Package 'ontoProc2'

Description

retrieve and cache all filenames of Semantic SQL ontologies available, checking for updated content relative to cache via ETag

Usage

bbop_sqlite_db_gz(
  url = "https://s3.amazonaws.com/bbop-sqlite",
  bfc = BiocFileCache::BiocFileCache(),
  rname = "bbop_sqlite_listing",
  timeout_connect = 5,
  timeout_total = 15
)

Arguments

Value

a character vector

Note

There is no real etag discipline for the metadata, so full metadata content is extracted on each call, digested, and compared to digest in cache. Cache is updated when there is a discrepancy, except there is a guard against rewriting cache with corrupted or zero-length data at endpoint. Note this code was negotiated at length with claude.ai Sonnet 4.6.

Examples

gzs = bbop_sqlite_db_gz()
head(gzs)
length(gzs)

Description

produce a table with cells exhibiting given proteins on plasma membrane according to CL

Usage

cells_with_pmp(curies)

Arguments

Value

a data.frame with columns cl, celltype, pr, protein

Examples

# 2064: microsialin, 1874: KLRB1-like protein
cells_with_pmp(c("PR:000002064", "PR:000001874"))

Description

a named vector with mapping from cell type phrase to CURIE for CL.owl of 2025-12-17

Usage

data(cn2tag)

Format

names character vector

Examples

data("cn2tag", package = "ontoProc2")
cn2tag["Kupffer cell"]

Description

Count labeled terms grouped by CURIE prefix

Usage

count_by_prefix(x, ...)

Arguments

Value

data.frame with columns prefix and n, ordered by n descending.

Examples

goref <- semsql_connect(ontology = "go")
count_by_prefix(goref)
disconnect(goref)

Description

Count the number of descendants of a term

Usage

count_descendants(x, term_id, predicate = "rdfs:subClassOf", ...)

Arguments

Value

integer(1).

Examples

goref <- semsql_connect(ontology = "go")
count_descendants(goref, "GO:0006915") # all apoptosis subtypes
disconnect(goref)

Description

Describe the columns of a table in a SemsqlConn database

Usage

describe_table(x, table_name, ...)

Arguments

Value

data.frame with PRAGMA table_info output (columns: cid, name, type, notnull, dflt_value, pk).

Examples

goref <- semsql_connect(ontology = "go")
describe_table(goref, "rdfs_label_statement")
disconnect(goref)

Description

Disconnect a SemsqlConn from its database

Usage

disconnect(x, quiet = FALSE, ...)

Arguments

Value

The SemsqlConn object invisibly.

Description

Find terms that have a given OWL someValuesFrom restriction

Usage

find_by_restriction(
  x,
  property,
  filler,
  include_filler_descendants = FALSE,
  ...
)

Arguments

Value

data.frame with columns id and label.

Examples

goref <- semsql_connect(ontology = "go")
# cellular components that are part_of nucleus (GO:0005634)
find_by_restriction(goref, "BFO:0000050", "GO:0005634")
disconnect(goref)

Description

Find terms that are descendants of a superclass and have a given restriction

Usage

find_intersection(x, superclass_id, relation_property, related_to_id, ...)

Arguments

Value

data.frame with columns id and label.

Examples

goref <- semsql_connect(ontology = "go")
# CC terms (GO:0005575) that are part_of nucleus (GO:0005634)
find_intersection(goref, "GO:0005575", "BFO:0000050", "GO:0005634")
disconnect(goref)

Description

Get all ancestors of a term via entailed edges

Usage

get_ancestors(
  x,
  term_id,
  predicates = "rdfs:subClassOf",
  include_self = FALSE,
  ...
)

Arguments

Value

data.frame with columns id, label, predicate.

Examples

goref <- semsql_connect(ontology = "go")
get_ancestors(goref, "GO:0006915")
disconnect(goref)

Description

Convenience wrapper around get_ancestors() that follows both rdfs:subClassOf and BFO:0000050 (part-of) edges.

Usage

get_ancestors_partonomy(conn, term_id, include_self = FALSE)

Arguments

Value

data.frame with columns id, label, predicate.

Examples

goref <- semsql_connect(ontology = "go")
get_ancestors_partonomy(goref, "GO:0005739") # mitochondrion
disconnect(goref)

Description

Get the text definition for a term

Usage

get_definition(x, term_id, ...)

Arguments

Value

character(1) definition text, or NA_character_ if not found.

Examples

goref <- semsql_connect(ontology = "go")
get_definition(goref, "GO:0006915")
disconnect(goref)

Description

Get all descendants of a term via entailed edges

Usage

get_descendants(
  x,
  term_id,
  predicates = "rdfs:subClassOf",
  include_self = FALSE,
  ...
)

Arguments

Value

data.frame with columns id, label, predicate.

Examples

goref <- semsql_connect(ontology = "go")
get_descendants(goref, "GO:0006915")
disconnect(goref)

Description

Convenience wrapper around get_descendants() that follows both rdfs:subClassOf and BFO:0000051 (has-part) edges.

Usage

get_descendants_partonomy(conn, term_id, include_self = FALSE)

Arguments

Value

data.frame with columns id, label, predicate.

Examples

goref <- semsql_connect(ontology = "go")
get_descendants_partonomy(goref, "GO:0005634") # nucleus sub-components
disconnect(goref)

Description

Get direct edges in the ontology graph for a term

Usage

get_direct_edges(
  x,
  term_id,
  direction = c("outgoing", "incoming", "both"),
  ...
)

Arguments

Value

data.frame with columns subject, subject_label, predicate, predicate_label, object, object_label.

Examples

goref <- semsql_connect(ontology = "go")
get_direct_edges(goref, "GO:0006915")
get_direct_edges(goref, "GO:0006915", direction = "both")
disconnect(goref)

Description

Get direct subclasses of a term

Usage

get_direct_subclasses(x, term_id, ...)

Arguments

Value

data.frame with columns id and label, ordered by label.

Examples

goref <- semsql_connect(ontology = "go")
# direct children of "apoptotic process" (GO:0006915)
get_direct_subclasses(goref, "GO:0006915")
disconnect(goref)

Description

Get direct superclasses of a term

Usage

get_direct_superclasses(x, term_id, ...)

Arguments

Value

data.frame with columns id and label, ordered by label.

Examples

goref <- semsql_connect(ontology = "go")
get_direct_superclasses(goref, "GO:0006915")
disconnect(goref)

Description

Get the rdfs:label for a term

Usage

get_label(x, term_id, ...)

Arguments

Value

character(1) label, or NA_character_ if not found.

Examples

goref <- semsql_connect(ontology = "go")
get_label(goref, "GO:0006915") # "apoptotic process"
disconnect(goref)

Description

Retrieve the ontology prefix from a SemsqlConn

Usage

get_prefix(x, ...)

Arguments

Value

character(1) the primary ontology prefix (e.g. "GO").

Examples

goref <- semsql_connect(ontology = "go")
get_prefix(goref)
disconnect(goref)

Description

produce a table with list of proteins from protein ontology identified as present on cell membranes for input cell type CURIEs

Usage

get_present_pmp(curies)

Arguments

Value

a data.frame with columns cl, celltype, pr, protein

Examples

get_present_pmp(c("CL:0000091", "CL:0000926"))

Description

Get OWL someValuesFrom restrictions for a term

Usage

get_restrictions(x, term_id, ...)

Arguments

Value

data.frame with columns restriction_id, property, property_label, filler, filler_label.

Examples

goref <- semsql_connect(ontology = "go")
# mitochondrion (GO:0005739) has part-of restrictions to cell
get_restrictions(goref, "GO:0005739")
disconnect(goref)

Description

Get synonyms for a term

Usage

get_synonyms(
  x,
  term_id,
  type = c("all", "exact", "broad", "narrow", "related"),
  ...
)

Arguments

Value

data.frame with columns subject, predicate, synonym.

Examples

goref <- semsql_connect(ontology = "go")
get_synonyms(goref, "GO:0006915")
get_synonyms(goref, "GO:0006915", type = "exact")
disconnect(goref)

Description

Retrieve a summary of information about a term

Usage

get_term_info(x, term_id, ...)

Arguments

Value

list with elements id, label, definition, synonyms, superclasses, subclasses.

Examples

goref <- semsql_connect(ontology = "go")
info <- get_term_info(goref, "GO:0006915")
info$label
info$superclasses
disconnect(goref)

Description

inject linefeeds for node names for graph, with textual annotation from ontology

Usage

improve_nodes(g, ont)

Arguments

Value

graphNEL instance

Examples

requireNamespace("Rgraphviz")
requireNamespace("graph")
clcon <- retrieve_semsql_conn("cl")
cl <- semsql_to_oi(clcon)
cl3k <- c(
  "CL:0000492", "CL:0001054", "CL:0000236", "CL:0000625",
  "CL:0000576", "CL:0000623", "CL:0000451", "CL:0000556"
)
p3k <- ontologyPlot::onto_plot(cl, cl3k)
gnel <- make_graphNEL_from_ontology_plot(p3k)
head(graph::nodes(gnel)) # before improving
gnel <- improve_nodes(gnel, cl)
head(graph::nodes(gnel))

Description

Test whether a SemsqlConn has a valid open connection

Usage

is_connected(x, ...)

Arguments

Value

logical(1).

Examples

goref <- semsql_connect(ontology = "go")
is_connected(goref) # TRUE
disconnect(goref)
is_connected(goref) # FALSE

Description

List tables in a SemsqlConn database

Usage

list_tables(x, ...)

Arguments

Value

character vector of table names.

Examples

goref <- semsql_connect(ontology = "go")
list_tables(goref)
disconnect(goref)

Description

obtain graphNEL from ontology_plot instance of ontologyPlot

Usage

make_graphNEL_from_ontology_plot(x)

Arguments

Value

instance of S4 graphNEL class

Examples

requireNamespace("Rgraphviz")
requireNamespace("graph")
clcon <- retrieve_semsql_conn("cl")
cl <- semsql_to_oi(clcon)
cl3k <- c(
  "CL:0000492", "CL:0001054", "CL:0000236", "CL:0000625",
  "CL:0000576", "CL:0000623", "CL:0000451", "CL:0000556"
)
p3k <- ontologyPlot::onto_plot(cl, cl3k)
gnel <- make_graphNEL_from_ontology_plot(p3k)
gnel <- improve_nodes(gnel, cl)
graph::graph.par(list(nodes = list(shape = "plaintext", cex = .8)))
gnel <- Rgraphviz::layoutGraph(gnel)
Rgraphviz::renderGraph(gnel)

Description

a named vector with values rdfs labels in NCI thesaurus, and names the corresponding formal ontology tags

Usage

data(ncit_map)

Format

named character vector

Examples

data("ncit_map", package = "ontoProc2")
ncit_map["EFO:1000899"]

Description

high-level use of graph/Rgraphviz for rendering ontology relations

Usage

onto_plot2(ont, terms2use, cex = 0.8, ...)

Arguments

Value

graphNEL instance (invisibly)

Examples

clcon <- retrieve_semsql_conn("cl")
cl <- semsql_to_oi(clcon)
cl3k <- c(
  "CL:0000492", "CL:0001054", "CL:0000236", "CL:0000625",
  "CL:0000576", "CL:0000623", "CL:0000451", "CL:0000556"
)
onto_plot2(cl, cl3k)

Description

A named list of commonly used predicate CURIEs in OBO-format ontologies, for use with get_ancestors(), get_descendants(), and related functions.

Usage

PREDICATES

Format

A named list with elements subclass_of, part_of, has_part, develops_from, located_in, has_characteristic.

Value

a named list

Examples

goref <- semsql_connect(ontology = "go")
# apoptotic process (GO:0006915) ancestors via is-a and part-of
anc <- get_ancestors(goref, "GO:0006915",
  predicates = c(PREDICATES$subclass_of, PREDICATES$part_of)
)
head(anc)
disconnect(goref)

Description

Show method for SemsqlConn. Concise one-line summary displayed when a SemsqlConn object is auto-printed at the R prompt.

Usage

## S7 method for class <ontoProc2::SemsqlConn>
print(x, ...)

Arguments

Value

x, invisibly

Description

Attempts to reconnect a disconnected SemsqlConn object to its database. Returns a new SemsqlConn; the original cannot be modified in place due to S7 value semantics.

Usage

reconnect(x, ...)

Arguments

Value

A new SemsqlConn object with an active connection.

Examples

goref <- semsql_connect(ontology = "go")
disconnect(goref)
goref <- reconnect(goref)
disconnect(goref)

Description

Displays a verbose, formatted representation of a SemsqlConn object including connection status, database statistics (labeled terms, edges, definitions), prefix breakdown, and available key tables. More informative than print(), intended for interactive exploration.

Usage

report(object, ...)

## S7 method for class <ontoProc2::SemsqlConn>
report(object, ...)

Arguments

Value

The SemsqlConn object invisibly.

Examples

goref <- semsql_connect(ontology = "go")
report(goref)
disconnect(goref)

Description

return a SQLite connection (read only) to an INCAtools Semantic SQL ontology

Usage

retrieve_semsql_conn(
  ontology = "efo",
  cache = BiocFileCache::BiocFileCache(),
  cacheid = NULL,
  ...
)

Arguments

Value

an RSQLite DBI connection instance

Note

When the cache is searched, the string given as 'ontology' will be prefixed with '^'. This helps avoid confusion between pcl.db and cl.db, for example.

Examples

# first time will involve a download and decompression
aionto <- retrieve_semsql_conn("aio")
head(DBI::dbListTables(aionto))
dplyr::tbl(aionto, "class_node") |> head()

Description

Run an arbitrary SQL query against a SemsqlConn database

Usage

run_query(x, sql, ...)

Arguments

Value

data.frame with query results.

Examples

goref <- semsql_connect(ontology = "go")
run_query(
  goref,
  "SELECT subject, value AS label FROM rdfs_label_statement LIMIT 5"
)
disconnect(goref)

Description

Search term labels in a SemsqlConn database

Usage

search_labels(x, pattern, limit = 20L)

Arguments

Value

data.frame with columns subject and label.

Examples

goref <- semsql_connect(ontology = "go")
search_labels(goref, "apoptosis")
disconnect(goref)

Description

Opens a connection to a SemanticSQL SQLite database, either by supplying a direct file path or by referencing a short ontology name that is retrieved and cached via BiocFileCache.

Usage

semsql_connect(
  db_path = NULL,
  ontology_prefix = NULL,
  ontology = NULL,
  cache = BiocFileCache::BiocFileCache(),
  validate = TRUE,
  ...
)

Arguments

Value

A SemsqlConn() object.

Note

The connection has flag SQLITE_RO for read-only access. There will be an attempt to validate the ontology tag that is supplied, against all available Semantic SQL resources available at INCAtools bucket. Function fails if a match cannot be made, which in general requires network access.

Examples

# by ontology short name (downloads if not cached)
goref <- semsql_connect(ontology = "go")
goref
disconnect(goref)

Description

produce an ontology_index instance from semantic sql sqlite connection

Usage

semsql_to_oi(con)

Arguments

Value

result of ontologyIndex::ontology_index evaluated for the labels and parent-child relations in tables statements and edge of the semantic sql resource

Examples

## Not run: 
conn <- semsql_connect(ontology = "aio")
oi <- suppressWarnings(semsql_to_oi(conn@con))
names(oi)

## End(Not run)

Description

produce INCAtools distribution URL

Usage

semsql_url(ontology = "efo")

Arguments

Value

a string with URL for INCAtools resource

Examples

semsql_url("cl")

Description

An S7 class that encapsulates a SQLite connection to an ontology database following the SemanticSQL schema. Provides methods for common ontology queries including label lookup, ancestor/descendant traversal, and relationship queries.

Properties:

con

The DBI connection object (SQLiteConnection)

db_path

character(1) path to the SQLite database file

ontology_prefix

character(1) primary ontology prefix, e.g. "CL" for the Cell Ontology

Usage

SemsqlConn(con = NULL, db_path = character(0), ontology_prefix = character(0))

Arguments

Value

wrapped connection

Description

a named vector with mapping from CURIE to cell type phrase for CL.owl of 2025-12-17

Usage

data(tag2cn)

Format

names character vector

Examples

data("tag2cn", package = "ontoProc2")
tag2cn[c("CL:0000000", "CL:0000006")]

Description

Opens a connection, evaluates an expression with conn bound to the open SemsqlConn, then closes the connection even if an error occurs. Analogous to Python's context manager (with statement).

Usage

with_connection(db_path, expr)

Arguments

Value

the value of expr.

Examples

## Not run: 
result <- with_connection("cl.db", {
  get_ancestors(conn, "CL:0000540")
})

## End(Not run)