-
Notifications
You must be signed in to change notification settings - Fork 13
Test
Toshiaki Katayama edited this page Nov 1, 2021
·
16 revisions
rdf-config --config config/mesh --sparql togodx:integbio
# Endpoint: https://integbio.jp/togosite/sparql
# Description: SPARQL for https://integbio.jp/togosite/sparqlist/disease_diseases_mesh
PREFIX meshv: <http://id.nlm.nih.gov/mesh/vocab#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT ?Descriptor ?TreeNumber ?descriptor_label
FROM <http://rdf.integbio.jp/dataset/togosite/mesh>
WHERE {
?Descriptor a meshv:TopicalDescriptor ;
meshv:treeNumber ?TreeNumber ;
rdfs:label ?descriptor_label .
?TreeNumber a meshv:TreeNumber .
}
LIMIT 100
↓
PREFIX meshv: <http://id.nlm.nih.gov/mesh/vocab#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT (?TreeNumber AS ?category) (?descriptor_label AS ?label) (COUNT(DISTINCT ?Descriptor) AS ?count)
FROM <http://rdf.integbio.jp/dataset/togosite/mesh>
WHERE {
?Descriptor a meshv:TopicalDescriptor ;
# meshv:treeNumber ?TreeNumber ;
meshv:treeNumber/meshv:parentTreeNumber* ?TreeNumber ;
rdfs:label ?descriptor_label .
?TreeNumber a meshv:TreeNumber .
MINUS {
?TreeNumber meshv:parentTreeNumber ?parent .
}
FILTER (CONTAINS(STR(?TreeNumber),"mesh/C"))
FILTER(lang(?descriptor_label) = "en")
}
ORDER BY DESC(?count)
LIMIT 100
↓
PREFIX meshv: <http://id.nlm.nih.gov/mesh/vocab#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT
(?TreeNumber AS ?category)
(?descriptor_label AS ?label)
(COUNT(DISTINCT ?Descriptor) AS ?count)
FROM <http://rdf.integbio.jp/dataset/togosite/mesh>
WHERE {
?Descriptor a meshv:TopicalDescriptor ;
meshv:treeNumber/meshv:parentTreeNumber* ?TreeNumber ;
MINUS {
?TreeNumber meshv:parentTreeNumber ?parent .
}
?TreeNumber a meshv:TreeNumber ;
^meshv:treeNumber/rdfs:label ?descriptor_label .
FILTER (contains(str(?TreeNumber), "mesh/C"))
FILTER (lang(?descriptor_label) = "en")
}
ORDER BY DESC(?count)
あと、中間階層の ID を受け取って集計するなど要改訂
# Endpoint: https://integbio.jp/togosite/sparql
# Description: SPARQL for https://togodx.integbio.jp/sparqlist/disease_diseases_mesh
PREFIX meshv: <http://id.nlm.nih.gov/mesh/vocab#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT DISTINCT
(?Descriptor AS ?mesh_id) # 本人
(?descriptor_label AS ?mesh_label) # ラベル
(?parentDescriptor AS ?parent_mesh_id) # 親
(SAMPLE(?child) AS ?tree_child) # leafフラグ
FROM <http://rdf.integbio.jp/dataset/togosite/mesh>
WHERE {
?Descriptor a meshv:TopicalDescriptor ;
meshv:treeNumber ?TreeNumber ;
rdfs:label ?descriptor_label .
?TreeNumber a meshv:TreeNumber .
OPTIONAL {
?TreeNumber meshv:parentTreeNumber ?parent .
?parentDescriptor meshv:treeNumber ?parent .
}
OPTIONAL {
?child meshv:parentTreeNumber ?TreeNumber.
}
FILTER (contains(str(?TreeNumber), "mesh/C"))
FILTER (lang(?descriptor_label) = "en")
}
GROUP BY ?Descriptor ?descriptor_label ?parentDescriptor
このあと JS で
leaf: (d.tree_child == undefined ? true : false),
parent: (d.parent_mesh_id == undefined ? "root" : d.parent_mesh_id.value.replace(idPrefix, ""))
のような処理をしているけど SPARQL だけで leaf を boolean に、parent が空なら root を補完できるとよい(宿題)。
rdf-config --config config/pubchem --sparql test_types
# Endpoint: https://integbio.jp/rdf/ncbi/sparql
PREFIX bao: <http://www.bioassayontology.org/bao#>
PREFIX obo: <http://purl.obolibrary.org/obo/>
PREFIX sio: <http://semanticscience.org/resource/>
SELECT DISTINCT ?PubChemEndpointClass # ?PubChemEndpoint ?value ?unit
FROM <http://rdf.integbio.jp/dataset/pubchem>
WHERE {
?PubChemBioAssay a bao:BAO_0000015 ;
bao:BAO_0000209 / obo:OBI_0000299 ?PubChemEndpoint .
?PubChemEndpoint a ?PubChemEndpointClass ;
sio:has-value ?value ;
sio:has-unit ?unit .
}
LIMIT 200
PubChemEndpointClass
bao:BAO_0000034
bao:BAO_0000186
bao:BAO_0000187
bao:BAO_0000188
bao:BAO_0000189
bao:BAO_0000190
bao:BAO_0000192
bao:BAO_0000194
bao:BAO_0000477
bao:BAO_0002117
bao:BAO_0002144
bao:BAO_0002145
bao:BAO_0002146
bao:BAO_0002162
bao:BAO_0002862
bao:BAO_0002877
bao:BAO_0002878
bao:BAO_0002879
bao:BAO_0002880
bao:BAO_0002881
bao:BAO_0002882
bao:BAO_0002883
bao:BAO_0002884
bao:BAO_0002886
bao:BAO_0002887
bao:BAO_0003036
PREFIX bao: <http://www.bioassayontology.org/bao#>
PREFIX obo: <http://purl.obolibrary.org/obo/>
PREFIX sio: <http://semanticscience.org/resource/>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT DISTINCT ?PubChemEndpointClass ?label # ?PubChemEndpoint ?value ?unit
FROM <http://rdf.integbio.jp/dataset/pubchem>
WHERE {
?PubChemBioAssay a bao:BAO_0000015 ;
bao:BAO_0000209 / obo:OBI_0000299 ?PubChemEndpoint .
?PubChemEndpoint a ?PubChemEndpointClass ;
rdfs:label ?label .
}
LIMIT 200
PubChemEndpointClass label
bao:BAO_0000034 "Average Kd"@en
bao:BAO_0000034 "IC50"@en
bao:BAO_0000034 "Kd (FL)"@en
bao:BAO_0000034 "Kd"@en
bao:BAO_0000034 "Ki"@en
bao:BAO_0000186 "AC50"@en
bao:BAO_0000186 "AC_50_uM"@en
bao:BAO_0000186 "POTENCY_uM"@en
bao:BAO_0000186 "Potency"@en
bao:BAO_0000186 "XC50_3D7"@en
bao:BAO_0000187 "CC50"@en
bao:BAO_0000187 "EC50"@en
bao:BAO_0000187 "IC50"@en
bao:BAO_0000188 "CC50"@en
bao:BAO_0000188 "EC50"@en
bao:BAO_0000188 "EC90"@en
bao:BAO_0000188 "IC50"@en
bao:BAO_0000188 "Ki"@en
bao:BAO_0000189 "GI50"@en
bao:BAO_0000189 "IC50"@en
bao:BAO_0000189 "LC50"@en
bao:BAO_0000190 "64"@en
bao:BAO_0000190 "CC50"@en
bao:BAO_0000190 "EC50"@en
bao:BAO_0000190 "GI50"@en
bao:BAO_0000190 "IC50"@en
bao:BAO_0000190 "IC80"@en
bao:BAO_0000190 "Imax"@en
bao:BAO_0000190 "Kd"@en
bao:BAO_0000190 "Ki "@en
bao:BAO_0000190 "Ki"@en
bao:BAO_0000190 "LC50"@en
bao:BAO_0000190 "TGI"@en
bao:BAO_0000192 "EC50"@en
bao:BAO_0000192 "IC50"@en
bao:BAO_0000192 "KI_MICROM"@en
bao:BAO_0000192 "Kd"@en
bao:BAO_0000192 "Ki"@en
bao:BAO_0000194 "IC50"@en
bao:BAO_0000194 "LC50"@en
bao:BAO_0000194 "TGI"@en
bao:BAO_0000477 "Km"@en
bao:BAO_0002117 "LD50"@en
bao:BAO_0002144 "Active Concentration IC90"@en
bao:BAO_0002144 "ActiveConcentrationIC90"@en
bao:BAO_0002144 "Active_Concentration_IC90"@en
bao:BAO_0002144 "Average IC90"@en
bao:BAO_0002144 "Avg IC90"@en
bao:BAO_0002144 "IC90"@en
bao:BAO_0002144 "LogCFU_IC90"@en
bao:BAO_0002144 "StarvMIC_IC90"@en
bao:BAO_0002145 "GI50"@en
bao:BAO_0002145 "IC50"@en
bao:BAO_0002145 "LC50"@en
bao:BAO_0002145 "TGI"@en
bao:BAO_0002146 "MIC [4 fold reduction]"@en
bao:BAO_0002146 "MIC"@en
bao:BAO_0002146 "MIC_EC_37"@en
bao:BAO_0002146 "MIC_YP_37"@en
bao:BAO_0002146 "Mean MIC"@en
bao:BAO_0002162 "2nd Test Concentration"@en
bao:BAO_0002162 "AC200"@en
bao:BAO_0002162 "AC90_uM"@en
bao:BAO_0002162 "ACTIVE_CONCENTRATION_(uM)"@en
bao:BAO_0002162 "AbsAC0.39_uM"@en
bao:BAO_0002162 "AbsAC0.47_uM"@en
bao:BAO_0002162 "AbsAC0.54_uM"@en
bao:BAO_0002162 "AbsAC1_uM"@en
bao:BAO_0002162 "AbsAC200_uM"@en
bao:BAO_0002162 "AbsAC30_uM"@en
bao:BAO_0002162 "AbsAC90_uM"@en
bao:BAO_0002162 "Ac50"@en
bao:BAO_0002162 "Active Concentration"@en
bao:BAO_0002162 "Activity at 9.921 uM"@en
bao:BAO_0002162 "Activity"@en
bao:BAO_0002162 "Agonism inflection point"@en
bao:BAO_0002162 "Average Kd"@en
bao:BAO_0002162 "Average_Ki_uM"@en
bao:BAO_0002162 "CC20"@en
bao:BAO_0002162 "CMC"@en
bao:BAO_0002162 "CO2"@en
bao:BAO_0002162 "CRC/CRC0 at 12.5 microM_mean"@en
bao:BAO_0002162 "CRC/CRC0 at 50 microM_mean"@en
bao:BAO_0002162 "Cell Proliferation EC50"@en
bao:BAO_0002162 "Cell Proliferation EC70"@en
bao:BAO_0002162 "Cell Proliferation IC50"@en
bao:BAO_0002162 "Cmax"@en
bao:BAO_0002162 "Compound_Concentration"@en
bao:BAO_0002162 "Cp"@en
bao:BAO_0002162 "DC50"@en
bao:BAO_0002162 "Drug uptake"@en
bao:BAO_0002162 "Drug uptake(free)"@en
bao:BAO_0002162 "EC"@en
bao:BAO_0002162 "EC200"@en
bao:BAO_0002162 "EC50"@en
bao:BAO_0002162 "EC90"@en
bao:BAO_0002162 "HC10"@en
bao:BAO_0002162 "HEPG2TOX ASSAY - CC50"@en
bao:BAO_0002162 "HEPG2TOX ASSAY - CC90"@en
bao:BAO_0002162 "IC25"@en
bao:BAO_0002162 "IC30"@en
bao:BAO_0002162 "IC50"@en
bao:BAO_0002162 "IC80"@en
bao:BAO_0002162 "IC90_uM"@en
bao:BAO_0002162 "ID50"@en
bao:BAO_0002162 "INH"@en
bao:BAO_0002162 "Imax"@en
bao:BAO_0002162 "Inhibition"@en
bao:BAO_0002162 "K"@en
bao:BAO_0002162 "K1/2"@en
bao:BAO_0002162 "KDss"@en
bao:BAO_0002162 "Kact"@en
bao:BAO_0002162 "Kb"@en
bao:BAO_0002162 "Kd apparent"@en
bao:BAO_0002162 "Kd for PAK2"@en
bao:BAO_0002162 "Kd"@en
bao:BAO_0002162 "Ki "@en
bao:BAO_0002162 "Ki1"@en
bao:BAO_0002162 "Ki2"@en
bao:BAO_0002162 "Ki_uM"@en
bao:BAO_0002162 "Kr"@en
bao:BAO_0002162 "LUCIFERASE EXPRESSION CONTROL - IC50"@en
bao:BAO_0002162 "LUCIFERASE EXPRESSION CONTROL - IC90"@en
bao:BAO_0002162 "LUCIFERASE INFECTION ASSAY - IC50"@en
bao:BAO_0002162 "LUCIFERASE INFECTION ASSAY - IC90"@en
bao:BAO_0002162 "LogChange"@en
bao:BAO_0002162 "MEC"@en
bao:BAO_0002162 "MEC1.5"@en
bao:BAO_0002162 "MEC2.0"@en
bao:BAO_0002162 "MIC90"@en
bao:BAO_0002162 "Max_Activity_Concentration_uM "@en
bao:BAO_0002162 "Max_Concentration(uM) "@en
bao:BAO_0002162 "Potentiation inflection point"@en
bao:BAO_0002162 "Solubility"@en
bao:BAO_0002162 "TC50 "@en
bao:BAO_0002162 "TC50 (2% Serum) "@en
bao:BAO_0002162 "TC50 (5% Serum) "@en
bao:BAO_0002162 "TC50 (5% Serum)"@en
bao:BAO_0002162 "TD100"@en
bao:BAO_0002162 "TD50 (microM)"@en
bao:BAO_0002162 "Toxicity"@en
bao:BAO_0002862 "5h_period"@en
bao:BAO_0002877 "AbsAC1000_uM"@en
bao:BAO_0002878 "AbsAC10_uM"@en
bao:BAO_0002879 "AbsAC26_uM"@en
bao:BAO_0002880 "AbsAC35_uM"@en
bao:BAO_0002881 "AbsAC40_uM"@en
bao:BAO_0002882 "AbsAC500_uM"@en
bao:BAO_0002883 "ECMax"@en
bao:BAO_0002884 "Max_Activity_Conc_uM"@en
bao:BAO_0002884 "Max_Delta_Tm_Conc_uM"@en
bao:BAO_0002886 "Conc @ Max Fold Increase"@en
bao:BAO_0002887 "Concentration @ Maximum % Inhibition"@en
bao:BAO_0003036 "ED50"@en
sort | uniq -c
1 bao:BAO_0000477
1 bao:BAO_0002117
1 bao:BAO_0002862
1 bao:BAO_0002877
1 bao:BAO_0002878
1 bao:BAO_0002879
1 bao:BAO_0002880
1 bao:BAO_0002881
1 bao:BAO_0002882
1 bao:BAO_0002883
1 bao:BAO_0002886
1 bao:BAO_0002887
1 bao:BAO_0003036
2 bao:BAO_0002884
3 bao:BAO_0000187
3 bao:BAO_0000189
3 bao:BAO_0000194
4 bao:BAO_0002145
5 bao:BAO_0000034
5 bao:BAO_0000186
5 bao:BAO_0000188
5 bao:BAO_0000192
5 bao:BAO_0002146
8 bao:BAO_0002144
12 bao:BAO_0000190
81 bao:BAO_0002162