Get functions — get_ • KGExplorer

Functions to get data resources.

get_alphamissense(
  types = c("canonical", "non_canonical", "merged"),
  agg_fun = mean,
  save_dir = cache_dir(),
  force_new = FALSE
)

get_clinvar(as_granges = FALSE, annotate = FALSE)

get_data_package(name, package = "KGExplorer")

get_definitions(ont, from = "id", to = "definition")

get_gencc(
  agg_by = c("disease_id", "gene_symbol"),
  dict = c(Definitive = 6, Strong = 5, Moderate = 4, Supportive = 3, Limited = 2,
    `Disputed Evidence` = 1, `Refuted Evidence` = 0, `No Known Disease Relationship` = 0),
  save_dir = cache_dir(),
  force_new = FALSE
)

get_gene_lengths(genes, keep_chr = c(seq(22), "X", "Y"), ensembl_version = 75)

get_genes_disease(
  maps = list(c("gene", "disease")),
  run_map_mondo = FALSE,
  to = c("OMIM", "Orphanet", "DECIPHER"),
  ...
)

get_graph_colnames(g, what = c("nodes", "edges"))

get_hpo(
  lvl = 2,
  force_new = FALSE,
  terms = NULL,
  method = "github",
  save_dir = cache_dir(package = "KGExplorer"),
  ...
)

get_medgen_maps()

get_metadata_omim(save_dir = cache_dir())

get_metadata_orphanet(save_dir = cache_dir())

get_monarch(
  queries = NULL,
  maps = NULL,
  domain = "https://data.monarchinitiative.org",
  subdir = "latest/tsv/all_associations/",
  rbind = FALSE,
  save_dir = cache_dir()
)

get_monarch_files(
  maps = NULL,
  queries = NULL,
  domain = "https://data.monarchinitiative.org",
  subdir = "latest/tsv/all_associations/",
  omit = c("...", "md5sums", "index.html")
)

get_monarch_kg(as_graph = TRUE, save_dir = cache_dir(), force_new = FALSE, ...)

get_monarch_models(
  maps = list(m2d = c("model", "disease")),
  filters = list(disease = NULL, gene = NULL, variant = NULL),
  input_col = "object",
  to = NULL,
  map_orthologs = TRUE,
  as_graph = FALSE,
  ...
)

get_mondo_maps(
  map_types = c("default", "broadmatch", "closematch", "exactmatch", "hasdbxref",
    "narrowmatch", "relatedmatch"),
  map_to = NULL,
  map_type_order = c("default", "exactmatch", "closematch", "narrowmatch", "broadmatch",
    "relatedmatch", "hasdbxref"),
  top_n = NULL,
  top_by = c("subject", "object"),
  save_dir = cache_dir()
)

get_mondo_maps_files(map_types, map_to, save_dir)

get_ols_options(ol = rols::Ontologies())

get_ontology(
  name = c("mondo", "hp", "upheno", "uberon", "cl")[1],
  method = c("github", "rols")[1],
  filetype = ".obo",
  import_func = NULL,
  terms = NULL,
  add_metadata = TRUE,
  lvl = 2,
  add_n_edges = TRUE,
  add_ontology_levels = TRUE,
  save_dir = cache_dir(),
  force_new = FALSE,
  ...
)

get_ontology_dict(
  ont,
  from = "short_id",
  to = c("name", "label", "term"),
  include_self = FALSE,
  include_alternative_terms = FALSE,
  as_datatable = FALSE
)

get_ontology_levels(
  ont,
  terms = NULL,
  remove_terms = TRUE,
  method = c("depth", "height"),
  absolute = TRUE,
  reverse = FALSE
)

get_pli(agg_fun = mean, save_dir = cache_dir(), force_new = FALSE)

get_prevalence(
  method = c("orphanet", "oard"),
  agg_by = c("mondo_id", "id", "Name"),
  include_mondo = TRUE,
  ...
)

get_ttd(save_dir = cache_dir(), force_new = FALSE, run_map_genes = TRUE)

get_upheno(file = c("ontology", "bestmatches", "upheno_mapping"))

get_version(obj, return_version = FALSE, verbose = TRUE)

Source

ClinVar server

ClinVar server README

monarchr R package (abandoned project?)

BioThings Explorer

rbiolink

KGX

Arguments

types

A character vector of types to return.

agg_fun

A function to aggregate multiple transcripts per gene.

save_dir

Directory to save a file to.

force_new

If TRUE, force a new download.

as_granges

Return the object as a GRanges.

annotate

Add variant annotations with map_variants.

name

<...>Any ontology name from get_ols_options
"mondo" Import the Mondo ontology. GitHub..
"hpo" Import the Human Phenotype Ontology. GitHub.

package

a character vector giving the package(s) to look in for data sets, or NULL.

By default, all packages in the search path are used, then the data subdirectory (if present) of the current working directory.

ont

An ontology of class ontology_DAG.

from

The designated from column in from-to mapping or relations.

to

A character string specifying the format to convert to.

agg_by

Column names to aggregate results by.

dict

A named vector of evidence score mappings. See here for more information.

genes

A character vector of gene symbols

keep_chr

Which chromosomes to keep.

ensembl_version

Which Ensembl database version to use.

maps

A list of paired to/from types to filter Monarch association files by. For example, list(c("gene","disease")) will return any files that contains gene-disease associations. Passes to get_monarch_files.

run_map_mondo

Run map_mondo to map MONDO IDs to disease IDs.

...

Arguments passed on to link_monarch, get_ontology, data.table::fread, data.table::fread, get_ontology_github

node_filters: A named list of filters to apply to the node data. Names should be name of the metadata column, and values should be a vector of valid options. For example, list("type" = c("gene","variant")) will return any rows where the "type" column contains either "gene" or "variant".
input: A single character string. The value is inspected and deferred to either file= (if no \n present), text= (if at least one \n is present) or cmd= (if no \n is present, at least one space is present, and it isn't a file name). Exactly one of input=, file=, text=, or cmd= should be used in the same call.
text: The input data itself as a character vector of one or more lines, for example as returned by readLines().
cmd: A shell command that pre-processes the file; e.g. fread(cmd=paste("grep",word,"filename")). See Details.
sep: The separator between columns. Defaults to the character in the set [,\t |;:] that separates the sample of rows into the most number of lines with the same number of fields. Use NULL or "" to specify no separator; i.e. each line a single character column like base::readLines does.
sep2: The separator within columns. A list column will be returned where each cell is a vector of values. This is much faster using less working memory than strsplit afterwards or similar techniques. For each column sep2 can be different and is the first character in the same set above [,\t |;], other than sep, that exists inside each field outside quoted regions in the sample. NB: sep2 is not yet implemented.
nrows: The maximum number of rows to read. Unlike read.table, you do not need to set this to an estimate of the number of rows in the file for better speed because that is already automatically determined by fread almost instantly using the large sample of lines. nrows=0 returns the column names and typed empty columns determined by the large sample; useful for a dry run of a large file or to quickly check format consistency of a set of files before starting to read any of them.
header: Does the first data line contain column names? Defaults according to whether every non-empty field on the first data line is type character. If so, or TRUE is supplied, any empty column names are given a default name.
na.strings: A character vector of strings which are to be interpreted as NA values. By default, ",," for columns of all types, including type character is read as NA for consistency. ,"", is unambiguous and read as an empty string. To read ,NA, as NA, set na.strings="NA". To read ,, as blank string "", set na.strings=NULL. When they occur in the file, the strings in na.strings should not appear quoted since that is how the string literal ,"NA", is distinguished from ,NA,, for example, when na.strings="NA".
stringsAsFactors: Convert all or some character columns to factors? Acceptable inputs are TRUE, FALSE, or a decimal value between 0.0 and 1.0. For stringsAsFactors = FALSE, all string columns are stored as character vs. all stored as factor when TRUE. When stringsAsFactors = p for 0 <= p <= 1, string columns col are stored as factor if uniqueN(col)/nrow < p.
skip: If 0 (default) start on the first line and from there finds the first row with a consistent number of columns. This automatically avoids irregular header information before the column names row. skip>0 means ignore the first skip rows manually. skip="string" searches for "string" in the file (e.g. a substring of the column names row) and starts on that line (inspired by read.xls in package gdata).
select: A vector of column names or numbers to keep, drop the rest. select may specify types too in the same way as colClasses; i.e., a vector of colname=type pairs, or a list of type=col(s) pairs. In all forms of select, the order that the columns are specified determines the order of the columns in the result.
drop: Vector of column names or numbers to drop, keep the rest.
colClasses: As in utils::read.csv; i.e., an unnamed vector of types corresponding to the columns in the file, or a named vector specifying types for a subset of the columns by name. The default, NULL means types are inferred from the data in the file. Further, data.table supports a named list of vectors of column names or numbers where the list names are the class names; see examples. The list form makes it easier to set a batch of columns to be a particular class. When column numbers are used in the list form, they refer to the column number in the file not the column number after select or drop has been applied. If type coercion results in an error, introduces NAs, or would result in loss of accuracy, the coercion attempt is aborted for that column with warning and the column's type is left unchanged. If you really desire data loss (e.g. reading 3.14 as integer) you have to truncate such columns afterwards yourself explicitly so that this is clear to future readers of your code.
integer64: "integer64" (default) reads columns detected as containing integers larger than 2^31 as type bit64::integer64. Alternatively, "double"|"numeric" reads as utils::read.csv does; i.e., possibly with loss of precision and if so silently. Or, "character".
dec: The decimal separator as in utils::read.csv. When "auto" (the default), an attempt is made to decide whether "." or "," is more suitable for this input. See details.
col.names: A vector of optional names for the variables (columns). The default is to use the header column if present or detected, or if not "V" followed by the column number. This is applied after check.names and before key and index.
check.names: default is FALSE. If TRUE then the names of the variables in the data.table are checked to ensure that they are syntactically valid variable names. If necessary they are adjusted (by make.names) so that they are, and also to ensure that there are no duplicates.
encoding: default is "unknown". Other possible options are "UTF-8" and "Latin-1". Note: it is not used to re-encode the input, rather enables handling of encoded strings in their native encoding.
quote: By default ("\""), if a field starts with a double quote, fread handles embedded quotes robustly as explained under Details. If it fails, then another attempt is made to read the field as is, i.e., as if quotes are disabled. By setting quote="", the field is always read as if quotes are disabled. It is not expected to ever need to pass anything other than \"\" to quote; i.e., to turn it off.
strip.white: Logical, default TRUE, in which case leading and trailing whitespace is stripped from unquoted "character" fields. "numeric" fields are always stripped of leading and trailing whitespace.
fill: logical or integer (default is FALSE). If TRUE then in case the rows have unequal length, number of columns is estimated and blank fields are implicitly filled. If an integer is provided it is used as an upper bound for the number of columns. If fill=Inf then the whole file is read for detecting the number of columns.
blank.lines.skip: logical, default is FALSE. If TRUE blank lines in the input are ignored.
key: Character vector of one or more column names which is passed to setkey. Only valid when argument data.table=TRUE. Where applicable, this should refer to column names given in col.names.
index: Character vector or list of character vectors of one or more column names which is passed to setindexv. As with key, comma-separated notation like index="x,y,z" is accepted for convenience. Only valid when argument data.table=TRUE. Where applicable, this should refer to column names given in col.names.
showProgress: TRUE displays progress on the console if the ETA is greater than 3 seconds. It is produced in fread's C code where the very nice (but R level) txtProgressBar and tkProgressBar are not easily available.
data.table: TRUE returns a data.table. FALSE returns a data.frame. The default for this argument can be changed with options(datatable.fread.datatable=FALSE).
nThread: The number of threads to use. Experiment to see what works best for your data on your hardware.
logical01: If TRUE a column containing only 0s and 1s will be read as logical, otherwise as integer.
keepLeadingZeros: If TRUE a column containing numeric data with leading zeros will be read as character, otherwise leading zeros will be removed and converted to numeric.
yaml: If TRUE, fread will attempt to parse (using yaml.load) the top of the input as YAML, and further to glean parameters relevant to improving the performance of fread on the data itself. The entire YAML section is returned as parsed into a list in the yaml_metadata attribute. See Details.
autostart: Deprecated and ignored with warning. Please use skip instead.
tmpdir: Directory to use as the tmpdir argument for any tempfile calls, e.g. when the input is a URL or a shell command. The default is tempdir() which can be controlled by setting TMPDIR before starting the R session; see base::tempdir.
tz: Relevant to datetime values which have no Z or UTC-offset at the end, i.e. unmarked datetime, as written by utils::write.csv. The default tz="UTC" reads unmarked datetime as UTC POSIXct efficiently. tz="" reads unmarked datetime as type character (slowly) so that as.POSIXct can interpret (slowly) the character datetimes in local timezone; e.g. by using "POSIXct" in colClasses=. Note that fwrite() by default writes datetime in UTC including the final Z and therefore fwrite's output will be read by fread consistently and quickly without needing to use tz= or colClasses=. If the TZ environment variable is set to "UTC" (or "" on non-Windows where unset vs `""` is significant) then the R session's timezone is already UTC and tz="" will result in unmarked datetimes being read as UTC POSIXct. For more information, please see the news items from v1.13.0 and v1.14.0.
repo: Repository name in format "owner/repo". Defaults to guess_repo().
tag: tag for the GitHub release to which this data should be attached.

g

tbl_graph object.

what

What should get activated? Possible values are nodes or edges.

lvl

Depth of the ancestor terms to add. Will get the closest ancestor to this level if none have this exact level.

terms

A vector of ontology term IDs.

method

Compute ontology levels using:

"height" (default) dag_height.
"depth" dag_depth.

queries

A list of free-form substring queries to filter files by (using any column in the metadata). For example, list("gene_disease","variant_disease") will return any files that contain either of the substrings "gene_disease" or "variant_disease". Passes to get_monarch_files.

domain

Web domain to search for Monarch files.

subdir

Subdirectory path to search for Monarch files within domain.

rbind

If TRUE, rbinds all data.tables together. Otherwise, returns a named list of separated data.tables.

omit

Files to omit from results.

as_graph

Return the object as a tbl_graph.

filters

A named list, where each element in the list is the name of a column in the data, and the vector within each element represents the values to include in the final data.

input_col

Column name of input IDs.

map_orthologs

Add gene-level data.

map_types

Mapping types to include.

map_to

Mapping outputs to include (from Mondo IDs to another database's IDs).

map_type_order

The order in which map_types will be prioritised when filtering the top_n rows by groupings.

top_n

Top number of mappings to return per top_by grouping. Set to NULL to skip this step.

top_by

Grouping columns when selecting top_n rows per grouping. Can be a character vector of one or more column names.

ol

An Ontologies object.

filetype

File type to search for.

import_func

Function to import the ontology with. If NULL, automatically tries to choose the correct function.

add_metadata

Add metadata to the resulting ontology object.

add_n_edges

Add the number of edges (connections) for each term.

add_ontology_levels

Add the ontology level for each term.

include_self

For dag_offspring() and dag_ancestors(), this controls whether to also include the query term itself.

include_alternative_terms

Include alternative terms in the dictionary.

as_datatable

Return as a data.table instead of a named vector.

remove_terms

Character vector of term IDs to exclude.

absolute

Make the levels absolute in the sense that they consider the entire ontology (TRUE). Otherwise, levels will be relative to only the terms that are in the provided subset of terms AND are directly adjacent (connected) to a given cluster of terms (FALSE).

reverse

If TRUE, ontology level numbers with be revered such that the level of the parent terms are larger than the child terms.

include_mondo

Include MONDO IDs in the output.

run_map_genes

Map genes to standardised HGNC symbols using map_genes.

file

Can be one of the following:

"ontology"Creates an ontology_DAG R object by importing the OBO file directly from the official uPheno GitHub repository.
"bestmatches"Returns a merged table with the best matches between human and non-human homologous phenotypes (from multiple species). Distributed by the official uPheno GitHub repository.
"upheno_mapping"Return a merged table with matches between human and non-human homologous phenotypes (from multiple species). Distributed by the Monarch Initiative server.

obj

An object.

return_version

Return the version as a character string.

verbose

Print messages.

Value

Data.

A named list of data.tables of AlphaMissense predictions.

data.table with columns:

"disease_id": Disease ID.
"gene_symbol": Gene symbol.
"evidence_score": Evidence score.

data.table

ontology_DAG object.

data.table

data.table of mappings.

ontology_DAG

A named vector of relative ontology level, where names are ontology term IDs and value is relative ontology level.

ontology_DAG or data.table.

Data object release version a character string.

Functions

get_alphamissense(): get_ Get AlphaMissense predictions

Get gene-level AlphaMissense predictions for all canonical and non-canonical protein-coding gene transcripts.
get_clinvar(): get_ Get ClinVar variant data

ClinSigSimple integer, 0 = no current value of Likely pathogenic; Pathogenic; Likely pathogenic, low penetrance; Pathogenic, low penetrance; Likely risk allele; or Risk allele 1 = at least one current record submitted with an interpretation of Likely pathogenic; Pathogenic; Likely pathogenic, low penetrance; Pathogenic, low penetrance; Likely risk allele; or Risk allele (independent of whether that record includes assertion criteria and evidence). -1 = no values for clinical significance at all for this variant or set of variants; used for the "included" variants that are only in ClinVar because they are included in a haplotype or genotype with an interpretation NOTE: Now that the aggregate values of clinical significance give precedence to records with assertion criteria and evidence, the values in this column may appear to be in conflict with the value reported in ClinicalSignificance. In other words, if a submission without assertion criteria and evidence interpreted an allele as pathogenic, and those with assertion criteria and evidence interpreted as benign, then ClinicalSignificance would be reported as Benign and ClinSigSimple as 1.
get_data_package(): get_
get_definitions(): get_ Add ancestor

For each term, get its ancestor at a given level and add the ID and name of the ancestor to the ontology metadata.
get_gencc(): get_ Get GenCC

Get phenotype-gene evidence score from the Gene Curation Coalition. Note that the column "submitted_as_moi_id" indicates the mechanism of action (e.g. "Autosomal dominant inheritance"), not specific HPO phenotypes. Set agg_by=NULL to return raw unaggregated data.

Data downloaded from here.
NOTE: Due to licensing restrictions, a GenCC download does not include OMIM data. OMIM data can be accessed and downloaded through OMIM.
NOTE: GenCC does not currently have any systematic versioning. There for the attr(obj,"version") attribute is set to the date it was downloaded and cached by get_gencc.
get_gene_lengths(): get_
get_genes_disease(): get_ Load disease genes

Load gene lists associated with each disease phenotype from:
- OMIM
- Orphanet
- DECIPHER
get_graph_colnames(): get_ Get column names in the nodes and/or edges of a tbl_graph.
get_hpo(): get_ Get Human Phenotype Ontology (HPO)

Updated version of Human Phenotype Ontology (HPO). Created from the OBO files distributed by the HPO project's GitHub. Adapted from get_hpo.

By comparison, the hpo data from ontologyIndex is from 2016. Note that the maximum ontology level depth in the 2016 version was 14, whereas in the 2023 version the maximum ontology level depth is 16 (due to an expansion of the HPO).
get_medgen_maps(): get_ Get MedGen maps.
get_metadata_omim(): get_
get_metadata_orphanet(): get_
get_monarch(): get_ Get Monarch

Get key datasets from the Monarch Initiative server. See here for all associations data, specifically.
get_monarch_files(): get_ Monarch files

Find files Monarch Initiative server.
get_monarch_kg(): get_ Get knowledge graph: Monarch

Imports the entire Monarch knowledge graph containing >500,000 nodes and >10,000,000 edges across many categories (e.g. Disease, Phenotypes, Cell Types, etc.).

Option 1: Use the biolink API to efficiently extract specific subset of data from the Monarch server. Option 2: Import the entire knowledge graph from the Monarch server.
get_monarch_models(): get_ Get Monarch models

Get disease-to-model mappings for multiple model species. Additionally maps mondo IDs to OMIM and Orphanet IDs. NOTE, adding additional maps will drastically reduce the number of results.
get_mondo_maps(): get_ Get Mondo ID maps

Get mappings between Mondo IDs and IDs in other databases/ontologies. All mappings stored on the official Mondo GitHub.
get_mondo_maps_files(): get_
get_ols_options(): get_ Get a complete up=to-date list of ontologies available via the EBML-EBI Ontology Lookup Service API.
get_ontology(): get_ontology Get ontology

Import an up-to-date ontology directly from from the creators or via the EBML-EBI Ontology Lookup Service API.
get_ontology_dict(): get_
get_ontology_levels(): get_ Get ontology level for ontology terms

For a given set of HPO terms, get their level within the hierarchically organised ontology. Ontology level can be computed either absolute mode (absolute=TRUE) where the entire ontology is considered when assigning levels, or relative mode (absolute=FALSE) where only a subset of the ontology that is connected to a given term is considered when assigning levels. Relative mode can be helpful when trying to make plot where nodes are scaled to the ontology level.
get_pli(): get_ Get pLI

Get gene-level pLI scores for all canonical and non-canonical protein-coding gene transcripts. NOTE: The MANE Select set consists of one transcript at each protein-coding locus across the genome that is representative of biology at that locus. NOTE: Mapping genes with map_genes only reduces the number of mapped genes compared to the provided "gene" column.
get_prevalence(): get_ Get prevalence

Get epidemiological disease and phenotype prevalence data.
get_ttd(): get_
get_upheno(): get_ Get uPheno

Get data from the Unified Phenotype Ontology (uPheno).
get_version(): get_ Get version

For a given ontology, extract the precise version of the Release that the data object was built from. For Human Phenotype Ontology specifically, all Releases can be found at the official HPO GitHub Releases page.

Examples

if (FALSE) { # \dontrun{
am <- get_alphamissense()
} # }
ont <- get_ontology("hp", terms=10)
#> Loading cached ontology: /github/home/.cache/R/KGExplorer/hp.rds
#> Randomly sampling 10 term(s).
def <- get_definitions(ont)
d <- get_gencc()
#> Gathering data from GenCC.
#> Evidence scores for: 
#>  - 10514 diseases 
#>  - 5171 genes
#> + Version: 2024-12-19
genes <- get_genes_disease()
#> Filtering with `maps`.
#> Files found: 1
#> Constructing data: gene <--> disease
#> genes(s): 0
hpo <- get_hpo()
dat <- get_monarch(maps=list(c("gene","disease")))
#> Filtering with `maps`.
#> Files found: 1
#> Importing 1 Monarch files.
#> - 1/1: gene_disease.all
files <- get_monarch_files() 
#> Files found: 35
if (FALSE) { # \dontrun{
g <- get_monarch_kg(save_dir=tempdir(), nrows=100)
} # }
models <- get_monarch_models()
#> Filtering with `maps`.
#> Files found: 1
#> Constructing data: model <--> disease
#> Model species: 21
map <- get_mondo_maps("default") 
#> Loading required namespace: downloadR
#> Downloading with download.file.
#> download.file download successful.
#> Time difference of 0.4 secs
mondo <- get_ontology(name="mondo")
#> ⠙ Iterating 9 done (4.5/s) | 2s
#> ⠙ Iterating 14 done (4.9/s) | 2.9s
#> Preparing ontology_index object from: https://github.com/monarch-initiative/mondo/releases/download/v2024-12-03/mondo.obo
#> Parsing [Typedef] sections in the obo file [268/268]
#> remove 2 obsolete terms
#> Parsing [Term] sections in the obo file [1000/54683]
#> Parsing [Term] sections in the obo file [2000/54683]
#> Parsing [Term] sections in the obo file [3000/54683]
#> Parsing [Term] sections in the obo file [4000/54683]
#> Parsing [Term] sections in the obo file [5000/54683]
#> Parsing [Term] sections in the obo file [6000/54683]
#> Parsing [Term] sections in the obo file [7000/54683]
#> Parsing [Term] sections in the obo file [8000/54683]
#> Parsing [Term] sections in the obo file [9000/54683]
#> Parsing [Term] sections in the obo file [10000/54683]
#> Parsing [Term] sections in the obo file [11000/54683]
#> Parsing [Term] sections in the obo file [12000/54683]
#> Parsing [Term] sections in the obo file [13000/54683]
#> Parsing [Term] sections in the obo file [14000/54683]
#> Parsing [Term] sections in the obo file [15000/54683]
#> Parsing [Term] sections in the obo file [16000/54683]
#> Parsing [Term] sections in the obo file [17000/54683]
#> Parsing [Term] sections in the obo file [18000/54683]
#> Parsing [Term] sections in the obo file [19000/54683]
#> Parsing [Term] sections in the obo file [20000/54683]
#> Parsing [Term] sections in the obo file [21000/54683]
#> Parsing [Term] sections in the obo file [22000/54683]
#> Parsing [Term] sections in the obo file [23000/54683]
#> Parsing [Term] sections in the obo file [24000/54683]
#> Parsing [Term] sections in the obo file [25000/54683]
#> Parsing [Term] sections in the obo file [26000/54683]
#> Parsing [Term] sections in the obo file [27000/54683]
#> Parsing [Term] sections in the obo file [28000/54683]
#> Parsing [Term] sections in the obo file [29000/54683]
#> Parsing [Term] sections in the obo file [30000/54683]
#> Parsing [Term] sections in the obo file [31000/54683]
#> Parsing [Term] sections in the obo file [32000/54683]
#> Parsing [Term] sections in the obo file [33000/54683]
#> Parsing [Term] sections in the obo file [34000/54683]
#> Parsing [Term] sections in the obo file [35000/54683]
#> Parsing [Term] sections in the obo file [36000/54683]
#> Parsing [Term] sections in the obo file [37000/54683]
#> Parsing [Term] sections in the obo file [38000/54683]
#> Parsing [Term] sections in the obo file [39000/54683]
#> Parsing [Term] sections in the obo file [40000/54683]
#> Parsing [Term] sections in the obo file [41000/54683]
#> Parsing [Term] sections in the obo file [42000/54683]
#> Parsing [Term] sections in the obo file [43000/54683]
#> Parsing [Term] sections in the obo file [44000/54683]
#> Parsing [Term] sections in the obo file [45000/54683]
#> Parsing [Term] sections in the obo file [46000/54683]
#> Parsing [Term] sections in the obo file [47000/54683]
#> Parsing [Term] sections in the obo file [48000/54683]
#> Parsing [Term] sections in the obo file [49000/54683]
#> Parsing [Term] sections in the obo file [50000/54683]
#> Parsing [Term] sections in the obo file [51000/54683]
#> Parsing [Term] sections in the obo file [52000/54683]
#> Parsing [Term] sections in the obo file [53000/54683]
#> Parsing [Term] sections in the obo file [54000/54683]
#> Parsing [Term] sections in the obo file [54683/54683]
#> remove 4250 obsolete terms
#> There are more than one root:
#>   BFO:0000001, CHEBI:24431, CHEBI:36342, CHEBI:50906, ECTO:0000015,
#>     and other 29 terms ...
#>   A super root (~~all~~) is added.
#> Adding term metadata.
#> IC_method: IC_offspring
#> Adding ancestor metadata.
#> Getting absolute ontology level for 50,425 IDs.
#> 206 ancestors found at level 2
#> Translating ontology terms to names.
#> Translating ontology terms to ids.
#> Converted ontology to: adjacency 
#> Getting absolute ontology level for 50,425 IDs.
#> Saving ontology --> /github/home/.cache/R/KGExplorer/mondo.rds
if (FALSE) { # \dontrun{
  hp <- get_ontology(name="hp")
  upheno <- get_ontology(name="upheno")
} # }
ont <- get_ontology("hp", terms=10)
#> Loading cached ontology: /github/home/.cache/R/KGExplorer/hp.rds
#> Randomly sampling 10 term(s).
dict <- get_ontology_dict(ont)
ont <- get_ontology("hp")
#> Loading cached ontology: /github/home/.cache/R/KGExplorer/hp.rds
terms <- ont@terms[1:10]
lvls <- get_ontology_levels(ont, terms = terms)
#> Getting absolute ontology level for 10 IDs.
lvls_rel <- get_ontology_levels(ont, terms = terms, absolute=FALSE)
#> Getting relative ontology level for 10 IDs.
#> Translating ontology terms to ids.
if (FALSE) { # \dontrun{
pli <- get_pli()
} # }
if (FALSE) { # \dontrun{
get_prevalence()
} # }
ttd <- get_ttd()
#> Loading required namespace: readxl
#> Retrieving all organisms available in gprofiler.
#> Using stored `gprofiler_orgs`.
#> Mapping species name: hsapiens
#> 1 organism identified from search: hsapiens
#> 13,815 / 27,118 (50.94%) genes mapped.
upheno <- get_upheno()
#> ⠙ Iterating 9 done (4.2/s) | 2.1s
#> ⠙ Iterating 14 done (4.7/s) | 3s
#> Parsing 279 <owl:ObjectProperty> ...
#> remove 2 obsolete terms
#> Parsing 190124 <owl:Class> ...
#> Parsing 87972 <rdf:Description> ...
#> remove 17351 obsolete terms
#> There are more than one root:
#>   BFO:0000001, BSPO:0000005, BSPO:0000010, BSPO:0000070, BSPO:0000086,
#>     and other 14 terms ...
#>   A super root (~~all~~) is added.
#> Adding term metadata.
#> IC_method: IC_offspring
#> Adding ancestor metadata.
#> Getting absolute ontology level for 172,772 IDs.
#> 114 ancestors found at level 2
#> Translating ontology terms to names.
#> Translating ontology terms to ids.
#> Converted ontology to: adjacency 
#> Getting absolute ontology level for 172,772 IDs.
#> Saving ontology --> /github/home/.cache/R/KGExplorer/upheno.rds
obj <- get_ontology("hp")
#> Loading cached ontology: /github/home/.cache/R/KGExplorer/hp.rds
get_version(obj=obj)
#> + Version: releases