rm(list = ls())
library("webchem")
data("jagst", package = "webchem")
#head(jagst)
data("lc50", package = "webchem")
#head(lc50)
dim(lc50)
## [1] 124 2
#4.3. Query identifiers
subs <- unique(jagst$substance)[1:3]
subs
## [1] "2,4-Dimethylphenol" "4-Chlor-2-methylphenol" "4-para-nonylphenol"
ids <- get_etoxid(subs, match = "best")
ids
## # A tibble: 3 x 3
## query match etoxid
## <chr> <chr> <chr>
## 1 2,4-Dimethylphenol 2,4-Xylenol 8668
## 2 4-Chlor-2-methylphenol 4-Chlor-2-methylphenol 8494
## 3 4-para-nonylphenol <NA> <NA>
etox_data <- etox_basic(ids$etoxid)
etox_data
## $`8668`
## $`8668`$cas
## [1] "105-67-9"
##
## $`8668`$ec
## # A tibble: 2 x 0
##
## $`8668`$gsbl
## <unspecified> [0]
##
## $`8668`$synonyms
## # A tibble: 5 x 2
## name language
## <chr> <chr>
## 1 2,4-Dimethylphenol English
## 2 2,4-dimethyl-phenol English
## 3 2,4-Dimethylphenol German
## 4 4-Hydroxy-m-xylol German
## 5 Phenol, 2,4-dimethyl- universal
##
## $`8668`$source_url
## [1] "https://webetox.uba.de/webETOX/public/basics/stoff.do?language=en&id=8668"
##
##
## $`8494`
## $`8494`$cas
## [1] "1570-64-5"
##
## $`8494`$ec
## # A tibble: 2 x 0
##
## $`8494`$gsbl
## [1] "978"
##
## $`8494`$synonyms
## # A tibble: 4 x 2
## name language
## <chr> <chr>
## 1 4-chloro-o-cresol English
## 2 5-Chlor-2-hydroxytoluol German
## 3 4-Chlor-o-kresol German
## 4 PCOC universal
##
## $`8494`$source_url
## [1] "https://webetox.uba.de/webETOX/public/basics/stoff.do?language=en&id=8494"
##
##
## $<NA>
## [1] NA
##
## attr(,"class")
## [1] "etox_basic" "list"
etox_cas <- cas(etox_data)
etox_cas
## 8668 8494 <NA>
## "105-67-9" "1570-64-5" NA
cids <- get_cid(etox_cas, from = "xref/rn", match = "first")
cids
## # A tibble: 3 x 2
## query cid
## <chr> <chr>
## 1 105-67-9 7771
## 2 1570-64-5 14855
## 3 <NA> <NA>
pc_data <- pc_prop(cids$cid, properties = "CanonicalSMILES")
pc_data
## CID CanonicalSMILES
## 1 7771 CC1=CC(=C(C=C1)O)C
## 2 14855 CC1=C(C=CC(=C1)Cl)O
## 3 NA <NA>
pc_smiles <- smiles(pc_data)
pc_smiles
## [1] "CC1=CC(=C(C=C1)O)C" "CC1=C(C=CC(=C1)Cl)O" NA
#csids <- get_csid(pc_smiles, from = "smiles")
#cs_inchikey <- cs_convert(csids$csid, from = "csid", to = "inchikey")
res <- data.frame(name = subs, cas = etox_cas, smiles = pc_smiles,
cid = pc_data$CID,# inchikey = cs_inchikey, #csid = csids$csid,
stringsAsFactors = FALSE, row.names = NULL)
res
## name cas smiles cid
## 1 2,4-Dimethylphenol 105-67-9 CC1=CC(=C(C=C1)O)C 7771
## 2 4-Chlor-2-methylphenol 1570-64-5 CC1=C(C=CC(=C1)Cl)O 14855
## 3 4-para-nonylphenol <NA> <NA> NA
#Toxicity of different pesticide groups
lc50 <- lc50[order(lc50$value),][1:3,]
lc50
## cas value
## 626 563-12-2 0.0560000
## 1851 96182-53-5 0.0735453
## 968 3383-96-8 0.0770714
aw_data <- bcpc_query(lc50$cas, from = "cas")
aw_data
## $`563-12-2`
## $`563-12-2`$cname
## [1] "ethion"
##
## $`563-12-2`$status
## [1] "ISO 1750 (published)"
##
## $`563-12-2`$pref_iupac_name
## [1] "O,O,O′,O′-tetraethyl S,S′-methylene bis(phosphorodithioate)"
##
## $`563-12-2`$iupac_name
## [1] "O,O,O′,O′-tetraethyl S,S′-methylene bis(phosphorodithioate)"
##
## $`563-12-2`$cas
## [1] "563-12-2"
##
## $`563-12-2`$formula
## [1] "C9H22O4P2S4"
##
## $`563-12-2`$activity
## [1] "acaricides (organothiophosphate acaricides)insecticides"
##
## $`563-12-2`$subactivity
## [1] "aliphatic organothiophosphate insecticides"
##
## $`563-12-2`$inchikey
## [1] "RIZMRRKBZQXFOY-UHFFFAOYSA-N"
##
## $`563-12-2`$inchi
## [1] "InChI=1S/C9H22O4P2S4/c1-5-10-14(16,11-6-2)18-9-19-15(17,12-7-3)13-8-4/h5-9H2,1-4H3"
##
## $`563-12-2`$source_url
## [1] "https://pesticidecompendium.bcpc.org/ethion.html"
##
##
## $`96182-53-5`
## $`96182-53-5`$cname
## [1] "tebupirimfos"
##
## $`96182-53-5`$status
## [1] "ISO 1750 (published)"
##
## $`96182-53-5`$pref_iupac_name
## [1] "(Ξ)-[O-(2-tert-butylpyrimidin-5-yl) O-ethyl O-propan-2-yl phosphorothioate]"
##
## $`96182-53-5`$iupac_name
## [1] "(RS)-[O-(2-tert-butylpyrimidin-5-yl) O-ethyl O-isopropyl phosphorothioate]"
##
## $`96182-53-5`$cas
## [1] "96182-53-5"
##
## $`96182-53-5`$formula
## [1] "C13H23N2O3PS"
##
## $`96182-53-5`$activity
## [1] "insecticides"
##
## $`96182-53-5`$subactivity
## [1] "pyrimidine organothiophosphate insecticides"
##
## $`96182-53-5`$inchikey
## [1] "AWYOMXWDGWUJHS-UHFFFAOYSA-N"
##
## $`96182-53-5`$inchi
## [1] "InChI=1S/C13H23N2O3PS/c1-7-16-19(20,17-10(2)3)18-11-8-14-12(15-9-11)13(4,5)6/h8-10H,7H2,1-6H3"
##
## $`96182-53-5`$source_url
## [1] "https://pesticidecompendium.bcpc.org/tebupirimfos.html"
##
##
## $`3383-96-8`
## $`3383-96-8`$cname
## [1] "temephos"
##
## $`3383-96-8`$status
## [1] "ISO 1750 (published)"
##
## $`3383-96-8`$pref_iupac_name
## [1] "O,O,O′,O′-tetramethyl O,O′-(sulfanediyldi-4,1-phenylene) bis(phosphorothioate)"
##
## $`3383-96-8`$iupac_name
## [1] "O,O,O′,O′-tetramethyl O,O′-(thiodi-p-phenylene) bis(phosphorothioate)orO,O,O′,O′-tetramethyl O,O′-(thiodi-p-phenylene) diphosphorothioate"
##
## $`3383-96-8`$cas
## [1] "3383-96-8"
##
## $`3383-96-8`$formula
## [1] "C16H20O6P2S3"
##
## $`3383-96-8`$activity
## [1] "insecticides"
##
## $`3383-96-8`$subactivity
## [1] "phenyl organothiophosphate insecticides"
##
## $`3383-96-8`$inchikey
## [1] "WWJZWCUNLNYYAU-UHFFFAOYSA-N"
##
## $`3383-96-8`$inchi
## [1] "InChI=1S/C16H20O6P2S3/c1-17-23(25,18-2)21-13-5-9-15(10-6-13)27-16-11-7-14(8-12-16)22-24(26,19-3)20-4/h5-12H,1-4H3"
##
## $`3383-96-8`$source_url
## [1] "https://pesticidecompendium.bcpc.org/temephos.html"
##
##
## attr(,"class")
## [1] "bcpc_query" "list"
igroup <- sapply(aw_data, function(y) {
if (is(y, "list")) y$subactivity[1] else NA_character_
})
igroup
## 563-12-2
## "aliphatic organothiophosphate insecticides"
## 96182-53-5
## "pyrimidine organothiophosphate insecticides"
## 3383-96-8
## "phenyl organothiophosphate insecticides"
#Identify common names and roles of chemicals
cas_rns <- lc50[order(lc50$value)[1:3], "cas"]
cas_rns
## [1] "563-12-2" "96182-53-5" "3383-96-8"
chebiids <- get_chebiid(cas_rns)
chebiids
## # A tibble: 3 x 5
## query chebiid chebiasciiname searchscore entitystar
## <chr> <chr> <chr> <chr> <chr>
## 1 563-12-2 CHEBI:38663 ethion 0.5 3
## 2 96182-53-5 CHEBI:38951 tebupirimfos 0.55 3
## 3 3383-96-8 CHEBI:38954 temephos 0.48 3
comp <- chebi_comp_entity(chebiids$chebiid)
pars <- lapply(comp, function(x)
with(x, parents))
pars
## $`CHEBI:38663`
## chebiName chebiId type status
## 1 insecticide CHEBI:24852 has role CHECKED
## 2 environmental contaminant CHEBI:78298 has role CHECKED
## 3 EC 3.1.1.7 (acetylcholinesterase) inhibitor CHEBI:38462 has role CHECKED
## 4 organic thiophosphate CHEBI:37512 is a CHECKED
## 5 acaricide CHEBI:22153 has role CHECKED
## 6 agrochemical CHEBI:33286 has role CHECKED
## cyclicRelationship
## 1 false
## 2 false
## 3 false
## 4 false
## 5 false
## 6 false
##
## $`CHEBI:38951`
## chebiName chebiId type
## 1 EC 3.1.1.7 (acetylcholinesterase) inhibitor CHEBI:38462 has role
## 2 organic thiophosphate CHEBI:37512 is a
## 3 organothiophosphate insecticide CHEBI:25715 is a
## 4 2-tert-butylpyrimidin-5-ol CHEBI:38952 has functional parent
## status cyclicRelationship
## 1 CHECKED false
## 2 CHECKED false
## 3 CHECKED false
## 4 CHECKED false
##
## $`CHEBI:38954`
## chebiName chebiId type
## 1 organic sulfide CHEBI:16385 is a
## 2 EC 3.1.1.7 (acetylcholinesterase) inhibitor CHEBI:38462 has role
## 3 organic thiophosphate CHEBI:37512 is a
## 4 organothiophosphate insecticide CHEBI:25715 is a
## 5 acaricide CHEBI:22153 has role
## 6 agrochemical CHEBI:33286 has role
## 7 ectoparasiticide CHEBI:38956 has role
## 8 4,4'-thiodiphenol CHEBI:38957 has functional parent
## status cyclicRelationship
## 1 CHECKED false
## 2 CHECKED false
## 3 CHECKED false
## 4 CHECKED false
## 5 CHECKED false
## 6 CHECKED false
## 7 CHECKED false
## 8 CHECKED false
str(pars)
## List of 3
## $ CHEBI:38663:'data.frame': 6 obs. of 5 variables:
## ..$ chebiName : chr [1:6] "insecticide" "environmental contaminant" "EC 3.1.1.7 (acetylcholinesterase) inhibitor" "organic thiophosphate" ...
## ..$ chebiId : chr [1:6] "CHEBI:24852" "CHEBI:78298" "CHEBI:38462" "CHEBI:37512" ...
## ..$ type : chr [1:6] "has role" "has role" "has role" "is a" ...
## ..$ status : chr [1:6] "CHECKED" "CHECKED" "CHECKED" "CHECKED" ...
## ..$ cyclicRelationship: chr [1:6] "false" "false" "false" "false" ...
## $ CHEBI:38951:'data.frame': 4 obs. of 5 variables:
## ..$ chebiName : chr [1:4] "EC 3.1.1.7 (acetylcholinesterase) inhibitor" "organic thiophosphate" "organothiophosphate insecticide" "2-tert-butylpyrimidin-5-ol"
## ..$ chebiId : chr [1:4] "CHEBI:38462" "CHEBI:37512" "CHEBI:25715" "CHEBI:38952"
## ..$ type : chr [1:4] "has role" "is a" "is a" "has functional parent"
## ..$ status : chr [1:4] "CHECKED" "CHECKED" "CHECKED" "CHECKED"
## ..$ cyclicRelationship: chr [1:4] "false" "false" "false" "false"
## $ CHEBI:38954:'data.frame': 8 obs. of 5 variables:
## ..$ chebiName : chr [1:8] "organic sulfide" "EC 3.1.1.7 (acetylcholinesterase) inhibitor" "organic thiophosphate" "organothiophosphate insecticide" ...
## ..$ chebiId : chr [1:8] "CHEBI:16385" "CHEBI:38462" "CHEBI:37512" "CHEBI:25715" ...
## ..$ type : chr [1:8] "is a" "has role" "is a" "is a" ...
## ..$ status : chr [1:8] "CHECKED" "CHECKED" "CHECKED" "CHECKED" ...
## ..$ cyclicRelationship: chr [1:8] "false" "false" "false" "false" ...
#Querying partitioning coefficients
cid <- get_cid(lc50$cas, from = "xref/rn", match = "first")
cid
## # A tibble: 3 x 2
## query cid
## <chr> <chr>
## 1 563-12-2 3286
## 2 96182-53-5 93516
## 3 3383-96-8 5392
pc_data <- pc_prop(cid$cid)
pc_data
## CID MolecularFormula MolecularWeight
## 1 3286 C9H22O4P2S4 384.5
## 2 93516 C13H23N2O3PS 318.37
## 3 5392 C16H20O6P2S3 466.5
## CanonicalSMILES
## 1 CCOP(=S)(OCC)SCSP(=S)(OCC)OCC
## 2 CCOP(=S)(OC1=CN=C(N=C1)C(C)(C)C)OC(C)C
## 3 COP(=S)(OC)OC1=CC=C(C=C1)SC2=CC=C(C=C2)OP(=S)(OC)OC
## IsomericSMILES
## 1 CCOP(=S)(OCC)SCSP(=S)(OCC)OCC
## 2 CCOP(=S)(OC1=CN=C(N=C1)C(C)(C)C)OC(C)C
## 3 COP(=S)(OC)OC1=CC=C(C=C1)SC2=CC=C(C=C2)OP(=S)(OC)OC
## InChI
## 1 InChI=1S/C9H22O4P2S4/c1-5-10-14(16,11-6-2)18-9-19-15(17,12-7-3)13-8-4/h5-9H2,1-4H3
## 2 InChI=1S/C13H23N2O3PS/c1-7-16-19(20,17-10(2)3)18-11-8-14-12(15-9-11)13(4,5)6/h8-10H,7H2,1-6H3
## 3 InChI=1S/C16H20O6P2S3/c1-17-23(25,18-2)21-13-5-9-15(10-6-13)27-16-11-7-14(8-12-16)22-24(26,19-3)20-4/h5-12H,1-4H3
## InChIKey
## 1 RIZMRRKBZQXFOY-UHFFFAOYSA-N
## 2 AWYOMXWDGWUJHS-UHFFFAOYSA-N
## 3 WWJZWCUNLNYYAU-UHFFFAOYSA-N
## IUPACName
## 1 diethoxyphosphinothioylsulfanylmethylsulfanyl-diethoxy-sulfanylidene-lambda5-phosphane
## 2 (2-tert-butylpyrimidin-5-yl)oxy-ethoxy-propan-2-yloxy-sulfanylidene-lambda5-phosphane
## 3 [4-(4-dimethoxyphosphinothioyloxyphenyl)sulfanylphenoxy]-dimethoxy-sulfanylidene-lambda5-phosphane
## XLogP ExactMass MonoisotopicMass TPSA Complexity Charge HBondDonorCount
## 1 5.1 383.98761787 383.98761787 152.0 279 0 0
## 2 4.2 318.11670077 318.11670077 85.6 339 0 0
## 3 6.0 465.98972587 465.98972587 145.0 474 0 0
## HBondAcceptorCount RotatableBondCount HeavyAtomCount IsotopeAtomCount
## 1 8 12 19 0
## 2 6 7 20 0
## 3 9 10 27 0
## AtomStereoCount DefinedAtomStereoCount UndefinedAtomStereoCount
## 1 0 0 0
## 2 1 0 1
## 3 0 0 0
## BondStereoCount DefinedBondStereoCount UndefinedBondStereoCount
## 1 0 0 0
## 2 0 0 0
## 3 0 0 0
## CovalentUnitCount Volume3D XStericQuadrupole3D YStericQuadrupole3D
## 1 1 272.4 9.91 4.78
## 2 1 244.6 12.00 2.92
## 3 1 330.5 16.56 4.71
## ZStericQuadrupole3D FeatureCount3D FeatureAcceptorCount3D FeatureDonorCount3D
## 1 1.71 0 0 0
## 2 1.22 5 1 0
## 3 1.92 2 0 0
## FeatureAnionCount3D FeatureCationCount3D FeatureRingCount3D
## 1 0 0 0
## 2 0 1 1
## 3 0 0 2
## FeatureHydrophobeCount3D ConformerModelRMSD3D EffectiveRotorCount3D
## 1 0 1.0 12
## 2 2 0.8 7
## 3 0 1.0 10
## ConformerCount3D
## 1 10
## 2 10
## 3 10
## Fingerprint2D
## 1 AAADceBwOANwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAGgQAACAAAACggAKCAAAAARAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA==
## 2 AAADceBzMAJAAAAAAAAAAAAAAAAAAAAAAAAsAAAAAAAAAAABgAAAHgAAACAADhThkwYvlpYIERCgABJnZASAgCkRQKABUCArRBCCCIBASUAEBAgIAALQACAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA==
## 3 AAADceB4OANgAAAAAAAAAAAAAAAAAAAAAAAwYAAAAAAAAAABQAAAGgQAACAACASA0AIyB4AAARiAACBCAAACAAAgKBAIiBgGCIgIJiKgERKAMAAkwBEoiAeAQAAAAIAAAAAAAAABAAAAAAAAAAAAAAAAAA==
lc50$logp <- pc_data$XLogP
#Regulatory information
eqs <- etox_targets(ids$etoxid)
ids$etoxid
## 2,4-Xylenol 4-Chlor-2-methylphenol
## "8668" "8494" NA
eqs
## $`8668`
## $`8668`$res
## ETOX_ID_NR Substance CAS_NO EC_NO ETOX_ID_NO_Substance
## 1 891 2,4-Xylenol 105-67-9 203-321-6 8668
## 2 892 2,4-Xylenol 105-67-9 203-321-6 8668
## 3 2091 2,4-Xylenol 105-67-9 203-321-6 8668
## 4 2092 2,4-Xylenol 105-67-9 203-321-6 8668
## 5 2093 2,4-Xylenol 105-67-9 203-321-6 8668
## Country_or_Region County Medium Status Protected_Asset Use Protection_Level
## 1 USA - AQ QC AQL-FRESH NA n.s.
## 2 USA - AQ QC AQL-MARIN NA n.s.
## 3 USA - AQ QC DRINK-FISH NA n.s.
## 4 USA - AQ QC FISH-CONSM NA n.s.
## 5 USA - AQ QC GESCHMACK NA n.s.
## Institution Designation Operator Value_Target_LR Value_Target_UR Unit
## 1 EPA_USA CCC NA 530.0 0 μg/l
## 2 EPA_USA CCC NA 110.0 0 μg/l
## 3 EPA_USA WQC NA 540.0 0 μg/l
## 4 EPA_USA WQC NA 2.3 0 μg/l
## 5 EPA_USA WQC NA 400.0 0 μg/l
## Concentration_Specification Concentration_Specification.Monitoring Remark
## 1 four-day average NA
## 2 four-day average NA
## 3 - - NA
## 4 - - NA
## 5 - - NA
## Derivation_Base Derivation_Method Note Target_Description
## 1 NA NA NA NA
## 2 NA NA NA NA
## 3 NA NA NA NA
## 4 NA NA NA NA
## 5 NA NA NA NA
## ETOX_ID_NO_Reference Author Year
## 1 1350 U.S. EPA 1993
## 2 1350 U.S. EPA 1993
## 3 1362 U.S. EPA 1999
## 4 1362 U.S. EPA 1999
## 5 1362 U.S. EPA 1999
## Title
## 1 Ambient aquatic life water quality criteria for 2,4-Dimethylphenol (CAS Registry Number 105-67-9)
## 2 Ambient aquatic life water quality criteria for 2,4-Dimethylphenol (CAS Registry Number 105-67-9)
## 3 National recommended water quality criteria-correction.
## 4 National recommended water quality criteria-correction.
## 5 National recommended water quality criteria-correction.
## Journal Volume Pages
## 1 NA NA NA
## 2 NA NA NA
## 3 NA NA NA
## 4 NA NA NA
## 5 NA NA NA
## Source
## 1 U.S. EPA, NTIS: PB 94-118551
## 2 U.S. EPA, NTIS: PB 94-118551
## 3 United States Environmental Protection Agency. Washington, DC. Office of Water. EPA-822-Z-99-001. PB99-149189. Updates are available. Please look up: https://www.epa.gov/wqc/national-recommended-water-quality-criteria.
## 4 United States Environmental Protection Agency. Washington, DC. Office of Water. EPA-822-Z-99-001. PB99-149189. Updates are available. Please look up: https://www.epa.gov/wqc/national-recommended-water-quality-criteria.
## 5 United States Environmental Protection Agency. Washington, DC. Office of Water. EPA-822-Z-99-001. PB99-149189. Updates are available. Please look up: https://www.epa.gov/wqc/national-recommended-water-quality-criteria.
##
## $`8668`$source_url
## [1] "https://webetox.uba.de/webETOX/public/basics/stoff/ziel.do?stoff=6203&language=en"
##
##
## $`8494`
## $`8494`$res
## ETOX_ID_NR Substance CAS_NO EC_NO ETOX_ID_NO_Substance
## 1 4639 4-Chlor-2-methylphenol 1570-64-5 NA 8494
## 2 4990 4-Chlor-2-methylphenol 1570-64-5 NA 8494
## Country_or_Region County Medium Status Protected_Asset Use Protection_Level
## 1 EEC / EU - AQ QC AQL-FRESH NA NA
## 2 NLD - AQ QC AQL-FRESH NA NA
## Institution Designation Operator Value_Target_LR Value_Target_UR Unit
## 1 PNEC = 50 0 μg/l
## 2 RIVM_NL MTR 50 0 μg/l
## Concentration_Specification Concentration_Specification.Monitoring Remark
## 1 NA NA NA
## 2 NA NA NA
## Derivation_Base Derivation_Method Note Target_Description
## 1 NA AF=10 NA NA
## 2 NA NA NA
## ETOX_ID_NO_Reference
## 1 24181
## 2 24276
## Author
## 1 European Commission ? Joint Research Centre\nInstitute for Health and Consumer Protection\nEuropean Chemicals Bureau (ECB)
## 2 Janus, J.A., Posthumus, R.
## Year
## 1 NA
## 2 NA
## Title
## 1 European Union Risk Assessment Report: 4-chloro-o-cresol CAS No: 1570-64-5 , EINECS No: 216-381-3
## 2 Environmental Risk Limits for 2-propanol, formaldehyde and 4-chloromethylphenols - updated proposals
## Journal Volume Pages
## 1 NA NA NA
## 2 NA NA NA
## Source
## 1 OFFICE FOR OFFICIAL PUBLICATIONS\nOF THE EUROPEAN COMMUNITIES\nL ? 2985 Luxembourg
## 2 RIVM report 601501015/2002
##
## $`8494`$source_url
## [1] "https://webetox.uba.de/webETOX/public/basics/stoff/ziel.do?stoff=6065&language=en"
##
##
## $<NA>
## [1] NA
#View(do.call("rbind",eqs))
ids$mac <- sapply(eqs, function(y) {
if (is(y, "list")) {
min(subset(y$res)[["Value_Target_LR"]])
} else NA_real_
})
ids
## # A tibble: 3 x 4
## query match etoxid mac
## <chr> <chr> <chr> <dbl>
## 1 2,4-Dimethylphenol 2,4-Xylenol 8668 2.3
## 2 4-Chlor-2-methylphenol 4-Chlor-2-methylphenol 8494 50
## 3 4-para-nonylphenol <NA> <NA> NA
(mac <- with(ids, ids[!is.na(mac) & is.finite(mac), c("etoxid", "query",
"mac")]))
## # A tibble: 2 x 3
## etoxid query mac
## <chr> <chr> <dbl>
## 1 8668 2,4-Dimethylphenol 2.3
## 2 8494 4-Chlor-2-methylphenol 50
jagst_eqs <- merge(jagst, mac, by.x = "substance", by.y = "query")
jagst_eqs
## substance date value qual etoxid mac
## 1 2,4-Dimethylphenol 2013-01-04 0.006 < 8668 2.3
## 2 2,4-Dimethylphenol 2013-01-29 0.006 < 8668 2.3
## 3 2,4-Dimethylphenol 2013-02-26 0.006 < 8668 2.3
## 4 2,4-Dimethylphenol 2013-03-26 0.006 < 8668 2.3
## 5 2,4-Dimethylphenol 2013-04-23 0.006 < 8668 2.3
## 6 2,4-Dimethylphenol 2013-05-22 0.006 < 8668 2.3
## 7 2,4-Dimethylphenol 2013-06-18 0.006 < 8668 2.3
## 8 2,4-Dimethylphenol 2013-07-16 0.006 < 8668 2.3
## 9 2,4-Dimethylphenol 2013-08-13 0.006 = 8668 2.3
## 10 2,4-Dimethylphenol 2013-09-10 0.006 = 8668 2.3
## 11 2,4-Dimethylphenol 2013-10-08 0.006 < 8668 2.3
## 12 2,4-Dimethylphenol 2013-11-05 0.006 < 8668 2.3
## 13 2,4-Dimethylphenol 2013-12-03 0.006 < 8668 2.3
## 14 4-Chlor-2-methylphenol 2013-01-04 0.006 < 8494 50.0
## 15 4-Chlor-2-methylphenol 2013-01-29 0.007 = 8494 50.0
## 16 4-Chlor-2-methylphenol 2013-02-26 0.006 < 8494 50.0
## 17 4-Chlor-2-methylphenol 2013-03-26 0.006 < 8494 50.0
## 18 4-Chlor-2-methylphenol 2013-04-23 0.006 < 8494 50.0
## 19 4-Chlor-2-methylphenol 2013-05-22 0.006 < 8494 50.0
## 20 4-Chlor-2-methylphenol 2013-06-18 0.006 < 8494 50.0
## 21 4-Chlor-2-methylphenol 2013-07-16 0.006 < 8494 50.0
## 22 4-Chlor-2-methylphenol 2013-08-13 0.006 < 8494 50.0
## 23 4-Chlor-2-methylphenol 2013-09-10 0.006 < 8494 50.0
## 24 4-Chlor-2-methylphenol 2013-10-08 0.006 < 8494 50.0
## 25 4-Chlor-2-methylphenol 2013-11-05 0.006 < 8494 50.0
## 26 4-Chlor-2-methylphenol 2013-12-03 0.006 < 8494 50.0
# Utility functions
is.inchikey("BQJCRHHNABKAKU-KBQPJGBKS-AN")
## [1] FALSE
is.cas("64-17-6")
## 64-17-6
## FALSE
is.inchikey("BQJCRHHNABKAKU-KBQPJGBKSA-5", type = "chemspider")
## [1] FALSE
#ref https://www.jstatsoft.org/article/view/v093i13
#https://cran.r-project.org/web/packages/webchem/vignettes/webchem.html