Analyzing Group ID Redundancy Across Rank 05 Components
Analysis
2025-11-02
Overview
This analysis examines whether the same group_id (orthogroup) appears across multiple components with the same GO BP terms, which would indicate redundancy in the cross-component frequency counts.
Load Libraries
library(tidyverse)
library(ggplot2)
library(RColorBrewer)
library(knitr)Define Paths
# Input directory
input_dir <- "/Users/sr320/Documents/GitHub/timeseries_molecular/M-multi-species/output/22-Visualizing-Rank-outs"
# Output directory
output_dir <- "/Users/sr320/Documents/GitHub/timeseries_molecular/M-multi-species/output/24-visualizing-rank05"
# Create output directory if it doesn't exist
dir.create(output_dir, showWarnings = FALSE, recursive = TRUE)Load All Data
# Get all rank_05 top100 annotation files
files <- list.files(input_dir,
pattern = "rank_05_comp.*_top100_annotation\\.csv$",
full.names = TRUE)
# Sort files by component number
file_df <- data.frame(
path = files,
component = str_extract(basename(files), "comp\\d+")
) %>%
mutate(comp_num = as.numeric(str_extract(component, "\\d+"))) %>%
arrange(comp_num)
cat(sprintf("Loading data from %d files...\n", nrow(file_df)))## Loading data from 5 files...# Read all files and combine
all_data <- map2_df(file_df$path, file_df$component, function(path, comp) {
read_csv(path, show_col_types = FALSE) %>%
mutate(component = comp)
})
cat(sprintf("Total rows loaded: %d\n", nrow(all_data)))## Total rows loaded: 500cat(sprintf("Unique group_ids: %d\n", n_distinct(all_data$group_id)))## Unique group_ids: 240Parse GO BP Terms with Group ID Tracking
# Function to expand GO BP terms while maintaining group_id
expand_go_bp_terms <- function(data) {
data %>%
filter(!is.na(go_bp) & go_bp != "") %>%
select(group_id, component, go_bp) %>%
mutate(
# Split GO terms by semicolon
go_terms = str_split(go_bp, ";")
) %>%
unnest(go_terms) %>%
mutate(
# Clean up the term (remove GO:XXXXX part)
go_term_clean = str_trim(go_terms),
go_term_clean = str_replace(go_term_clean, "\\s*\\[GO:.*\\]", "")
) %>%
filter(go_term_clean != "") %>%
select(group_id, component, go_term = go_term_clean)
}
# Expand all GO terms with group_id tracking
go_expanded <- expand_go_bp_terms(all_data)
cat(sprintf("Total GO term occurrences: %d\n", nrow(go_expanded)))## Total GO term occurrences: 2290cat(sprintf("Unique GO terms: %d\n", n_distinct(go_expanded$go_term)))## Unique GO terms: 833Analyze Redundancy
# For each GO term, count:
# 1. Total occurrences across all components
# 2. Number of unique group_ids
# 3. Number of components it appears in
# 4. How many times the same group_id appears in multiple components
go_term_analysis <- go_expanded %>%
group_by(go_term) %>%
summarise(
total_occurrences = n(),
unique_group_ids = n_distinct(group_id),
n_components = n_distinct(component),
# Calculate redundancy: if a group_id appears in 3 components, that's 2 redundant occurrences
redundant_occurrences = total_occurrences - unique_group_ids
) %>%
mutate(
# Percentage of occurrences that are redundant (same group_id in multiple components)
redundancy_pct = (redundant_occurrences / total_occurrences) * 100,
# Average times each unique group_id appears
avg_times_per_group = total_occurrences / unique_group_ids
) %>%
arrange(desc(total_occurrences))
# Display top terms
cat("\n### Top 30 GO Terms with Redundancy Analysis\n\n")##
## ### Top 30 GO Terms with Redundancy Analysisprint(kable(head(go_term_analysis, 30), digits = 2))##
##
## |go_term | total_occurrences| unique_group_ids| n_components| redundant_occurrences| redundancy_pct| avg_times_per_group|
## |:---------------------------------------------------------------------------|-----------------:|----------------:|------------:|---------------------:|--------------:|-------------------:|
## |negative regulation of transcription by RNA polymerase II | 28| 12| 5| 16| 57.14| 2.33|
## |regulation of transcription by RNA polymerase II | 26| 12| 5| 14| 53.85| 2.17|
## |positive regulation of transcription by RNA polymerase II | 23| 13| 5| 10| 43.48| 1.77|
## |positive regulation of DNA-templated transcription | 19| 10| 5| 9| 47.37| 1.90|
## |positive regulation of gene expression | 17| 8| 5| 9| 52.94| 2.12|
## |nervous system development | 16| 7| 5| 9| 56.25| 2.29|
## |cell division | 15| 7| 5| 8| 53.33| 2.14|
## |cell population proliferation | 15| 6| 5| 9| 60.00| 2.50|
## |Wnt signaling pathway | 14| 6| 5| 8| 57.14| 2.33|
## |negative regulation of apoptotic process | 14| 7| 5| 7| 50.00| 2.00|
## |kidney development | 12| 4| 4| 8| 66.67| 3.00|
## |regulation of DNA-templated transcription | 11| 4| 5| 7| 63.64| 2.75|
## |basement membrane organization | 10| 5| 5| 5| 50.00| 2.00|
## |cellular response to leukemia inhibitory factor | 10| 3| 4| 7| 70.00| 3.33|
## |homophilic cell adhesion via plasma membrane adhesion molecules | 10| 5| 5| 5| 50.00| 2.00|
## |proteolysis | 10| 5| 5| 5| 50.00| 2.00|
## |regulation of cell cycle | 10| 3| 4| 7| 70.00| 3.33|
## |roof of mouth development | 10| 5| 4| 5| 50.00| 2.00|
## |sensory perception of sound | 10| 3| 5| 7| 70.00| 3.33|
## |negative regulation of cell population proliferation | 9| 5| 5| 4| 44.44| 1.80|
## |neuron projection morphogenesis | 9| 3| 5| 6| 66.67| 3.00|
## |retina layer formation | 9| 3| 5| 6| 66.67| 3.00|
## |sprouting angiogenesis | 9| 3| 4| 6| 66.67| 3.00|
## |DNA repair | 8| 4| 5| 4| 50.00| 2.00|
## |branching involved in ureteric bud morphogenesis | 8| 3| 5| 5| 62.50| 2.67|
## |defense response to bacterium | 8| 2| 4| 6| 75.00| 4.00|
## |extracellular matrix organization | 8| 3| 5| 5| 62.50| 2.67|
## |heterophilic cell-cell adhesion via plasma membrane cell adhesion molecules | 8| 3| 5| 5| 62.50| 2.67|
## |intracellular signal transduction | 8| 5| 4| 3| 37.50| 1.60|
## |positive regulation of mesenchymal stem cell proliferation | 8| 3| 5| 5| 62.50| 2.67|Detailed Analysis: Top Terms
# Focus on top 30 terms from previous analysis
top_30_terms <- head(go_term_analysis$go_term, 30)
# For each top term, show which group_ids appear in multiple components
redundancy_details <- go_expanded %>%
filter(go_term %in% top_30_terms) %>%
group_by(go_term, group_id) %>%
summarise(
n_components = n_distinct(component),
components = paste(sort(unique(component)), collapse = ", "),
.groups = "drop"
) %>%
filter(n_components > 1) %>%
arrange(go_term, desc(n_components))
cat(sprintf("\nFound %d group_ids that appear in multiple components\n", nrow(redundancy_details)))##
## Found 88 group_ids that appear in multiple componentscat(sprintf("Across the top 30 GO terms\n\n"))## Across the top 30 GO terms# Show examples
if (nrow(redundancy_details) > 0) {
cat("### Examples of Group IDs Appearing in Multiple Components\n\n")
print(kable(head(redundancy_details, 50)))
}## ### Examples of Group IDs Appearing in Multiple Components
##
##
##
## |go_term |group_id | n_components|components |
## |:---------------------------------------------------------------------------|:--------|------------:|:--------------------------|
## |DNA repair |OG_04129 | 4|comp1, comp2, comp4, comp5 |
## |DNA repair |OG_09650 | 2|comp1, comp4 |
## |Wnt signaling pathway |OG_04737 | 4|comp1, comp2, comp4, comp5 |
## |Wnt signaling pathway |OG_07762 | 4|comp1, comp2, comp4, comp5 |
## |Wnt signaling pathway |OG_01366 | 2|comp4, comp5 |
## |Wnt signaling pathway |OG_03779 | 2|comp3, comp5 |
## |basement membrane organization |OG_02599 | 4|comp1, comp2, comp4, comp5 |
## |basement membrane organization |OG_01941 | 3|comp1, comp2, comp4 |
## |branching involved in ureteric bud morphogenesis |OG_01489 | 4|comp1, comp2, comp4, comp5 |
## |branching involved in ureteric bud morphogenesis |OG_10087 | 3|comp1, comp2, comp4 |
## |cell division |OG_07762 | 4|comp1, comp2, comp4, comp5 |
## |cell division |OG_01941 | 3|comp1, comp2, comp4 |
## |cell division |OG_05776 | 3|comp2, comp4, comp5 |
## |cell division |OG_03926 | 2|comp4, comp5 |
## |cell population proliferation |OG_02599 | 4|comp1, comp2, comp4, comp5 |
## |cell population proliferation |OG_05208 | 4|comp1, comp2, comp4, comp5 |
## |cell population proliferation |OG_06522 | 4|comp1, comp2, comp4, comp5 |
## |cellular response to leukemia inhibitory factor |OG_00887 | 4|comp1, comp2, comp4, comp5 |
## |cellular response to leukemia inhibitory factor |OG_05395 | 4|comp1, comp2, comp4, comp5 |
## |cellular response to leukemia inhibitory factor |OG_01366 | 2|comp4, comp5 |
## |defense response to bacterium |OG_01210 | 4|comp1, comp2, comp4, comp5 |
## |defense response to bacterium |OG_04170 | 4|comp1, comp2, comp4, comp5 |
## |extracellular matrix organization |OG_04737 | 4|comp1, comp2, comp4, comp5 |
## |extracellular matrix organization |OG_10087 | 3|comp1, comp2, comp4 |
## |heterophilic cell-cell adhesion via plasma membrane cell adhesion molecules |OG_01489 | 4|comp1, comp2, comp4, comp5 |
## |heterophilic cell-cell adhesion via plasma membrane cell adhesion molecules |OG_01941 | 3|comp1, comp2, comp4 |
## |homophilic cell adhesion via plasma membrane adhesion molecules |OG_01489 | 4|comp1, comp2, comp4, comp5 |
## |homophilic cell adhesion via plasma membrane adhesion molecules |OG_01941 | 3|comp1, comp2, comp4 |
## |intracellular signal transduction |OG_04195 | 3|comp2, comp4, comp5 |
## |intracellular signal transduction |OG_09727 | 2|comp3, comp5 |
## |kidney development |OG_01489 | 4|comp1, comp2, comp4, comp5 |
## |kidney development |OG_02599 | 4|comp1, comp2, comp4, comp5 |
## |kidney development |OG_04195 | 3|comp2, comp4, comp5 |
## |negative regulation of apoptotic process |OG_02599 | 4|comp1, comp2, comp4, comp5 |
## |negative regulation of apoptotic process |OG_04195 | 3|comp2, comp4, comp5 |
## |negative regulation of apoptotic process |OG_05776 | 3|comp2, comp4, comp5 |
## |negative regulation of cell population proliferation |OG_02599 | 4|comp1, comp2, comp4, comp5 |
## |negative regulation of cell population proliferation |OG_09650 | 2|comp1, comp4 |
## |negative regulation of transcription by RNA polymerase II |OG_02599 | 4|comp1, comp2, comp4, comp5 |
## |negative regulation of transcription by RNA polymerase II |OG_05110 | 4|comp1, comp2, comp4, comp5 |
## |negative regulation of transcription by RNA polymerase II |OG_05395 | 4|comp1, comp2, comp4, comp5 |
## |negative regulation of transcription by RNA polymerase II |OG_07762 | 4|comp1, comp2, comp4, comp5 |
## |negative regulation of transcription by RNA polymerase II |OG_05348 | 3|comp1, comp2, comp4 |
## |negative regulation of transcription by RNA polymerase II |OG_01366 | 2|comp4, comp5 |
## |negative regulation of transcription by RNA polymerase II |OG_09650 | 2|comp1, comp4 |
## |nervous system development |OG_02599 | 4|comp1, comp2, comp4, comp5 |
## |nervous system development |OG_05400 | 4|comp1, comp2, comp4, comp5 |
## |nervous system development |OG_09806 | 3|comp1, comp3, comp5 |
## |nervous system development |OG_03926 | 2|comp4, comp5 |
## |neuron projection morphogenesis |OG_04335 | 4|comp1, comp2, comp4, comp5 |Summary Statistics
# Overall statistics
overall_stats <- data.frame(
Metric = c(
"Total GO term occurrences",
"Unique GO terms",
"Unique group_ids with GO terms",
"Redundant occurrences (same group_id in multiple components)",
"Overall redundancy percentage"
),
Value = c(
nrow(go_expanded),
n_distinct(go_expanded$go_term),
n_distinct(go_expanded$group_id),
sum(go_term_analysis$redundant_occurrences),
round(sum(go_term_analysis$redundant_occurrences) / nrow(go_expanded) * 100, 2)
)
)
cat("\n### Overall Statistics\n\n")##
## ### Overall Statisticsprint(kable(overall_stats))##
##
## |Metric | Value|
## |:------------------------------------------------------------|-------:|
## |Total GO term occurrences | 2290.00|
## |Unique GO terms | 833.00|
## |Unique group_ids with GO terms | 94.00|
## |Redundant occurrences (same group_id in multiple components) | 1154.00|
## |Overall redundancy percentage | 50.39|# Stats for top 30 terms
top_30_stats <- go_term_analysis %>%
slice_head(n = 30) %>%
summarise(
total_occurrences = sum(total_occurrences),
redundant_occurrences = sum(redundant_occurrences),
avg_redundancy_pct = mean(redundancy_pct)
)
cat("\n### Top 30 Terms Statistics\n\n")##
## ### Top 30 Terms Statisticscat(sprintf("Total occurrences: %d\n", top_30_stats$total_occurrences))## Total occurrences: 372cat(sprintf("Redundant occurrences: %d\n", top_30_stats$redundant_occurrences))## Redundant occurrences: 210cat(sprintf("Redundancy percentage: %.2f%%\n", (top_30_stats$redundant_occurrences / top_30_stats$total_occurrences * 100)))## Redundancy percentage: 56.45%cat(sprintf("Average redundancy per term: %.2f%%\n", top_30_stats$avg_redundancy_pct))## Average redundancy per term: 57.63%Visualization: Redundancy Analysis
# Plot for top 30 terms
plot_data <- go_term_analysis %>%
slice_head(n = 30) %>%
mutate(
go_term = factor(go_term, levels = rev(go_term))
) %>%
pivot_longer(
cols = c(unique_group_ids, redundant_occurrences),
names_to = "type",
values_to = "count"
) %>%
mutate(
type = case_when(
type == "unique_group_ids" ~ "Unique group_ids",
type == "redundant_occurrences" ~ "Redundant (same group_id)"
)
)
p1 <- ggplot(plot_data, aes(x = go_term, y = count, fill = type)) +
geom_bar(stat = "identity", position = "stack") +
coord_flip() +
scale_fill_manual(
values = c("Unique group_ids" = "steelblue",
"Redundant (same group_id)" = "orange"),
name = "Occurrence Type"
) +
labs(
title = "Redundancy Analysis: Top 30 GO BP Terms (Rank 05)",
subtitle = "Blue = unique group_ids, Orange = redundant occurrences (same group_id in multiple components)",
x = "GO Biological Process Term",
y = "Count"
) +
theme_minimal(base_size = 12) +
theme(
plot.title = element_text(size = 16, face = "bold"),
plot.subtitle = element_text(size = 11, color = "gray40"),
axis.text.y = element_text(size = 10),
legend.position = "bottom"
)
print(p1)
ggsave(
filename = file.path(output_dir, "rank05_GO_redundancy_analysis.png"),
plot = p1,
width = 14,
height = 10,
dpi = 300
)Redundancy Percentage Plot
p2 <- go_term_analysis %>%
slice_head(n = 30) %>%
mutate(go_term = factor(go_term, levels = rev(go_term))) %>%
ggplot(aes(x = go_term, y = redundancy_pct)) +
geom_bar(stat = "identity", fill = "coral", alpha = 0.8) +
geom_text(aes(label = sprintf("%.1f%%", redundancy_pct)),
hjust = -0.1, size = 3) +
coord_flip() +
labs(
title = "Redundancy Percentage: Top 30 GO BP Terms (Rank 05)",
subtitle = "Percentage of occurrences due to same group_id appearing in multiple components",
x = "GO Biological Process Term",
y = "Redundancy Percentage (%)"
) +
theme_minimal(base_size = 12) +
theme(
plot.title = element_text(size = 16, face = "bold"),
plot.subtitle = element_text(size = 11, color = "gray40"),
axis.text.y = element_text(size = 10),
panel.grid.major.y = element_blank()
)
print(p2)
ggsave(
filename = file.path(output_dir, "rank05_GO_redundancy_percentage.png"),
plot = p2,
width = 14,
height = 10,
dpi = 300
)Group IDs Appearing in Most Components
# Which group_ids appear in the most components?
group_id_frequency <- go_expanded %>%
group_by(group_id) %>%
summarise(
n_components = n_distinct(component),
n_go_terms = n_distinct(go_term),
go_terms_sample = paste(head(unique(go_term), 3), collapse = "; ")
) %>%
arrange(desc(n_components)) %>%
head(50)
cat("\n### Top 50 Group IDs by Component Frequency\n\n")##
## ### Top 50 Group IDs by Component Frequencyprint(kable(head(group_id_frequency, 50)))##
##
## |group_id | n_components| n_go_terms|go_terms_sample |
## |:--------|------------:|----------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------|
## |OG_04439 | 5| 1|cilium movement involved in cell motility |
## |OG_00887 | 4| 6|cellular response to leukemia inhibitory factor; glycine catabolic process; glycine decarboxylation via glycine cleavage system |
## |OG_01210 | 4| 12|blood circulation; defense response to bacterium; immune system process |
## |OG_01475 | 4| 5|chloride transmembrane transport; chloride transport; oxalate transport |
## |OG_01489 | 4| 18|branching involved in ureteric bud morphogenesis; cerebral cortex development; condensed mesenchymal cell proliferation |
## |OG_02599 | 4| 64|anterior neuropore closure; basement membrane organization; bone morphogenesis |
## |OG_03061 | 4| 3|pore complex assembly; protein localization to plasma membrane; protein maturation |
## |OG_04129 | 4| 3|base-excision repair; DNA repair; response to oxidative stress |
## |OG_04170 | 4| 4|defense response to bacterium; hydrogen peroxide catabolic process; immune response |
## |OG_04335 | 4| 5|axon guidance; modulation of chemical synaptic transmission; negative regulation of fat cell differentiation |
## |OG_04737 | 4| 13|blood vessel maturation; canonical Wnt signaling pathway; dorsal root ganglion development |
## |OG_04999 | 4| 8|camera-type eye development; circadian regulation of gene expression; embryonic retina morphogenesis in camera-type eye |
## |OG_05110 | 4| 11|atrial septum primum morphogenesis; atrial septum secundum morphogenesis; bone development |
## |OG_05208 | 4| 9|cell population proliferation; cholangiocyte proliferation; chromosome segregation |
## |OG_05395 | 4| 15|angiogenesis; cellular response to leukemia inhibitory factor; cellular response to peptide |
## |OG_05400 | 4| 9|bone resorption; epithelial cell differentiation; lysosomal protein catabolic process |
## |OG_06522 | 4| 7|astrocyte development; cell population proliferation; cell surface receptor protein tyrosine kinase signaling pathway |
## |OG_07103 | 4| 1|unsaturated fatty acid biosynthetic process |
## |OG_07519 | 4| 9|actin filament organization; auditory receptor cell stereocilium organization; cilium assembly |
## |OG_07631 | 4| 7|fatty acid elongation, monounsaturated fatty acid; fatty acid elongation, polyunsaturated fatty acid; fatty acid elongation, saturated fatty acid |
## |OG_07762 | 4| 27|animal organ regeneration; antral ovarian follicle growth; cell division |
## |OG_07861 | 4| 3|cell development; neuron differentiation; regulation of transcription by RNA polymerase II |
## |OG_08226 | 4| 4|actomyosin contractile ring assembly; mitotic cytokinesis; positive regulation of bleb assembly |
## |OG_01941 | 3| 7|actin cytoskeleton organization; basement membrane organization; cell division |
## |OG_02550 | 3| 1|deoxyribonucleotide biosynthetic process |
## |OG_04075 | 3| 1|blastocyst hatching |
## |OG_04195 | 3| 67|activin receptor signaling pathway; angiogenesis; angiogenesis involved in coronary vascular morphogenesis |
## |OG_05348 | 3| 26|adenylate cyclase-inhibiting G protein-coupled receptor signaling pathway; aorta development; cAMP-mediated signaling |
## |OG_05445 | 3| 5|cellular response to nitric oxide; cGMP biosynthetic process; cGMP-mediated signaling |
## |OG_05776 | 3| 6|cell division; central nervous system development; mitotic nuclear membrane reassembly |
## |OG_09806 | 3| 28|artery morphogenesis; cellular response to lipoprotein particle stimulus; cholesterol efflux |
## |OG_10087 | 3| 6|branching involved in ureteric bud morphogenesis; extracellular matrix organization; male gamete generation |
## |OG_01366 | 2| 4|cellular response to leukemia inhibitory factor; negative regulation of canonical Wnt signaling pathway; negative regulation of transcription by RNA polymerase II |
## |OG_03332 | 2| 14|autophagosome maturation; cellular response to glucose starvation; early endosome to late endosome transport |
## |OG_03779 | 2| 15|cell migration; establishment or maintenance of cell polarity; Golgi to plasma membrane protein transport |
## |OG_03926 | 2| 3|cell division; nervous system development; regulation of cell cycle |
## |OG_04041 | 2| 16|B cell differentiation; definitive hemopoiesis; embryonic camera-type eye morphogenesis |
## |OG_04538 | 2| 2|antibacterial innate immune response; defense response to Gram-negative bacterium |
## |OG_05765 | 2| 5|DNA replication; DNA replication initiation; double-strand break repair via break-induced replication |
## |OG_07349 | 2| 7|cell-matrix adhesion; cortical microtubule organization; negative regulation of protein localization to plasma membrane |
## |OG_07351 | 2| 8|adenylate cyclase-activating G protein-coupled receptor signaling pathway; cellular response to luteinizing hormone stimulus; hormone-mediated signaling pathway |
## |OG_07441 | 2| 15|adult walking behavior; brain development; cell differentiation |
## |OG_08089 | 2| 14|cilium assembly; cloaca development; cytoskeleton organization |
## |OG_08842 | 2| 1|sensory perception of sound |
## |OG_09650 | 2| 19|anterior/posterior pattern specification; associative learning; cellular response to phorbol 13-acetate 12-myristate |
## |OG_09727 | 2| 4|intracellular signal transduction; negative regulation of Ras protein signal transduction; platelet activation |
## |OG_00145 | 1| 8|embryonic organ development; hippo signaling; positive regulation of cell growth |
## |OG_00281 | 1| 12|cell cycle comprising mitosis without cytokinesis; chorionic trophoblast cell differentiation; fibroblast proliferation |
## |OG_00403 | 1| 8|cerebellum development; glutamate biosynthetic process; glutamate catabolic process |
## |OG_00615 | 1| 2|proteolysis; regulation of inflammatory response |# Plot
p3 <- group_id_frequency %>%
head(30) %>%
mutate(group_id = factor(group_id, levels = rev(group_id))) %>%
ggplot(aes(x = group_id, y = n_components)) +
geom_bar(stat = "identity", fill = "darkgreen", alpha = 0.7) +
geom_text(aes(label = n_components), hjust = -0.2, size = 3) +
coord_flip() +
labs(
title = "Top 30 Group IDs by Number of Components (Rank 05)",
subtitle = "Group IDs that appear in the most components",
x = "Group ID",
y = "Number of Components"
) +
theme_minimal(base_size = 12) +
theme(
plot.title = element_text(size = 14, face = "bold"),
axis.text.y = element_text(size = 9),
panel.grid.major.y = element_blank()
)
print(p3)
ggsave(
filename = file.path(output_dir, "rank05_most_frequent_group_ids.png"),
plot = p3,
width = 12,
height = 8,
dpi = 300
)Export Detailed Results
# Export full redundancy analysis
write_csv(
go_term_analysis,
file.path(output_dir, "rank05_GO_redundancy_full_analysis.csv")
)
# Export group IDs appearing in multiple components
write_csv(
redundancy_details,
file.path(output_dir, "rank05_redundant_group_ids_details.csv")
)
# Export group ID frequency
write_csv(
group_id_frequency,
file.path(output_dir, "rank05_group_id_component_frequency.csv")
)
cat("\nExported detailed results to CSV files\n")##
## Exported detailed results to CSV filesSession Info
sessionInfo()## R version 4.3.2 (2023-10-31)
## Platform: aarch64-apple-darwin20 (64-bit)
## Running under: macOS Sonoma 14.7.6
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/lib/libRlapack.dylib; LAPACK version 3.11.0
##
## locale:
## [1] C
##
## time zone: America/Los_Angeles
## tzcode source: internal
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] knitr_1.48 RColorBrewer_1.1-3 lubridate_1.9.3 forcats_1.0.0
## [5] stringr_1.5.1 dplyr_1.1.4 purrr_1.0.2 readr_2.1.5
## [9] tidyr_1.3.1 tibble_3.2.1 ggplot2_3.5.1 tidyverse_2.0.0
##
## loaded via a namespace (and not attached):
## [1] sass_0.4.9 utf8_1.2.4 generics_0.1.3 stringi_1.8.4
## [5] hms_1.1.3 digest_0.6.37 magrittr_2.0.3 evaluate_1.0.0
## [9] grid_4.3.2 timechange_0.3.0 fastmap_1.2.0 jsonlite_1.8.9
## [13] fansi_1.0.6 scales_1.3.0 textshaping_0.4.0 jquerylib_0.1.4
## [17] cli_3.6.3 rlang_1.1.4 crayon_1.5.3 bit64_4.5.2
## [21] munsell_0.5.1 withr_3.0.1 cachem_1.1.0 yaml_2.3.10
## [25] tools_4.3.2 parallel_4.3.2 tzdb_0.4.0 colorspace_2.1-1
## [29] vctrs_0.6.5 R6_2.5.1 lifecycle_1.0.4 bit_4.5.0
## [33] vroom_1.6.5 ragg_1.3.3 pkgconfig_2.0.3 pillar_1.9.0
## [37] bslib_0.8.0 gtable_0.3.6 glue_1.8.0 systemfonts_1.1.0
## [41] highr_0.11 xfun_0.48 tidyselect_1.2.1 farver_2.1.2
## [45] htmltools_0.5.8.1 rmarkdown_2.28 labeling_0.4.3 compiler_4.3.2