diff --git a/.gitignore b/.gitignore index 3433027..f1ab582 100644 --- a/.gitignore +++ b/.gitignore @@ -1,7 +1,5 @@ .vscode __pycache__ .env -/data/mappings.ttl -/data/mappings.jsonld -/data/registry.yml +/data/* poetry.lock \ No newline at end of file diff --git a/Makefile b/Makefile index 98ee6fa..a9d25c0 100644 --- a/Makefile +++ b/Makefile @@ -6,7 +6,7 @@ REGISTRY_URL = https://raw.githubusercontent.com/mapping-commons/mh_mapping_init $(PWD)/data/registry.yml: wget $(REGISTRY_URL) -O $@ -jsonld_from_registry: $(PWD)/data/registry.yml +ttl_from_registry: $(PWD)/data/registry.yml cd src && python3 registry_parser.py $< deploy_api: @@ -19,3 +19,7 @@ rebuild-%: build-sssom-api: docker-compose up --build +OBO_CONTEXT_URL = https://raw.githubusercontent.com/biopragmatics/bioregistry/main/exports/contexts/obo.context.jsonld +.PHONY: update_obo_context +update_obo_context: + wget $(OBO_CONTEXT_URL) -O resources/obo.context.jsonld diff --git a/api.Dockerfile b/api.Dockerfile index aec36d5..8c14d03 100644 --- a/api.Dockerfile +++ b/api.Dockerfile @@ -13,6 +13,4 @@ RUN pip install poetry RUN poetry config virtualenvs.create false -RUN poetry install - -# CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "80"] \ No newline at end of file +RUN poetry install \ No newline at end of file diff --git a/blazegraph.Dockerfile b/blazegraph.Dockerfile new file mode 100644 index 0000000..6247d56 --- /dev/null +++ b/blazegraph.Dockerfile @@ -0,0 +1,22 @@ +FROM ubuntu:20.04 +WORKDIR /tools + +# Install base tools from Ubuntu. +RUN apt-get update && \ + DEBIAN_FRONTEND="noninteractive" apt-get install -y --no-install-recommends \ + wget \ + curl \ + openjdk-11-jdk \ + ca-certificates \ + ca-certificates-java + +ENV JAVA_HOME /usr/lib/jvm/java-11-openjdk-amd64/ +RUN export JAVA_HOME + +###### Blazegraph ##### +ENV JAVA_OPTS -Xmx16G +RUN wget -nv https://github.com/blazegraph/database/releases/download/BLAZEGRAPH_2_1_6_RC/blazegraph.jar + +CMD java -server $JAVA_OPTS -Dcom.bigdata.rdf.sail.webapp.ConfigParams.propertyFile=/RWStore.properties -Dcom.bigdata.util.config.LogUtil=/log4.properties -jar blazegraph.jar + + diff --git a/config/RWStore.properties b/config/RWStore.properties new file mode 100644 index 0000000..3d51f4a --- /dev/null +++ b/config/RWStore.properties @@ -0,0 +1,45 @@ +# +# Note: These options are applied when the journal and the triple store are +# first created. + +## +## Journal options. +## + +# The backing file. This contains all your data. You want to put this someplace +# safe. The default locator will wind up in the directory from which you start +# your servlet container. +com.bigdata.journal.AbstractJournal.file=blazegraph-mappings.jnl + +# The persistence engine. Use 'Disk' for the WORM or 'DiskRW' for the RWStore. +com.bigdata.journal.AbstractJournal.bufferMode=DiskRW + +# Setup for the RWStore recycler rather than session protection. +com.bigdata.service.AbstractTransactionService.minReleaseAge=1 + +com.bigdata.btree.writeRetentionQueue.capacity=4000 +com.bigdata.btree.BTree.branchingFactor=128 + +# 200M initial extent. +com.bigdata.journal.AbstractJournal.initialExtent=209715200 +com.bigdata.journal.AbstractJournal.maximumExtent=209715200 + +## +## Setup for triples mode without the full text index. +## +com.bigdata.rdf.sail.truthMaintenance=false +com.bigdata.rdf.store.AbstractTripleStore.quads=false +com.bigdata.rdf.store.AbstractTripleStore.statementIdentifiers=false +com.bigdata.rdf.store.AbstractTripleStore.textIndex=false +com.bigdata.rdf.store.AbstractTripleStore.axiomsClass=com.bigdata.rdf.axioms.NoAxioms + +# Bump up the branching factor for the lexicon indices on the default kb. +com.bigdata.namespace.kb.lex.com.bigdata.btree.BTree.branchingFactor=400 + +# Bump up the branching factor for the statement indices on the default kb. +com.bigdata.namespace.kb.spo.com.bigdata.btree.BTree.branchingFactor=1024 + +com.bigdata.search.FullTextIndex.analyzerFactoryClass=com.bigdata.search.ConfigurableAnalyzerFactory +com.bigdata.search.ConfigurableAnalyzerFactory.analyzer.eng.analyzerClass=org.apache.lucene.analysis.standard.StandardAnalyzer +com.bigdata.search.ConfigurableAnalyzerFactory.analyzer.eng.stopwords=none +com.bigdata.search.ConfigurableAnalyzerFactory.analyzer._.like=eng \ No newline at end of file diff --git a/config/dataloader.xml b/config/dataloader.xml new file mode 100644 index 0000000..f368fb3 --- /dev/null +++ b/config/dataloader.xml @@ -0,0 +1,24 @@ + + + + + kb + + /RWStore.properties + + kb + + /data + + x-turtle + + false + + 100 + + false + + true + \ No newline at end of file diff --git a/data/ols/ado.ols.sssom.tsv.jsonld.gz b/data/ols/ado.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4fa3acd..0000000 Binary files a/data/ols/ado.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/aeo.ols.sssom.tsv.jsonld.gz b/data/ols/aeo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 6ef2c81..0000000 Binary files a/data/ols/aeo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/aero.ols.sssom.tsv.jsonld.gz b/data/ols/aero.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4ac2b35..0000000 Binary files a/data/ols/aero.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/afo.ols.sssom.tsv.jsonld.gz b/data/ols/afo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 555ca6c..0000000 Binary files a/data/ols/afo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/agro.ols.sssom.tsv.jsonld.gz b/data/ols/agro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4d8f921..0000000 Binary files a/data/ols/agro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/aism.ols.sssom.tsv.jsonld.gz b/data/ols/aism.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 21e18e6..0000000 Binary files a/data/ols/aism.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/amphx.ols.sssom.tsv.jsonld.gz b/data/ols/amphx.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index ab5c7f3..0000000 Binary files a/data/ols/amphx.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/apo.ols.sssom.tsv.jsonld.gz b/data/ols/apo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index db0297a..0000000 Binary files a/data/ols/apo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/apollo_sv.ols.sssom.tsv.jsonld.gz b/data/ols/apollo_sv.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index dff380f..0000000 Binary files a/data/ols/apollo_sv.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/aro.ols.sssom.tsv.jsonld.gz b/data/ols/aro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index c97dcb2..0000000 Binary files a/data/ols/aro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/bao.ols.sssom.tsv.jsonld.gz b/data/ols/bao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 8c8a313..0000000 Binary files a/data/ols/bao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/bcgo.ols.sssom.tsv.jsonld.gz b/data/ols/bcgo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index ca7d7fc..0000000 Binary files a/data/ols/bcgo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/bcio.ols.sssom.tsv.jsonld.gz b/data/ols/bcio.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index dc34e96..0000000 Binary files a/data/ols/bcio.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/bco.ols.sssom.tsv.jsonld.gz b/data/ols/bco.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index aeb81e5..0000000 Binary files a/data/ols/bco.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/bfo.ols.sssom.tsv.jsonld.gz b/data/ols/bfo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index fef73bf..0000000 Binary files a/data/ols/bfo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/bila.ols.sssom.tsv.jsonld.gz b/data/ols/bila.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index e8c6a25..0000000 Binary files a/data/ols/bila.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/bspo.ols.sssom.tsv.jsonld.gz b/data/ols/bspo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 355dcc0..0000000 Binary files a/data/ols/bspo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/bto.ols.sssom.tsv.jsonld.gz b/data/ols/bto.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index d4f6b13..0000000 Binary files a/data/ols/bto.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cao.ols.sssom.tsv.jsonld.gz b/data/ols/cao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index c97ce27..0000000 Binary files a/data/ols/cao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/caro.ols.sssom.tsv.jsonld.gz b/data/ols/caro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 6d4a024..0000000 Binary files a/data/ols/caro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ccf.ols.sssom.tsv.jsonld.gz b/data/ols/ccf.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 8616c70..0000000 Binary files a/data/ols/ccf.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cco.ols.sssom.tsv.jsonld.gz b/data/ols/cco.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 30612b7..0000000 Binary files a/data/ols/cco.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cdao.ols.sssom.tsv.jsonld.gz b/data/ols/cdao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index e68b9da..0000000 Binary files a/data/ols/cdao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cdno.ols.sssom.tsv.jsonld.gz b/data/ols/cdno.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 31292f5..0000000 Binary files a/data/ols/cdno.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ceph.ols.sssom.tsv.jsonld.gz b/data/ols/ceph.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 707fa1f..0000000 Binary files a/data/ols/ceph.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cheminf.ols.sssom.tsv.jsonld.gz b/data/ols/cheminf.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index cb990f3..0000000 Binary files a/data/ols/cheminf.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/chiro.ols.sssom.tsv.jsonld.gz b/data/ols/chiro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 57e42db..0000000 Binary files a/data/ols/chiro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/chmo.ols.sssom.tsv.jsonld.gz b/data/ols/chmo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 0b12909..0000000 Binary files a/data/ols/chmo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cio.ols.sssom.tsv.jsonld.gz b/data/ols/cio.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 5f13d0b..0000000 Binary files a/data/ols/cio.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cl.ols.sssom.tsv.jsonld.gz b/data/ols/cl.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index f904a70..0000000 Binary files a/data/ols/cl.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/clao.ols.sssom.tsv.jsonld.gz b/data/ols/clao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index b18a777..0000000 Binary files a/data/ols/clao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/clo.ols.sssom.tsv.jsonld.gz b/data/ols/clo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 8022539..0000000 Binary files a/data/ols/clo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/clyh.ols.sssom.tsv.jsonld.gz b/data/ols/clyh.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index c7e91f8..0000000 Binary files a/data/ols/clyh.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cmo.ols.sssom.tsv.jsonld.gz b/data/ols/cmo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 31eb205..0000000 Binary files a/data/ols/cmo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cmpo.ols.sssom.tsv.jsonld.gz b/data/ols/cmpo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 5e89999..0000000 Binary files a/data/ols/cmpo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cob.ols.sssom.tsv.jsonld.gz b/data/ols/cob.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 10f78d6..0000000 Binary files a/data/ols/cob.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/colao.ols.sssom.tsv.jsonld.gz b/data/ols/colao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 8e5d282..0000000 Binary files a/data/ols/colao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/covoc.ols.sssom.tsv.jsonld.gz b/data/ols/covoc.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4d9f512..0000000 Binary files a/data/ols/covoc.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cpont.ols.sssom.tsv.jsonld.gz b/data/ols/cpont.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 2dbb562..0000000 Binary files a/data/ols/cpont.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cro.ols.sssom.tsv.jsonld.gz b/data/ols/cro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index ea5d982..0000000 Binary files a/data/ols/cro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cryoem.ols.sssom.tsv.jsonld.gz b/data/ols/cryoem.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 419958a..0000000 Binary files a/data/ols/cryoem.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/cteno.ols.sssom.tsv.jsonld.gz b/data/ols/cteno.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index cd51b88..0000000 Binary files a/data/ols/cteno.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/dc.ols.sssom.tsv.jsonld.gz b/data/ols/dc.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 6f98e5b..0000000 Binary files a/data/ols/dc.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/dcterms.ols.sssom.tsv.jsonld.gz b/data/ols/dcterms.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index c7e1108..0000000 Binary files a/data/ols/dcterms.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ddanat.ols.sssom.tsv.jsonld.gz b/data/ols/ddanat.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4191b37..0000000 Binary files a/data/ols/ddanat.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ddpheno.ols.sssom.tsv.jsonld.gz b/data/ols/ddpheno.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 7d8da6a..0000000 Binary files a/data/ols/ddpheno.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/dicom.ols.sssom.tsv.jsonld.gz b/data/ols/dicom.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index da5213e..0000000 Binary files a/data/ols/dicom.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/dideo.ols.sssom.tsv.jsonld.gz b/data/ols/dideo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 7cbcd4c..0000000 Binary files a/data/ols/dideo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/disdriv.ols.sssom.tsv.jsonld.gz b/data/ols/disdriv.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 94821ec..0000000 Binary files a/data/ols/disdriv.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/doid.ols.sssom.tsv.jsonld.gz b/data/ols/doid.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 2b74ff1..0000000 Binary files a/data/ols/doid.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/dpo.ols.sssom.tsv.jsonld.gz b/data/ols/dpo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 2d7c82b..0000000 Binary files a/data/ols/dpo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/dron.ols.sssom.tsv.jsonld.gz b/data/ols/dron.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index e303ed0..0000000 Binary files a/data/ols/dron.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/duo.ols.sssom.tsv.jsonld.gz b/data/ols/duo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index fd06217..0000000 Binary files a/data/ols/duo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ecao.ols.sssom.tsv.jsonld.gz b/data/ols/ecao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 56e5d2b..0000000 Binary files a/data/ols/ecao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/eco.ols.sssom.tsv.jsonld.gz b/data/ols/eco.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 7c43749..0000000 Binary files a/data/ols/eco.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ecocore.ols.sssom.tsv.jsonld.gz b/data/ols/ecocore.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 17dcd03..0000000 Binary files a/data/ols/ecocore.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ecto.ols.sssom.tsv.jsonld.gz b/data/ols/ecto.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index da58f07..0000000 Binary files a/data/ols/ecto.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/edam.ols.sssom.tsv.jsonld.gz b/data/ols/edam.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index a3c8451..0000000 Binary files a/data/ols/edam.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/efo.ols.sssom.tsv.jsonld.gz b/data/ols/efo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 39af30d..0000000 Binary files a/data/ols/efo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ehdaa2.ols.sssom.tsv.jsonld.gz b/data/ols/ehdaa2.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 382fd64..0000000 Binary files a/data/ols/ehdaa2.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/emap.ols.sssom.tsv.jsonld.gz b/data/ols/emap.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index d293dc5..0000000 Binary files a/data/ols/emap.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/emapa.ols.sssom.tsv.jsonld.gz b/data/ols/emapa.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index e36c0e8..0000000 Binary files a/data/ols/emapa.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/enm.ols.sssom.tsv.jsonld.gz b/data/ols/enm.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index da7dc63..0000000 Binary files a/data/ols/enm.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ensemblglossary.ols.sssom.tsv.jsonld.gz b/data/ols/ensemblglossary.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 54c4e74..0000000 Binary files a/data/ols/ensemblglossary.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/envo.ols.sssom.tsv.jsonld.gz b/data/ols/envo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 8ee1432..0000000 Binary files a/data/ols/envo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/epio.ols.sssom.tsv.jsonld.gz b/data/ols/epio.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 2d781b1..0000000 Binary files a/data/ols/epio.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/eupath.ols.sssom.tsv.jsonld.gz b/data/ols/eupath.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 098cb01..0000000 Binary files a/data/ols/eupath.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/exo.ols.sssom.tsv.jsonld.gz b/data/ols/exo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index db951eb..0000000 Binary files a/data/ols/exo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fao.ols.sssom.tsv.jsonld.gz b/data/ols/fao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index ebbb034..0000000 Binary files a/data/ols/fao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fbbi.ols.sssom.tsv.jsonld.gz b/data/ols/fbbi.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 06a76d4..0000000 Binary files a/data/ols/fbbi.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fbbt.ols.sssom.tsv.jsonld.gz b/data/ols/fbbt.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 9553bee..0000000 Binary files a/data/ols/fbbt.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fbcv.ols.sssom.tsv.jsonld.gz b/data/ols/fbcv.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 997a30f..0000000 Binary files a/data/ols/fbcv.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fbdv.ols.sssom.tsv.jsonld.gz b/data/ols/fbdv.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 5773708..0000000 Binary files a/data/ols/fbdv.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fbsp.ols.sssom.tsv.jsonld.gz b/data/ols/fbsp.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index ada55f9..0000000 Binary files a/data/ols/fbsp.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fideo.ols.sssom.tsv.jsonld.gz b/data/ols/fideo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index ddade9d..0000000 Binary files a/data/ols/fideo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fix.ols.sssom.tsv.jsonld.gz b/data/ols/fix.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 65b84d1..0000000 Binary files a/data/ols/fix.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/flopo.ols.sssom.tsv.jsonld.gz b/data/ols/flopo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index ad130df..0000000 Binary files a/data/ols/flopo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fma.ols.sssom.tsv.jsonld.gz b/data/ols/fma.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 0552790..0000000 Binary files a/data/ols/fma.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fobi.ols.sssom.tsv.jsonld.gz b/data/ols/fobi.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index c2ab872..0000000 Binary files a/data/ols/fobi.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/foodon.ols.sssom.tsv.jsonld.gz b/data/ols/foodon.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index e84d213..0000000 Binary files a/data/ols/foodon.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fovt.ols.sssom.tsv.jsonld.gz b/data/ols/fovt.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index b67fa15..0000000 Binary files a/data/ols/fovt.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/fypo.ols.sssom.tsv.jsonld.gz b/data/ols/fypo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index f258a7b..0000000 Binary files a/data/ols/fypo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/gecko.ols.sssom.tsv.jsonld.gz b/data/ols/gecko.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 78884c8..0000000 Binary files a/data/ols/gecko.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/geno.ols.sssom.tsv.jsonld.gz b/data/ols/geno.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 3b6689f..0000000 Binary files a/data/ols/geno.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/geo.ols.sssom.tsv.jsonld.gz b/data/ols/geo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 3b9c864..0000000 Binary files a/data/ols/geo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/gexo.ols.sssom.tsv.jsonld.gz b/data/ols/gexo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 724253b..0000000 Binary files a/data/ols/gexo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/gno.ols.sssom.tsv.jsonld.gz b/data/ols/gno.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 0b8e34f..0000000 Binary files a/data/ols/gno.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/go.ols.sssom.tsv.jsonld.gz b/data/ols/go.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 1bffb9c..0000000 Binary files a/data/ols/go.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/gsso.ols.sssom.tsv.jsonld.gz b/data/ols/gsso.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 798abc5..0000000 Binary files a/data/ols/gsso.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/hancestro.ols.sssom.tsv.jsonld.gz b/data/ols/hancestro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 9977663..0000000 Binary files a/data/ols/hancestro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/hao.ols.sssom.tsv.jsonld.gz b/data/ols/hao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 378032f..0000000 Binary files a/data/ols/hao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/hcao.ols.sssom.tsv.jsonld.gz b/data/ols/hcao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 208755f..0000000 Binary files a/data/ols/hcao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/hom.ols.sssom.tsv.jsonld.gz b/data/ols/hom.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 207d08a..0000000 Binary files a/data/ols/hom.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/hp.ols.sssom.tsv.jsonld.gz b/data/ols/hp.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index baeb219..0000000 Binary files a/data/ols/hp.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/hsapdv.ols.sssom.tsv.jsonld.gz b/data/ols/hsapdv.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 67f40fa..0000000 Binary files a/data/ols/hsapdv.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/hso.ols.sssom.tsv.jsonld.gz b/data/ols/hso.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index fcf065d..0000000 Binary files a/data/ols/hso.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/htn.ols.sssom.tsv.jsonld.gz b/data/ols/htn.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index ef73123..0000000 Binary files a/data/ols/htn.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/iao.ols.sssom.tsv.jsonld.gz b/data/ols/iao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index f1d2e54..0000000 Binary files a/data/ols/iao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/iceo.ols.sssom.tsv.jsonld.gz b/data/ols/iceo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4ac992c..0000000 Binary files a/data/ols/iceo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ico.ols.sssom.tsv.jsonld.gz b/data/ols/ico.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index c200db1..0000000 Binary files a/data/ols/ico.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ido.ols.sssom.tsv.jsonld.gz b/data/ols/ido.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 6dec966..0000000 Binary files a/data/ols/ido.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/idocovid19.ols.sssom.tsv.jsonld.gz b/data/ols/idocovid19.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 71c945c..0000000 Binary files a/data/ols/idocovid19.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/idomal.ols.sssom.tsv.jsonld.gz b/data/ols/idomal.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 808bc64..0000000 Binary files a/data/ols/idomal.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ino.ols.sssom.tsv.jsonld.gz b/data/ols/ino.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 5ce1568..0000000 Binary files a/data/ols/ino.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/kisao.ols.sssom.tsv.jsonld.gz b/data/ols/kisao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 5edb5fc..0000000 Binary files a/data/ols/kisao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/labo.ols.sssom.tsv.jsonld.gz b/data/ols/labo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index fe9ca95..0000000 Binary files a/data/ols/labo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/lepao.ols.sssom.tsv.jsonld.gz b/data/ols/lepao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 90c25e9..0000000 Binary files a/data/ols/lepao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ma.ols.sssom.tsv.jsonld.gz b/data/ols/ma.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 73005a2..0000000 Binary files a/data/ols/ma.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mappings.jsonld.gz b/data/ols/mappings.jsonld.gz deleted file mode 100644 index 39ec974..0000000 Binary files a/data/ols/mappings.jsonld.gz and /dev/null differ diff --git a/data/ols/maxo.ols.sssom.tsv.jsonld.gz b/data/ols/maxo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 72c5c70..0000000 Binary files a/data/ols/maxo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mco.ols.sssom.tsv.jsonld.gz b/data/ols/mco.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 133defe..0000000 Binary files a/data/ols/mco.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mf.ols.sssom.tsv.jsonld.gz b/data/ols/mf.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4def181..0000000 Binary files a/data/ols/mf.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mfmo.ols.sssom.tsv.jsonld.gz b/data/ols/mfmo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 08e8fe1..0000000 Binary files a/data/ols/mfmo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mfoem.ols.sssom.tsv.jsonld.gz b/data/ols/mfoem.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 22e8d51..0000000 Binary files a/data/ols/mfoem.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mfomd.ols.sssom.tsv.jsonld.gz b/data/ols/mfomd.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 284b417..0000000 Binary files a/data/ols/mfomd.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mi.ols.sssom.tsv.jsonld.gz b/data/ols/mi.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 6a2e49c..0000000 Binary files a/data/ols/mi.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/miapa.ols.sssom.tsv.jsonld.gz b/data/ols/miapa.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 9297313..0000000 Binary files a/data/ols/miapa.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/micro.ols.sssom.tsv.jsonld.gz b/data/ols/micro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index eb1881d..0000000 Binary files a/data/ols/micro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/miro.ols.sssom.tsv.jsonld.gz b/data/ols/miro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 3834e52..0000000 Binary files a/data/ols/miro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mmo.ols.sssom.tsv.jsonld.gz b/data/ols/mmo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index aca4df8..0000000 Binary files a/data/ols/mmo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mmusdv.ols.sssom.tsv.jsonld.gz b/data/ols/mmusdv.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4dbcf51..0000000 Binary files a/data/ols/mmusdv.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mod.ols.sssom.tsv.jsonld.gz b/data/ols/mod.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index f91ef8b..0000000 Binary files a/data/ols/mod.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mondo-ingest-literal-matches.sssom.tsv.jsonld.gz b/data/ols/mondo-ingest-literal-matches.sssom.tsv.jsonld.gz deleted file mode 100644 index 5c971d7..0000000 Binary files a/data/ols/mondo-ingest-literal-matches.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mondo.ols.sssom.tsv.jsonld.gz b/data/ols/mondo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 9f2aee1..0000000 Binary files a/data/ols/mondo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mondo.sssom.tsv.jsonld.gz b/data/ols/mondo.sssom.tsv.jsonld.gz deleted file mode 100644 index 5183989..0000000 Binary files a/data/ols/mondo.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mop.ols.sssom.tsv.jsonld.gz b/data/ols/mop.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index c64c716..0000000 Binary files a/data/ols/mop.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mp.ols.sssom.tsv.jsonld.gz b/data/ols/mp.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 6a8a043..0000000 Binary files a/data/ols/mp.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mp_hp_mgi_all.sssom.tsv.jsonld.gz b/data/ols/mp_hp_mgi_all.sssom.tsv.jsonld.gz deleted file mode 100644 index 191a53a..0000000 Binary files a/data/ols/mp_hp_mgi_all.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mpath.ols.sssom.tsv.jsonld.gz b/data/ols/mpath.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 2abe17e..0000000 Binary files a/data/ols/mpath.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mpio.ols.sssom.tsv.jsonld.gz b/data/ols/mpio.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 05ddf16..0000000 Binary files a/data/ols/mpio.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/mro.ols.sssom.tsv.jsonld.gz b/data/ols/mro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index e26f5cf..0000000 Binary files a/data/ols/mro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ms.ols.sssom.tsv.jsonld.gz b/data/ols/ms.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 3950ed1..0000000 Binary files a/data/ols/ms.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/msio.ols.sssom.tsv.jsonld.gz b/data/ols/msio.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index cacc554..0000000 Binary files a/data/ols/msio.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/nbo.ols.sssom.tsv.jsonld.gz b/data/ols/nbo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 9861fbf..0000000 Binary files a/data/ols/nbo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ncit.ols.sssom.tsv.jsonld.gz b/data/ols/ncit.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 8b29aff..0000000 Binary files a/data/ols/ncit.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ncro.ols.sssom.tsv.jsonld.gz b/data/ols/ncro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index b95df06..0000000 Binary files a/data/ols/ncro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ngbo.ols.sssom.tsv.jsonld.gz b/data/ols/ngbo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 30a6e43..0000000 Binary files a/data/ols/ngbo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/nmrcv.ols.sssom.tsv.jsonld.gz b/data/ols/nmrcv.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index aef0371..0000000 Binary files a/data/ols/nmrcv.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/nomen.ols.sssom.tsv.jsonld.gz b/data/ols/nomen.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4ecad0c..0000000 Binary files a/data/ols/nomen.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/oae.ols.sssom.tsv.jsonld.gz b/data/ols/oae.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index f0d3c96..0000000 Binary files a/data/ols/oae.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/oarcs.ols.sssom.tsv.jsonld.gz b/data/ols/oarcs.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 59cbd27..0000000 Binary files a/data/ols/oarcs.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/oba.ols.sssom.tsv.jsonld.gz b/data/ols/oba.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 970fe3b..0000000 Binary files a/data/ols/oba.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/obcs.ols.sssom.tsv.jsonld.gz b/data/ols/obcs.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 6d7aeac..0000000 Binary files a/data/ols/obcs.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/obi.ols.sssom.tsv.jsonld.gz b/data/ols/obi.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 7e0a65b..0000000 Binary files a/data/ols/obi.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/obib.ols.sssom.tsv.jsonld.gz b/data/ols/obib.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 3d6e4a3..0000000 Binary files a/data/ols/obib.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/oboinowl.ols.sssom.tsv.jsonld.gz b/data/ols/oboinowl.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 574581c..0000000 Binary files a/data/ols/oboinowl.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ogg.ols.sssom.tsv.jsonld.gz b/data/ols/ogg.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 566aea0..0000000 Binary files a/data/ols/ogg.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ogms.ols.sssom.tsv.jsonld.gz b/data/ols/ogms.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index bcafcc2..0000000 Binary files a/data/ols/ogms.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ogsf.ols.sssom.tsv.jsonld.gz b/data/ols/ogsf.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index bb00fe4..0000000 Binary files a/data/ols/ogsf.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ohd.ols.sssom.tsv.jsonld.gz b/data/ols/ohd.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 141c994..0000000 Binary files a/data/ols/ohd.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ohmi.ols.sssom.tsv.jsonld.gz b/data/ols/ohmi.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 01926bb..0000000 Binary files a/data/ols/ohmi.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ohpi.ols.sssom.tsv.jsonld.gz b/data/ols/ohpi.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 56cf3fa..0000000 Binary files a/data/ols/ohpi.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/olatdv.ols.sssom.tsv.jsonld.gz b/data/ols/olatdv.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 6a0b393..0000000 Binary files a/data/ols/olatdv.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/om.ols.sssom.tsv.jsonld.gz b/data/ols/om.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4565323..0000000 Binary files a/data/ols/om.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/omiabis.ols.sssom.tsv.jsonld.gz b/data/ols/omiabis.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index ad40241..0000000 Binary files a/data/ols/omiabis.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/omit.ols.sssom.tsv.jsonld.gz b/data/ols/omit.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 6d8938a..0000000 Binary files a/data/ols/omit.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/omo.ols.sssom.tsv.jsonld.gz b/data/ols/omo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 59fae69..0000000 Binary files a/data/ols/omo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/omp.ols.sssom.tsv.jsonld.gz b/data/ols/omp.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 2fdb6ed..0000000 Binary files a/data/ols/omp.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/omrse.ols.sssom.tsv.jsonld.gz b/data/ols/omrse.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 0a34447..0000000 Binary files a/data/ols/omrse.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/one.ols.sssom.tsv.jsonld.gz b/data/ols/one.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index d5f0b06..0000000 Binary files a/data/ols/one.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ons.ols.sssom.tsv.jsonld.gz b/data/ols/ons.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 737651b..0000000 Binary files a/data/ols/ons.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ontoavida.ols.sssom.tsv.jsonld.gz b/data/ols/ontoavida.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 78e6c60..0000000 Binary files a/data/ols/ontoavida.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ontoneo.ols.sssom.tsv.jsonld.gz b/data/ols/ontoneo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 0eef4fe..0000000 Binary files a/data/ols/ontoneo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/oostt.ols.sssom.tsv.jsonld.gz b/data/ols/oostt.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 8a74777..0000000 Binary files a/data/ols/oostt.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/opl.ols.sssom.tsv.jsonld.gz b/data/ols/opl.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 5f9ef46..0000000 Binary files a/data/ols/opl.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/opmi.ols.sssom.tsv.jsonld.gz b/data/ols/opmi.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 1a14e08..0000000 Binary files a/data/ols/opmi.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ordo.ols.sssom.tsv.jsonld.gz b/data/ols/ordo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 5544ae0..0000000 Binary files a/data/ols/ordo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ornaseq.ols.sssom.tsv.jsonld.gz b/data/ols/ornaseq.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index df3a7b0..0000000 Binary files a/data/ols/ornaseq.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/orth.ols.sssom.tsv.jsonld.gz b/data/ols/orth.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 5b3b8e6..0000000 Binary files a/data/ols/orth.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ovae.ols.sssom.tsv.jsonld.gz b/data/ols/ovae.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 253bbb6..0000000 Binary files a/data/ols/ovae.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/owl.ols.sssom.tsv.jsonld.gz b/data/ols/owl.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 651dac7..0000000 Binary files a/data/ols/owl.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/pato.ols.sssom.tsv.jsonld.gz b/data/ols/pato.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 580b733..0000000 Binary files a/data/ols/pato.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/pcl.ols.sssom.tsv.jsonld.gz b/data/ols/pcl.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 31198e2..0000000 Binary files a/data/ols/pcl.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/pco.ols.sssom.tsv.jsonld.gz b/data/ols/pco.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index a4e83e9..0000000 Binary files a/data/ols/pco.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/pdro.ols.sssom.tsv.jsonld.gz b/data/ols/pdro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index fc9acc5..0000000 Binary files a/data/ols/pdro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/pdumdv.ols.sssom.tsv.jsonld.gz b/data/ols/pdumdv.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index bde090a..0000000 Binary files a/data/ols/pdumdv.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/peco.ols.sssom.tsv.jsonld.gz b/data/ols/peco.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 560308c..0000000 Binary files a/data/ols/peco.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/phipo.ols.sssom.tsv.jsonld.gz b/data/ols/phipo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 786f13d..0000000 Binary files a/data/ols/phipo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/plana.ols.sssom.tsv.jsonld.gz b/data/ols/plana.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 7640bbd..0000000 Binary files a/data/ols/plana.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/planp.ols.sssom.tsv.jsonld.gz b/data/ols/planp.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 2af1688..0000000 Binary files a/data/ols/planp.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/po.ols.sssom.tsv.jsonld.gz b/data/ols/po.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 9a85b80..0000000 Binary files a/data/ols/po.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/poro.ols.sssom.tsv.jsonld.gz b/data/ols/poro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 769893c..0000000 Binary files a/data/ols/poro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ppo.ols.sssom.tsv.jsonld.gz b/data/ols/ppo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index bea40e7..0000000 Binary files a/data/ols/ppo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/pr.ols.sssom.tsv.jsonld.gz b/data/ols/pr.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 1581b1f..0000000 Binary files a/data/ols/pr.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/proco.ols.sssom.tsv.jsonld.gz b/data/ols/proco.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index df967c9..0000000 Binary files a/data/ols/proco.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/prov.ols.sssom.tsv.jsonld.gz b/data/ols/prov.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index ef55b67..0000000 Binary files a/data/ols/prov.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/psdo.ols.sssom.tsv.jsonld.gz b/data/ols/psdo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 75f3b30..0000000 Binary files a/data/ols/psdo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/pso.ols.sssom.tsv.jsonld.gz b/data/ols/pso.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index a27c000..0000000 Binary files a/data/ols/pso.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/pw.ols.sssom.tsv.jsonld.gz b/data/ols/pw.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 9310db6..0000000 Binary files a/data/ols/pw.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/rbo.ols.sssom.tsv.jsonld.gz b/data/ols/rbo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 669c8fb..0000000 Binary files a/data/ols/rbo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/rdfs.ols.sssom.tsv.jsonld.gz b/data/ols/rdfs.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index fe0efb7..0000000 Binary files a/data/ols/rdfs.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/reproduceme.ols.sssom.tsv.jsonld.gz b/data/ols/reproduceme.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 8ad8e70..0000000 Binary files a/data/ols/reproduceme.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/reto.ols.sssom.tsv.jsonld.gz b/data/ols/reto.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index b6a5dab..0000000 Binary files a/data/ols/reto.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/rex.ols.sssom.tsv.jsonld.gz b/data/ols/rex.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index bfca5d7..0000000 Binary files a/data/ols/rex.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/rexo.ols.sssom.tsv.jsonld.gz b/data/ols/rexo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index aeec1d2..0000000 Binary files a/data/ols/rexo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/ro.ols.sssom.tsv.jsonld.gz b/data/ols/ro.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 25cac28..0000000 Binary files a/data/ols/ro.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/rs.ols.sssom.tsv.jsonld.gz b/data/ols/rs.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 2d19e59..0000000 Binary files a/data/ols/rs.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/rxno.ols.sssom.tsv.jsonld.gz b/data/ols/rxno.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 6e2216b..0000000 Binary files a/data/ols/rxno.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/sbo.ols.sssom.tsv.jsonld.gz b/data/ols/sbo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 349699e..0000000 Binary files a/data/ols/sbo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/scdo.ols.sssom.tsv.jsonld.gz b/data/ols/scdo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 0cfc0a5..0000000 Binary files a/data/ols/scdo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/schemaorg_http.ols.sssom.tsv.jsonld.gz b/data/ols/schemaorg_http.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4316187..0000000 Binary files a/data/ols/schemaorg_http.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/schemaorg_https.ols.sssom.tsv.jsonld.gz b/data/ols/schemaorg_https.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 3a2a371..0000000 Binary files a/data/ols/schemaorg_https.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/sdgio.ols.sssom.tsv.jsonld.gz b/data/ols/sdgio.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index c63e8f4..0000000 Binary files a/data/ols/sdgio.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/sepio.ols.sssom.tsv.jsonld.gz b/data/ols/sepio.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 18c55a2..0000000 Binary files a/data/ols/sepio.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/shareloc.ols.sssom.tsv.jsonld.gz b/data/ols/shareloc.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index fcf32cb..0000000 Binary files a/data/ols/shareloc.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/sibo.ols.sssom.tsv.jsonld.gz b/data/ols/sibo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index a31eaf6..0000000 Binary files a/data/ols/sibo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/sio.ols.sssom.tsv.jsonld.gz b/data/ols/sio.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 685f54c..0000000 Binary files a/data/ols/sio.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/skos.ols.sssom.tsv.jsonld.gz b/data/ols/skos.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 06e0f35..0000000 Binary files a/data/ols/skos.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/snomed.ols.sssom.tsv.jsonld.gz b/data/ols/snomed.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 16d4477..0000000 Binary files a/data/ols/snomed.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/so.ols.sssom.tsv.jsonld.gz b/data/ols/so.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index fe8d071..0000000 Binary files a/data/ols/so.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/spd.ols.sssom.tsv.jsonld.gz b/data/ols/spd.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 19e1a80..0000000 Binary files a/data/ols/spd.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/srao.ols.sssom.tsv.jsonld.gz b/data/ols/srao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 4798b57..0000000 Binary files a/data/ols/srao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/stato.ols.sssom.tsv.jsonld.gz b/data/ols/stato.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 11f4f49..0000000 Binary files a/data/ols/stato.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/swo.ols.sssom.tsv.jsonld.gz b/data/ols/swo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index b98523d..0000000 Binary files a/data/ols/swo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/symp.ols.sssom.tsv.jsonld.gz b/data/ols/symp.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 7038b17..0000000 Binary files a/data/ols/symp.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/t4fs.ols.sssom.tsv.jsonld.gz b/data/ols/t4fs.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index f6ea2d5..0000000 Binary files a/data/ols/t4fs.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/tads.ols.sssom.tsv.jsonld.gz b/data/ols/tads.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index cda0c67..0000000 Binary files a/data/ols/tads.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/tao.ols.sssom.tsv.jsonld.gz b/data/ols/tao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 52b1a34..0000000 Binary files a/data/ols/tao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/taxrank.ols.sssom.tsv.jsonld.gz b/data/ols/taxrank.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 0482494..0000000 Binary files a/data/ols/taxrank.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/tgma.ols.sssom.tsv.jsonld.gz b/data/ols/tgma.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 6819808..0000000 Binary files a/data/ols/tgma.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/to.ols.sssom.tsv.jsonld.gz b/data/ols/to.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 9a487f3..0000000 Binary files a/data/ols/to.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/trans.ols.sssom.tsv.jsonld.gz b/data/ols/trans.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 333c4dc..0000000 Binary files a/data/ols/trans.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/tto.ols.sssom.tsv.jsonld.gz b/data/ols/tto.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 985f2b1..0000000 Binary files a/data/ols/tto.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/txpo.ols.sssom.tsv.jsonld.gz b/data/ols/txpo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 9a23eb2..0000000 Binary files a/data/ols/txpo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/uberon.ols.sssom.tsv.jsonld.gz b/data/ols/uberon.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 3e5ca28..0000000 Binary files a/data/ols/uberon.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/uo.ols.sssom.tsv.jsonld.gz b/data/ols/uo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index c3dcc39..0000000 Binary files a/data/ols/uo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/upa.ols.sssom.tsv.jsonld.gz b/data/ols/upa.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 8551508..0000000 Binary files a/data/ols/upa.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/vbo.ols.sssom.tsv.jsonld.gz b/data/ols/vbo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 0ededd7..0000000 Binary files a/data/ols/vbo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/vo.ols.sssom.tsv.jsonld.gz b/data/ols/vo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 1a5927b..0000000 Binary files a/data/ols/vo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/vsao.ols.sssom.tsv.jsonld.gz b/data/ols/vsao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index f406d1a..0000000 Binary files a/data/ols/vsao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/vt.ols.sssom.tsv.jsonld.gz b/data/ols/vt.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index c9e1dee..0000000 Binary files a/data/ols/vt.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/vto.ols.sssom.tsv.jsonld.gz b/data/ols/vto.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index f1d489c..0000000 Binary files a/data/ols/vto.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/wbbt.ols.sssom.tsv.jsonld.gz b/data/ols/wbbt.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 8f70023..0000000 Binary files a/data/ols/wbbt.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/wbls.ols.sssom.tsv.jsonld.gz b/data/ols/wbls.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 760df29..0000000 Binary files a/data/ols/wbls.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/wbphenotype.ols.sssom.tsv.jsonld.gz b/data/ols/wbphenotype.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index b781188..0000000 Binary files a/data/ols/wbphenotype.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/xao.ols.sssom.tsv.jsonld.gz b/data/ols/xao.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 9fdc5f9..0000000 Binary files a/data/ols/xao.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/xco.ols.sssom.tsv.jsonld.gz b/data/ols/xco.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 09e13ba..0000000 Binary files a/data/ols/xco.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/xlmod.ols.sssom.tsv.jsonld.gz b/data/ols/xlmod.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index b06f016..0000000 Binary files a/data/ols/xlmod.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/xpo.ols.sssom.tsv.jsonld.gz b/data/ols/xpo.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 7e47624..0000000 Binary files a/data/ols/xpo.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/zeco.ols.sssom.tsv.jsonld.gz b/data/ols/zeco.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index c3d000e..0000000 Binary files a/data/ols/zeco.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/zfa.ols.sssom.tsv.jsonld.gz b/data/ols/zfa.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index 30ff291..0000000 Binary files a/data/ols/zfa.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/zfs.ols.sssom.tsv.jsonld.gz b/data/ols/zfs.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index b190e53..0000000 Binary files a/data/ols/zfs.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/data/ols/zp.ols.sssom.tsv.jsonld.gz b/data/ols/zp.ols.sssom.tsv.jsonld.gz deleted file mode 100644 index fce197f..0000000 Binary files a/data/ols/zp.ols.sssom.tsv.jsonld.gz and /dev/null differ diff --git a/docker-compose.yml b/docker-compose.yml index 8d1d615..89a4fbc 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -15,14 +15,22 @@ services: - triplestore - upload-triplestore environment: - - SPARQL_ENDPOINT=http://triplestore:8080/rdf4j-server/repositories/sssom + - SPARQL_ENDPOINT=http://triplestore:9999/blazegraph/namespace/kb/sparql triplestore: - image: eclipse/rdf4j-workbench:latest + image: anitacaron/blazegraph:v0.4 environment: - - JAVA_OPTS=-Xms10g -Xmx20g - - RDF4J_DATA=/data + - JAVA_OPTS=-Xmx10G ports: - - 8080:8080 + - 9999:9999 + volumes: + - ./data:/data + - ./config/RWStore.properties:/RWStore.properties + - ./config/log4j.properties:/log4j.properties + healthcheck: + test: ["CMD", "curl", "-f", "http://triplestore:9999/"] + interval: 3s + timeout: 5s + retries: 3 upload-triplestore: build: context: . @@ -32,6 +40,7 @@ services: links: - triplestore environment: - - SERVER=http://triplestore:8080 + - SERVER=http://triplestore:9999/blazegraph volumes: - - ./data:/data \ No newline at end of file + - ./data:/data + - ./config/RWStore.properties:/RWStore.properties \ No newline at end of file diff --git a/process.sh b/process.sh index 3243baf..86c5675 100644 --- a/process.sh +++ b/process.sh @@ -7,22 +7,23 @@ echo "Start: upload-triplestore" echo "TIME:" date -SETUP=${WORKSPACE}/rdf4j_sssom.txt -RDF4J=/opt/eclipse-rdf4j-${RDF4J_VERSION} -RDF4JSERVER=${SERVER}/rdf4j-server -DATA=/data/ols +# SETUP=${WORKSPACE}/rdf4j_sssom.txt +#BLAZEGRAPH_UID=/opt/eclipse-rdf4j-${RDF4J_VERSION} +BLAZEGRAPHSERVER=${SERVER}/dataloader +DATA=/data +DATALOADER=/opt/SSSOM/ -if [ `ls $DATA/*.jsonld.gz | wc -l` -lt 1 ]; then echo "ERROR: No data in data directory! Aborting.. " && exit 1; fi +#if [ `ls $DATA/*.jsonld.gz | wc -l` -lt 1 ]; then echo "ERROR: No data in data directory! Aborting.. " && exit 1; fi -echo 'Waiting for RDF4J server..' -until $(curl --output /dev/null --silent --head --fail ${RDF4JSERVER}); do +echo 'Waiting for BLAZEGRAPH WORKBENCH..' +until $(curl --output /dev/null --silent --head --fail ${SERVER}); do printf '.' sleep 5 done -echo "connect "${RDF4JSERVER}|cat - ${SETUP} > /tmp/out && mv /tmp/out ${SETUP} -cat ${SETUP} -cat ${SETUP} | sh ${RDF4J}/bin/console.sh +# echo "connect "${RDF4JSERVER}|cat - ${SETUP} > /tmp/out && mv /tmp/out ${SETUP} +# cat ${SETUP} +# cat ${SETUP} | sh ${RDF4J}/bin/console.sh ls -lh $DATA @@ -30,22 +31,30 @@ ls -lh $DATA echo "TIME:" date -cd $DATA +cd $DATALOADER +echo $BLAZEGRAPHSERVER + +echo "curl -X POST --data-binary @dataloader.xml --header 'Content-Type:application/xml' http://localhost:9999/blazegraph/dataloader" +curl POST -v --data-binary @dataloader.xml --header 'Content-Type:application/xml' ${BLAZEGRAPHSERVER} + + # The following for loop writes the load commands into the RDF4J setup script -for i in *.jsonld.gz; do - [ -f "$i" ] || break - #arg="load "$DATA/$i" into ns:"$i - echo $i +# for i in *.jsonld.gz; do +# [ -f "$i" ] || break +# #arg="load "$DATA/$i" into ns:"$i +# echo $i #awk -v line="$arg" '/open vfb/ { print; print line; next }1' $WS/rdf4j.txt > $WS/tmp.txt #cp $WS/tmp.txt $WS/rdf4j.txt # URI="%3Chttp%3A%2F%2Fvirtualflybrain.org%2Fdata%2FVFB%2FOWL%2F${i}%3E" - echo "curl -v --retry 5 --retry-delay 10 -X POST -H \"Content-type: application/ld+json\" --data-binary @$i ${RDF4JSERVER}/repositories/sssom/statements?context=null" - curl -v --retry 5 --retry-delay 10 -X POST -H "Content-type: application/ld+json" --data-binary @$i ${RDF4JSERVER}/repositories/sssom/statements?context=null || exit 1 - echo "TIME:" - date - sleep 5 -done + # echo "curl -v --retry 5 --retry-delay 10 -X POST -H \"Content-type: application/ld+json\" --data-binary @$i ${RDF4JSERVER}/repositories/sssom/statements?context=null" + # echo "curl -X POST --data-binary @dataloader.xml --header 'Content-Type:application/xml' http://localhost:9999/bigdata/dataloader" + # curl -v --retry 5 --retry-delay 10 -X POST -H "Content-type: application/ld+json" --data-binary @$i ${RDF4JSERVER}/repositories/sssom/statements?context=null || exit 1 + # curl -X POST --data-binary @dataloader.xml --header 'Content-Type:application/xml' ${BLAZEGRAPHSERVER} + # echo "TIME:" + # date + # sleep 5 +# done echo "End: upload-triplestore" diff --git a/pyproject.toml b/pyproject.toml index edf9249..a7f5995 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -11,10 +11,11 @@ python = "^3.9" fastapi = "^0.95.0" uvicorn = {extras = ["standard"], version = "^0.21.1"} pydantic = {extras = ["dotenv"], version = "^1.10.7"} -oaklib = "0.1.71" -sssom-schema = "^v0.9.4" -sssom = "^0.3.26" +sssom-schema = "^0.15.0" +sssom = "0.4.10" toolz = "^0.12.0" +pyld = "^2.0.3" +oaklib = "^0.5.21" [tool.poetry.group.dev.dependencies] pytest = "^7.2.2" diff --git a/rdf4j_sssom.txt b/rdf4j_sssom.txt deleted file mode 100644 index 8004d7b..0000000 --- a/rdf4j_sssom.txt +++ /dev/null @@ -1,14 +0,0 @@ -show repositories -drop sssom. -yes -create native. -sssom -SSSOM triplestore -10000 -spoc,posc -org.eclipse.rdf4j.query.algebra.evaluation.impl.StrictEvaluationStrategyFactory -show repositories -open sssom. -select * where {?s ?p ?o } LIMIT 5. -close. -quit. \ No newline at end of file diff --git a/resources/obo.context.jsonld b/resources/obo.context.jsonld index da6b854..3bd35a7 100644 --- a/resources/obo.context.jsonld +++ b/resources/obo.context.jsonld @@ -92,12 +92,10 @@ "DINTO": "http://purl.obolibrary.org/obo/DINTO_", "DISDRIV": "http://purl.obolibrary.org/obo/DISDRIV_", "DMBA": "https://biopragmatics.github.io/providers/dmba/", - "DOI": "http://dx.doi.org/", "DOID": "http://purl.obolibrary.org/obo/DOID_", "DRON": "http://purl.obolibrary.org/obo/DRON_", "DUO": "http://purl.obolibrary.org/obo/DUO_", "DataCite": "http://purl.org/spar/datacite/", - "DeBiO": "https://biopragmatics.github.io/debio/", "DoCO": "http://purl.org/spar/doco/", "ECAO": "http://purl.obolibrary.org/obo/ECAO_", "ECO": "http://purl.obolibrary.org/obo/ECO_", @@ -144,7 +142,7 @@ "GEO": "http://purl.obolibrary.org/obo/GEO_", "GNO": "http://purl.obolibrary.org/obo/GNO_", "GO": "http://purl.obolibrary.org/obo/GO_", - "GOCHE": "https://biopragmatics.github.io/providers/goche/", + "GOCHE": "http://purl.obolibrary.org/obo/GOCHE_", "GRO": "http://purl.obolibrary.org/obo/GRO_", "GSSO": "http://purl.obolibrary.org/obo/GSSO_", "HABRONATTUS": "http://purl.obolibrary.org/obo/HABRONATTUS_", @@ -179,6 +177,7 @@ "MAXO": "http://purl.obolibrary.org/obo/MAXO_", "MBA": "https://biopragmatics.github.io/providers/mba/", "MCO": "http://purl.obolibrary.org/obo/MCO_", + "MCRO": "http://purl.obolibrary.org/obo/MCRO_", "MF": "http://purl.obolibrary.org/obo/MF_", "MFMO": "http://purl.obolibrary.org/obo/MFMO_", "MFO": "http://purl.obolibrary.org/obo/MFO_", @@ -241,6 +240,7 @@ "ORNASEQ": "http://purl.obolibrary.org/obo/ORNASEQ_", "OVAE": "http://purl.obolibrary.org/obo/OVAE_", "OlatDv": "http://purl.obolibrary.org/obo/OlatDv_", + "Orphanet": "http://www.orpha.net/ORDO/Orphanet_", "PAO": "http://purl.obolibrary.org/obo/PAO_", "PATO": "http://purl.obolibrary.org/obo/PATO_", "PBA": "https://biopragmatics.github.io/providers/pba/", @@ -254,6 +254,7 @@ "PLANA": "http://purl.obolibrary.org/obo/PLANA_", "PLANP": "http://purl.obolibrary.org/obo/PLANP_", "PLO": "http://purl.obolibrary.org/obo/PLO_", + "PMID": "https://www.ncbi.nlm.nih.gov/pubmed/", "PO": "http://purl.obolibrary.org/obo/PO_", "PORO": "http://purl.obolibrary.org/obo/PORO_", "PPO": "http://purl.obolibrary.org/obo/PPO_", @@ -342,7 +343,9 @@ "agricola": "https://agricola.nal.usda.gov/vwebv/holdingsInfo?bibId=", "agrkb": "https://www.alliancegenome.org/accession/", "agrovoc": "http://aims.fao.org/aos/agrovoc/", + "agsc": "https://scicrunch.org/resolver/RRID:AGSC_", "agsd": "http://www.genomesize.com/result_species.php?id=", + "aio": "https://w3id.org/aio/", "alfred": "https://alfred.med.yale.edu/alfred/recordinfo.asp?UNID=", "allergome": "http://www.allergome.org/script/dettaglio.php?id_molecule=", "alzforum.mutation": "https://www.alzforum.org/mutations/", @@ -379,14 +382,16 @@ "atfdb.family": "http://www.bioguo.org/AnimalTFDB/family.php?fam=", "atol": "http://opendata.inra.fr/ATOL/ATOL_", "autdb": "http://autism.mindspec.org/GeneDetail/", + "babelon": "https://w3id.org/babelon/", "bacdive": "https://bacdive.dsmz.de/strain/", "bacmap.biog": "http://bacmap.wishartlab.com/organisms/", "bacmap.map": "https://identifiers.org/bacmap.map:", "bactibase": "http://bactibase.hammamilab.org/", - "bao": "http://bioportal.bioontology.org/ontologies/BAO/bao:BAO_", - "bartoc": "https://bartoc.org/en/node/", + "bao": "http://www.bioassayontology.org/bao#BAO_", + "bartoc": "http://bartoc.org/en/node/", "bbkg": "https://bbp.epfl.ch/nexus/web/studios/public/", "bbtp": "https://bbp.epfl.ch/nexus/web/studios/public/topological-sampling/studios/data:", + "bcbc": "https://scicrunch.org/resolver/RRID:BCBC_", "bcio": "https://w3id.org/BCI-ontology#", "bcrc": "https://catalog.bcrc.firdi.org.tw/BcrcContent?bid=", "bcrj": "http://bcrj.org.br/celula/", @@ -421,6 +426,7 @@ "bionumbers": "https://bionumbers.hms.harvard.edu/bionumber.aspx?id=", "biopixie": "http://avis.princeton.edu/pixie/viewgraph.php?graphID=", "bioportal": "http://bioportal.bioontology.org/ontologies/", + "bioproject": "https://www.ncbi.nlm.nih.gov/bioproject/?term=", "bioregistry": "https://bioregistry.io/registry/", "bioregistry.collection": "https://bioregistry.io/collection/", "bioregistry.registry": "https://bioregistry.io/metaregistry/", @@ -453,6 +459,7 @@ "cadsr": "https://identifiers.org/cadsr:", "caloha": "https://www.nextprot.org/term/", "cameo": "https://www.cameo3d.org/sp/targets/target/", + "cao": "http://champ-project.org/images/ontology/cao.owl#CAO_", "caps": "http://www.bioinsilico.org/cgi-bin/CAPSDB/getCAPScluster?nidcl=", "cas": "https://commonchemistry.cas.org/detail?cas_rn=", "casspc": "https://researcharchive.calacademy.org/research/ichthyology/catalog/fishcatget.asp?spid=", @@ -461,10 +468,12 @@ "cazy": "https://identifiers.org/cazy:", "cba": "https://europepmc.org/article/CBA/", "cbioportal": "https://www.cbioportal.org/study/summary?id=", + "cc": "https://creativecommons.org/ns#", "ccdc": "https://identifiers.org/ccdc:", "ccds": "http://www.ncbi.nlm.nih.gov/CCDS/CcdsBrowse.cgi?REQUEST=CCDS&DATA=", + "ccf": "http://purl.org/ccf/", "ccle": "https://www.cbioportal.org/patient?studyId=ccle_broad_2019&caseId=", - "cco": "https://www.ebi.ac.uk/ols/ontologies/cco/terms?obo_id=CCO:", + "cco": "https://www.ebi.ac.uk/ols4/ontologies/cco/terms?obo_id=CCO:", "ccrid": "http://www.cellresource.cn/cellsearch.aspx?sc=1&where=", "cdd": "https://www.ncbi.nlm.nih.gov/Structure/cdd/cddsrv.cgi?uid=", "cdpd": "http://webprod3.hc-sc.gc.ca/dpd-bdpp/info.do?lang=eng&code=", @@ -501,7 +510,7 @@ "clb": "https://www.checklistbank.org/dataset/", "cldb": "https://identifiers.org/cldb:", "clingene": "https://reg.clinicalgenome.org/redmine/projects/registry/genboree_registry/by_caid?caid=", - "clinicaltrials": "https://clinicaltrials.gov/ct2/show/", + "clinicaltrials": "https://www.clinicaltrials.gov/study/", "clinvar": "https://www.ncbi.nlm.nih.gov/clinvar/variation/", "clinvar.record": "http://www.ncbi.nlm.nih.gov/clinvar/", "clinvar.submission": "http://www.ncbi.nlm.nih.gov/clinvar?term=", @@ -548,6 +557,7 @@ "cstr": "https://cstr.cn/", "ctis": "https://euclinicaltrials.eu/app/#/view/", "cubedb": "https://identifiers.org/cubedb:", + "cvx": "https://biopragmatics.github.io/providers/cvx/", "d1id": "https://identifiers.org/d1id:", "dailymed": "https://dailymed.nlm.nih.gov/dailymed/drugInfo.cfm?setid=", "dandi": "https://dandiarchive.org/dandiset/", @@ -574,17 +584,20 @@ "dctypes": "http://purl.org/dc/dcmitype/", "ddinter.drug": "http://ddinter.scbdd.com/ddinter/drug-detail/", "ddinter.interaction": "http://ddinter.scbdd.com/ddinter/interact/", + "debio": "https://biopragmatics.github.io/debio/", "decipher": "https://www.deciphergenomics.org/syndrome/", "degradome": "http://degradome.uniovi.es/cgi-bin/protease/", "depmap": "https://depmap.org/portal/cell_line/", "dermo": "http://purl.obolibrary.org/obo/DERMO_", "dev.ga4ghdos": "https://dos-gdc.ucsc-cgp-dev.org/ga4gh/dos/v1/dataobjects/", + "devtox": "https://www.devtox.org/nomenclature/ml_manus.php?mno=", "dg.4503": "https://gen3.biodatacatalyst.nhlbi.nih.gov/ga4gh/drs/v1/objects/", "dg.4dfc": "https://nci-crdc.datacommons.io/ga4gh/drs/v1/objects/", "dg.6vts": "https://jcoin.datacommons.io/ga4gh/drs/v1/objects/", "dg.anv0": "https://gen3.theanvil.io/ga4gh/drs/v1/objects/", "dg.f82a1a": "https://data.kidsfirstdrc.org/ga4gh/drs/v1/objects/", "dg5b0d": "https://data.bloodpac.org/ga4gh/drs/v1/objects/", + "dggr": "https://kyotofly.kit.jp/cgi-bin/stocks/search_res_det.cgi?DB_NUM=1&DG_NUM=", "dgrc": "https://dgrc.bio.indiana.edu/product/View?product=", "dicom": "http://dicom.nema.org/resources/ontology/DCM/", "dictybase": "http://dictybase.org/gene/", @@ -596,6 +609,7 @@ "dlxb": "https://doulix.com/biomodules/", "dlxc": "https://doulix.com/constructs/", "doap": "http://usefulinc.com/ns/doap#", + "doi": "http://dx.doi.org/", "dommino": "http://orion.rnet.missouri.edu/~nz953/DOMMINO/index.php/result/show_network/", "door": "http://csbl.bmb.uga.edu/DOOR/operon.php?id=", "doqcs.model": "http://doqcs.ncbs.res.in/template.php?&y=accessiondetails&an=", @@ -607,11 +621,15 @@ "dragondb.protein": "https://identifiers.org/dragondb.protein:", "drduke": "https://phytochem.nal.usda.gov/phytochem/chemicals/show/", "drks": "https://drks.de/search/en/trial/", + "drsanv0": "https://data.terra.bio/ga4gh/drs/v1/objects/", "drsc": "http://www.flyrnai.org/cgi-bin/RNAi_gene_lookup_public.pl?gname=", "drugbank": "http://www.drugbank.ca/drugs/", + "drugbank.bioentity": "https://go.drugbank.com/bio_entities/", "drugbank.category": "https://www.drugbank.ca/categories/", + "drugbank.condition": "https://go.drugbank.com/indications/", + "drugbank.metabolite": "https://go.drugbank.com/metabolites/", + "drugbank.reaction": "https://go.drugbank.com/reactions/", "drugbank.salt": "https://go.drugbank.com/salts/", - "drugbankv4.target": "http://www.drugbank.ca/biodb/bio_entities/", "drugcentral": "http://drugcentral.org/drugcard/", "dsmz": "https://www.dsmz.de/collection/catalogue/details/culture/", "dso": "https://www.datascienceontology.org/concept/", @@ -634,7 +652,7 @@ "ecyano.experiment": "https://www.e-cyanobacterium.org/experiments-repository/?action=detail&id=", "ecyano.model": "https://e-cyanobacterium.org/models/model/", "ecyano.rule": "https://e-cyanobacterium.org/bcs/rule/", - "edam": "https://www.ebi.ac.uk/ols/ontologies/edam/terms?iri=http://edamontology.org/", + "edam": "http://edamontology.org/", "edam.data": "http://edamontology.org/data_", "edam.format": "http://edamontology.org/format_", "edam.operation": "http://edamontology.org/operation_", @@ -650,7 +668,6 @@ "emolecules": "https://reaxys.emolecules.com/cgi-bin/more?vid=", "empiar": "https://www.ebi.ac.uk/pdbe/emdb/empiar/entry/", "emsl.project": "https://www.emsl.pnnl.gov/project/", - "ena.embl": "https://www.ebi.ac.uk/ena/browser/view/", "encode": "https://www.encodeproject.org/", "enm": "http://purl.enanomapper.org/onto/ENM_", "ensembl.metazoa": "https://metazoa.ensembl.org/id/", @@ -680,6 +697,7 @@ "fairsharing.organization": "https://fairsharing.org/organisations/", "fairsharing.user": "https://fairsharing.org/users/", "faldo": "http://biohackathon.org/resource/faldo#", + "fao.asfis": "https://www.fao.org/fishery/en/species/", "fbol": "https://identifiers.org/fbol:", "fbrf": "https://flybase.org/reports/FBrf", "fbtc": "https://flybase.org/reports/FBtc", @@ -764,6 +782,7 @@ "goldbook": "http://dx.doi.org/10.1351/goldbook.", "google.book": "https://books.google.com/books?id=", "google.patent": "https://www.google.com/patents/", + "gorel": "http://purl.obolibrary.org/obo/GOREL_", "gpcrdb": "https://gpcrdb.org/protein/", "gpcrnava": "http://nava.liacs.nl/cgi-bin/nava.py?id=", "gpmdb": "http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=", @@ -796,8 +815,10 @@ "hathitrust": "https://catalog.hathitrust.org/Record/", "hbvar": "http://globin.bx.psu.edu/cgi-bin/hbvar/query_vars3?mode=output&display_format=page&i=", "hc.npn": "http://webprod.hc-sc.gc.ca/nhpid-bdipsn/ingredReq.do?id=", + "hc.trial": "https://health-products.canada.ca/ctdb-bdec/brand/?submissionNo=", "hcpcs": "http://purl.bioontology.org/ontology/HCPCS/", "hcvdb": "https://euhcvdb.ibcp.fr/euHCVdb/do/displayHCVEntry?primaryAC=", + "hdl": "http://hdl.handle.net/", "hdr": "http://research.nhgri.nih.gov/apps/homeodomain/web/index.cgi?mode=view&view=proteins&id=", "hgmd": "http://www.hgmd.cf.ac.uk/ac/gene.php?gene=", "hgnc": "https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/", @@ -814,6 +835,7 @@ "hms.lincs.cell": "https://lincs.hms.harvard.edu/db/cells/", "hms.lincs.compound": "https://lincs.hms.harvard.edu/db/sm/", "hms.lincs.dataset": "https://lincs.hms.harvard.edu/db/datasets/", + "hoelzel": "https://www.hoelzel-biotech.com/de/catalogsearch/result/?q=", "hog": "https://biopragmatics.github.io/providers/hog/", "hogenom": "http://pbil.univ-lyon1.fr/cgi-bin/view-tree.pl?db=HOGENOM5&query=", "hoip": "http://purl.bioontology.org/ontology/HOIP/HOIP_", @@ -842,6 +864,7 @@ "icepo": "https://biopragmatics.github.io/providers/icepo/", "icf": "http://id.who.int/icd/entity/", "iclc": "http://www.iclc.it/details/det_list.php?line_id=", + "icldb": "https://entomology.ca.uky.edu/content/", "ideal": "http://idp1.force.cs.is.nagoya-u.ac.jp/IDEAL/ideal.php?id=", "idocovid19": "http://purl.obolibrary.org/obo/COVIDO_", "idoden": "http://purl.bioontology.org/ontology/IDODEN_", @@ -861,6 +884,9 @@ "imgt.hla": "https://www.ebi.ac.uk/cgi-bin/imgt/hla/get_allele.cgi?", "imgt.ligm": "http://www.imgt.org/ligmdb/view?id=", "imotdb": "http://caps.ncbs.res.in/cgi-bin/mini/databases/imotdb/imotdb.cgi?sfcode=", + "imsr.apb": "https://pb.apf.edu.au/phenbank/strain.html?id=", + "imsr_em": "https://www.infrafrontier.eu/emma/strain-search/straindetails/?q=", + "imsr_tac": "https://scicrunch.org/resolver/RRID:IMSR_TAC_", "inaturalist.observation": "https://www.inaturalist.org/observations/", "inaturalist.place": "https://www.inaturalist.org/places/", "inaturalist.taxon": "https://www.inaturalist.org/taxa/", @@ -870,6 +896,7 @@ "inn": "https://mednet-communities.net/inn/db/ViewINN.aspx?i=", "innatedb": "http://www.innatedb.ca/getGeneCard.do?id=", "insdc": "https://www.ncbi.nlm.nih.gov/nuccore/", + "insdc.run": "https://www.ebi.ac.uk/ena/browser/view/", "insdc.sra": "https://www.ncbi.nlm.nih.gov/sra/", "intact": "https://www.ebi.ac.uk/intact/interaction/", "intact.molecule": "https://www.ebi.ac.uk/intact/search?query=", @@ -887,7 +914,7 @@ "isrctn": "https://www.isrctn.com/", "issn": "https://portal.issn.org/resource/ISSN/", "itis": "https://www.itis.gov/servlet/SingleRpt/SingleRpt?search_topic=TSN&search_value=", - "ito": "https://bioportal.bioontology.org/ontologies/ITO/?p=classes&conceptid=https://identifiers.org/ito:", + "ito": "https://bioportal.bioontology.org/ontologies/ITO/?p=classes&conceptid=https://identifiers.org/ito:ITO_", "iuphar.family": "http://www.guidetopharmacology.org/GRAC/FamilyDisplayForward?familyId=", "iuphar.ligand": "http://www.guidetopharmacology.org/GRAC/LigandDisplayForward?ligandId=", "iuphar.receptor": "http://www.guidetopharmacology.org/GRAC/ObjectDisplayForward?objectId=", @@ -906,9 +933,11 @@ "kclb": "https://cellbank.snu.ac.kr/english/sub/catalog.php?s_cellid=464&page=detail_info&CatNo=59&strQ=", "kegg": "http://www.kegg.jp/entry/", "kegg.brite": "http://www.genome.jp/kegg-bin/get_htext?-p+/kegg/brite/br+br", + "kestrelo": "http://purl.obolibrary.org/obo/kestrelo_", "knapsack": "http://www.knapsackfamily.com/knapsack_core/information.php?word=", "langual": "https://www.langual.org/langual_thesaurus.asp?termid=", "lbo": "http://purl.obolibrary.org/obo/LBO_", + "lcsh": "http://id.loc.gov/authorities/names/", "lei": "https://www.gleif.org/lei/", "lgai.cede": "https://s3.us-east-2.amazonaws.com/lg.cede/", "lgic": "https://identifiers.org/lgic:", @@ -934,7 +963,9 @@ "lrg": "https://identifiers.org/lrg:", "lspci": "https://labsyspharm.github.io/lspci/", "lter": "https://vocab.lternet.edu/vocab/vocab/index.php?tema=", + "m4i": "http://w3id.org/nfdi4ing/metadata4ing#", "macie": "https://www.ebi.ac.uk/thornton-srv/databases/cgi-bin/MACiE/entry/getPage.pl?id=", + "maggot": "https://pmb-bordeaux.fr/maggot/metadata/", "maizegdb.locus": "http://www.maizegdb.org/cgi-bin/displaylocusrecord.cgi?id=", "mampol": "http://mampol.uab.es/cgi-bin/MamPol_s2.pl?Accession=", "massbank": "https://massbank.jp/RecordDisplay?id=", @@ -945,6 +976,9 @@ "mdm": "https://medical-data-models.org/forms/", "meddra": "http://purl.bioontology.org/ontology/MDRFRE/", "medgen": "https://www.ncbi.nlm.nih.gov/medgen/", + "mediadive.ingredient": "https://mediadive.dsmz.de/ingredients/", + "mediadive.medium": "https://mediadive.dsmz.de/medium/", + "mediadive.solution": "https://mediadive.dsmz.de/solutions/", "medlineplus": "https://identifiers.org/medlineplus:", "merops.clan": "https://www.ebi.ac.uk/merops/cgi-bin/clansum?clan=", "merops.entry": "https://www.ebi.ac.uk/merops/cgi-bin/pepsum?id=", @@ -982,7 +1016,7 @@ "miriam.collection": "https://www.ebi.ac.uk/miriam/main/", "miriam.resource": "https://www.ebi.ac.uk/miriam/main/resources/", "mirnest": "http://rhesus.amu.edu.pl/mirnest/copy/details.php?id=", - "mirtarbase": "http://mirtarbase.mbc.nctu.edu.tw/php/detail.php?mirtid=", + "mirtarbase": "https://mirtarbase.cuhk.edu.cn/~miRTarBase/miRTarBase_2022/php/detail.php?mirtid=", "mixs": "https://w3id.org/mixs/", "mlc": "https://www.mlcommons.org/mlc-id/", "mmdb": "http://www.ncbi.nlm.nih.gov/Structure/mmdb/mmdbsrv.cgi?uid=", @@ -993,7 +1027,7 @@ "mmp.ref": "https://mmp.sfb.uit.no/databases/marref/#/records/", "mmrrc": "http://www.mmrrc.org/catalog/getSDS.php?mmrrc_id=", "mmsinc": "http://mms.dsfarm.unipd.it/mmsinc/search/molecule.php?mmscode=", - "modeldb": "http://senselab.med.yale.edu/ModelDB/ShowModel.asp?model=", + "modeldb": "https://modeldb.science/", "modeldb.concept": "https://senselab.med.yale.edu/ModelDB/ModelList?id=", "molbase": "http://www.molbase.com/en/index.php?app=search&search_keyword=", "molmedb": "https://molmedb.upol.cz/mol/", @@ -1005,6 +1039,7 @@ "msio": "http://purl.obolibrary.org/obo/MSIO_", "mtbd": "http://tumor.informatics.jax.org/mtbwi/strainDetails.do?key=", "multicellds": "http://multicellds.org/MultiCellDB/", + "mvx": "https://phinvads.cdc.gov/vads/ViewCodeSystemConcept.action?oid=2.16.840.1.113883.12.227&code=", "mw.project": "http://www.metabolomicsworkbench.org/data/DRCCMetadata.php?Mode=Project&ProjectID=", "mw.study": "http://www.metabolomicsworkbench.org/data/DRCCMetadata.php?Mode=Study&StudyID=", "myco.lepra": "http://mycobrowser.epfl.ch/leprosysearch.php?gene+name=", @@ -1013,6 +1048,7 @@ "myco.tuber": "http://tuberculist.epfl.ch/quicksearch.php?gene+name=", "mycobank": "http://www.mycobank.org/Biolomics.aspx?Table=Mycobank&MycoBankNr_=", "mzspec": "http://proteomecentral.proteomexchange.org/usi/?usi=mzspec:", + "nando": "https://nanbyodata.jp/disease/NANDO:", "napdi": "https://repo.napdi.org/study/", "napp": "http://rna.igmors.u-psud.fr/NAPP/Niveau2.php?specie=", "narcis": "http://www.narcis.nl/publication/RecordID/", @@ -1021,10 +1057,12 @@ "nbrc": "http://www.nbrc.nite.go.jp/NBRC2/NBRCCatalogueDetailServlet?ID=NBRC&CAT=", "ncats.bioplanet": "https://tripod.nih.gov/bioplanet/detail.jsp?pid=bioplanet_", "ncats.drug": "https://drugs.ncats.io/drug/", - "ncbi.assembly": "https://www.ncbi.nlm.nih.gov/assembly/", + "ncbi.assembly": "https://www.ncbi.nlm.nih.gov/datasets/genome/", "ncbi.genome": "https://www.ncbi.nlm.nih.gov/genome/", "ncbi.resource": "https://bioregistry.io/metaregistry/ncbi/", "ncbibook": "https://www.ncbi.nlm.nih.gov/books/", + "ncbidrs": "https://locate.be-md.ncbi.nlm.nih.gov/ga4gh/drs/v1/objects/", + "nci.drug": "https://www.cancer.gov/publications/dictionaries/cancer-drug/def/", "ncim": "http://ncim.nci.nih.gov/ncimbrowser/ConceptReport.jsp?dictionary=NCI%20MetaThesaurus&code=", "ndc": "http://www.hipaaspace.com/Medical_Billing/Coding/National.Drug.Codes/", "nddf": "http://purl.bioontology.org/ontology/NDDF/", @@ -1042,13 +1080,15 @@ "nextdb": "http://nematode.lab.nig.ac.jp/db2/ShowCloneInfo.php?clone=", "nextprot": "https://www.nextprot.org/db/entry/", "nextprot.family": "https://www.nextprot.org/term/FA-", - "nfdi4chem.cao": "http://champ-project.org/images/ontology/cao.owl#CAO_", "ngl": "https://genelab-data.ndc.nasa.gov/genelab/accession/", "nhcdr": "https://stemcells.nindsgenetics.org?line=", "niaest": "http://lgsun.grc.nia.nih.gov/cgi-bin/pro3?sname1=", + "niaid.chemdb": "http://chemdb.niaid.nih.gov/CompoundDetails.aspx?AIDSNO=", "nif.ext": "http://uri.neuinfo.org/nif/nifstd/nifext_", "nif.std": "http://uri.neuinfo.org/nif/nifstd/", + "nihhesc": "https://grants.nih.gov/stem_cells/registry/current.htm?ID=", "nihreporter.project": "https://reporter.nih.gov/project-details/", + "nist.codata": "http://physics.nist.gov/cgi-bin/cuu/Value?", "nkos": "http://w3id.org/nkos/", "nlfff": "http://database.deepsolar.space:18080/dbs/nlfff/", "nlm": "https://www.ncbi.nlm.nih.gov/nlmcatalog/", @@ -1065,10 +1105,11 @@ "nlx.qual": "http://uri.neuinfo.org/nif/nifstd/nlx_qual_", "nlx.res": "http://uri.neuinfo.org/nif/nifstd/nlx_res_", "nlx.sub": "http://uri.neuinfo.org/nif/nifstd/nlx_subcell_", - "nmdc": "https://drs.microbiomedata.org/objects/", + "nmdc": "https://w3id.org/nmdc/", "nmpdr": "http://www.nmpdr.org/FIG/wiki/rest.cgi/NmpdrPlugin/SeedViewer?page=Annotation;feature=", "nmrshiftdb2": "https://nmrshiftdb.nmr.uni-koeln.de/molecule/", "noaa": "https://www.fisheries.noaa.gov/species/", + "noaa.cameo": "https://cameochemicals.noaa.gov/chemical/", "noncodev3": "http://www.noncode.org/NONCODERv3/ncrna.php?ncid=", "noncodev4.gene": "http://www.bioinfo.org/NONCODEv4/show_gene.php?id=", "noncodev4.rna": "http://www.bioinfo.org/NONCODEv4/show_rna.php?id=", @@ -1078,8 +1119,10 @@ "nsc": "https://dtp.cancer.gov/dtpstandard/servlet/ChemData?searchtype=NSC&searchlist=", "nsf.award": "https://www.nsf.gov/awardsearch/showAward?AWD_ID=", "nucleardb": "http://www.receptors.org/nucleardb/proteins/", + "nxr": "https://scicrunch.org/resolver/RRID:NXR_", "oa": "http://www.w3.org/ns/oa#", "oban": "http://purl.org/oban/", + "obo": "http://purl.obolibrary.org/obo/", "oboInOwl": "http://www.geneontology.org/formats/oboInOwl#", "obv": "https://permalink.obvsg.at/", "occ": "https://w3id.org/oc/corpus/", @@ -1102,15 +1145,16 @@ "omim.ps": "https://omim.org/MIM:PS", "omop": "https://athena.ohdsi.org/search-terms/terms/", "oncotree": "http://oncotree.mskcc.org/api/tumorTypes/search/code/", + "ontie": "https://ontology.iedb.org/ontology/ONTIE_", "opb": "https://bioportal.bioontology.org/ontologies/OPB/?p=classes&conceptid=http%3A%2F%2Fbhi.washington.edu%2FOPB%23OPB_", "openalex": "https://openalex.org/", + "openwemi": "https://dcmi.github.io/openwemi/ns#", "opm": "http://opm.phar.umich.edu/protein.php?pdbid=", "orcid": "https://orcid.org/", "ordb": "http://senselab.med.yale.edu/ORDB/Data/", "oridb.sacch": "http://cerevisiae.oridb.org/details.php?id=", "oridb.schizo": "http://pombe.oridb.org/details.php?id=", "orphanet": "http://www.orpha.net/consor/cgi-bin/OC_Exp.php?Lng=EN&Expert=", - "orphanet.ordo": "http://www.orpha.net/ORDO/Orphanet_", "orth": "http://purl.org/net/orth#", "oryzabase.gene": "http://www.shigen.nig.ac.jp/rice/oryzabaseV4/gene/detail/", "oryzabase.mutant": "http://www.shigen.nig.ac.jp/rice/oryzabaseV4/strain/inducedMutationLine/detail/", @@ -1149,6 +1193,7 @@ "peptideatlas.dataset": "http://www.peptideatlas.org/PASS/", "perkinelmer": "https://www.perkinelmer.com/searchresult?searchName=", "peroxibase": "http://peroxibase.toulouse.inra.fr/browse/process/view_perox.php?id=", + "pesticideinfo": "https://www.pesticideinfo.org/chemical/", "pfam": "https://www.ebi.ac.uk/interpro/entry/pfam/", "pfam.clan": "https://www.ebi.ac.uk/interpro/set/pfam/", "pfr": "http://repository.topdownproteomics.org/proteoforms/", @@ -1167,6 +1212,7 @@ "phosphopoint.protein": "https://identifiers.org/phosphopoint.protein:", "phosphosite.protein": "http://www.phosphosite.org/proteinAction.do?id=", "phosphosite.residue": "http://www.phosphosite.org/siteAction.do?id=", + "phrr": "https://registry.healthresearch.ph/index.php/registry?view=research&layout=details&cid=", "phylomedb": "http://phylomedb.org/?seqid=", "phytozome.locus": "http://www.phytozome.net/genePage.php?crown&method=0&search=1&detail=1&searchText=locusname:", "pibase": "http://modbase.compbio.ucsf.edu/pibase-cgi/get_details.pl?object_type=complexes&bdp_id=", @@ -1214,7 +1260,6 @@ "pubchem.substance": "http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID", "publons.publication": "https://publons.com/publon/", "publons.researcher": "https://publons.com/researcher/", - "pubmed": "http://rdf.ncbi.nlm.nih/pubmed/", "px": "http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=", "pypi": "https://pypi.org/project/", "qb": "http://purl.org/linked-data/cube#", @@ -1228,6 +1273,7 @@ "rbk": "https://www.rebuildingakidney.org/id/", "rcb": "https://cellbank.brc.riken.jp/cell_bank/CellInfo/?cellNo=", "rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#", + "rdfa": "http://www.w3.org/ns/rdfa#", "rdfs": "http://www.w3.org/2000/01/rdf-schema#", "rdo": "http://www.semanticweb.org/mca/ontologies/2018/8/untitled-ontology-47#", "re3data": "https://www.re3data.org/repository/", @@ -1266,6 +1312,7 @@ "rouge": "https://www.kazusa.or.jp/rouge/gfpage/", "rpcec": "https://rpcec.sld.cu/en/trials/", "rrid": "https://scicrunch.org/resolver/RRID:", + "rrrc": "https://www.rrrc.us/Strain/?x=", "runbiosimulations": "https://run.biosimulations.org/simulations/", "rxnorm": "https://mor.nlm.nih.gov/RxNav/search?searchBy=RXCUI&searchTerm=", "s_mart_db": "http://smartdb.bioinf.med.uni-goettingen.de/cgi-bin/SMARtDB/getSMAR.cgi?", @@ -1319,7 +1366,7 @@ "sigmaaldrich": "https://www.sigmaaldrich.com/US/en/product/sigma/", "signaling-gateway": "http://www.signaling-gateway.org/molecule/query?afcsid=", "signor": "https://signor.uniroma2.it/relation_result.php?id=", - "sio": "https://www.ebi.ac.uk/ols/ontologies/sio/terms?short_form=", + "sio": "https://www.ebi.ac.uk/ols4/ontologies/sio/terms?short_form=", "sisu": "http://search.sisuproject.fi/#/variant/", "sitex": "http://www-bionet.sscc.ru/sitex/index.php?siteid=", "skip": "https://skip.stemcellinformatics.org/SKIPSearch/cell_line_detail?accession=", @@ -1329,9 +1376,8 @@ "slkbase": "https://sumlineknowledgebase.com/?page_id=", "smart": "http://smart.embl-heidelberg.de/smart/do_annotation.pl?DOMAIN=", "smid": "https://smid-db.org/smid/", - "smiles": "https://chemapps.stolaf.edu/jmol/jmol.php?model=", "smpdb": "https://smpdb.ca/view/", - "snap": "http://snap.humgen.au.dk/views/geneview.cgi?gene=", + "snap": "http://www.ifomis.org/bfo/1.1/snap#", "snornabase": "http://www-snorna.biotoul.fr/plus.php?id=", "snp500cancer": "http://snp500cancer.nci.nih.gov/snp.cfm?both_snp_id=", "soybase": "http://www.soybase.org/sbt/search/search_results.php?category=SNP&search_term=", @@ -1378,6 +1424,7 @@ "tigrfam": "https://www.ncbi.nlm.nih.gov/cdd?term=", "time": "http://www.w3.org/2006/time#", "tngb": "http://biobanknetwork.telethon.it/Sample/View?sampleId=", + "togovar": "https://grch38.togovar.org/variant/", "tol": "http://tolweb.org/", "topdb": "http://topdb.enzim.hu/?m=show&id=", "toxoplasma": "http://toxodb.org/toxo/showRecord.do?name=GeneRecordClasses.GeneRecordClass&source_id=", @@ -1386,9 +1433,11 @@ "tred": "http://rulai.cshl.edu/cgi-bin/TRED/tred.cgi?process=geneInfo&gid=", "treebase": "https://identifiers.org/treebase:", "treefam": "http://www.treefam.org/family/", + "tricdb": "http://biomeddb.org/Disease/Details?DISEASEID=", "trichdb": "http://trichdb.org/trichdb/showRecord.do?name=GeneRecordClasses.GeneRecordClass&source_id=", "tritrypdb": "http://tritrypdb.org/tritrypdb/showRecord.do?name=GeneRecordClasses.GeneRecordClass&source_id=", "trnadbce": "http://trna.nagahama-i-bio.ac.jp/cgi-bin/trnadb/whole_detail.cgi?SID=", + "tsc": "https://tetrahymena.vet.cornell.edu/display.php?stockid=", "ttd.drug": "http://bidd.nus.edu.sg/group/TTD/ZFTTDDRUG.asp?ID=", "ttd.target": "http://bidd.nus.edu.sg/group/TTD/ZFTTDDetail.asp?ID=", "ubio.namebank": "http://www.ubio.org/browser/details.php?namebankID=", @@ -1449,6 +1498,7 @@ "vmhgene": "https://www.vmh.life/#gene/", "vmhmetabolite": "https://www.vmh.life/#metabolite/", "vmhreaction": "https://www.vmh.life/#reaction/", + "voc4cat": "https://w3id.org/nfdi4cat/voc4cat_", "void": "http://rdfs.org/ns/void#", "vsmo": "http://purl.obolibrary.org/obo/VSMO_", "vso": "https://bioportal.bioontology.org/ontologies/VSO/?p=classes&conceptid=http%3A%2F%2Fpurl.obolibrary.org%2Fobo%2FVSO_", @@ -1465,6 +1515,7 @@ "worldavatar.kin": "http://www.theworldavatar.com/ontology/ontokin/OntoKin.owl#", "wormpep": "https://www.wormbase.org/db/seq/protein?name=", "worms": "http://www.marinespecies.org/aphia.php?p=taxdetails&id=", + "wos": "https://www.webofscience.com/wos/woscc/full-record/WOS:", "wwf.ecoregion": "https://www.worldwildlife.org/ecoregions/", "xenbase": "https://www.xenbase.org/entry/", "ximbio": "https://ximbio.com/reagent/", diff --git a/src/__init__.py b/src/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/src/database/sparql_implementation.py b/src/database/sparql_implementation.py index fecd132..40292d8 100644 --- a/src/database/sparql_implementation.py +++ b/src/database/sparql_implementation.py @@ -9,10 +9,18 @@ from sssom_schema import SSSOM, Mapping, MappingSet from ..models import SearchEntity -from ..utils import compress_uri, expand_uri, parse_fields_type, sci2dec +from ..utils import compress_uri, expand_uri, parse_fields_type class SparqlImpl(SparqlImplementation): + MIN_FIELDS = [ + "uuid", + "subject_id", + "predicate_id", + "object_id", + "mapping_justification", + "confidence" + ] def __post_init__(self, schema_view): super(SparqlImplementation, self).__post_init__() self.schema_view = schema_view @@ -36,39 +44,74 @@ def get_slot_uri(self, field: str) -> str: def default_query( self, type: str, - slots: set[str], + slots: Union[set[str], None] = None, subject: Union[str, None] = None, fields: Union[dict, None] = None, inverse: bool = False, + query_min: bool = False, ) -> SparqlQuery: query = SparqlQuery( select=["*"], where=[], ) + # Add Blazegraph optimization query hint + query.where.append("hint:Query hint:optimizer 'Static'") + if subject is None: subject = "?_x" else: subject = f"<{subject}>" - query.where.append( + query.where = query.where + [ f"{subject} {self.value_to_sparql(RDF.type)} {self.value_to_sparql(type)}" - ) + ] - for f in slots: - f_uri = self.get_slot_uri(f) - opt = f"OPTIONAL {{ {subject} <{f_uri}> ?{f} }}" - query.where.append(opt) + if query_min: + for field in self.MIN_FIELDS: + f_uri = self.get_slot_uri(field) + opt = f"{subject} <{f_uri}> ?{field}" + query.where.append(opt) + else: + query.where = query.where + [ + f"OPTIONAL {{ {subject} <{self.get_slot_uri(slot)}> ?{slot} }}" + for slot in slots if slot not in self.MIN_FIELDS # type: ignore + ] + + # if fields is not None: + # fields_query = [] + # for field, _ in fields.items(): + # fields_query.append(f"{subject} <{self.get_slot_uri(field)}> ?{field}") + # query.where = query.where + fields_query + + # if not query_min: + # query.add_filter( + # f"""?p NOT IN ( + # {', '.join( + # [ + # self.value_to_sparql(self.get_slot_uri(pred)) + # for pred in self.MIN_FIELDS + # ] + + # [self.value_to_sparql(RDF.type)] + # ) + # })""") if fields is not None: for field, values in fields.items(): if field == "mapping_set": - filter = self.value_to_sparql(self.get_slot_uri(field)) + filter_value = self.value_to_sparql(self.get_slot_uri(field)) if inverse: - query.where.append(f"OPTIONAL {{ ?{field} {filter} {subject} }}") + query.where.append(f"OPTIONAL {{ ?{field} {filter_value} {subject} }}") + continue - if values is not None: - values = list(map(lambda x: self.value_to_sparql(x), values)) + if field == "confidence" and query_min: + query.add_filter( + f'STR(?{field}) >= "{values["min"]}" && STR(?{field}) <= "{values["max"]}"' + ) + continue + + if values is not None and query_min: + values = [self.value_to_sparql(x) for x in values] query.add_filter(f'?{field} IN ( {", ".join(values)})') return query @@ -100,7 +143,7 @@ def transform_result(self, row: dict) -> dict: if v["value"] == "None": result[k] = None elif "confidence" in k: - result["confidence"] = sci2dec(v["value"]) + result["confidence"] = float(v["value"]) else: result[k] = v["value"] return result @@ -146,11 +189,27 @@ def get_mappings_by_field(self, fields: dict) -> Iterable[dict]: fields_list, fields_single = self._get_fields( slots_type=self.schema_view.mapping_slots.copy() ) - default_query = self.default_query( - type=Mapping.class_class_uri, slots=fields_single.union(fields_list), fields=fields + query_min = self.default_query( + type=Mapping.class_class_uri, + fields=fields, + query_min=True ) - bindings = self._query(default_query) - results = self.merge_objects(bindings, fields_list) + bindings_min = self._sparql_query(query_min) + results = [] + if bindings_min: + bindings_total = bindings_min.copy() + for i, mapping in enumerate(bindings_min): + mapping_uri = mapping["_x"]["value"] + query_full = self.default_query( + type=Mapping.class_class_uri, + subject=mapping_uri, + slots=fields_single.union(fields_list), + fields=fields, + ) + bindings_full = self._sparql_query(query_full) + for results in bindings_full: + bindings_total[i] = {**bindings_total[i], **results} + results = self.merge_objects(bindings_total, fields_list) for row in results: row.pop("_x") yield row @@ -183,14 +242,19 @@ def get_sssom_mappings_by_curie(self, search_filter: SearchEntity) -> Iterable[M def get_ui_mappings_by_curie(self, search_filter: SearchEntity) -> Iterable[dict]: filters = search_filter.dict() - curies = filters.pop("curies") + if filters["mapping_justification"] is not None: + justifs = filters["mapping_justification"] + filters["mapping_justification"] = [expand_uri(justif) for justif in justifs] + + curies = filters.pop("curies") filters["subject_id"] = [expand_uri(curie) for curie in curies] bindings = self.get_mappings_by_field(filters) for row in bindings: row["subject_id_curie"] = compress_uri(row["subject_id"]) row["predicate_id_curie"] = compress_uri(row["predicate_id"]) row["object_id_curie"] = compress_uri(row["object_id"]) + row["mapping_justification_curie"] = compress_uri(row["mapping_justification"]) yield row filters.pop("subject_id") @@ -200,21 +264,37 @@ def get_ui_mappings_by_curie(self, search_filter: SearchEntity) -> Iterable[dict row["subject_id_curie"] = compress_uri(row["subject_id"]) row["predicate_id_curie"] = compress_uri(row["predicate_id"]) row["object_id_curie"] = compress_uri(row["object_id"]) + row["mapping_justification_curie"] = compress_uri(row["mapping_justification"]) yield row def get_mappings_by_filter(self, filter: Union[List[dict], None]) -> Iterable[dict]: fields_list, fields_single = self._get_fields( slots_type=self.schema_view.mapping_slots.copy() ) - default_query = self.add_filters( + query_min = self.add_filters( self.default_query( type=Mapping.class_class_uri, - slots=fields_single.union(fields_list), + query_min=True ), filter, ) - bindings = self._query(default_query) - results = self.merge_objects(bindings, fields_list) + bindings_min = self._sparql_query(query_min) + if bindings_min: + bindings_total = bindings_min.copy() + for i, mapping in enumerate(bindings_min): + mapping_uri = mapping["_x"]["value"] + query_full = self.add_filters( + self.default_query( + type=Mapping.class_class_uri, + subject=mapping_uri, + slots=fields_single.union(fields_list) + ), + filter, + ) + bindings_full = self._sparql_query(query_full) + for results in bindings_full: + bindings_total[i] = {**bindings_total[i], **results} + results = self.merge_objects(bindings_total, fields_list) for row in results: row.pop("_x") yield row @@ -239,7 +319,7 @@ def get_sssom_mapping_sets_query( default_query = self.add_filters( self.default_query(type=MappingSet.class_class_uri, slots=fields_single), filter ) - bindings = self._query(default_query) + bindings = self._sparql_query(default_query) for row in bindings: r = self.transform_result(row) # Search for multiple value attributes @@ -248,10 +328,17 @@ def get_sssom_mapping_sets_query( default_query_list = self.default_query( type=MappingSet.class_class_uri, slots={field}, subject=r["_x"] ) - bindings_list = self.transform_result_list(self._query(default_query_list)) + bindings_list = self.transform_result_list( + self._sparql_query(default_query_list) + ) r[f"{field}"] = bindings_list - r["mappings"] = {"href": request.url_for(name="mappings_by_mapping_set", id=r["uuid"])} + r["mappings"] = { + "href": request.url_for( + name="mappings_by_mapping_set", # type: ignore + id=r["uuid"], + ) + } r.pop("_x") yield r @@ -259,13 +346,21 @@ def get_mapping_by_id(self, id: str) -> dict: fields_list, fields_single = self._get_fields( slots_type=self.schema_view.mapping_slots.copy() ) - default_query = self.default_query( + query_min = self.default_query( type=Mapping.class_class_uri, - slots=fields_single.union(fields_list), subject=f"{SSSOM}{id}", + query_min=True ) - bindings = self._query(default_query) - result = self.merge_objects(bindings, fields_list)[0] + bindings_min = self._sparql_query(query_min) + query_full = self.default_query( + type=Mapping.class_class_uri, + subject=f"{SSSOM}{id}", + slots=fields_single.union(fields_list) + ) + bindings_full = self._sparql_query(query_full) + for results in bindings_full: + bindings_min[0] = {**bindings_min[0], **results} + result = self.merge_objects(bindings_min, fields_list)[0] return result @@ -282,7 +377,7 @@ def get_sssom_mappings_by_mapping_set_id(self, id: str) -> Iterable[Mapping]: fields=fields, inverse=True, ) - bindings = self._query(default_query) + bindings = self._sparql_query(default_query) for row in bindings: r = self.transform_result(row) r.pop("_x") @@ -297,7 +392,6 @@ def get_stats(self) -> dict: (COUNT(DISTINCT ?mapping) as ?nb_mapping) (COUNT(DISTINCT ?mapping_set) as ?nb_mapping_set) (COUNT(DISTINCT ?mapping_provider) as ?nb_mapping_provider) - (COUNT(DISTINCT ?entity) as ?nb_entity) """ ], where=[], @@ -305,6 +399,9 @@ def get_stats(self) -> dict: mappingset_uri = MappingSet.class_class_uri mapping_uri = Mapping.class_class_uri + # Add Blazegraph optimization query hint + query.where.append("hint:Query hint:optimizer 'Runtime'") + query.where.append( f"?mapping_set {self.value_to_sparql(RDF.type)} {self.value_to_sparql(mappingset_uri)}" ) @@ -312,9 +409,12 @@ def get_stats(self) -> dict: f"?mapping {self.value_to_sparql(RDF.type)} {self.value_to_sparql(mapping_uri)}" ) query.where.append( - f"?_x {self.value_to_sparql(self.get_slot_uri('mapping_provider'))} ?mapping_provider" + f""" + OPTIONAL {{ + ?_x {self.value_to_sparql(self.get_slot_uri('mapping_provider'))} ?mapping_provider . + }}""" ) - bindings = self._query(query) + bindings = self._sparql_query(query) results = self.transform_result(bindings[0]) # Splitting the query for efficiency (get results faster) @@ -327,7 +427,7 @@ def get_stats(self) -> dict: for pred in ["subject_id", "object_id"] ] query.where.append(" UNION ".join([f"{{ {clause} }}" for clause in clauses_entity])) - bindings = self._query(query) + bindings = self._sparql_query(query) results.update(self.transform_result(bindings[0])) return results @@ -389,6 +489,7 @@ def get_mappings_by_filter_ui( m["subject_id_curie"] = compress_uri(m["subject_id"]) m["predicate_id_curie"] = compress_uri(m["predicate_id"]) m["object_id_curie"] = compress_uri(m["object_id"]) + m["mapping_justification_curie"] = compress_uri(m["mapping_justification"]) yield m @@ -409,6 +510,7 @@ def get_ui_mapping_by_id(imp: SparqlImpl, id: str) -> dict: mapping["subject_id_curie"] = compress_uri(mapping["subject_id"]) mapping["predicate_id_curie"] = compress_uri(mapping["predicate_id"]) mapping["object_id_curie"] = compress_uri(mapping["object_id"]) + mapping["mapping_justification_curie"] = compress_uri(mapping["mapping_justification"]) return mapping diff --git a/src/models.py b/src/models.py index 6a38e24..d314a91 100644 --- a/src/models.py +++ b/src/models.py @@ -45,3 +45,4 @@ class SearchEntity(BaseModel): curies: List[str] mapping_justification: Union[List[str], None] = None predicate_id: Union[List[str], None] = None + confidence: ConfidenceInfo diff --git a/src/registry_parser.py b/src/registry_parser.py index 4b3f1a3..426fc7a 100644 --- a/src/registry_parser.py +++ b/src/registry_parser.py @@ -1,9 +1,10 @@ import argparse -import json import uuid -from typing import List, Tuple +from typing import Tuple import yaml +from pyld.jsonld import expand +from rdflib import Graph from sssom.parsers import parse_sssom_table from sssom.writers import to_json from sssom_schema import SSSOM, MappingRegistry, MappingSetReference @@ -17,6 +18,7 @@ def registry_parser(config: str) -> MappingRegistry: MappingSetReference( mapping_set_id=mapping["mapping_set_id"], mapping_set_group=mapping["mapping_set_group"], + local_name=mapping["local_name"], ) for mapping in data["mapping_set_references"] ) @@ -54,8 +56,14 @@ def update_context(input: dict) -> dict: return input -def add_uuid(input) -> dict: +def add_uuid_n_expand_curie(input) -> dict: input["@id"], input["uuid"] = generate_uuid([input["mapping_set_id"]]) + + if not input.get("mappings"): + return input + + context = get_context(input) + for mapping in input["mappings"]: mapping_key = [ mapping["subject_id"], @@ -65,30 +73,45 @@ def add_uuid(input) -> dict: ] mapping["@id"], mapping["uuid"] = generate_uuid(mapping_key) mapping["@type"] = "Mapping" + + mapping["subject_id"] = expand_curie(mapping["subject_id"], context) + mapping["object_id"] = expand_curie(mapping["object_id"], context) return input -def read_mappings(config: str) -> List[dict]: - # mappings_graph = ConjunctiveGraph() - mappings_json = [] +def get_context(input) -> dict: + return input["@context"] + + +def expand_curie(curie, context): + namespace = curie.split(":")[0] + if "http" in namespace: + return curie + return curie.replace(f"{namespace}:", context[f"{namespace}"]) + + +def read_mappings(config: str): registry = registry_parser(config) for _, mapping_set_ref in registry.mapping_set_references.items(): # type: ignore print(f"Parsing mapping_set_id {mapping_set_ref.mapping_set_id}") - # mappings_graph += to_rdf_graph(parse_sssom_table(mapping_set_ref.mapping_set_id)) - mappings_json.append( - update_context(add_uuid(to_json(parse_sssom_table(mapping_set_ref.mapping_set_id)))) + + mapping_jsonld = update_context( + add_uuid_n_expand_curie(to_json(parse_sssom_table(mapping_set_ref.mapping_set_id))) ) - return mappings_json + context = get_context(mapping_jsonld) + + g = Graph() + g.parse(data={"@graph": expand(mapping_jsonld, None)}, format="json-ld") # type: ignore + g.parse(data={"@context": context}, format="json-ld") # type: ignore + + g.serialize(f"../data/monarch/{mapping_set_ref.local_name}.ttl", format="turtle") def main(args): - mappings_graph = read_mappings(args.registry) - # mappings_graph.serialize("../data/mappings.ttl") - with open("../data/mappings.jsonld", "w", encoding="utf-8") as f: - json.dump(mappings_graph, f, ensure_ascii=False, indent=2) + read_mappings(args.registry) if __name__ == "__main__": diff --git a/src/utils.py b/src/utils.py index 325e370..08f97f9 100644 --- a/src/utils.py +++ b/src/utils.py @@ -57,8 +57,15 @@ def _create_facets(data: Iterable[object]) -> FacetInfo: iter_mj, iter_pred, iter_conf = itertools.tee(data, 3) list_iter_conf = list(iter_conf) + + if len(list_iter_conf) == 0: + return FacetInfo( + mapping_justification={}, + predicate_id={}, + confidence=ConfidenceInfo(min=0, max=1), + ) return FacetInfo( - mapping_justification=countby(lambda d: d["mapping_justification"], iter_mj), + mapping_justification=countby(lambda d: compress_uri(d["mapping_justification"]), iter_mj), predicate_id=countby(lambda d: compress_uri(d["predicate_id"]), iter_pred), confidence=ConfidenceInfo( min=min( @@ -95,11 +102,11 @@ def parser_filter( return None if field == "confidence": - value = dec2sci(float(value)) + value = float(value) if field == "subject_id" or field == "object_id": - value = expand_uri(value) + value = expand_uri(str(value)) if field == "predicate_id": - value = expand_uri(value) + value = expand_uri(str(value)) filter_pars.append({"field": field, "operator": operator, "value": value}) return filter_pars @@ -112,16 +119,6 @@ def parse_fields_type(multivalued_fields: List[str], slots: List[str]) -> Tuple[ return fields_list, fields_single -# scientific e notation to decimal notation -def sci2dec(number: str) -> float: - return float(number) - - -# decimal notation to scientific e notation -def dec2sci(number: float) -> str: - return "{:.2E}".format(float(number)) - - def expand_uri(uri: str) -> str: return str(CURIE_OBO_CONVERTER.expand(uri)) diff --git a/upload.Dockerfile b/upload.Dockerfile index b75b033..3474d49 100644 --- a/upload.Dockerfile +++ b/upload.Dockerfile @@ -1,14 +1,13 @@ -FROM yyz1989/rdf4j:latest +FROM anitacaron/blazegraph:v0.4 VOLUME /data ENV WORKSPACE=/opt/SSSOM WORKDIR /opt/SSSOM -ENV BUILD_OUTPUT=${WORKSPACE}/build.out +COPY /config/dataloader.xml /opt/SSSOM/dataloader.xml COPY process.sh /opt/SSSOM/process.sh -COPY rdf4j_sssom.txt /opt/SSSOM/rdf4j_sssom.txt RUN chmod +x /opt/SSSOM/*.sh