Skip to content

fix(proteinGroups): Adjust annotateProteinInfoFromIndra to handle protein groups #108

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tonywu1999 merged 4 commits into from
Sep 22, 2026
Merged

fix(proteinGroups): Adjust annotateProteinInfoFromIndra to handle protein groups #108

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
857a36c
fix(proteinGroups): Adjust annotateProteinInfoFromIndra to handle pro…
tonywu1999 Sep 1, 2026
70f0e8a
fix documentation, slight code adjustments
tonywu1999 Sep 22, 2026
5440e73
fix some unit tests based on feedback
tonywu1999 Sep 22, 2026
5c65ef6
fix styling of remaining tests
tonywu1999 Sep 22, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
239 changes: 172 additions & 67 deletions R/annotateProteinInfoFromIndra.R
View file
Open in desktop

Large diffs are not rendered by default.

27 changes: 18 additions & 9 deletions man/annotateProteinInfoFromIndra.Rd
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

25 changes: 0 additions & 25 deletions man/dot-populateEntityInformationWithGilda.Rd
View file
Open in desktop

This file was deleted.

20 changes: 0 additions & 20 deletions man/dot-populateEntityInformationWithIndraCogex.Rd
View file
Open in desktop

This file was deleted.

20 changes: 0 additions & 20 deletions man/dot-populateKinaseInfoInDataFrame.Rd
View file
Open in desktop

This file was deleted.

20 changes: 0 additions & 20 deletions man/dot-populatePhophataseInfoInDataFrame.Rd
View file
Open in desktop

This file was deleted.

20 changes: 0 additions & 20 deletions man/dot-populateTranscriptionFactorInfoInDataFrame.Rd
View file
Open in desktop

This file was deleted.

19 changes: 0 additions & 19 deletions man/dot-populateUniprotIdsInDataFrame.Rd
View file
Open in desktop

This file was deleted.

206 changes: 206 additions & 0 deletions tests/testthat/test-annotateProteinInfoFromIndra.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,3 +128,209 @@ test_that("annotateProteinInfoFromIndra works correctly with HGNC name", {
expect_type(annotated_df$IsPhosphatase, "logical")

})

test_that(".splitProteinGroup splits, trims and drops empty members", {
expect_equal(MSstatsBioNet:::.splitProteinGroup("P13747;P23132"),
c("P13747", "P23132"))
expect_equal(MSstatsBioNet:::.splitProteinGroup("P13747"), "P13747")
expect_equal(MSstatsBioNet:::.splitProteinGroup(" P13747 ; P23132 "),
c("P13747", "P23132"))
expect_equal(MSstatsBioNet:::.splitProteinGroup(";P13747;;"), "P13747")
expect_equal(MSstatsBioNet:::.splitProteinGroup(NA), character(0))
expect_equal(MSstatsBioNet:::.splitProteinGroup(""), character(0))
})

test_that(".joinProteinGroup round-trips and returns NA when empty", {
expect_equal(MSstatsBioNet:::.joinProteinGroup(c("P13747", "P23132")),
"P13747;P23132")
expect_equal(MSstatsBioNet:::.joinProteinGroup("P13747"), "P13747")
expect_true(is.na(MSstatsBioNet:::.joinProteinGroup(character(0))))
})

test_that(".stripPtmSite removes only the site suffix", {
expect_equal(MSstatsBioNet:::.stripPtmSite(c("P13747_S148", "P23132")),
Comment thread
tonywu1999 marked this conversation as resolved.
c("P13747", "P23132"))
expect_equal(MSstatsBioNet:::.stripPtmSite("CLH1_HUMAN"), "CLH1_HUMAN")
expect_equal(MSstatsBioNet:::.stripPtmSite(c("P13747_S148_T149")),
c("P13747"))
})

test_that("PTM site suffixes are stripped from every protein group member", {
df <- data.frame(Protein = c("P13747;P23132_T20", "P13747_S148"),
stringsAsFactors = FALSE)
out <- MSstatsBioNet:::.populateUniprotIdsInDataFrame(df, "Uniprot")

expect_equal(out$GlobalProtein, c("P13747;P23132", "P13747"))
expect_equal(out$UniprotId, c("P13747;P23132", "P13747"))
})

test_that("annotateProteinInfoFromIndra grounds each Uniprot protein group member", {
df <- data.frame(Protein = c("P13747;P23132", "Q00610"),
stringsAsFactors = FALSE)
local_mocked_bindings(
.callGetHgncIdsFromUniprotIdsApi = function(uniprotIds) {
list(P13747 = "4931", P23132 = "10012", Q00610 = "2092")
},
.callGetHgncNamesFromHgncIdsApi = function(hgncIds) {
list(`4931` = "HLA-E", `10012` = "RAD23A", `2092` = "CLTC")
},
.callIsTranscriptionFactorApi = function(genes) list(RAD23A = FALSE, `HLA-E` = FALSE, CLTC = FALSE),
.callIsKinaseApi = function(genes) list(RAD23A = FALSE, `HLA-E` = FALSE, CLTC = FALSE),
.callIsPhosphataseApi = function(genes) list(RAD23A = FALSE, `HLA-E` = FALSE, CLTC = FALSE)
)
annotated_df <- annotateProteinInfoFromIndra(df, "Uniprot")

group_row <- annotated_df[annotated_df$Protein == "P13747;P23132", ]
expect_equal(group_row$UniprotId, "P13747;P23132")
expect_equal(group_row$EntityNamespace, "HGNC;HGNC")
expect_equal(group_row$EntityId, "4931;10012")
expect_equal(group_row$EntityName, "HLA-E;RAD23A")
expect_true(is.na(group_row$IsTranscriptionFactor))
expect_true(is.na(group_row$IsKinase))
expect_true(is.na(group_row$IsPhosphatase))

single_row <- annotated_df[annotated_df$Protein == "Q00610", ]
expect_equal(single_row$EntityNamespace, "HGNC")
expect_equal(single_row$EntityId, "2092")
expect_equal(single_row$EntityName, "CLTC")
expect_equal(single_row$IsKinase, FALSE)
})

test_that("a protein group whose members share a gene collapses to one grounding", {
df <- data.frame(Protein = "P13747;P13747-2", stringsAsFactors = FALSE)
local_mocked_bindings(
.callGetHgncIdsFromUniprotIdsApi = function(uniprotIds) {
list(P13747 = "4931", `P13747-2` = "4931")
},
.callGetHgncNamesFromHgncIdsApi = function(hgncIds) list(`4931` = "HLA-E"),
.callIsTranscriptionFactorApi = function(genes) list(`HLA-E` = FALSE),
.callIsKinaseApi = function(genes) list(`HLA-E` = FALSE),
.callIsPhosphataseApi = function(genes) list(`HLA-E` = TRUE)
)
annotated_df <- annotateProteinInfoFromIndra(df, "Uniprot")

expect_equal(annotated_df$EntityNamespace, "HGNC")
expect_equal(annotated_df$EntityId, "4931")
expect_equal(annotated_df$EntityName, "HLA-E")
expect_equal(annotated_df$IsTranscriptionFactor, FALSE)
expect_equal(annotated_df$IsPhosphatase, TRUE)
})

test_that("unresolvable protein group members are dropped, not carried as NA", {
df <- data.frame(Protein = c("P13747;NOTANID", "NOTANID;ALSONOT"),
stringsAsFactors = FALSE)
local_mocked_bindings(
.callGetHgncIdsFromUniprotIdsApi = function(uniprotIds) list(P13747 = "4931"),
.callGetHgncNamesFromHgncIdsApi = function(hgncIds) list(`4931` = "HLA-E"),
.callIsTranscriptionFactorApi = function(genes) list(`HLA-E` = FALSE),
.callIsKinaseApi = function(genes) list(`HLA-E` = FALSE),
.callIsPhosphataseApi = function(genes) list(`HLA-E` = FALSE)
)
annotated_df <- annotateProteinInfoFromIndra(df, "Uniprot")

expect_equal(annotated_df$EntityId[1], "4931")
expect_equal(annotated_df$EntityName[1], "HLA-E")
expect_equal(annotated_df$IsKinase[1], FALSE)

expect_true(is.na(annotated_df$EntityNamespace[2]))
expect_true(is.na(annotated_df$EntityId[2]))
expect_true(is.na(annotated_df$EntityName[2]))
expect_true(is.na(annotated_df$IsKinase[2]))
})

test_that("Uniprot_Mnemonic groups map each member to its own UniProt id", {
df <- data.frame(Protein = c("CLH1_HUMAN;HLAE_HUMAN", "CLH1_HUMAN;NOPE_HUMAN"),
stringsAsFactors = FALSE)
local_mocked_bindings(
.callGetUniprotIdsFromUniprotMnemonicIdsApi = function(uniprotMnemonicIds) {
list(CLH1_HUMAN = "Q00610", HLAE_HUMAN = "P13747")
},
.callGetHgncIdsFromUniprotIdsApi = function(uniprotIds) {
list(Q00610 = "2092", P13747 = "4931")
},
.callGetHgncNamesFromHgncIdsApi = function(hgncIds) {
list(`2092` = "CLTC", `4931` = "HLA-E")
},
.callIsTranscriptionFactorApi = function(genes) list(CLTC = FALSE),
.callIsKinaseApi = function(genes) list(CLTC = FALSE),
.callIsPhosphataseApi = function(genes) list(CLTC = FALSE)
)
annotated_df <- annotateProteinInfoFromIndra(df, "Uniprot_Mnemonic")

expect_equal(annotated_df$UniprotId[1], "Q00610;P13747")
expect_equal(annotated_df$EntityNamespace[1], "HGNC;HGNC")
expect_equal(annotated_df$EntityId[1], "2092;4931")
expect_equal(annotated_df$EntityName[1], "CLTC;HLA-E")

expect_equal(annotated_df$UniprotId[2], "Q00610")
expect_equal(annotated_df$EntityName[2], "CLTC")
expect_equal(annotated_df$IsKinase[2], FALSE)
})

test_that("Hgnc_Name groups pool and deduplicate Gilda groundings", {
df <- data.frame(Protein = c("EGFR;ERBB2", "EGFR;EGFR"),
stringsAsFactors = FALSE)
local_mocked_bindings(
.callGroundEntitiesFromGildaApi = function(textInputs, keep_only = NULL, organisms = NULL) {
list(EGFR = list(ns = "HGNC", id = "3236", name = "EGFR"),
ERBB2 = list(ns = "HGNC", id = "3430", name = "ERBB2"))
},
.callIsTranscriptionFactorApi = function(genes) list(EGFR = FALSE),
.callIsKinaseApi = function(genes) list(EGFR = TRUE),
.callIsPhosphataseApi = function(genes) list(EGFR = FALSE)
)
annotated_df <- annotateProteinInfoFromIndra(df, "Hgnc_Name")

expect_equal(annotated_df$EntityNamespace[1], "HGNC;HGNC")
expect_equal(annotated_df$EntityId[1], "3236;3430")
expect_equal(annotated_df$EntityName[1], "EGFR;ERBB2")

expect_equal(annotated_df$EntityId[2], "3236")
expect_equal(annotated_df$EntityName[2], "EGFR")
expect_equal(annotated_df$IsKinase[2], TRUE)
})

test_that("Metabolite groups keep every namespace Gilda returns per member", {
df <- data.frame(Protein = "glucose;citrate", stringsAsFactors = FALSE)
local_mocked_bindings(
.callGroundEntitiesFromGildaApi = function(textInputs, keep_only = NULL, organisms = NULL) {
list(glucose = list(ns = c("CHEBI", "MESH"),
id = c("17234", "D005947"),
name = c("glucose", "Glucose")),
citrate = list(ns = "CHEBI", id = "133748", name = "citrate"))
}
)
annotated_df <- annotateProteinInfoFromIndra(df, "Metabolite")

expect_equal(annotated_df$EntityNamespace, "CHEBI;MESH;CHEBI")
expect_equal(annotated_df$EntityId, "17234;D005947;133748")
expect_equal(annotated_df$EntityName, "glucose;Glucose;citrate")
expect_true(is.na(annotated_df$UniprotId))
expect_true(is.na(annotated_df$IsKinase))
})

test_that("a protein group's groundings fan out into separate query nodes", {
df <- data.frame(Protein = "P13747;P23132", stringsAsFactors = FALSE)
local_mocked_bindings(
.callGetHgncIdsFromUniprotIdsApi = function(uniprotIds) {
list(P13747 = "4931", P23132 = "10012")
},
.callGetHgncNamesFromHgncIdsApi = function(hgncIds) {
list(`4931` = "HLA-E", `10012` = "RAD23A")
},
.callIsTranscriptionFactorApi = function(genes) list(),
.callIsKinaseApi = function(genes) list(),
.callIsPhosphataseApi = function(genes) list()
)
annotated_df <- annotateProteinInfoFromIndra(df, "Uniprot")

pairs <- MSstatsBioNet:::.buildCogexGroundings(
namespaces = annotated_df$EntityNamespace,
ids = annotated_df$EntityId,
force_include_other = NULL
)
expect_setequal(
vapply(pairs, function(p) paste(p[[1]], p[[2]], sep = ":"), character(1)),
c("HGNC:4931", "HGNC:10012")
)
})
2 changes: 1 addition & 1 deletion tests/testthat/test-multi-grounding.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,7 +197,7 @@ test_that("annotateProteinInfoFromIndra with Metabolite mocks Gilda and skips ge
# ----- Metabolite E2E test (mocked end-to-end; skipped if real fixture absent) -----

test_that("annotateProteinInfoFromIndra(Metabolite) -> getSubnetworkFromIndra E2E (mocked, real fixture)", {
fixture_path <- system.file("extdata/groupComparisonModel_metabolite.csv",
fixture_path <- system.file("extdata/groupComparisonModel_compound.csv",
package = "MSstatsBioNet")
skip_if_not(nzchar(fixture_path) && file.exists(fixture_path),
"Metabolite fixture not yet provided (see TODO-MSBio-20260528).")
Expand Down
Loading