Skip to content

tests(anomaly-models): Fix unit tests around anomaly models #123

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
Apr 2, 2026
Merged

tests(anomaly-models): Fix unit tests around anomaly models #123

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
585213a
tests(anomaly-scores): Fix unit tests around anomaly scores
tonywu1999 Apr 2, 2026
c9ea825
fix unit tests
tonywu1999 Apr 2, 2026
539229d
add unit tests for duplicitiy
tonywu1999 Apr 2, 2026
1b796ca
fix q-value tests
tonywu1999 Apr 2, 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
2 changes: 1 addition & 1 deletion R/clean_DIANN.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -175,7 +175,7 @@
getOption("MSstatsLog")("INFO", msg)
getOption("MSstatsMsg")("INFO", msg)

dn_input = dn_input[QValue >= global_qvalue_cutoff, quantificationColumn := 0]
dn_input = dn_input[QValue >= global_qvalue_cutoff, (quantificationColumn) := 0]
if (MBR) {
msg = '** MBR was used to analyze the data. Now setting names and filtering'
msg_1_mbr = paste0('-- LibPGQValue < ', pg_qvalue_cutoff)
Expand Down
38 changes: 28 additions & 10 deletions inst/tinytest/test_clean_DIANN.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,13 +26,31 @@ output = MSstatsConvert:::.cleanRawDIANN(input, quantificationColumn = "Fragment
.validateOutput(output)

# Q-value filtering
output = MSstatsConvert:::.cleanRawDIANN(input, global_qvalue_cutoff = 0.005)
expect_equal(sum(output$DetectionQValue < 0.005), nrow(output))
output = MSstatsConvert:::.cleanRawDIANN(input, qvalue_cutoff = 0.00001)
expect_equal(sum(output$LibQValue < 0.00001), nrow(output))
output = MSstatsConvert:::.cleanRawDIANN(input, pg_qvalue_cutoff = 0.001)
expect_equal(sum(output$LibPGQValue < 0.001), nrow(output))
output = MSstatsConvert:::.cleanRawDIANN(input, MBR = TRUE, qvalue_cutoff = 0.005)
expect_equal(sum(output$LibQValue < 0.005), nrow(output))
output = MSstatsConvert:::.cleanRawDIANN(input, MBR = TRUE, pg_qvalue_cutoff = 0.001)
expect_equal(sum(output$LibPGQValue < 0.001), nrow(output))
expect_qvalue_cutoff <- function(output, col, cutoff) {
expect_equal(
sum(output[[col]] > cutoff),
sum(output[["Intensity"]] == 0 & output[[col]] > cutoff),
info = sprintf(
"All rows with %s > %s should have %s == 0",
col, cutoff, "Intensity"
)
)
expect_equal(
sum(output[[col]] <= cutoff),
nrow(output) - sum(output[[col]] > cutoff),
info = sprintf(
"Rows with %s <= %s should account for all rows not above the cutoff",
col, cutoff
)
)
}
output <- MSstatsConvert:::.cleanRawDIANN(input, global_qvalue_cutoff = 0.005)
expect_qvalue_cutoff(output, "DetectionQValue", 0.005)
output <- MSstatsConvert:::.cleanRawDIANN(input, qvalue_cutoff = 0.00001)
expect_qvalue_cutoff(output, "LibQValue", 0.00001)
output <- MSstatsConvert:::.cleanRawDIANN(input, pg_qvalue_cutoff = 0.001)
expect_qvalue_cutoff(output, "LibPGQValue", 0.001)
output <- MSstatsConvert:::.cleanRawDIANN(input, MBR = FALSE, qvalue_cutoff = 0.001)
expect_qvalue_cutoff(output, "GlobalQValue", 0.001)
output <- MSstatsConvert:::.cleanRawDIANN(input, MBR = FALSE, pg_qvalue_cutoff = 0.0002)
expect_qvalue_cutoff(output, "GlobalPGQValue", 0.0002)
4 changes: 2 additions & 2 deletions inst/tinytest/test_converters_DIANNtoMSstatsFormat.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ input = data.table::fread(input_file_path)
annot = data.table::fread(annotation_file_path)
output = DIANNtoMSstatsFormat(input, annotation = annot, MBR = FALSE, use_log_file = FALSE)
expect_equal(ncol(output), 11)
expect_equal(nrow(output), 174)
expect_equal(nrow(output), 348)
expect_true("Run" %in% colnames(output))
expect_true("ProteinName" %in% colnames(output))
expect_true("PeptideSequence" %in% colnames(output))
Expand All @@ -25,7 +25,7 @@ input = arrow::read_parquet(input_file_path)
annot = data.table::fread(annotation_file_path)
output = DIANNtoMSstatsFormat(input, annotation = annot, MBR = FALSE, use_log_file = FALSE, quantificationColumn = 'auto')
expect_equal(ncol(output), 11)
expect_equal(nrow(output), 180)
expect_equal(nrow(output), 192)
expect_true("Run" %in% colnames(output))
expect_true("ProteinName" %in% colnames(output))
expect_true("PeptideSequence" %in% colnames(output))
Expand Down
36 changes: 27 additions & 9 deletions inst/tinytest/test_utils_anomaly_score.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,9 +37,9 @@ baseline_scores = run_quality_metrics(
# Data with progressively higher cumulative sums
high_scores = run_quality_metrics(
base_df_10,
c(rep(0.1, 5), seq(2.0, 5.0, length.out = 5)), # mean_increase
c(rep(0.1, 5), seq(2.0, 5.0, length.out = 5)), # mean_decrease
c(rep(0.1, 5), seq(2.0, 5.0, length.out = 5)) # dispersion_increase
c(seq(0, 0.1, length.out = 5), seq(2.0, 5.0, length.out = 5)), # mean_increase
c(seq(0, 0.1, length.out = 5), seq(2.0, 5.0, length.out = 5)), # mean_decrease
c(seq(0, 0.1, length.out = 5), seq(2.0, 5.0, length.out = 5)) # dispersion_increase
)

# The last 5 rows (with high values) should have higher mean anomaly scores
Expand All @@ -51,9 +51,9 @@ base_df_20 = create_base_df(20)

extreme_scores = run_quality_metrics(
base_df_20,
c(rep(0.1, 19), 10.0), # Last value is extreme
c(rep(0.1, 19), 8.0), # Last value is extreme
c(rep(0.1, 19), 12.0) # Last value is extreme
c(seq(0, 0.1, length.out = 19), 10.0), # Last value is extreme
c(seq(0, 0.1, length.out = 19), 8.0), # Last value is extreme
c(seq(0, 0.1, length.out = 19), 12.0) # Last value is extreme
)

# The extreme outlier (last row) should have the highest anomaly score
Expand Down Expand Up @@ -267,9 +267,9 @@ base_df_6_rank = create_base_df(6)
# Create data with obvious ranking: Row 6 > Row 5 > Row 4 > Rows 1,2,3
ranking_scores = run_quality_metrics(
base_df_6_rank,
c(0.1, 0.1, 0.1, 1.0, 2.0, 5.0),
c(0.1, 0.1, 0.1, 1.0, 2.0, 5.0),
c(0.1, 0.1, 0.1, 1.0, 2.0, 5.0)
c(0.1, 0.11, 0.12, 1.0, 2.0, 5.0),
c(0.1, 0.11, 0.12, 1.0, 2.0, 5.0),
c(0.1, 0.11, 0.12, 1.0, 2.0, 5.0)
)

# Row 5 should have highest score, Row 4 second highest, etc.
Expand Down Expand Up @@ -367,3 +367,21 @@ low_abundance_excluded = MSstatsConvert:::.prepareSpectronautAnomalyInput(
missing_run_count = 0.95)
expect_true("AFPLAEWQPSDVDQR" %in% low_abundance_excluded$PeptideSequence)
expect_false("LowAbundancePeptide" %in% low_abundance_excluded$PeptideSequence)


# Test 11: Testing duplicity of quality metrics, applicable considering
# multiple fragments share the same precursor level metrics

# Data with progressively higher cumulative sums
duplicate_metrics = run_quality_metrics(
base_df_10,
c(rep(0.1, 5), seq(2.0, 4.0, length.out = 5)), # mean_increase
c(rep(0.1, 5), seq(2.0, 4.0, length.out = 5)), # mean_decrease
c(rep(0.1, 5), seq(2.0, 4.0, length.out = 5)) # dispersion_increase
)

# The last 5 rows (with high values) should have lower mean anomaly scores
# Since they are all clumped between 2 and 4, whereas 0.1 is by itself
expect_true(mean(duplicate_metrics$AnomalyScores[6:10]) < mean(duplicate_metrics$AnomalyScores[1:5]),
info = "Rows 6-10 (values clumped 2-4) should have lower
anomaly scores than rows 1-5 (isolated value of 0.1)")
Loading