qlever 0.2.5__py3-none-any.whl → 0.5.41__py3-none-any.whl

qlever/Qleverfiles/Qleverfile.pubchem

@@ -0,0 +1,131 @@
+# Qleverfile for PubChem, use with the QLever CLI (`pip install qlever`)
+#
+# qlever get-data  # ~2 hours, ~120 GB, ~19 billion triples
+# qlever index     # ~6 hours, ~20 GB RAM, ~350 GB disk space (for the index)
+# qlever start     # a few seconds
+#
+# Measured on an AMD Ryzen 9 7950X with 128 GB RAM, and NVMe SSD (17.12.2024)
+#
+# NOTE 1: `qlever get-data` does not only download the PubChem RDF data, but also
+# a number of ontologies. These are very useful to obtain names for IRIs like
+# `sio:SIO_000008` or `obo:IAO_0000412` (otherwise very hard to understand).
+# The ontologies BAO and NDF-RT are occasionally updated; for latest versions,
+# see the download links at https://bioportal.bioontology.org/ontologies/BAO
+# and https://bioportal.bioontology.org/ontologies/NDF-RT .
+#
+# NOTE 2: The `MULTI_INPUT_JSON` zcats selected files together in one input
+# stream because there are too many files and the command line triggered by
+# `qlever index` would be too long otherwise.
+
+[data]
+NAME                = pubchem
+GET_DATA_URL        = ftp://ftp.ncbi.nlm.nih.gov/pubchem/RDF
+ONTOLOGIES_DIR      = RDF.ontologies
+PUBCHEM_DIR         = RDF.pubchem
+ONTOLOGIES_CSV      = ontologies.csv
+CHECK_REQUIREMENTS  = for CMD in docker parallel; do $$CMD --version >/dev/null 2>&1 || (echo "Requires \"$$CMD\", please install it"; false); done
+GET_DATA_CMD_1      = mkdir -p ${ONTOLOGIES_DIR} && cd ${ONTOLOGIES_DIR} && cat ${ONTOLOGIES_CSV} | parallel --colsep "," 'FILE={2} && URL={3} && ERRFILE=$${FILE%.*}.jena-stderr; echo "Processing $$URL ($$FILE) ..." && curl -sLRo $$FILE $$URL && docker run --rm -v $$(pwd):/data stain/jena riot --output=NT /data/$$FILE 2> $$ERRFILE | gzip -c > $${FILE%.*}.nt.gz && rm -f $$FILE; if [ -s $$ERRFILE ]; then grep -q "ERROR *riot" $$ERRFILE && echo "riot ERRORs in $$FILE, check $$ERRFILE"; else rm $$ERRFILE; fi'
+GET_DATA_CMD_2      = mkdir -p ${PUBCHEM_DIR} && wget -r -nv -nH --cut-dirs=2 --no-parent -P ${PUBCHEM_DIR} ${GET_DATA_URL}
+GET_DATA_CMD        = ${CHECK_REQUIREMENTS} && ${GET_DATA_CMD_1} 2>&1 | tee pubchem.get-data-log.txt; ${GET_DATA_CMD_2} 2>&1 | tee -a pubchem.get-data-log.txt
+VERSION             = $$(date -r void.ttl +%d.%m.%Y || echo "NO_DATE")
+DESCRIPTION         = PubChem, RDF TTL from ${GET_DATA_URL} + associated ontologies (bao, bfo, biopax-level3, chebi, cheminf, cito, dublin_core_terms, fabio, go, iao, ncit, obi, pr, ro, sio, skos, so, uo), version ${data:VERSION}
+MAKE_ONTOLOGIES_CSV = $$(mkdir -p ${ONTOLOGIES_DIR} && echo "BAO - BioAssay Ontology,bao.owl,https://data.bioontology.org/ontologies/BAO/submissions/56/download?apikey=8b5b7825-538d-40e0-9e9e-5ab9274a9aeb\nBFO - Basic Formal Ontology,bfo.owl,http://purl.obolibrary.org/obo/bfo.owl\nBioPAX - biological pathway data,bp.owl,http://www.biopax.org/release/biopax-level3.owl\nCHEMINF - Chemical Information Ontology,cheminf.owl,http://purl.obolibrary.org/obo/cheminf.owl\nChEBI - Chemical Entities of Biological Interest,chebi.owl,http://purl.obolibrary.org/obo/chebi.owl\nCiTO,cito.nt,http://purl.org/spar/cito.nt\nDCMI Terms,dcterms.nt,https://www.dublincore.org/specifications/dublin-core/dcmi-terms/dublin_core_terms.nt\nFaBiO,fabio.nt,http://purl.org/spar/fabio.nt\nGO - Gene Ontology,go.owl,http://purl.obolibrary.org/obo/go.owl\nIAO - Information Artifact Ontology,iao.owl,http://purl.obolibrary.org/obo/iao.owl\nNCIt,ncit.owl,http://purl.obolibrary.org/obo/ncit.owl\nNDF-RT,ndfrt.owl,https://data.bioontology.org/ontologies/NDF-RT/submissions/1/download?apikey=8b5b7825-538d-40e0-9e9e-5ab9274a9aeb\nOBI - Ontology for Biomedical Investigations,obi.owl,http://purl.obolibrary.org/obo/obi.owl\nOWL,owl.ttl,http://www.w3.org/2002/07/owl.ttl\nPDBo,pdbo.owl,http://rdf.wwpdb.org/schema/pdbx-v40.owl\nPR - PRotein Ontology (PRO),pr.owl,http://purl.obolibrary.org/obo/pr.owl\nRDF Schema,rdfs.ttl,https://www.w3.org/2000/01/rdf-schema.ttl\nRDF,rdf.ttl,http://www.w3.org/1999/02/22-rdf-syntax-ns.ttl\nRO - Relation Ontology,ro.owl,http://purl.obolibrary.org/obo/ro.owl\nSIO - Semanticscience Integrated Ontology,sio.owl,http://semanticscience.org/ontology/sio.owl\nSKOS,skos.rdf,http://www.w3.org/TR/skos-reference/skos.rdf\nSO - Sequence types and features ontology,so.owl,http://purl.obolibrary.org/obo/so.owl\nUO - Units of measurement ontology,uo.owl,http://purl.obolibrary.org/obo/uo.owl" > ${ONTOLOGIES_DIR}/${ONTOLOGIES_CSV})
+
+[index]
+INPUT_FILES      = ${data:ONTOLOGIES_DIR}/*.nt.gz ${data:PUBCHEM_DIR}/*/*.ttl.gz ${data:PUBCHEM_DIR}/*/*/*.ttl.gz
+BASE_URL         = http://rdf.ncbi.nlm.nih.gov/pubchem
+MULTI_INPUT_JSON = [{ "cmd": "zcat ${data:ONTOLOGIES_DIR}/*.nt.gz", "graph": "${BASE_URL}/ruleset"},
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/anatomy", "for-each": "${data:PUBCHEM_DIR}/anatomy/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/author", "for-each": "${data:PUBCHEM_DIR}/author/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/bioassay", "for-each": "${data:PUBCHEM_DIR}/bioassay/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/book", "for-each": "${data:PUBCHEM_DIR}/book/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/cell", "for-each": "${data:PUBCHEM_DIR}/cell/*.ttl.gz" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/compound/general/*0.ttl.gz", "graph": "${BASE_URL}/compound" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/compound/general/*1.ttl.gz", "graph": "${BASE_URL}/compound" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/compound/general/*2.ttl.gz", "graph": "${BASE_URL}/compound" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/compound/general/*3.ttl.gz", "graph": "${BASE_URL}/compound" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/compound/general/*4.ttl.gz", "graph": "${BASE_URL}/compound" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/compound/general/*5.ttl.gz", "graph": "${BASE_URL}/compound" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/compound/general/*6.ttl.gz", "graph": "${BASE_URL}/compound" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/compound/general/*7.ttl.gz", "graph": "${BASE_URL}/compound" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/compound/general/*8.ttl.gz", "graph": "${BASE_URL}/compound" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/compound/general/*9.ttl.gz", "graph": "${BASE_URL}/compound" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/compound", "for-each": "${data:PUBCHEM_DIR}/compound/general/*[!0-9].ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/concept", "for-each": "${data:PUBCHEM_DIR}/concept/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/conserveddomain", "for-each": "${data:PUBCHEM_DIR}/conserveddomain/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/cooccurrence", "for-each": "${data:PUBCHEM_DIR}/cooccurrence/*.ttl.gz" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/descriptor/compound/*0.ttl.gz", "graph": "${BASE_URL}/descriptor" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/descriptor/compound/*1.ttl.gz", "graph": "${BASE_URL}/descriptor" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/descriptor/compound/*2.ttl.gz", "graph": "${BASE_URL}/descriptor" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/descriptor/compound/*3.ttl.gz", "graph": "${BASE_URL}/descriptor" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/descriptor/compound/*4.ttl.gz", "graph": "${BASE_URL}/descriptor" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/descriptor/compound/*5.ttl.gz", "graph": "${BASE_URL}/descriptor" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/descriptor/compound/*6.ttl.gz", "graph": "${BASE_URL}/descriptor" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/descriptor/compound/*7.ttl.gz", "graph": "${BASE_URL}/descriptor" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/descriptor/compound/*8.ttl.gz", "graph": "${BASE_URL}/descriptor" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/descriptor/compound/*9.ttl.gz", "graph": "${BASE_URL}/descriptor" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/descriptor", "for-each": "${data:PUBCHEM_DIR}/descriptor/compound/*[!0-9].ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/descriptor", "for-each": "${data:PUBCHEM_DIR}/descriptor/substance/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/disease", "for-each": "${data:PUBCHEM_DIR}/disease/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/endpoint", "for-each": "${data:PUBCHEM_DIR}/endpoint/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/gene", "for-each": "${data:PUBCHEM_DIR}/gene/*.ttl.gz"},
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/grant", "for-each": "${data:PUBCHEM_DIR}/grant/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/inchikey", "for-each": "${data:PUBCHEM_DIR}/inchikey/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/journal", "for-each": "${data:PUBCHEM_DIR}/journal/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/measuregroup", "for-each": "${data:PUBCHEM_DIR}/measuregroup/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/organization", "for-each": "${data:PUBCHEM_DIR}/organization/*.ttl.gz" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/*0.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/*1.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/*2.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/*3.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/*4.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/*5.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/*6.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/*7.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/*8.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/*9.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/cpc/*.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/patent/ipc/*.ttl.gz", "graph": "${BASE_URL}/patent" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/patent", "for-each": "${data:PUBCHEM_DIR}/patent/*[!0-9].ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/pathway", "for-each": "${data:PUBCHEM_DIR}/pathway/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/protein", "for-each": "${data:PUBCHEM_DIR}/protein/*.ttl.gz" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/reference/*0.ttl.gz", "graph": "${BASE_URL}/reference" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/reference/*1.ttl.gz", "graph": "${BASE_URL}/reference" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/reference/*2.ttl.gz", "graph": "${BASE_URL}/reference" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/reference/*3.ttl.gz", "graph": "${BASE_URL}/reference" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/reference/*4.ttl.gz", "graph": "${BASE_URL}/reference" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/reference/*5.ttl.gz", "graph": "${BASE_URL}/reference" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/reference/*6.ttl.gz", "graph": "${BASE_URL}/reference" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/reference/*7.ttl.gz", "graph": "${BASE_URL}/reference" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/reference/*8.ttl.gz", "graph": "${BASE_URL}/reference" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/reference/*9.ttl.gz", "graph": "${BASE_URL}/reference" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/reference", "for-each": "${data:PUBCHEM_DIR}/reference/*[!0-9].ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/source", "for-each": "${data:PUBCHEM_DIR}/source/*.ttl.gz" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/substance/*0.ttl.gz", "graph": "${BASE_URL}/substance" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/substance/*1.ttl.gz", "graph": "${BASE_URL}/substance" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/substance/*2.ttl.gz", "graph": "${BASE_URL}/substance" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/substance/*3.ttl.gz", "graph": "${BASE_URL}/substance" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/substance/*4.ttl.gz", "graph": "${BASE_URL}/substance" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/substance/*5.ttl.gz", "graph": "${BASE_URL}/substance" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/substance/*6.ttl.gz", "graph": "${BASE_URL}/substance" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/substance/*7.ttl.gz", "graph": "${BASE_URL}/substance" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/substance/*8.ttl.gz", "graph": "${BASE_URL}/substance" },
+                    { "cmd": "zcat ${data:PUBCHEM_DIR}/substance/*9.ttl.gz", "graph": "${BASE_URL}/substance" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/substance", "for-each": "${data:PUBCHEM_DIR}/substance/*[!0-9].ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/synonym", "for-each": "${data:PUBCHEM_DIR}/synonym/*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "${BASE_URL}/taxonomy", "for-each": "${data:PUBCHEM_DIR}/taxonomy/*.ttl.gz" }]
+SETTINGS_JSON   = { "languages-internal": [], "prefixes-external": [""], "num-triples-per-batch": 10000000 }
+STXXL_MEMORY    = 20G
+
+[server]
+PORT               = 7023
+ACCESS_TOKEN       = ${data:NAME}
+MEMORY_FOR_QUERIES = 20G
+TIMEOUT            = 600s
+
+[runtime]
+SYSTEM = docker
+IMAGE  = docker.io/adfreiburg/qlever:latest
+
+[ui]
+UI_CONFIG = pubchem

qlever/Qleverfiles/Qleverfile.scientists

@@ -0,0 +1,29 @@
+# Qleverfile for "scientists", use with qlever script (pip install qlever)
+#
+# qlever get-data  # get "scientists" dataset (370M triples, 2.2 M texts records)
+# qlever index     # build index, including text index (takes ~20 seconds)
+# qlever start     # start the server (instant)
+
+[data]
+NAME             = scientists
+GET_DATA_CMD     = curl -LRC - -O https://github.com/ad-freiburg/qlever/raw/master/e2e/scientist-collection.zip && unzip -j scientist-collection.zip && rm -f scientist-collection.zip
+DESCRIPTION      = Test collection from https://github.com/ad-freiburg/qlever/tree/master/e2e (triples and text about scientists)
+TEXT_DESCRIPTION = Text from all literals and Wikipedia articles on scientists (use ql:contains-entity and ql:contains-word)
+
+[index]
+INPUT_FILES     = ${data:NAME}.nt
+CAT_INPUT_FILES = cat ${INPUT_FILES}
+SETTINGS_JSON   = { "ascii-prefixes-only": true, "num-triples-per-batch": 100000 }
+TEXT_INDEX      = from_text_records_and_literals
+
+[server]
+PORT               = 7020
+ACCESS_TOKEN       = ${data:NAME}
+MEMORY_FOR_QUERIES = 5G
+
+[runtime]
+SYSTEM = docker
+IMAGE  = docker.io/adfreiburg/qlever:latest
+
+[ui]
+UI_CONFIG = scientists

qlever/Qleverfiles/Qleverfile.uniprot

@@ -0,0 +1,74 @@
+# Qleverfile for UniProt, use with https://github.com/ad-freiburg/qlever-control
+#
+# qlever get-data  # takes ~ 30 hours and ~ 1.6 TB of disk (for the TTL files)
+# qlever index     # takes ~ 40 hours and ~ 60 GB RAM (on an AMD Ryzen 9 9950X)
+# qlever start     # starts the server (takes a few seconds)
+#
+# Install packages: sudo apt install -y libxml2-utils raptor2-utils parallel xz-utils wget
+# Install manually: Apache Jena binaries (https://dlcdn.apache.org/jena/binaries)
+#
+# Set DATE to the date of the latest release. Build on SSD (requires ~ 7 TB
+# during build, ~ 3 TB after build).
+
+[data]
+NAME             = uniprot
+DATE             = 2025-06-18
+RDFXML_DIR       = rdf.${DATE}
+TTL_DIR          = ttl.${DATE}
+UNIPROT_URL      = https://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf
+RHEA_URL         = https://ftp.expasy.org/databases/rhea/rdf
+EXAMPLES_URL     = https://github.com/sib-swiss/sparql-examples
+GET_EXAMPLES_CMD = mkdir -p ${TTL_DIR} && git clone ${EXAMPLES_URL} && (cd sparql-examples && ./convertToOneTurtle.sh -p uniprot && gzip examples_uniprot.ttl && mv -f examples_uniprot.ttl.gz ../${TTL_DIR} && cd .. && rm -rf sparql-examples)
+GET_RDFXML_CMD   = mkdir -p ${RDFXML_DIR} && (echo "${RHEA_URL}/chebi.owl.gz"; echo "${RHEA_URL}/rhea.rdf.gz"; curl -s ${UNIPROT_URL}/RELEASE.meta4 | sed "s/<metalink.*/<metalink>/" | xmllint --xpath "/metalink/files/file/url[@location=\"ch\"]/text()" -) | while read URL; do wget --no-verbose -P ${RDFXML_DIR} $$URL 2>&1 | tee -a uniprot.download-log; done
+RDFXML2TTL_CMD   = mkdir -p ${TTL_DIR} && for RDFXML in ${RDFXML_DIR}/*.{owl,owl.xz,rdf,rdf.xz}; do echo "xzcat -f $$RDFXML | rdfxml --output=ttl -q 2> ${TTL_DIR}/$$(basename $$RDFXML).stderr | gzip -c > ${TTL_DIR}/$$(basename $$RDFXML | sed 's/\(rdf\|rdf.xz\|owl\|owl.xz\)$$/ttl.gz/') && echo 'DONE converting $$RDFXML'"; done | parallel
+GET_DATA_CMD     = date > ${NAME}.get-data.begin-date && ${GET_EXAMPLES_CMD} && ${GET_RDFXML_CMD} && ${RDFXML2TTL_CMD} && date > ${NAME}.get-data.end-date
+DESCRIPTION      = UniProt, RDF XML from ${UNIPROT_URL} + additional data from ${RHEA_URL} and ${EXAMPLES_URL}, version ${DATE}
+
+[index]
+INPUT_FILES      = ${data:TTL_DIR}/*.ttl.gz
+MULTI_INPUT_JSON = [{ "cmd": "zcat {}", "graph": "http://sparql.uniprot.org/uniprot", "for-each": "${data:TTL_DIR}/uniprotkb_reviewed_*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "http://sparql.uniprot.org/uniprot", "for-each": "${data:TTL_DIR}/uniprotkb_unreviewed_*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "http://sparql.uniprot.org/uniparc", "for-each": "${data:TTL_DIR}/uniparc_*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "http://sparql.uniprot.org/uniref", "for-each": "${data:TTL_DIR}/uniref*.ttl.gz" },
+                    { "cmd": "zcat {}", "graph": "http://sparql.uniprot.org/obsolete", "for-each": "${data:TTL_DIR}/uniprotkb_obsolete_*.ttl.gz" },
+                    { "cmd": "zcat ${data:TTL_DIR}/chebi.ttl.gz", "graph": "http://sparql.uniprot.org/chebi" },
+                    { "cmd": "zcat ${data:TTL_DIR}/citation_mapping.ttl.gz", "graph": "http://sparql.uniprot.org/citationmapping" },
+                    { "cmd": "zcat ${data:TTL_DIR}/citations.ttl.gz", "graph": "http://sparql.uniprot.org/citations" },
+                    { "cmd": "zcat ${data:TTL_DIR}/databases.ttl.gz", "graph": "http://sparql.uniprot.org/databases" },
+                    { "cmd": "zcat ${data:TTL_DIR}/diseases.ttl.gz", "graph": "http://sparql.uniprot.org/diseases" },
+                    { "cmd": "zcat ${data:TTL_DIR}/enzyme-hierarchy.ttl.gz", "graph": "http://sparql.uniprot.org/enzymes" },
+                    { "cmd": "zcat ${data:TTL_DIR}/enzyme.ttl.gz", "graph": "http://sparql.uniprot.org/enzymes" },
+                    { "cmd": "zcat ${data:TTL_DIR}/go-hierarchy.ttl.gz", "graph": "http://sparql.uniprot.org/go" },
+                    { "cmd": "zcat ${data:TTL_DIR}/go.ttl.gz", "graph": "http://sparql.uniprot.org/go" },
+                    { "cmd": "zcat ${data:TTL_DIR}/journals.ttl.gz", "graph": "http://sparql.uniprot.org/journal" },
+                    { "cmd": "zcat ${data:TTL_DIR}/keywords-hierarchy.ttl.gz", "graph": "http://sparql.uniprot.org/keywords" },
+                    { "cmd": "zcat ${data:TTL_DIR}/keywords.ttl.gz", "graph": "http://sparql.uniprot.org/keywords" },
+                    { "cmd": "zcat ${data:TTL_DIR}/locations-hierarchy.ttl.gz", "graph": "http://sparql.uniprot.org/locations" },
+                    { "cmd": "zcat ${data:TTL_DIR}/locations.ttl.gz", "graph": "http://sparql.uniprot.org/locations" },
+                    { "cmd": "zcat ${data:TTL_DIR}/pathways-hierarchy*.ttl.gz", "graph": "http://sparql.uniprot.org/pathways" },
+                    { "cmd": "zcat ${data:TTL_DIR}/pathways.ttl.gz", "graph": "http://sparql.uniprot.org/pathways" },
+                    { "cmd": "zcat ${data:TTL_DIR}/proteomes.ttl.gz", "graph": "http://sparql.uniprot.org/proteomes" },
+                    { "cmd": "zcat ${data:TTL_DIR}/taxonomy-hierarchy.ttl.gz", "graph": "http://sparql.uniprot.org/taxonomy" },
+                    { "cmd": "zcat ${data:TTL_DIR}/taxonomy.ttl.gz", "graph": "http://sparql.uniprot.org/taxonomy" },
+                    { "cmd": "zcat ${data:TTL_DIR}/tissues.ttl.gz", "graph": "http://sparql.uniprot.org/tissues" },
+                    { "cmd": "zcat ${data:TTL_DIR}/rhea.ttl.gz", "graph": "https://sparql.rhea-db.org/rhea" },
+                    { "cmd": "zcat ${data:TTL_DIR}/examples_uniprot.ttl.gz", "graph": "http://sparql.uniprot.org/.well-known/sparql-examples" },
+                    { "cmd": "zcat ${data:TTL_DIR}/core.ttl.gz", "graph": "http://purl.uniprot.org/core" }]
+SETTINGS_JSON    = { "languages-internal": [], "prefixes-external": [""], "locale": { "language": "en", "country": "US", "ignore-punctuation": true }, "ascii-prefixes-only": true, "num-triples-per-batch": 25000000 }
+STXXL_MEMORY     = 80G
+ULIMIT           = 50000
+
+[server]
+PORT                        = 7018
+ACCESS_TOKEN                = ${data:NAME}
+MEMORY_FOR_QUERIES          = 20G
+CACHE_MAX_SIZE              = 10G
+CACHE_MAX_SIZE_SINGLE_ENTRY = 5G
+TIMEOUT	                    = 300s
+
+[runtime]
+SYSTEM = docker
+IMAGE  = docker.io/adfreiburg/qlever:latest
+
+[ui]
+UI_CONFIG = uniprot

qlever/Qleverfiles/Qleverfile.vvz

@@ -0,0 +1,31 @@
+# Qleverfile for VVZ, use with https://github.com/ad-freiburg/qlever-control
+#
+# qlever get-data  # this requires a separate internal tool
+# qlever index     # builds the index (takes a few seconds)
+# qlever start     # starts the server (takes a few seconds)
+#
+# Also builds a text index for fast kewyword search in literals.
+
+[data]
+NAME             = vvz
+GET_DATA_CMD     = echo "This requires a separate tool"
+DESCRIPTION      = VVZ Uni Freiburg, selected faculties
+TEXT_DESCRIPTION = All literals, search with FILTER KEYWORDS(?text, "...")
+
+[index]
+INPUT_FILES     = vvz.ttl
+CAT_INPUT_FILES = cat ${INPUT_FILES}
+SETTINGS_JSON   = { "ascii-prefixes-only": false, "num-triples-per-batch": 1000000 }
+TEXT_INDEX      = from_literals
+
+[server]
+PORT               = 7041
+ACCESS_TOKEN       = ${data:NAME}
+MEMORY_FOR_QUERIES = 10G
+
+[runtime]
+SYSTEM = docker
+IMAGE  = docker.io/adfreiburg/qlever:latest
+
+[ui]
+UI_CONFIG = vvz

qlever/Qleverfiles/Qleverfile.wikidata

@@ -0,0 +1,42 @@
+# Qleverfile for Wikidata, use with the QLever CLI (`pip install qlever`)
+#
+# qlever get-data  # ~7 hours, ~110 GB (compressed), ~20 billion triples
+# qlever index     # ~5 hours, ~20 GB RAM, ~500 GB index size on disk
+# qlever start     # a few seconds, adjust MEMORY_FOR_QUERIES as needed
+#
+# Adding a text index takes an additional ~2 hours and ~50 GB of disk space
+#
+# Measured on an AMD Ryzen 9 5950X with 128 GB RAM, and NVMe SSD (18.10.2024)
+
+[DEFAULT]
+NAME = wikidata
+
+[data]
+GET_DATA_URL      = https://dumps.wikimedia.org/wikidatawiki/entities
+GET_DATA_CMD      = curl -LRC - -O ${GET_DATA_URL}/latest-all.ttl.bz2 -O ${GET_DATA_URL}/latest-lexemes.ttl.bz2 2>&1 | tee wikidata.download-log.txt && curl -sL ${GET_DATA_URL}/dcatap.rdf | docker run -i --rm -v $$(pwd):/data stain/jena riot --syntax=RDF/XML --output=NT /dev/stdin > dcatap.nt
+DATE_WIKIDATA     = $$(date -r latest-all.ttl.bz2 +%d.%m.%Y || echo "NO_DATE")
+DATE_WIKIPEDIA    = $$(date -r wikipedia-abstracts.nt +%d.%m.%Y || echo "NO_DATE")
+DESCRIPTION       = Complete Wikidata, from ${GET_DATA_URL} (latest-all.ttl.bz2 and latest-lexemes.ttl.bz2), version ${DATE_WIKIDATA}
+
+[index]
+INPUT_FILES      = latest-all.ttl.bz2 latest-lexemes.ttl.bz2 dcatap.nt
+MULTI_INPUT_JSON = [{ "cmd": "lbzcat -n 4 latest-all.ttl.bz2", "format": "ttl", "parallel": "true" },
+                    { "cmd": "lbzcat -n 1 latest-lexemes.ttl.bz2", "format": "ttl", "parallel": "false" },
+                    { "cmd": "cat dcatap.nt", "format": "nt", "parallel": "false" }]
+SETTINGS_JSON    = { "languages-internal": [], "prefixes-external": [""], "locale": { "language": "en", "country": "US", "ignore-punctuation": true }, "ascii-prefixes-only": true, "num-triples-per-batch": 5000000 }
+STXXL_MEMORY     = 10G
+
+[server]
+PORT                        = 7001
+ACCESS_TOKEN                = ${data:NAME}
+MEMORY_FOR_QUERIES          = 20G
+CACHE_MAX_SIZE              = 15G
+CACHE_MAX_SIZE_SINGLE_ENTRY = 5G
+TIMEOUT                     = 600s
+
+[runtime]
+SYSTEM = docker
+IMAGE  = adfreiburg/qlever
+
+[ui]
+UI_CONFIG = wikidata

qlever/Qleverfiles/Qleverfile.wikipathways

@@ -0,0 +1,40 @@
+# Qleverfile for WikiPathways, use with https://github.com/ad-freiburg/qlever-control
+#
+# qlever get-data  # takes ~3 seconds, generates TTL of size ~600 MB
+# qlever index     # takes ~20 seconds and little RAM (on an AMD Ryzen 9 5900X)
+# qlever start     # instant
+#
+# Limitations: does not include the ontologies (WP, GPML, ChEBI, PW, CLO, ...) yet
+
+[data]
+NAME             = wikipathways
+RELEASE          = current
+GET_DATA_URL     = https://data.wikipathways.org/${RELEASE}/rdf
+GET_DATA_CMD     = wget -O wikipathways-rdf-void.ttl ${GET_DATA_URL}/wikipathways-rdf-void.ttl && \
+                    wget ${GET_DATA_URL}/wikipathways-${RELEASE}-rdf-wp.zip && \
+                      unzip -qq -c wikipathways-${RELEASE}-rdf-wp.zip -x wp/wpOntology.ttl > wikipathways-rdf-wp.ttl && \
+                    wget ${GET_DATA_URL}/wikipathways-${RELEASE}-rdf-gpml.zip && 
+                      unzip -qq -c wikipathways-${RELEASE}-rdf-gpml.zip -x gpml/gpmlOntology.ttl > wikipathways-rdf-gpml.ttl && \
+                    wget ${GET_DATA_URL}/wikipathways-${RELEASE}-rdf-authors.zip && \
+                      unzip -qq -c wikipathways-${RELEASE}-rdf-authors.zip > wikipathways-rdf-authors.ttl && \
+                    cat wikipathways-rdf-*.ttl | grep ^@prefix | tr -s ' ' | sort -u > ${NAME}.prefix-definitions
+DESCRIPTION      = WikiPathways RDF, from ${GET_DATA_URL}
+TEXT_DESCRIPTION = All literals, search with FILTER KEYWORDS(?text, "...")
+
+[index]
+INPUT_FILES     = ${data:NAME}.prefix-definitions wikipathways-rdf-wp.ttl wikipathways-rdf-gpml.ttl wikipathways-rdf-void.ttl wikipathways-rdf-authors.ttl
+CAT_INPUT_FILES = cat ${INPUT_FILES}
+SETTINGS_JSON   = { "ascii-prefixes-only": false, "num-triples-per-batch": 1000000, "prefixes-external": [""] }
+TEXT_INDEX      = from_literals
+
+[server]
+PORT               = 7040
+ACCESS_TOKEN       = ${data:NAME}
+MEMORY_FOR_QUERIES = 5G
+
+[runtime]
+SYSTEM = docker
+IMAGE  = docker.io/adfreiburg/qlever:latest
+
+[ui]
+UI_CONFIG = wikipathways

qlever/Qleverfiles/Qleverfile.yago-4

@@ -0,0 +1,33 @@
+# Qleverfile for YAGO 4, use with https://github.com/ad-freiburg/qlever-control
+#
+# qlever get-data  # downloads 8 nt.gz file of size ~60 GB (as of 12.03.2020)
+# qlever index     # takes ~4 hours and ~10 GB RAM (on an AMD Ryzen 9 5900X)
+# qlever start     # starts the server
+
+# NOTE concerning GET_DATA_CMD: The triples from wd-annotated-facts are
+# contained in wd-facts. The "full types" are the YAGO types, the "simple
+# types" are the schema.org types. They don't interfere with each other because
+# they have distinct prefixes.
+
+[data]
+NAME         = yago-4
+GET_DATA_CMD = curl --location --continue-at - --remote-name-all https://yago-knowledge.org/data/yago4/full/2020-02-24/yago-wd-class.nt.gz https://yago-knowledge.org/data/yago4/full/2020-02-24/yago-wd-facts.nt.gz https://yago-knowledge.org/data/yago4/full/2020-02-24/yago-wd-full-types.nt.gz https://yago-knowledge.org/data/yago4/full/2020-02-24/yago-wd-labels.nt.gz https://yago-knowledge.org/data/yago4/full/2020-02-24/yago-wd-sameAs.nt.gz https://yago-knowledge.org/data/yago4/full/2020-02-24/yago-wd-schema.nt.gz https://yago-knowledge.org/data/yago4/full/2020-02-24/yago-wd-shapes.nt.gz https://yago-knowledge.org/data/yago4/full/2020-02-24/yago-wd-simple-types.nt.gz
+DESCRIPTION  = "Full dump from https://yago-knowledge.org/downloads/yago-4, version 12.03.2020"
+
+[index]
+INPUT_FILES     = yago-wd-*.nt.gz
+CAT_INPUT_FILES = zcat ${INPUT_FILES}
+SETTINGS_JSON   = { "languages-internal": ["en"], "locale": { "language": "en", "country": "US", "ignore-punctuation": true }, "ascii-prefixes-only": false, "num-triples-per-batch": 5000000 }
+STXXL_MEMORY    = 10G
+
+[server]
+PORT               = 9004
+ACCESS_TOKEN       = ${data:NAME}
+MEMORY_FOR_QUERIES = 30G
+
+[runtime]
+SYSTEM = docker
+IMAGE  = docker.io/adfreiburg/qlever:latest
+
+[ui]
+UI_CONFIG = yago-4