Take NCBI taxa IDs and get the corresponding taxa ranks from a name and node SQLite database
Usage
getTaxonomy(
ids,
sqlFile = "nameNode.sqlite",
...,
desiredTaxa = c("domain", "phylum", "class", "order", "family", "genus", "species"),
getNames = TRUE
)Arguments
- ids
a vector of ids to find taxonomy for
- sqlFile
a string giving the path to a SQLite file containing names and nodes tables
- ...
legacy additional arguments to original data.table based getTaxonomy function. Used only for support for deprecated function, do not use in new code.
- desiredTaxa
a vector of strings giving the desired taxa levels
- getNames
a logical indicating whether to convert taxon IDs to names if TRUE or simply return the taxon ID if FALSE
Examples
sqlFile<-tempfile()
namesText<-c(
"1\t|\tall\t|\t\t|\tsynonym\t|",
"1\t|\troot\t|\t\t|\tscientific name\t|",
"2\t|\tBacteria\t|\tBacteria <prokaryotes>\t|\tscientific name\t|",
"2\t|\tMonera\t|\tMonera <Bacteria>\t|\tin-part\t|",
"2\t|\tProcaryotae\t|\tProcaryotae <Bacteria>\t|\tin-part\t|",
"9606\t|\tHomo sapiens\t|\t\t|\tscientific name",
"9605\t|\tHomo\t|\t\t|\tscientific name",
"207598\t|\tHomininae\t|\t\t|\tscientific name",
"9604\t|\tHominidae\t|\t\t|\tscientific name",
"314295\t|\tHominoidea\t|\t\t|\tscientific name",
"9526\t|\tCatarrhini\t|\t\t|\tscientific name",
"314293\t|\tSimiiformes\t|\t\t|\tscientific name",
"376913\t|\tHaplorrhini\t|\t\t|\tscientific name",
"9443\t|\tPrimates\t|\t\t|\tscientific name",
"314146\t|\tEuarchontoglires\t|\t\t|\tscientific name",
"1437010\t|\tBoreoeutheria\t|\t\t|\tscientific name",
"9347\t|\tEutheria\t|\t\t|\tscientific name",
"32525\t|\tTheria\t|\t\t|\tscientific name",
"40674\t|\tMammalia\t|\t\t|\tscientific name",
"32524\t|\tAmniota\t|\t\t|\tscientific name",
"32523\t|\tTetrapoda\t|\t\t|\tscientific name",
"1338369\t|\tDipnotetrapodomorpha\t|\t\t|\tscientific name",
"8287\t|\tSarcopterygii\t|\t\t|\tscientific name",
"117571\t|\tEuteleostomi\t|\t\t|\tscientific name",
"117570\t|\tTeleostomi\t|\t\t|\tscientific name",
"7776\t|\tGnathostomata\t|\t\t|\tscientific name",
"7742\t|\tVertebrata\t|\t\t|\tscientific name",
"89593\t|\tCraniata\t|\t\t|\tscientific name",
"7711\t|\tChordata\t|\t\t|\tscientific name",
"33511\t|\tDeuterostomia\t|\t\t|\tscientific name",
"33213\t|\tBilateria\t|\t\t|\tscientific name",
"6072\t|\tEumetazoa\t|\t\t|\tscientific name",
"33208\t|\tMetazoa\t|\t\t|\tscientific name",
"33154\t|\tOpisthokonta\t|\t\t|\tscientific name",
"2759\t|\tEukaryota\t|\t\t|\tscientific name",
"131567\t|\tcellular organisms\t|\t\t|\tscientific name"
)
tmpFile<-tempfile()
writeLines(namesText,tmpFile)
taxaNames<-read.names.sql(tmpFile,sqlFile)
nodesText<-c(
"1\t|\t1\t|\tno rank\t|\t\t|\t8\t|\t0\t|\t1\t|\t0\t|\t0\t|\t0\t|\t0\t|\t0\t|\t\t|",
"2\t|\t131567\t|\tdomain\t|\t\t|\t0\t|\t0\t|\t11\t|\t0\t|\t0\t|\t0\t|\t0\t|\t0\t|\t\t|",
"6\t|\t335928\t|\tgenus\t|\t\t|\t0\t|\t1\t|\t11\t|\t1\t|\t0\t|\t1\t|\t0\t|\t0\t|\t\t|",
"7\t|\t6\t|\tspecies\t|\tAC\t|\t0\t|\t1\t|\t11\t|\t1\t|\t0\t|\t1\t|\t1\t|\t0\t|\t\t|",
"9\t|\t32199\t|\tspecies\t|\tBA\t|\t0\t|\t1\t|\t11\t|\t1\t|\t0\t|\t1\t|\t1\t|\t0\t|\t\t|",
"9606\t|\t9605\t|\tspecies", "9605\t|\t207598\t|\tgenus", "207598\t|\t9604\t|\tsubfamily",
"9604\t|\t314295\t|\tfamily", "314295\t|\t9526\t|\tsuperfamily",
"9526\t|\t314293\t|\tparvorder", "314293\t|\t376913\t|\tinfraorder",
"376913\t|\t9443\t|\tsuborder", "9443\t|\t314146\t|\torder",
"314146\t|\t1437010\t|\tsuperorder", "1437010\t|\t9347\t|\tno rank",
"9347\t|\t32525\t|\tno rank", "32525\t|\t40674\t|\tno rank",
"40674\t|\t32524\t|\tclass", "32524\t|\t32523\t|\tno rank", "32523\t|\t1338369\t|\tno rank",
"1338369\t|\t8287\t|\tno rank", "8287\t|\t117571\t|\tno rank",
"117571\t|\t117570\t|\tno rank", "117570\t|\t7776\t|\tno rank",
"7776\t|\t7742\t|\tno rank", "7742\t|\t89593\t|\tno rank", "89593\t|\t7711\t|\tsubphylum",
"7711\t|\t33511\t|\tphylum", "33511\t|\t33213\t|\tno rank", "33213\t|\t6072\t|\tno rank",
"6072\t|\t33208\t|\tno rank", "33208\t|\t33154\t|\tkingdom",
"33154\t|\t2759\t|\tno rank", "2759\t|\t131567\t|\tdomain",
"131567\t|\t1\t|\tno rank"
)
writeLines(nodesText,tmpFile)
taxaNodes<-read.nodes.sql(tmpFile,sqlFile)
getTaxonomy(c(9606,9605),sqlFile)
#> domain phylum class order family genus
#> 9606 "Eukaryota" "Chordata" "Mammalia" "Primates" "Hominidae" "Homo"
#> 9605 "Eukaryota" "Chordata" "Mammalia" "Primates" "Hominidae" "Homo"
#> species
#> 9606 "Homo sapiens"
#> 9605 NA