbsolute:1
42 flopo.owl OntologyVersionIRINotAbsolute:2
45 gaz.owl UseOfReservedVocabularyForObjectPropertyIRI:30 OntologyVersionIRINotAbsolute:1 UseOfNonSimplePropertyInCardinalityRestriction:5
46 genepio.owl OntologyVersionIRINotAbsolute:29 UseOfUnknownDatatype:11
47 geo.owl OntologyVersionIRINotAbsolute:5
51 hp.owl OntologyVersionIRINotAbsolute:11
53 iao.owl UseOfUnknownDatatype:1
54 ico_merged.owl OntologyVersionIRINotAbsolute:1
55 ido-merged.owl LexicalNotInLexicalSpace:1
57 kisao_full.owl LexicalNotInLexicalSpace:10 OntologyVersionIRINotAbsolute:2 UseOfUnknownDatatype:186
59 mamo-xml.owl OntologyVersionIRINotAbsolute:1 LexicalNotInLexicalSpace:1
60 MF.owl OntologyVersionIRINotAbsolute:6
61 MFOEM.owl OntologyVersionIRINotAbsolute:7
63 MicrO.owl IllegalPunning:1000 LexicalNotInLexicalSpace:3 OntologyVersionIRINotAbsolute:20
64 mirnao.owl OntologyVersionIRINotAbsolute:1
70 mp.owl OntologyVersionIRINotAbsolute:10
72 mro.owl UseOfReservedVocabularyForAnnotationPropertyIRI:1
76 NCITNCBO.owl IllegalPunning:1186881 OntologyVersionIRINotAbsolute:1
77 ncro-all-in-one.owl UseOfUnknownDatatype:1
78 oae.owl IllegalPunning:8 OntologyVersionIRINotAbsolute:10
79 oba.owl OntologyVersionIRINotAbsolute:9
80 obcs_merged_inferred.owl LexicalNotInLexicalSpace:3
81 obi.owl UseOfUnknownDatatype:1
83 ogg-merged.owl OntologyVersionIRINotAbsolute:1
84 OGI.owl OntologyVersionIRINotAbsolute:1 UseOfReservedVocabularyForAnnotationPropertyIRI:3
85 ogms.owl OntologyVersionIRINotAbsolute:2
86 ogsf-merged.owl IllegalPunning:17 OntologyVersionIRINotAbsolute:1 UseOfReservedVocabularyForAnnotationPropertyIRI:3
88 omiabis_merged.owl OntologyVersionIRINotAbsolute:1 UseOfReservedVocabularyForAnnotationPropertyIRI:1
90 ontoneo.owl IllegalPunning:108 LexicalNotInLexicalSpace:10 UseOfReservedVocabularyForAnnotationPropertyIRI:39 UseOfNonSimplePropertyInCardinalityRestriction:4
91 oostt.owl OntologyVersionIRINotAbsolute:7 UseOfUnknownDatatype:1
93 ovae_merged.owl IllegalPunning:8 OntologyVersionIRINotAbsolute:1
95 pco_merged_inferred.owl IllegalPunning:14
96 PDRO.owl IllegalPunning:28 OntologyVersionIRINotAbsolute:28 UseOfReservedVocabularyForAnnotationPropertyIRI:2 UseOfUnknownDatatype:2
98 plant-environment-ontology.obo.owl OntologyVersionIRINotAbsolute:1
100 poro.owl OntologyVersionIRINotAbsolute:6
103 ro.owl OntologyVersionIRINotAbsolute:10
110 stato.owl OntologyVersionIRINotAbsolute:1
111 swo_merged.owl OntologyVersionIRINotAbsolute:1 UseOfReservedVocabularyForClassIRI:6
116 to.owl OntologyVersionIRINotAbsolute:6
119 uberon.owl UseOfNonSimplePropertyInCardinalityRestriction:4
121 upheno.owl OntologyVersionIRINotAbsolute:1
123 VO.owl IllegalPunning:28 OntologyVersionIRINotAbsolute:19
124 vt.owl OntologyVersionIRINotAbsolute:1
131 zeco.owl LexicalNotInLexicalSpace:1 OntologyVersionIRINotAbsolute:1