The tritrypdb just released a new version. Let us make new annotation data from it.
## These functions take _forever_ the first time around.
lm_annot <- make_eupath_organismdbi(species="Leishmania major", reinstall=TRUE)In order to load these new packages, I rather need to remember their names… Happily I have a function for that.
lm_name <- get_eupath_pkgnames("Leishmania major", version="37")## Starting metadata download.## Finished metadata download.## Found the following hits: Leishmania major strain Friedlin, Leishmania major strain LV39c5, Leishmania major strain SD 75.1, choosing the first.lm_name$organismdbi## [1] "eupathdb.Leishmania.major.Friedlin.v37"lmx_name <- get_eupath_pkgnames("Leishmania mexicana", version="37")## Starting metadata download.## Finished metadata download.## Found the following hits: Leishmania mexicana MHOM/GT/2001/U1103, choosing the first.lmx_name$organismdbi## [1] "eupathdb.Leishmania.mexicana.MHOMGT2001U1103.v37"For those packages I have generated/installed, use this to generate an annotation table. Oh, but I prefixed the column names with ‘annot_’ in order to make sure that nothing is duplicated with the GO tables, ortholog tables, etc. As a result, these are wrong until the new annotations are loaded.
## Just to save on typing
library(lm_name$orgdb, character=TRUE)## Loading required package: AnnotationDbi## Loading required package: stats4## Loading required package: BiocGenerics## Loading required package: parallel##
## Attaching package: 'BiocGenerics'## The following objects are masked from 'package:parallel':
##
## clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
## clusterExport, clusterMap, parApply, parCapply, parLapply,
## parLapplyLB, parRapply, parSapply, parSapplyLB## The following objects are masked from 'package:stats':
##
## IQR, mad, sd, var, xtabs## The following objects are masked from 'package:base':
##
## anyDuplicated, append, as.data.frame, basename, cbind,
## colMeans, colnames, colSums, dirname, do.call, duplicated,
## eval, evalq, Filter, Find, get, grep, grepl, intersect,
## is.unsorted, lapply, lengths, Map, mapply, match, mget, order,
## paste, pmax, pmax.int, pmin, pmin.int, Position, rank, rbind,
## Reduce, rowMeans, rownames, rowSums, sapply, setdiff, sort,
## table, tapply, union, unique, unsplit, which, which.max,
## which.min## Loading required package: Biobase## Welcome to Bioconductor
##
## Vignettes contain introductory material; view with
## 'browseVignettes()'. To cite Bioconductor, see
## 'citation("Biobase")', and for packages 'citation("pkgname")'.## Loading required package: IRanges## Loading required package: S4Vectors##
## Attaching package: 'S4Vectors'## The following object is masked from 'package:base':
##
## expand.grid## lm_db <- get0(lm_name$orgdb)
lm_db## OrgDb object:
## | DBSCHEMAVERSION: 2.1
## | DBSCHEMA: NOSCHEMA_DB
## | ORGANISM: Leishmania major strain Friedlin
## | SPECIES: Leishmania major strain Friedlin
## | CENTRALID: GID
## | Taxonomy ID: 347515
## | Db type: OrgDb
## | Supporting package: AnnotationDbi##
## Please see: help('select') for usage informationlibrary(lmx_name$orgdb, character=TRUE)## lmx_db <- get0(lmx_name$orgdb)
lmx_db## OrgDb object:
## | DBSCHEMAVERSION: 2.1
## | DBSCHEMA: NOSCHEMA_DB
## | ORGANISM: Leishmania mexicana MHOM/GT/2001/U1103
## | SPECIES: Leishmania mexicana MHOM/GT/2001/U1103
## | CENTRALID: GID
## | Taxonomy ID: 929439
## | Db type: OrgDb
## | Supporting package: AnnotationDbi##
## Please see: help('select') for usage informationwanted_fields <- c("annot_gene_location_text",
"annot_cds_length",
"annot_gene_name",
"annot_gene_product",
"annot_gene_type",
"annot_strand",
"annot_gene_entrez_id",
"annot_gene_orthomcl_name")
lm_annot <- load_orgdb_annotations(lm_db,
keytype="gid",
fields=wanted_fields)## Unable to find CDSNAME, setting it to ANNOT_GENE_NAME.## Unable to find CDSCHROM in the db, removing it.## Unable to find CDSSTRAND in the db, removing it.## Unable to find CDSSTART in the db, removing it.## Unable to find CDSEND in the db, removing it.## Extracted all gene ids.## Attempting to select: ANNOT_GENE_NAME, GENE_TYPE, ANNOT_GENE_LOCATION_TEXT, ANNOT_CDS_LENGTH, ANNOT_GENE_NAME, ANNOT_GENE_PRODUCT, ANNOT_GENE_TYPE, ANNOT_STRAND, ANNOT_GENE_ENTREZ_ID, ANNOT_GENE_ORTHOMCL_NAME## 'select()' returned 1:many mapping between keys and columnslm_annot <- extract_gene_locations(lm_annot$genes)
rownames(lm_annot) <- paste0(rownames(lm_annot), ".1")
lmx_annot <- load_orgdb_annotations(lmx_db,
keytype="gid",
fields=wanted_fields)## Unable to find CDSNAME, setting it to ANNOT_GENE_NAME.## Unable to find CDSCHROM in the db, removing it.## Unable to find CDSSTRAND in the db, removing it.## Unable to find CDSSTART in the db, removing it.## Unable to find CDSEND in the db, removing it.## Extracted all gene ids.## Attempting to select: ANNOT_GENE_NAME, GENE_TYPE, ANNOT_GENE_LOCATION_TEXT, ANNOT_CDS_LENGTH, ANNOT_GENE_NAME, ANNOT_GENE_PRODUCT, ANNOT_GENE_TYPE, ANNOT_STRAND, ANNOT_GENE_ENTREZ_ID, ANNOT_GENE_ORTHOMCL_NAME## 'select()' returned 1:1 mapping between keys and columnslmx_annot <- extract_gene_locations(lmx_annot$genes)
rownames(lmx_annot) <- paste0(rownames(lmx_annot), ".1")lm_gff_file <- "reference/TriTrypDB-37_LmajorFriedlin.gff"
lm_gff_annotations <- sm(load_gff_annotations(lm_gff_file, type="exon"))if (!isTRUE(get0("skip_load"))) {
pander::pander(sessionInfo())
message(paste0("This is hpgltools commit: ", get_git_commit()))
message(paste0("Saving to ", savefile))
tmp <- sm(saveme(filename=savefile))
}## If you wish to reproduce this exact build of hpgltools, invoke the following:## > git clone http://github.com/abelew/hpgltools.git## > git reset 0b63ce6abcbb822832fe4631b4916f94931d8648## R> packrat::restore()## This is hpgltools commit: Wed Sep 5 12:04:45 2018 -0400: 0b63ce6abcbb822832fe4631b4916f94931d8648## Saving to 01_annotation_v20180828.rda.xz