Chromosome engineering to correct a complex rearrangement on chromosome 8 reveals the effects of 8p syndrome on gene expression and neural differentiation
Computational Analysis for Figure 5 and Supplementary
Lu Qiao
2025-08-12
Load Libraries
library("readxl")
library("tidyverse")
library("edgeR")
library("clusterProfiler")
library("org.Hs.eg.db")
library("enrichplot")
library("msigdbr")
library("biomaRt")
library(grid)
library(scales)
library(ggrepel)
library(gtsummary)
library(gt)
library(MetBrewer)
library(eulerr)
library(ggthemes)Differential Expression analysis
define functions
fc_threshold = 1
get_results <- function(contrast, qlf, p_value = 0.05, n_top = Inf) {
# identify significant DE genes
is.de <- decideTests(qlf, p.value = p_value)
summary_de <- summary(is.de)
top_tags <- topTags(qlf, n = n_top)
upregulated <- sum(is.de == 1)
downregulated <- sum(is.de == -1)
no_change <- sum(is.de == 0)
# apply a threshold for DE genes
thresholded_results <- top_tags$table[
top_tags$table$FDR <= 0.05 & abs(top_tags$table$logFC) >= fc_threshold, ]
return(list(
contrast = contrast,
qlf = qlf,
is_de = is.de,
summary_de = summary_de,
top_tags = top_tags,
upregulated = upregulated,
downregulated = downregulated,
no_change = no_change,
thresholded_results = thresholded_results
))
}
# Function to plot multiple group comparisons
plot_all_results <- function(results_list) {
plot_data <- do.call(rbind, lapply(results_list, function(result) {
data.frame(
Category = c("Upregulated", "Downregulated", "No Change"),
Count = c(result$upregulated, result$downregulated, result$no_change),
Comparison = result$contrast
)
}))
plot <- ggplot(plot_data, aes(x = Comparison, y = Count, fill = Category)) +
geom_bar(stat = "identity", position = "dodge") +
geom_text(aes(label = Count),
position = position_dodge(width = 0.9),
vjust = -0.5) +
labs(title = "Differential Expression Across Comparisons",
x = "Comparison",
y = "Number of Genes") +
theme_minimal() +
scale_fill_manual(values = c("Upregulated" = "green", "Downregulated" = "red", "No Change" = "gray"))
print(plot)
}
plot_thresholded_results <- function(results_list) {
plot_data <- lapply(results_list, function(result) {
thresholded_results <- result$thresholded_results
# Count the number of upregulated genes (logFC >= 1.0)
upregulated_genes <- thresholded_results[thresholded_results$logFC >= fc_threshold & thresholded_results$FDR <= 0.05, ]
num_upregulated <- nrow(upregulated_genes)
# Count the number of downregulated genes (logFC <= -1.0)
downregulated_genes <- thresholded_results[thresholded_results$logFC <= -fc_threshold & thresholded_results$FDR <= 0.05, ]
num_downregulated <- nrow(downregulated_genes)
all <- num_downregulated + num_upregulated
data.frame(
Category = c("Upregulated", "Downregulated", "ALL"),
Count = c(num_upregulated, num_downregulated, all),
Comparison = result$contrast
)
})
plot_data <- do.call(rbind, plot_data)
plot <- ggplot(plot_data, aes(x = Comparison, y = Count, fill = Category)) +
geom_bar(stat = "identity", position = "dodge") +
geom_text(aes(label = Count),
position = position_dodge(width = 0.9),
vjust = -0.5) + # Adds numbers on top of bars
labs(title = "Differential Expression Across Comparisons (padj <= 0.05 or |logFC| >= 0.5) ",
x = "Comparison",
y = "Number of Genes") +
theme_minimal() +
scale_fill_manual(values = c("Upregulated" = "green", "Downregulated" = "red", "ALL" = "gray"))
print(plot)
return(plot_data)
}
custom_rollmean <- function(x, k = 40) {
n <- length(x)
half_window <- k / 2
rolling_avg <- rep(NA, n) # Initialize the rolling average vector
# First half (start) of the series: fewer previous values
for (i in 1:half_window) {
rolling_avg[i] <- mean(x[1:(i + half_window)], na.rm = TRUE)
}
# Middle part: use full window size
for (i in (half_window + 1):(n - half_window)) {
rolling_avg[i] <- mean(x[(i - half_window):(i + half_window)], na.rm = TRUE)
}
# Last half (end) of the series: fewer subsequent values
for (i in (n - half_window + 1):n) {
rolling_avg[i] <- mean(x[(i - half_window):n], na.rm = TRUE)
}
return(rolling_avg)
}ensembl <- useEnsembl(biomart = "genes", dataset = "hsapiens_gene_ensembl")
# region of interest
chromosome_of_interest <- "8"
deletion_start <- 0
deletion_end <- 7247573
duplication_start <- 11828865
duplication_end <- 40361770
attributes <- c(
"ensembl_gene_id",
"external_gene_name",
"chromosome_name",
"start_position",
"end_position",
"strand",
"gene_biotype",
"description"
)
# deletion region
filters_del <- c("chromosome_name", "start", "end")
values_del <- list(chromosome_of_interest, deletion_start, deletion_end)
genes_in_deletion <- getBM(
attributes = attributes,
filters = filters_del,
values = values_del,
mart = ensembl
)
protein_coding_genes_del <- genes_in_deletion[genes_in_deletion$gene_biotype == "protein_coding", ]
number_of_genes_del <- length(unique(protein_coding_genes_del$ensembl_gene_id))
cat("Number of protein-coding genes in the deletion region:", number_of_genes_del, "\n")## Number of protein-coding genes in the deletion region: 23# duplication region
filters_dup <- c("chromosome_name", "start", "end")
values_dup <- list(chromosome_of_interest, duplication_start, duplication_end)
genes_in_duplication <- getBM(
attributes = attributes,
filters = filters_dup,
values = values_dup,
mart = ensembl
)
protein_coding_genes_dup <- genes_in_duplication[genes_in_duplication$gene_biotype == "protein_coding", ]
number_of_genes_dup <- length(unique(protein_coding_genes_dup$ensembl_gene_id))
cat("Number of protein-coding genes in the duplication region:", number_of_genes_dup, "\n")## Number of protein-coding genes in the duplication region: 172protein_coding_genes_del$region <- "Deletion"
protein_coding_genes_dup$region <- "Duplication"
combined_genes <- rbind(protein_coding_genes_del, protein_coding_genes_dup)
combined_genes| ensembl_gene_id | external_gene_name | chromosome_name | start_position | end_position | strand | gene_biotype | description | region | |
|---|---|---|---|---|---|---|---|---|---|
| 6 | ENSG00000176269 | OR4F21 | 8 | 166086 | 167024 | -1 | protein_coding | olfactory receptor family 4 subfamily F member 21 [Source:HGNC Symbol;Acc:HGNC:19583] | Deletion |
| 10 | ENSG00000172748 | ZNF596 | 8 | 232137 | 264703 | 1 | protein_coding | zinc finger protein 596 [Source:HGNC Symbol;Acc:HGNC:27268] | Deletion |
| 21 | ENSG00000147364 | FBXO25 | 8 | 406428 | 477967 | 1 | protein_coding | F-box protein 25 [Source:HGNC Symbol;Acc:HGNC:13596] | Deletion |
| 24 | ENSG00000180190 | TDRP | 8 | 489803 | 545781 | -1 | protein_coding | testis development related protein [Source:HGNC Symbol;Acc:HGNC:26951] | Deletion |
| 26 | ENSG00000104714 | ERICH1 | 8 | 614746 | 738106 | -1 | protein_coding | glutamate rich 1 [Source:HGNC Symbol;Acc:HGNC:27234] | Deletion |
| 31 | ENSG00000198010 | DLGAP2 | 8 | 737628 | 1708476 | 1 | protein_coding | DLG associated protein 2 [Source:HGNC Symbol;Acc:HGNC:2906] | Deletion |
| 48 | ENSG00000182372 | CLN8 | 8 | 1755778 | 1801711 | 1 | protein_coding | CLN8 transmembrane ER and ERGIC protein [Source:HGNC Symbol;Acc:HGNC:2079] | Deletion |
| 50 | ENSG00000283239 | KBTBD11-OT1 | 8 | 1763888 | 1958627 | 1 | protein_coding | KBTBD11 overlapping transcript 1 [Source:NCBI gene (formerly Entrezgene);Acc:104266957] | Deletion |
| 54 | ENSG00000104728 | ARHGEF10 | 8 | 1823926 | 1958641 | 1 | protein_coding | Rho guanine nucleotide exchange factor 10 [Source:HGNC Symbol;Acc:HGNC:14103] | Deletion |
| 60 | ENSG00000176595 | KBTBD11 | 8 | 1973677 | 2006936 | 1 | protein_coding | kelch repeat and BTB domain containing 11 [Source:HGNC Symbol;Acc:HGNC:29104] | Deletion |
| 64 | ENSG00000036448 | MYOM2 | 8 | 2045046 | 2165552 | 1 | protein_coding | myomesin 2 [Source:HGNC Symbol;Acc:HGNC:7614] | Deletion |
| 85 | ENSG00000183117 | CSMD1 | 8 | 2935353 | 4994972 | -1 | protein_coding | CUB and Sushi multiple domains 1 [Source:HGNC Symbol;Acc:HGNC:14026] | Deletion |
| 121 | ENSG00000147316 | MCPH1 | 8 | 6406592 | 6648508 | 1 | protein_coding | microcephalin 1 [Source:HGNC Symbol;Acc:HGNC:6954] | Deletion |
| 123 | ENSG00000091879 | ANGPT2 | 8 | 6499632 | 6563409 | -1 | protein_coding | angiopoietin 2 [Source:HGNC Symbol;Acc:HGNC:485] | Deletion |
| 130 | ENSG00000155189 | AGPAT5 | 8 | 6708642 | 6761503 | 1 | protein_coding | 1-acylglycerol-3-phosphate O-acyltransferase 5 [Source:HGNC Symbol;Acc:HGNC:20886] | Deletion |
| 137 | ENSG00000275591 | XKR5 | 8 | 6808517 | 6835524 | -1 | protein_coding | XK related 5 [Source:HGNC Symbol;Acc:HGNC:20782] | Deletion |
| 141 | ENSG00000164825 | DEFB1 | 8 | 6870592 | 6877936 | -1 | protein_coding | defensin beta 1 [Source:HGNC Symbol;Acc:HGNC:2766] | Deletion |
| 144 | ENSG00000164822 | DEFA6 | 8 | 6924697 | 6926076 | -1 | protein_coding | defensin alpha 6 [Source:HGNC Symbol;Acc:HGNC:2765] | Deletion |
| 147 | ENSG00000164821 | DEFA4 | 8 | 6935820 | 6938306 | -1 | protein_coding | defensin alpha 4 [Source:HGNC Symbol;Acc:HGNC:2763] | Deletion |
| 152 | ENSG00000206047 | DEFA1 | 8 | 6977649 | 6980092 | -1 | protein_coding | defensin alpha 1 [Source:HGNC Symbol;Acc:HGNC:2761] | Deletion |
| 155 | ENSG00000240247 | DEFA1B | 8 | 6996766 | 6999198 | -1 | protein_coding | defensin alpha 1B [Source:HGNC Symbol;Acc:HGNC:33596] | Deletion |
| 158 | ENSG00000239839 | DEFA3 | 8 | 7015869 | 7018297 | -1 | protein_coding | defensin alpha 3 [Source:HGNC Symbol;Acc:HGNC:2762] | Deletion |
| 161 | ENSG00000164816 | DEFA5 | 8 | 7055304 | 7056739 | -1 | protein_coding | defensin alpha 5 [Source:HGNC Symbol;Acc:HGNC:2764] | Deletion |
| 1 | ENSG00000079459 | FDFT1 | 8 | 11795573 | 11839395 | 1 | protein_coding | farnesyl-diphosphate farnesyltransferase 1 [Source:HGNC Symbol;Acc:HGNC:3629] | Duplication |
| 2 | ENSG00000164733 | CTSB | 8 | 11842524 | 11869533 | -1 | protein_coding | cathepsin B [Source:HGNC Symbol;Acc:HGNC:2527] | Duplication |
| 101 | ENSG00000205884 | DEFB136 | 8 | 11973937 | 11974599 | -1 | protein_coding | defensin beta 136 [Source:HGNC Symbol;Acc:HGNC:34433] | Duplication |
| 11 | ENSG00000205883 | DEFB135 | 8 | 11982256 | 11984590 | 1 | protein_coding | defensin beta 135 [Source:HGNC Symbol;Acc:HGNC:32400] | Duplication |
| 12 | ENSG00000205882 | DEFB134 | 8 | 11993174 | 12000752 | -1 | protein_coding | defensin beta 134 [Source:HGNC Symbol;Acc:HGNC:32399] | Duplication |
| 20 | ENSG00000233050 | DEFB130B | 8 | 12064389 | 12071747 | -1 | protein_coding | defensin beta 130B [Source:HGNC Symbol;Acc:HGNC:39814] | Duplication |
| 22 | ENSG00000215343 | ZNF705D | 8 | 12089338 | 12115516 | 1 | protein_coding | zinc finger protein 705D [Source:HGNC Symbol;Acc:HGNC:33202] | Duplication |
| 262 | ENSG00000226430 | USP17L7 | 8 | 12132417 | 12134099 | -1 | protein_coding | ubiquitin specific peptidase 17 like family member 7 [Source:HGNC Symbol;Acc:HGNC:37180] | Duplication |
| 27 | ENSG00000223443 | USP17L2 | 8 | 12136435 | 12138849 | -1 | protein_coding | ubiquitin specific peptidase 17 like family member 2 [Source:HGNC Symbol;Acc:HGNC:34434] | Duplication |
| 28 | ENSG00000254866 | DEFB109D | 8 | 12150888 | 12158033 | -1 | protein_coding | defensin beta 109D (pseudogene) [Source:HGNC Symbol;Acc:HGNC:30838] | Duplication |
| 311 | ENSG00000186523 | FAM86B1 | 8 | 12182096 | 12194133 | -1 | protein_coding | family with sequence similarity 86 member B1 [Source:HGNC Symbol;Acc:HGNC:28268] | Duplication |
| 35 | ENSG00000232948 | DEFB130A | 8 | 12310962 | 12318316 | -1 | protein_coding | defensin beta 130A [Source:HGNC Symbol;Acc:HGNC:18107] | Duplication |
| 47 | ENSG00000145002 | FAM86B2 | 8 | 12424411 | 12436406 | -1 | protein_coding | family with sequence similarity 86 member B2 [Source:HGNC Symbol;Acc:HGNC:32222] | Duplication |
| 65 | ENSG00000154359 | LONRF1 | 8 | 12721906 | 12756073 | -1 | protein_coding | LON peptidase N-terminal domain and ring finger 1 [Source:HGNC Symbol;Acc:HGNC:26302] | Duplication |
| 73 | ENSG00000250305 | TRMT9B | 8 | 12945642 | 13031503 | 1 | protein_coding | tRNA methyltransferase 9B (putative) [Source:HGNC Symbol;Acc:HGNC:26725] | Duplication |
| 78 | ENSG00000164741 | DLC1 | 8 | 13083361 | 13604610 | -1 | protein_coding | DLC1 Rho GTPase activating protein [Source:HGNC Symbol;Acc:HGNC:2897] | Duplication |
| 84 | ENSG00000164743 | C8orf48 | 8 | 13566869 | 13568288 | 1 | protein_coding | chromosome 8 open reading frame 48 [Source:HGNC Symbol;Acc:HGNC:26345] | Duplication |
| 95 | ENSG00000185053 | SGCZ | 8 | 14084845 | 15238431 | -1 | protein_coding | sarcoglycan zeta [Source:HGNC Symbol;Acc:HGNC:14075] | Duplication |
| 110 | ENSG00000104723 | TUSC3 | 8 | 15417215 | 15766649 | 1 | protein_coding | tumor suppressor candidate 3 [Source:HGNC Symbol;Acc:HGNC:30242] | Duplication |
| 117 | ENSG00000038945 | MSR1 | 8 | 16107878 | 16567490 | -1 | protein_coding | macrophage scavenger receptor 1 [Source:HGNC Symbol;Acc:HGNC:7376] | Duplication |
| 125 | ENSG00000078579 | FGF20 | 8 | 16992181 | 17002345 | -1 | protein_coding | fibroblast growth factor 20 [Source:HGNC Symbol;Acc:HGNC:3677] | Duplication |
| 127 | ENSG00000155970 | MICU3 | 8 | 17027238 | 17125880 | 1 | protein_coding | mitochondrial calcium uptake family member 3 [Source:HGNC Symbol;Acc:HGNC:27820] | Duplication |
| 131 | ENSG00000104219 | ZDHHC2 | 8 | 17156482 | 17224799 | 1 | protein_coding | zinc finger DHHC-type palmitoyltransferase 2 [Source:HGNC Symbol;Acc:HGNC:18469] | Duplication |
| 132 | ENSG00000198791 | CNOT7 | 8 | 17224966 | 17246878 | -1 | protein_coding | CCR4-NOT transcription complex subunit 7 [Source:HGNC Symbol;Acc:HGNC:14101] | Duplication |
| 134 | ENSG00000155975 | VPS37A | 8 | 17246931 | 17302427 | 1 | protein_coding | VPS37A subunit of ESCRT-I [Source:HGNC Symbol;Acc:HGNC:24928] | Duplication |
| 136 | ENSG00000003987 | MTMR7 | 8 | 17296794 | 17413528 | -1 | protein_coding | myotubularin related protein 7 [Source:HGNC Symbol;Acc:HGNC:7454] | Duplication |
| 1411 | ENSG00000003989 | SLC7A2 | 8 | 17497088 | 17570573 | 1 | protein_coding | solute carrier family 7 member 2 [Source:HGNC Symbol;Acc:HGNC:11060] | Duplication |
| 146 | ENSG00000104213 | PDGFRL | 8 | 17576433 | 17644071 | 1 | protein_coding | platelet derived growth factor receptor like [Source:HGNC Symbol;Acc:HGNC:8805] | Duplication |
| 149 | ENSG00000129422 | MTUS1 | 8 | 17643795 | 17801094 | -1 | protein_coding | microtubule associated scaffold protein 1 [Source:HGNC Symbol;Acc:HGNC:29789] | Duplication |
| 156 | ENSG00000104760 | FGL1 | 8 | 17864380 | 17910365 | -1 | protein_coding | fibrinogen like 1 [Source:HGNC Symbol;Acc:HGNC:3695] | Duplication |
| 159 | ENSG00000078674 | PCM1 | 8 | 17922842 | 18029948 | 1 | protein_coding | pericentriolar material 1 [Source:HGNC Symbol;Acc:HGNC:8727] | Duplication |
| 1611 | ENSG00000104763 | ASAH1 | 8 | 18055992 | 18084998 | -1 | protein_coding | N-acylsphingosine amidohydrolase 1 [Source:HGNC Symbol;Acc:HGNC:735] | Duplication |
| 164 | ENSG00000171428 | NAT1 | 8 | 18170477 | 18223689 | 1 | protein_coding | N-acetyltransferase 1 [Source:HGNC Symbol;Acc:HGNC:7645] | Duplication |
| 171 | ENSG00000156006 | NAT2 | 8 | 18391282 | 18401218 | 1 | protein_coding | N-acetyltransferase 2 [Source:HGNC Symbol;Acc:HGNC:7646] | Duplication |
| 172 | ENSG00000156011 | PSD3 | 8 | 18527303 | 19084730 | -1 | protein_coding | pleckstrin and Sec7 domain containing 3 [Source:HGNC Symbol;Acc:HGNC:19093] | Duplication |
| 190 | ENSG00000104611 | SH2D4A | 8 | 19313693 | 19396218 | 1 | protein_coding | SH2 domain containing 4A [Source:HGNC Symbol;Acc:HGNC:26102] | Duplication |
| 192 | ENSG00000147408 | CSGALNACT1 | 8 | 19404161 | 19758029 | -1 | protein_coding | chondroitin sulfate N-acetylgalactosaminyltransferase 1 [Source:HGNC Symbol;Acc:HGNC:24290] | Duplication |
| 198 | ENSG00000104613 | INTS10 | 8 | 19817391 | 19852083 | 1 | protein_coding | integrator complex subunit 10 [Source:HGNC Symbol;Acc:HGNC:25548] | Duplication |
| 199 | ENSG00000175445 | LPL | 8 | 19901717 | 19967259 | 1 | protein_coding | lipoprotein lipase [Source:HGNC Symbol;Acc:HGNC:6677] | Duplication |
| 204 | ENSG00000036565 | SLC18A1 | 8 | 20144855 | 20183206 | -1 | protein_coding | solute carrier family 18 member A1 [Source:HGNC Symbol;Acc:HGNC:10934] | Duplication |
| 206 | ENSG00000147416 | ATP6V1B2 | 8 | 20197381 | 20230399 | 1 | protein_coding | ATPase H+ transporting V1 subunit B2 [Source:HGNC Symbol;Acc:HGNC:854] | Duplication |
| 209 | ENSG00000061337 | LZTS1 | 8 | 20246165 | 20303963 | -1 | protein_coding | leucine zipper tumor suppressor 1 [Source:HGNC Symbol;Acc:HGNC:13861] | Duplication |
| 235 | ENSG00000168546 | GFRA2 | 8 | 21690398 | 21812357 | -1 | protein_coding | GDNF family receptor alpha 2 [Source:HGNC Symbol;Acc:HGNC:4244] | Duplication |
| 237 | ENSG00000147443 | DOK2 | 8 | 21908873 | 21913690 | -1 | protein_coding | docking protein 2 [Source:HGNC Symbol;Acc:HGNC:2991] | Duplication |
| 238 | ENSG00000130227 | XPO7 | 8 | 21919662 | 22006585 | 1 | protein_coding | exportin 7 [Source:HGNC Symbol;Acc:HGNC:14108] | Duplication |
| 241 | ENSG00000158806 | NPM2 | 8 | 22024125 | 22036897 | 1 | protein_coding | nucleophosmin/nucleoplasmin 2 [Source:HGNC Symbol;Acc:HGNC:7930] | Duplication |
| 242 | ENSG00000158815 | FGF17 | 8 | 22042398 | 22048809 | 1 | protein_coding | fibroblast growth factor 17 [Source:HGNC Symbol;Acc:HGNC:3673] | Duplication |
| 243 | ENSG00000158856 | DMTN | 8 | 22048995 | 22082527 | 1 | protein_coding | dematin actin binding protein [Source:HGNC Symbol;Acc:HGNC:3382] | Duplication |
| 245 | ENSG00000158863 | FHIP2B | 8 | 22089150 | 22104911 | 1 | protein_coding | FHF complex subunit HOOK interacting protein 2B [Source:HGNC Symbol;Acc:HGNC:16492] | Duplication |
| 246 | ENSG00000275074 | NUDT18 | 8 | 22105748 | 22109419 | -1 | protein_coding | nudix hydrolase 18 [Source:HGNC Symbol;Acc:HGNC:26194] | Duplication |
| 247 | ENSG00000168453 | HR | 8 | 22114419 | 22133384 | -1 | protein_coding | HR lysine demethylase and nuclear receptor corepressor [Source:HGNC Symbol;Acc:HGNC:5172] | Duplication |
| 248 | ENSG00000288677 | HRURF | 8 | 22130458 | 22131010 | -1 | protein_coding | HR upstream open reading frame [Source:HGNC Symbol;Acc:HGNC:55085] | Duplication |
| 249 | ENSG00000168476 | REEP4 | 8 | 22138020 | 22141951 | -1 | protein_coding | receptor accessory protein 4 [Source:HGNC Symbol;Acc:HGNC:26176] | Duplication |
| 251 | ENSG00000168481 | LGI3 | 8 | 22146830 | 22157084 | -1 | protein_coding | leucine rich repeat LGI family member 3 [Source:HGNC Symbol;Acc:HGNC:18711] | Duplication |
| 252 | ENSG00000168484 | SFTPC | 8 | 22156913 | 22164479 | 1 | protein_coding | surfactant protein C [Source:HGNC Symbol;Acc:HGNC:10802] | Duplication |
| 253 | ENSG00000168487 | BMP1 | 8 | 22165140 | 22212326 | 1 | protein_coding | bone morphogenetic protein 1 [Source:HGNC Symbol;Acc:HGNC:1067] | Duplication |
| 256 | ENSG00000168490 | PHYHIP | 8 | 22219703 | 22232101 | -1 | protein_coding | phytanoyl-CoA 2-hydroxylase interacting protein [Source:HGNC Symbol;Acc:HGNC:16865] | Duplication |
| 259 | ENSG00000168495 | POLR3D | 8 | 22245133 | 22254601 | 1 | protein_coding | RNA polymerase III subunit D [Source:HGNC Symbol;Acc:HGNC:1080] | Duplication |
| 261 | ENSG00000197181 | PIWIL2 | 8 | 22275316 | 22357568 | 1 | protein_coding | piwi like RNA-mediated gene silencing 2 [Source:HGNC Symbol;Acc:HGNC:17644] | Duplication |
| 263 | ENSG00000104635 | SLC39A14 | 8 | 22367278 | 22434129 | 1 | protein_coding | solute carrier family 39 member 14 [Source:HGNC Symbol;Acc:HGNC:20858] | Duplication |
| 266 | ENSG00000120910 | PPP3CC | 8 | 22440819 | 22541142 | 1 | protein_coding | protein phosphatase 3 catalytic subunit gamma [Source:HGNC Symbol;Acc:HGNC:9316] | Duplication |
| 269 | ENSG00000120896 | SORBS3 | 8 | 22544986 | 22575788 | 1 | protein_coding | sorbin and SH3 domain containing 3 [Source:HGNC Symbol;Acc:HGNC:30907] | Duplication |
| 273 | ENSG00000120913 | PDLIM2 | 8 | 22578279 | 22598025 | 1 | protein_coding | PDZ and LIM domain 2 [Source:HGNC Symbol;Acc:HGNC:13992] | Duplication |
| 274 | ENSG00000248235 | 8 | 22589274 | 22602084 | 1 | protein_coding | novel protein | Duplication | |
| 275 | ENSG00000241852 | C8orf58 | 8 | 22599599 | 22604150 | 1 | protein_coding | chromosome 8 open reading frame 58 [Source:HGNC Symbol;Acc:HGNC:32233] | Duplication |
| 277 | ENSG00000158941 | CCAR2 | 8 | 22604757 | 22620964 | 1 | protein_coding | cell cycle and apoptosis regulator 2 [Source:HGNC Symbol;Acc:HGNC:23360] | Duplication |
| 279 | ENSG00000147439 | BIN3 | 8 | 22620418 | 22669148 | -1 | protein_coding | bridging integrator 3 [Source:HGNC Symbol;Acc:HGNC:1054] | Duplication |
| 283 | ENSG00000179388 | EGR3 | 8 | 22687659 | 22693480 | -1 | protein_coding | early growth response 3 [Source:HGNC Symbol;Acc:HGNC:3240] | Duplication |
| 288 | ENSG00000134020 | PEBP4 | 8 | 22713251 | 23000000 | -1 | protein_coding | phosphatidylethanolamine binding protein 4 [Source:HGNC Symbol;Acc:HGNC:28319] | Duplication |
| 297 | ENSG00000008853 | RHOBTB2 | 8 | 22987417 | 23020509 | 1 | protein_coding | Rho related BTB domain containing 2 [Source:HGNC Symbol;Acc:HGNC:18756] | Duplication |
| 298 | ENSG00000120889 | TNFRSF10B | 8 | 23020133 | 23069031 | -1 | protein_coding | TNF receptor superfamily member 10b [Source:HGNC Symbol;Acc:HGNC:11905] | Duplication |
| 302 | ENSG00000284956 | 8 | 23084403 | 23115536 | 1 | protein_coding | novel protein | Duplication | |
| 303 | ENSG00000173535 | TNFRSF10C | 8 | 23102921 | 23117445 | 1 | protein_coding | TNF receptor superfamily member 10c [Source:HGNC Symbol;Acc:HGNC:11906] | Duplication |
| 304 | ENSG00000173530 | TNFRSF10D | 8 | 23135588 | 23164027 | -1 | protein_coding | TNF receptor superfamily member 10d [Source:HGNC Symbol;Acc:HGNC:11907] | Duplication |
| 307 | ENSG00000104689 | TNFRSF10A | 8 | 23190452 | 23225102 | -1 | protein_coding | TNF receptor superfamily member 10a [Source:HGNC Symbol;Acc:HGNC:11904] | Duplication |
| 312 | ENSG00000147457 | CHMP7 | 8 | 23243637 | 23262000 | 1 | protein_coding | charged multivesicular body protein 7 [Source:HGNC Symbol;Acc:HGNC:28439] | Duplication |
| 314 | ENSG00000104679 | R3HCC1 | 8 | 23270120 | 23296279 | 1 | protein_coding | R3H domain and coiled-coil containing 1 [Source:HGNC Symbol;Acc:HGNC:27329] | Duplication |
| 316 | ENSG00000134013 | LOXL2 | 8 | 23296897 | 23425328 | -1 | protein_coding | lysyl oxidase like 2 [Source:HGNC Symbol;Acc:HGNC:6666] | Duplication |
| 318 | ENSG00000197217 | ENTPD4 | 8 | 23385783 | 23457695 | -1 | protein_coding | ectonucleoside triphosphate diphosphohydrolase 4 [Source:HGNC Symbol;Acc:HGNC:14573] | Duplication |
| 326 | ENSG00000147454 | SLC25A37 | 8 | 23528956 | 23575463 | 1 | protein_coding | solute carrier family 25 member 37 [Source:HGNC Symbol;Acc:HGNC:29786] | Duplication |
| 330 | ENSG00000167034 | NKX3-1 | 8 | 23678697 | 23682938 | -1 | protein_coding | NK3 homeobox 1 [Source:HGNC Symbol;Acc:HGNC:7838] | Duplication |
| 331 | ENSG00000180053 | NKX2-6 | 8 | 23701740 | 23706756 | -1 | protein_coding | NK2 homeobox 6 [Source:HGNC Symbol;Acc:HGNC:32940] | Duplication |
| 338 | ENSG00000159167 | STC1 | 8 | 23841929 | 23854806 | -1 | protein_coding | stanniocalcin 1 [Source:HGNC Symbol;Acc:HGNC:11373] | Duplication |
| 343 | ENSG00000042980 | ADAM28 | 8 | 24294069 | 24359014 | 1 | protein_coding | ADAM metallopeptidase domain 28 [Source:HGNC Symbol;Acc:HGNC:206] | Duplication |
| 344 | ENSG00000134028 | ADAMDEC1 | 8 | 24384285 | 24406013 | 1 | protein_coding | ADAM like decysin 1 [Source:HGNC Symbol;Acc:HGNC:16299] | Duplication |
| 345 | ENSG00000069206 | ADAM7 | 8 | 24440930 | 24526970 | 1 | protein_coding | ADAM metallopeptidase domain 7 [Source:HGNC Symbol;Acc:HGNC:214] | Duplication |
| 349 | ENSG00000104722 | NEFM | 8 | 24913758 | 24919098 | 1 | protein_coding | neurofilament medium chain [Source:HGNC Symbol;Acc:HGNC:7734] | Duplication |
| 351 | ENSG00000277586 | NEFL | 8 | 24950955 | 24956721 | -1 | protein_coding | neurofilament light chain [Source:HGNC Symbol;Acc:HGNC:7739] | Duplication |
| 362 | ENSG00000147459 | DOCK5 | 8 | 25184689 | 25418082 | 1 | protein_coding | dedicator of cytokinesis 5 [Source:HGNC Symbol;Acc:HGNC:23476] | Duplication |
| 366 | ENSG00000147437 | GNRH1 | 8 | 25419258 | 25424654 | -1 | protein_coding | gonadotropin releasing hormone 1 [Source:HGNC Symbol;Acc:HGNC:4419] | Duplication |
| 368 | ENSG00000104756 | KCTD9 | 8 | 25427847 | 25458476 | -1 | protein_coding | potassium channel tetramerization domain containing 9 [Source:HGNC Symbol;Acc:HGNC:22401] | Duplication |
| 369 | ENSG00000184661 | CDCA2 | 8 | 25459199 | 25507911 | 1 | protein_coding | cell division cycle associated 2 [Source:HGNC Symbol;Acc:HGNC:14623] | Duplication |
| 377 | ENSG00000221818 | EBF2 | 8 | 25841725 | 26045413 | -1 | protein_coding | EBF transcription factor 2 [Source:HGNC Symbol;Acc:HGNC:19090] | Duplication |
| 386 | ENSG00000221914 | PPP2R2A | 8 | 26291508 | 26372680 | 1 | protein_coding | protein phosphatase 2 regulatory subunit Balpha [Source:HGNC Symbol;Acc:HGNC:9304] | Duplication |
| 389 | ENSG00000104765 | BNIP3L | 8 | 26383054 | 26505636 | 1 | protein_coding | BCL2 interacting protein 3 like [Source:HGNC Symbol;Acc:HGNC:1085] | Duplication |
| 394 | ENSG00000240694 | PNMA2 | 8 | 26504701 | 26514092 | -1 | protein_coding | PNMA family member 2 [Source:HGNC Symbol;Acc:HGNC:9159] | Duplication |
| 395 | ENSG00000092964 | DPYSL2 | 8 | 26514031 | 26658178 | 1 | protein_coding | dihydropyrimidinase like 2 [Source:HGNC Symbol;Acc:HGNC:3014] | Duplication |
| 399 | ENSG00000120907 | ADRA1A | 8 | 26748150 | 26867278 | -1 | protein_coding | adrenoceptor alpha 1A [Source:HGNC Symbol;Acc:HGNC:277] | Duplication |
| 411 | ENSG00000015592 | STMN4 | 8 | 27235308 | 27258420 | -1 | protein_coding | stathmin 4 [Source:HGNC Symbol;Acc:HGNC:16078] | Duplication |
| 412 | ENSG00000104228 | TRIM35 | 8 | 27284886 | 27311272 | -1 | protein_coding | tripartite motif containing 35 [Source:HGNC Symbol;Acc:HGNC:16285] | Duplication |
| 413 | ENSG00000120899 | PTK2B | 8 | 27311482 | 27459391 | 1 | protein_coding | protein tyrosine kinase 2 beta [Source:HGNC Symbol;Acc:HGNC:9612] | Duplication |
| 415 | ENSG00000120903 | CHRNA2 | 8 | 27459756 | 27479883 | -1 | protein_coding | cholinergic receptor nicotinic alpha 2 subunit [Source:HGNC Symbol;Acc:HGNC:1956] | Duplication |
| 416 | ENSG00000120915 | EPHX2 | 8 | 27490781 | 27548615 | 1 | protein_coding | epoxide hydrolase 2 [Source:HGNC Symbol;Acc:HGNC:3402] | Duplication |
| 420 | ENSG00000120885 | CLU | 8 | 27596917 | 27614700 | -1 | protein_coding | clusterin [Source:HGNC Symbol;Acc:HGNC:2095] | Duplication |
| 422 | ENSG00000168077 | SCARA3 | 8 | 27633868 | 27676776 | 1 | protein_coding | scavenger receptor class A member 3 [Source:HGNC Symbol;Acc:HGNC:19000] | Duplication |
| 430 | ENSG00000147419 | CCDC25 | 8 | 27733316 | 27772653 | -1 | protein_coding | coiled-coil domain containing 25 [Source:HGNC Symbol;Acc:HGNC:25591] | Duplication |
| 431 | ENSG00000171320 | ESCO2 | 8 | 27771949 | 27812640 | 1 | protein_coding | establishment of sister chromatid cohesion N-acetyltransferase 2 [Source:HGNC Symbol;Acc:HGNC:27230] | Duplication |
| 433 | ENSG00000168078 | PBK | 8 | 27809624 | 27838082 | -1 | protein_coding | PDZ binding kinase [Source:HGNC Symbol;Acc:HGNC:18282] | Duplication |
| 436 | ENSG00000168079 | SCARA5 | 8 | 27869883 | 27992673 | -1 | protein_coding | scavenger receptor class A member 5 [Source:HGNC Symbol;Acc:HGNC:28701] | Duplication |
| 441 | ENSG00000189233 | NUGGC | 8 | 28021964 | 28083936 | -1 | protein_coding | nuclear GTPase, germinal center associated [Source:HGNC Symbol;Acc:HGNC:33550] | Duplication |
| 442 | ENSG00000134014 | ELP3 | 8 | 28089673 | 28191156 | 1 | protein_coding | elongator acetyltransferase complex subunit 3 [Source:HGNC Symbol;Acc:HGNC:20696] | Duplication |
| 449 | ENSG00000168081 | PNOC | 8 | 28316986 | 28343355 | 1 | protein_coding | prepronociceptin [Source:HGNC Symbol;Acc:HGNC:9163] | Duplication |
| 450 | ENSG00000186918 | ZNF395 | 8 | 28345590 | 28402701 | -1 | protein_coding | zinc finger protein 395 [Source:HGNC Symbol;Acc:HGNC:18737] | Duplication |
| 451 | ENSG00000214050 | FBXO16 | 8 | 28348287 | 28490278 | -1 | protein_coding | F-box protein 16 [Source:HGNC Symbol;Acc:HGNC:13618] | Duplication |
| 457 | ENSG00000104290 | FZD3 | 8 | 28494205 | 28574267 | 1 | protein_coding | frizzled class receptor 3 [Source:HGNC Symbol;Acc:HGNC:4041] | Duplication |
| 461 | ENSG00000012232 | EXTL3 | 8 | 28600469 | 28756561 | 1 | protein_coding | exostosin like glycosyltransferase 3 [Source:HGNC Symbol;Acc:HGNC:3518] | Duplication |
| 465 | ENSG00000104299 | INTS9 | 8 | 28767661 | 28890242 | -1 | protein_coding | integrator complex subunit 9 [Source:HGNC Symbol;Acc:HGNC:25592] | Duplication |
| 468 | ENSG00000147421 | HMBOX1 | 8 | 28890395 | 29064764 | 1 | protein_coding | homeobox containing 1 [Source:HGNC Symbol;Acc:HGNC:26137] | Duplication |
| 475 | ENSG00000197892 | KIF13B | 8 | 29067278 | 29263124 | -1 | protein_coding | kinesin family member 13B [Source:HGNC Symbol;Acc:HGNC:14405] | Duplication |
| 481 | ENSG00000120875 | DUSP4 | 8 | 29333064 | 29350684 | -1 | protein_coding | dual specificity phosphatase 4 [Source:HGNC Symbol;Acc:HGNC:3070] | Duplication |
| 512 | ENSG00000133872 | SARAF | 8 | 30063003 | 30083208 | -1 | protein_coding | store-operated calcium entry associated regulatory factor [Source:HGNC Symbol;Acc:HGNC:28789] | Duplication |
| 515 | ENSG00000104660 | LEPROTL1 | 8 | 30095408 | 30177208 | 1 | protein_coding | leptin receptor overlapping transcript like 1 [Source:HGNC Symbol;Acc:HGNC:6555] | Duplication |
| 517 | ENSG00000177669 | MBOAT4 | 8 | 30131671 | 30144665 | -1 | protein_coding | membrane bound O-acyltransferase domain containing 4 [Source:HGNC Symbol;Acc:HGNC:32311] | Duplication |
| 519 | ENSG00000104671 | DCTN6 | 8 | 30156319 | 30183639 | 1 | protein_coding | dynactin subunit 6 [Source:HGNC Symbol;Acc:HGNC:16964] | Duplication |
| 535 | ENSG00000157110 | RBPMS | 8 | 30384511 | 30572256 | 1 | protein_coding | RNA binding protein, mRNA processing factor [Source:HGNC Symbol;Acc:HGNC:19097] | Duplication |
| 539 | ENSG00000197265 | GTF2E2 | 8 | 30578318 | 30658236 | -1 | protein_coding | general transcription factor IIE subunit 2 [Source:HGNC Symbol;Acc:HGNC:4651] | Duplication |
| 541 | ENSG00000253457 | SMIM18 | 8 | 30638580 | 30646064 | 1 | protein_coding | small integral membrane protein 18 [Source:HGNC Symbol;Acc:HGNC:42973] | Duplication |
| 543 | ENSG00000104687 | GSR | 8 | 30678066 | 30727846 | -1 | protein_coding | glutathione-disulfide reductase [Source:HGNC Symbol;Acc:HGNC:4623] | Duplication |
| 544 | ENSG00000104691 | UBXN8 | 8 | 30729131 | 30767006 | 1 | protein_coding | UBX domain protein 8 [Source:HGNC Symbol;Acc:HGNC:30307] | Duplication |
| 546 | ENSG00000104695 | PPP2CB | 8 | 30774457 | 30814314 | -1 | protein_coding | protein phosphatase 2 catalytic subunit beta [Source:HGNC Symbol;Acc:HGNC:9300] | Duplication |
| 547 | ENSG00000133863 | TEX15 | 8 | 30831544 | 30913008 | -1 | protein_coding | testis expressed 15, meiosis and synapsis associated [Source:HGNC Symbol;Acc:HGNC:11738] | Duplication |
| 551 | ENSG00000172733 | PURG | 8 | 30995802 | 31033715 | -1 | protein_coding | purine rich element binding protein G [Source:HGNC Symbol;Acc:HGNC:17930] | Duplication |
| 552 | ENSG00000165392 | WRN | 8 | 31033788 | 31176138 | 1 | protein_coding | WRN RecQ like helicase [Source:HGNC Symbol;Acc:HGNC:12791] | Duplication |
| 563 | ENSG00000157168 | NRG1 | 8 | 31639222 | 32855666 | 1 | protein_coding | neuregulin 1 [Source:HGNC Symbol;Acc:HGNC:7997] | Duplication |
| 571 | ENSG00000286131 | 8 | 32647202 | 32647390 | 1 | protein_coding | novel protein | Duplication | |
| 582 | ENSG00000172728 | FUT10 | 8 | 33370824 | 33473146 | -1 | protein_coding | fucosyltransferase 10 [Source:HGNC Symbol;Acc:HGNC:19234] | Duplication |
| 585 | ENSG00000129696 | TTI2 | 8 | 33473386 | 33513185 | -1 | protein_coding | TELO2 interacting protein 2 [Source:HGNC Symbol;Acc:HGNC:26262] | Duplication |
| 586 | ENSG00000198042 | MAK16 | 8 | 33485182 | 33501262 | 1 | protein_coding | MAK16 homolog [Source:HGNC Symbol;Acc:HGNC:13703] | Duplication |
| 592 | ENSG00000133874 | RNF122 | 8 | 33547754 | 33567128 | -1 | protein_coding | ring finger protein 122 [Source:HGNC Symbol;Acc:HGNC:21147] | Duplication |
| 594 | ENSG00000133878 | DUSP26 | 8 | 33591330 | 33600023 | -1 | protein_coding | dual specificity phosphatase 26 [Source:HGNC Symbol;Acc:HGNC:28161] | Duplication |
| 615 | ENSG00000156687 | UNC5D | 8 | 35235475 | 35796550 | 1 | protein_coding | unc-5 netrin receptor D [Source:HGNC Symbol;Acc:HGNC:18634] | Duplication |
| 633 | ENSG00000215262 | KCNU1 | 8 | 36784324 | 36936125 | 1 | protein_coding | potassium calcium-activated channel subfamily U member 1 [Source:HGNC Symbol;Acc:HGNC:18867] | Duplication |
| 659 | ENSG00000183779 | ZNF703 | 8 | 37695782 | 37700019 | 1 | protein_coding | zinc finger protein 703 [Source:HGNC Symbol;Acc:HGNC:25883] | Duplication |
| 663 | ENSG00000147475 | ERLIN2 | 8 | 37736601 | 37758422 | 1 | protein_coding | ER lipid raft associated 2 [Source:HGNC Symbol;Acc:HGNC:1356] | Duplication |
| 666 | ENSG00000147471 | PLPBP | 8 | 37762595 | 37779768 | 1 | protein_coding | pyridoxal phosphate binding protein [Source:HGNC Symbol;Acc:HGNC:9457] | Duplication |
| 668 | ENSG00000020181 | ADGRA2 | 8 | 37784191 | 37844896 | 1 | protein_coding | adhesion G protein-coupled receptor A2 [Source:HGNC Symbol;Acc:HGNC:17849] | Duplication |
| 670 | ENSG00000104221 | BRF2 | 8 | 37843268 | 37849861 | -1 | protein_coding | BRF2 RNA polymerase III transcription initiation factor subunit [Source:HGNC Symbol;Acc:HGNC:17298] | Duplication |
| 671 | ENSG00000156675 | RAB11FIP1 | 8 | 37858618 | 37899497 | -1 | protein_coding | RAB11 family interacting protein 1 [Source:HGNC Symbol;Acc:HGNC:30265] | Duplication |
| 674 | ENSG00000169154 | GOT1L1 | 8 | 37934281 | 37940124 | -1 | protein_coding | glutamic-oxaloacetic transaminase 1 like 1 [Source:HGNC Symbol;Acc:HGNC:28487] | Duplication |
| 675 | ENSG00000285880 | 8 | 37934340 | 37965953 | -1 | protein_coding | ADRB3-GOT1L1 readthrough | Duplication | |
| 677 | ENSG00000188778 | ADRB3 | 8 | 37962990 | 37966599 | -1 | protein_coding | adrenoceptor beta 3 [Source:HGNC Symbol;Acc:HGNC:288] | Duplication |
| 679 | ENSG00000187840 | EIF4EBP1 | 8 | 38030534 | 38060365 | 1 | protein_coding | eukaryotic translation initiation factor 4E binding protein 1 [Source:HGNC Symbol;Acc:HGNC:3288] | Duplication |
| 684 | ENSG00000129691 | ASH2L | 8 | 38105493 | 38144076 | 1 | protein_coding | ASH2 like, histone lysine methyltransferase complex subunit [Source:HGNC Symbol;Acc:HGNC:744] | Duplication |
| 687 | ENSG00000147465 | STAR | 8 | 38142700 | 38150992 | -1 | protein_coding | steroidogenic acute regulatory protein [Source:HGNC Symbol;Acc:HGNC:11359] | Duplication |
| 689 | ENSG00000175324 | LSM1 | 8 | 38163335 | 38176730 | -1 | protein_coding | LSM1 homolog, mRNA degradation associated [Source:HGNC Symbol;Acc:HGNC:20472] | Duplication |
| 691 | ENSG00000156735 | BAG4 | 8 | 38176533 | 38213301 | 1 | protein_coding | BAG cochaperone 4 [Source:HGNC Symbol;Acc:HGNC:940] | Duplication |
| 694 | ENSG00000085788 | DDHD2 | 8 | 38225218 | 38275558 | 1 | protein_coding | DDHD domain containing 2 [Source:HGNC Symbol;Acc:HGNC:29106] | Duplication |
| 695 | ENSG00000147535 | PLPP5 | 8 | 38263130 | 38269243 | -1 | protein_coding | phospholipid phosphatase 5 [Source:HGNC Symbol;Acc:HGNC:25026] | Duplication |
| 696 | ENSG00000147548 | NSD3 | 8 | 38269704 | 38382272 | -1 | protein_coding | nuclear receptor binding SET domain protein 3 [Source:HGNC Symbol;Acc:HGNC:12767] | Duplication |
| 701 | ENSG00000165046 | LETM2 | 8 | 38386207 | 38409527 | 1 | protein_coding | leucine zipper and EF-hand containing transmembrane protein 2 [Source:HGNC Symbol;Acc:HGNC:14648] | Duplication |
| 702 | ENSG00000077782 | FGFR1 | 8 | 38400215 | 38468834 | -1 | protein_coding | fibroblast growth factor receptor 1 [Source:HGNC Symbol;Acc:HGNC:3688] | Duplication |
| 718 | ENSG00000147526 | TACC1 | 8 | 38728186 | 38853028 | 1 | protein_coding | transforming acidic coiled-coil containing protein 1 [Source:HGNC Symbol;Acc:HGNC:11522] | Duplication |
| 723 | ENSG00000169499 | PLEKHA2 | 8 | 38901235 | 38973912 | 1 | protein_coding | pleckstrin homology domain containing A2 [Source:HGNC Symbol;Acc:HGNC:14336] | Duplication |
| 725 | ENSG00000169495 | HTRA4 | 8 | 38974228 | 38988663 | 1 | protein_coding | HtrA serine peptidase 4 [Source:HGNC Symbol;Acc:HGNC:26909] | Duplication |
| 726 | ENSG00000169490 | TM2D2 | 8 | 38988808 | 38996824 | -1 | protein_coding | TM2 domain containing 2 [Source:HGNC Symbol;Acc:HGNC:24127] | Duplication |
| 727 | ENSG00000168615 | ADAM9 | 8 | 38996754 | 39105445 | 1 | protein_coding | ADAM metallopeptidase domain 9 [Source:HGNC Symbol;Acc:HGNC:216] | Duplication |
| 729 | ENSG00000197140 | ADAM32 | 8 | 39106990 | 39284917 | 1 | protein_coding | ADAM metallopeptidase domain 32 [Source:HGNC Symbol;Acc:HGNC:15479] | Duplication |
| 739 | ENSG00000168619 | ADAM18 | 8 | 39584489 | 39730065 | 1 | protein_coding | ADAM metallopeptidase domain 18 [Source:HGNC Symbol;Acc:HGNC:196] | Duplication |
| 740 | ENSG00000104755 | ADAM2 | 8 | 39743735 | 39838227 | -1 | protein_coding | ADAM metallopeptidase domain 2 [Source:HGNC Symbol;Acc:HGNC:198] | Duplication |
| 743 | ENSG00000131203 | IDO1 | 8 | 39902275 | 39928790 | 1 | protein_coding | indoleamine 2,3-dioxygenase 1 [Source:HGNC Symbol;Acc:HGNC:6059] | Duplication |
| 747 | ENSG00000188676 | IDO2 | 8 | 39934614 | 40016392 | 1 | protein_coding | indoleamine 2,3-dioxygenase 2 [Source:HGNC Symbol;Acc:HGNC:27269] | Duplication |
| 753 | ENSG00000176907 | TCIM | 8 | 40153482 | 40155310 | 1 | protein_coding | transcriptional and immune response regulator [Source:HGNC Symbol;Acc:HGNC:1357] | Duplication |
overlapping_genes <- intersect(protein_coding_genes_del$ensembl_gene_id, protein_coding_genes_dup$ensembl_gene_id)
if (length(overlapping_genes) > 0) {
cat("Genes present in both regions:\n")
print(overlapping_genes)
} else {
cat("No genes are present in both the deletion and duplication regions.\n")
}## No genes are present in both the deletion and duplication regions.8p analysis
counts <- read.csv("data/gene_count.csv")
samples <- read_xlsx("data/Sample List.xlsx")
raw.counts <- counts %>% dplyr::select(gene_id, samples$`Sample Name`)
annotation <- counts %>% dplyr::select(-all_of(samples$`Sample Name`))samples.parents <- samples %>%
mutate(`Group Name` = ifelse(`Group Name` %in% c("MOM", "DAD"), "Parents", `Group Name`))
print(samples.parents)## # A tibble: 12 × 7
## `Sample Name` `Cell line` Concentration (ng/uL…¹ `Volume (uL)` `A260/A280`
## <chr> <chr> <dbl> <dbl> <dbl>
## 1 SL_1 31.3 (Sample … 1194. 30 2.09
## 2 SL_2 31.3 (Sample … 1068. 30 2.08
## 3 SL_3 31.3 (Sample … 1097. 30 2.08
## 4 SL_4 JE01 214 (Sam… 523. 30 2.00
## 5 SL_5 JE01 214 (Sam… 762. 30 2.04
## 6 SL_6 JE01 214 (Sam… 410. 30 1.96
## 7 SL_7 255-1 (p13) 244. 30 2.08
## 8 SL_8 255-4 (p13) 606. 30 2.09
## 9 SL_9 255-3 (p13) 495. 30 2.06
## 10 SL_10 294-1 1128. 30 2.07
## 11 SL_11 294-2 750. 30 2.07
## 12 SL_12 294-3 382. 30 2.09
## # ℹ abbreviated name: ¹`Concentration (ng/uL)`
## # ℹ 2 more variables: `A260/A230` <dbl>, `Group Name` <chr>y.parents <- DGEList(counts = raw.counts, samples = samples.parents, group = samples.parents$`Group Name`)
y.parents$genes <- annotation
keep <- filterByExpr(y.parents, min.count = 30, min.total.count = 50, large.n = 10, min.prop = 0.75) # filter lowly expressed transcripts #, min.count = 30, min.total.count = 50, large.n = 10, min.prop = 0.75
table(keep)## keep
## FALSE TRUE
## 43987 14748y.parents <- y.parents[keep, , keep.lib.sizes=FALSE]
y.parents <- normLibSizes(y.parents) # TMM normalization
# calculate CPM
log2_cpm <- cpm(y.parents, log = TRUE, prior.count = 1, normalized.lib.sizes = T)
log2_tmm_data_with_annotations <- cbind(y.parents$genes, log2_cpm)
# DE analysis
plotMDS(y.parents) 
samples.design.parents <- model.matrix(~ 0 + group,data = y.parents$samples) # design
colnames(samples.design.parents) <- gsub("group", "", colnames(samples.design.parents))
y.parents <- estimateDisp(y.parents, samples.design.parents, robust=TRUE)
print(y.parents$common.dispersion)## [1] 0.03257095plotBCV(y.parents)
fit.parents <- glmQLFit(y.parents, samples.design.parents, robust=TRUE)
plotQLDisp(fit.parents)
# make contrast
rev.contrast <- makeContrasts(PROvsREV=PRO-REV, levels=samples.design.parents)
qlf.PROvsREV <- glmQLFTest(fit.parents, contrast=rev.contrast[,"PROvsREV"])
contr.rev <- get_results("PRO - REV", qlf.PROvsREV)
parents_results_list <- list(contr.rev)
plot_all_results(parents_results_list)
table.results <- plot_thresholded_results(parents_results_list)
Supplementary Figure S3BC
centromeres <- read_tsv("data/centromeres-UCSC.bed", comment = "#")
centromeres_summary <- centromeres %>%
group_by(chrom) %>%
summarize(
start = min(chromStart),
end = max(chromEnd)
)
sample_to_group <- samples %>%
dplyr::select(`Sample Name`,`Group Name`) %>%
dplyr::filter(`Group Name` == "REV" |`Group Name` == "PRO")
gene_logfc <- contr.rev$top_tags$table %>%
dplyr::select(gene_id, logFC, gene_chr) # Select relevant columns (adjust the names if needed)
summary_list <- list()
for (i in 1:22) {
chrom_gene_logfc <- gene_logfc %>%
filter(gene_chr == as.character(i))
avg_logfc <- mean(chrom_gene_logfc$logFC, na.rm = TRUE)
median_logfc <- median(chrom_gene_logfc$logFC, na.rm = TRUE)
summary_df <- tibble(
CHR = i,
mean_logFC = avg_logfc,
median_logFC = median_logfc
)
summary_list[[i]] <- summary_df
}
final_summary <- bind_rows(summary_list)
final_summary %>% gt()| CHR | mean_logFC | median_logFC |
|---|---|---|
| 1 | 0.03530399 | 0.002479699 |
| 2 | 0.07225343 | 0.001113815 |
| 3 | 0.04830308 | 0.014212023 |
| 4 | 0.07049886 | 0.027990760 |
| 5 | 0.07644282 | 0.011892850 |
| 6 | 0.01334637 | -0.009420676 |
| 7 | 0.04393906 | 0.002151135 |
| 8 | 0.19836010 | 0.121154181 |
| 9 | 0.03652699 | -0.010908634 |
| 10 | 0.07900521 | -0.009744297 |
| 11 | 0.02607693 | -0.019861725 |
| 12 | 0.09566353 | 0.033873698 |
| 13 | 0.12699998 | 0.020871230 |
| 14 | 0.05985903 | 0.020982288 |
| 15 | 0.07295819 | 0.038859233 |
| 16 | 0.02208292 | -0.034985374 |
| 17 | 0.02113778 | -0.019461390 |
| 18 | 0.13336673 | 0.018704282 |
| 19 | 0.09589128 | 0.035091883 |
| 20 | 0.06615149 | 0.002520803 |
| 21 | 0.05502288 | 0.008762923 |
| 22 | 0.04180247 | -0.027330879 |
library(grid)# chr 7
chr <- paste0("chr", 7)
centromere_start <- centromeres_summary %>%
filter(chrom == chr) %>%
pull(start)
centromere_end <- centromeres_summary %>%
filter(chrom == chr) %>%
pull(end)
gene.deldup.tmm <- log2_tmm_data_with_annotations %>%
filter(gene_chr == as.character(7)) %>%
filter(!(gene_start >= centromere_start & gene_start < centromere_end)) %>%
dplyr::select(gene_id, gene_start, gene_end, samples$`Sample Name`) %>%
pivot_longer(cols = -c(gene_id, gene_start, gene_end), names_to = "Sample", values_to = "Expression") %>%
left_join(sample_to_group, by = c("Sample" = "Sample Name")) %>% # Map samples to their groups
group_by(gene_id, gene_start, gene_end, `Group Name`) %>%
summarise(Average_Expression = mean(Expression, na.rm = TRUE), .groups = "drop") %>%
arrange(gene_start, desc(Average_Expression))
gene.deldup.tmm.plot.relative.PRO <- gene.deldup.tmm %>%
mutate(region = case_when(
gene_start >= 0 & gene_start < centromere_start ~ "p",
gene_start >= centromere_end ~ "q"
)) %>%
filter(`Group Name` %in% c('PRO', 'REV')) %>% # Filter for PRO and REV
tidyr::pivot_wider(names_from = `Group Name`, values_from = Average_Expression) %>%
# Calculate relative expression as PRO average minus REV average
mutate(relative_expression = PRO - REV) %>%
group_by(region) %>%
mutate(rolling_avg = custom_rollmean(relative_expression, k = 14)) %>%
ungroup()
text_cen <- textGrob("Centromere", gp=gpar(fontsize=18, fontface="bold"))
plot_object <- ggplot(gene.deldup.tmm.plot.relative.PRO, aes(x = (gene_start+gene_end)/2, y = rolling_avg)) +
theme(plot.margin = unit(c(1,1,2,1), "lines")) +
geom_rect(aes(xmin = centromere_start, xmax = centromere_end, ymin = -Inf, ymax = Inf),
fill = "grey", color = "grey", alpha = 0.6) +
annotation_custom(text_cen,xmin=(centromere_start + centromere_end) / 2,xmax=(centromere_start + centromere_end) / 2,ymin=-1.35,ymax=-1.35) +
geom_hline(yintercept = 0, linetype = "dashed", color = "black", size = 0.5, alpha = 0.8 ) +
geom_point(size = 1.5, alpha = 0.9, color = "#727572") +
labs(
title = paste("Gene Expression on Chromosome 7 - Proband relative to Revertant"),
x = "Chromosome Position (bp)",
y = "Relative Expression Level (log2)",
color =NULL
) +
scale_y_continuous(limits = c(-1, 1.5), breaks = seq(-1.5, 1.5, by = 0.5)) +
scale_x_continuous(expand = c(0, 0),
limits = c(0, max(gene.deldup.tmm.plot.relative.PRO$gene_end) + 2e6),
breaks = seq(from = 0, to = max(gene.deldup.tmm.plot.relative.PRO$gene_end), by = 20000000),
labels = c("0", "20,000,000", "40,000,000", "60,000,000", "80,000,000", "100,000,000", "120,000,000", "140,000,000")) +
expand_limits(x = 0, y = -1.5) +
theme_classic() +
coord_cartesian(clip = "off") +
theme(
text = element_text(family = "Arial", face = "bold"),
plot.title = element_text(size = 28, face = "bold", hjust = 0.5, family = "Arial"),
axis.title = element_text(size = 20, family = "Arial"),
axis.text = element_text(size = 18, family = "Arial"),
axis.title.x = element_text(margin = margin(t = 20)),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()
)## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.print(plot_object)
# ggsave(
# filename = paste("CHR7_gene_expression_plot_log2_PROvsREV.png"),
# plot = plot_object,
# width = 18, # Adjust the width to make the canvas longer
# height = 6, # Adjust the height to control the aspect ratio
# dpi = 300, # Set the resolution to 300 dpi
# bg = "transparent"
# )
# chr 9
chr <- paste0("chr", 9)
centromere_start <- centromeres_summary %>%
filter(chrom == chr) %>%
pull(start)
centromere_end <- centromeres_summary %>%
filter(chrom == chr) %>%
pull(end)
gene.deldup.tmm <- log2_tmm_data_with_annotations %>%
filter(gene_chr == as.character(9)) %>%
filter(!(gene_start >= centromere_start & gene_start < centromere_end)) %>%
dplyr::select(gene_id, gene_start, gene_end, samples$`Sample Name`) %>%
pivot_longer(cols = -c(gene_id, gene_start, gene_end), names_to = "Sample", values_to = "Expression") %>%
left_join(sample_to_group, by = c("Sample" = "Sample Name")) %>% # Map samples to their groups
group_by(gene_id, gene_start, gene_end, `Group Name`) %>%
summarise(Average_Expression = mean(Expression, na.rm = TRUE), .groups = "drop") %>%
arrange(gene_start, desc(Average_Expression))
gene.deldup.tmm.plot.relative.PRO <- gene.deldup.tmm %>%
mutate(region = case_when(
gene_start >= 0 & gene_start < centromere_start ~ "p",
gene_start >= centromere_end ~ "q"
)) %>%
filter(`Group Name` %in% c('PRO', 'REV'), region != "c") %>% # Filter for PRO and REV
tidyr::pivot_wider(names_from = `Group Name`, values_from = Average_Expression) %>%
# Calculate relative expression as PRO average minus REV average
mutate(relative_expression = PRO - REV) %>%
group_by(region) %>%
mutate(rolling_avg = custom_rollmean(relative_expression, k = 14)) %>%
ungroup()
text_cen <- textGrob("Centromere", gp=gpar(fontsize=18, fontface="bold"))
plot_object <- ggplot(gene.deldup.tmm.plot.relative.PRO, aes(x = (gene_start+gene_end)/2, y = rolling_avg)) +
theme(plot.margin = unit(c(1,1,2,1), "lines")) +
geom_rect(aes(xmin = centromere_start, xmax = centromere_end, ymin = -Inf, ymax = Inf),
fill = "grey", color = "grey", alpha = 0.6) +
annotation_custom(text_cen,xmin=(centromere_start + centromere_end) / 2,xmax=(centromere_start + centromere_end) / 2,ymin=-1.35,ymax=-1.35) +
geom_hline(yintercept = 0, linetype = "dashed", color = "black", size = 0.5, alpha = 0.8 ) +
geom_point(size = 1.5, alpha = 0.9, color = "#727572") +
labs(
title = paste("Gene Expression on Chromosome 9 - Proband relative to Revertant"),
x = "Chromosome Position (bp)",
y = "Relative Expression Level (log2)",
color =NULL
) +
scale_y_continuous(limits = c(-1, 1.5), breaks = seq(-1.5, 1.5, by = 0.5)) +
scale_x_continuous(expand = c(0, 0),
limits = c(0, max(gene.deldup.tmm.plot.relative.PRO$gene_end) + 2e6),
breaks = seq(from = 0, to = max(gene.deldup.tmm.plot.relative.PRO$gene_end), by = 20000000),
labels = c("0", "20,000,000", "40,000,000", "60,000,000", "80,000,000", "100,000,000", "120,000,000")) +
expand_limits(x = 0, y = -1.5) +
theme_classic() +
coord_cartesian(clip = "off") +
theme(
text = element_text(family = "Arial", face = "bold"),
plot.title = element_text(size = 28, face = "bold", hjust = 0.5, family = "Arial"),
axis.title = element_text(size = 20, family = "Arial"),
axis.text = element_text(size = 18, family = "Arial"),
axis.title.x = element_text(margin = margin(t = 20)),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()
)
print(plot_object)
# ggsave(
# filename = paste("CHR9_gene_expression_plot_log2_PROvsREV.png"),
# plot = plot_object,
# width = 18, # Adjust the width to make the canvas longer
# height = 6, # Adjust the height to control the aspect ratio
# dpi = 300, # Set the resolution to 300 dpi
# bg = "transparent"
# )GSE185192 DE analysis
new_counts <- read.csv("data/gene_counts_GSE185192.csv", comment.char = "#")
in_both <- new_counts$Geneid %in% counts$gene_id
all(in_both)## [1] TRUEsample_names <- c("IsoE_Rep1", "IsoE_Rep2", "IsoE_Rep3", "IsoT_Rep1", "IsoT_Rep2", "IsoT_Rep3")
GSE185192.samples <- data.frame(
sample_name = sample_names,
group = c("DS","DS","DS","TS","TS","TS")
)
GSE185192 <- new_counts %>%
dplyr::select(Geneid, all_of(starts_with("aligned"))) %>%
dplyr::rename(gene_id = Geneid,
"IsoE_Rep1" = "aligned.SRR16242104.sorted.bam",
"IsoE_Rep2" = "aligned.SRR16242105.sorted.bam",
"IsoE_Rep3" = "aligned.SRR16242106.sorted.bam",
"IsoT_Rep1" = "aligned.SRR16242107.sorted.bam",
"IsoT_Rep2" = "aligned.SRR16242108.sorted.bam",
"IsoT_Rep3" = "aligned.SRR16242109.sorted.bam")
GSE185192.full <- GSE185192 %>%
dplyr::left_join(annotation, by = "gene_id")
# get counts and annotation
GSE185192.annotation <- GSE185192.full %>% dplyr::select(-all_of(GSE185192.samples$sample_name))
GSE185192.counts <- GSE185192.full %>% dplyr::select(gene_id, all_of(GSE185192.samples$sample_name))
y.GSE185192 <- DGEList(counts = GSE185192.counts, samples = GSE185192.samples, group = GSE185192.samples$group)
y.GSE185192$genes <- GSE185192.annotation
keep <- filterByExpr(y.GSE185192, min.count = 30, min.total.count = 50, large.n = 10, min.prop = 0.75) # filter lowly expressed transcripts
table(keep)## keep
## FALSE TRUE
## 42304 16431y.GSE185192 <- y.GSE185192[keep, , keep.lib.sizes = FALSE]
y.GSE185192 <- normLibSizes(y.GSE185192) # TMM normalization
biotypes <- y.GSE185192$genes$gene_biotype
# Count the occurrences of each gene biotype
biotype_table <- table(biotypes)
# Calculate the fraction of each gene biotype
biotype_fraction <- prop.table(biotype_table)
biotype_df <- data.frame(
Biotype = names(biotype_fraction),
Count = as.numeric(biotype_table),
Fraction = round(biotype_fraction, 3)
)
# calculate CPM
log2_cpm.GSE185192 <- cpm(y.GSE185192, log = TRUE, prior.count = 1, normalized.lib.sizes = T)
log2_tmm_data_with_annotations.GSE185192 <- cbind(y.GSE185192$genes, log2_cpm.GSE185192)
colnames(log2_cpm.GSE185192) <- GSE185192.samples$sample_name
# DE analysis
plotMDS(y.GSE185192)
samples.design <- model.matrix(~ 0 + group,data = y.GSE185192$samples) # design
colnames(samples.design) <- gsub("group", "", colnames(samples.design))
y.GSE185192 <- estimateDisp(y.GSE185192, samples.design, robust=TRUE)
print(y.GSE185192$common.dispersion)## [1] 0.004212285plotBCV(y.GSE185192)
fit <- glmQLFit(y.GSE185192, samples.design, robust=TRUE)
plotQLDisp(fit)
# make contrast
contrast <- makeContrasts(TSvsDS=TS-DS, levels=samples.design)
qlf.TSvsDS <- glmQLFTest(fit, contrast=contrast[,"TSvsDS"])
contr <- get_results("TS - DS", qlf.TSvsDS)
results_list <- list(contr)
plot_all_results(results_list)
table.results <- plot_thresholded_results(results_list)
### Figure 5
chr <- paste0("chr", 21)
centromere_start <- centromeres_summary %>%
filter(chrom == chr) %>%
pull(start)
centromere_end <- centromeres_summary %>%
filter(chrom == chr) %>%
pull(end)
gene.deldup.tmm <- log2_tmm_data_with_annotations %>%
filter(gene_chr == as.character(21)) %>%
filter(!(gene_start >= centromere_start & gene_start < centromere_end)) %>%
dplyr::select(gene_id, gene_start, gene_end, samples$`Sample Name`) %>%
pivot_longer(cols = -c(gene_id, gene_start, gene_end), names_to = "Sample", values_to = "Expression") %>%
left_join(sample_to_group, by = c("Sample" = "Sample Name")) %>% # Map samples to their groups
group_by(gene_id, gene_start, gene_end, `Group Name`) %>%
summarise(Average_Expression = mean(Expression, na.rm = TRUE), .groups = "drop") %>%
arrange(gene_start, desc(Average_Expression))
gene.deldup.tmm.plot.relative.PRO <- gene.deldup.tmm %>%
mutate(region = case_when(
gene_start >= 0 & gene_start < centromere_start ~ "p",
gene_start >= centromere_end ~ "q"
)) %>%
filter(`Group Name` %in% c('PRO', 'REV')) %>% # Filter for PRO and REV
tidyr::pivot_wider(names_from = `Group Name`, values_from = Average_Expression) %>%
# Calculate relative expression as PRO average minus REV average
mutate(relative_expression = PRO - REV) %>%
group_by(region) %>%
mutate(rolling_avg = custom_rollmean(relative_expression, k = 8)) %>%
ungroup()
## TS21
gene.deldup.tmm.GSE185192 <- log2_tmm_data_with_annotations.GSE185192 %>%
filter(gene_chr == as.character(21)) %>%
filter(!(gene_start >= centromere_start & gene_start < centromere_end)) %>%
dplyr::select(gene_id, gene_start, gene_end, GSE185192.samples$sample_name) %>%
pivot_longer(cols = -c(gene_id, gene_start, gene_end), names_to = "Sample", values_to = "Expression") %>%
left_join(GSE185192.samples, by = c("Sample" = "sample_name")) %>% # Map samples to their groups
group_by(gene_id, gene_start, gene_end, group) %>%
summarise(Average_Expression = mean(Expression, na.rm = TRUE), .groups = "drop") %>%
arrange(gene_start, desc(Average_Expression))
gene.deldup.tmm.plot.relative.TS.GSE185192 <- gene.deldup.tmm.GSE185192 %>%
mutate(region = case_when(
gene_start >= 0 & gene_start < centromere_start ~ "p",
gene_start >= centromere_end ~ "q"
)) %>%
filter(group %in% c('TS', 'DS')) %>% # Filter for PRO and REV
tidyr::pivot_wider(names_from = group, values_from = Average_Expression) %>%
# Calculate relative expression as PRO average minus REV average
mutate(relative_expression = TS - DS) %>%
group_by(region) %>%
mutate(rolling_avg = custom_rollmean(relative_expression, k = 8)) %>%
ungroup()
plot_combined_data <- inner_join(gene.deldup.tmm.plot.relative.PRO %>% dplyr::select(gene_id, gene_start, gene_end, rolling_avg),
gene.deldup.tmm.plot.relative.TS.GSE185192 %>% dplyr::select(gene_id, rolling_avg), by = "gene_id", suffix = c("_8p", "_21"))
plot_combined_data_long <- plot_combined_data %>%
pivot_longer(cols = c(rolling_avg_8p, rolling_avg_21),
names_to = "Dataset",
names_prefix = "rolling_avg_",
values_to = "rolling_avg") %>%
mutate(Dataset = recode(Dataset,
"8p" = "8p Proband",
"21" = "Trisomy 21"))
text_cen <- textGrob("Centromere", gp=gpar(fontsize=18, fontface="bold"))
plot_object <- ggplot(plot_combined_data_long, aes(x = (gene_start+gene_end)/2, y = rolling_avg, color = Dataset)) +
theme(plot.margin = unit(c(1,1,2,1), "lines")) +
geom_rect(aes(xmin = centromere_start, xmax = centromere_end, ymin = -Inf, ymax = Inf),
fill = "grey", color = "grey", alpha = 0.6) +
annotation_custom(text_cen,xmin=(centromere_start + centromere_end) / 2,xmax=(centromere_start + centromere_end) / 2,ymin=-1.35,ymax=-1.35) +
geom_hline(yintercept = 0, linetype = "dashed", color = "black", size = 0.5, alpha = 0.8 ) +
geom_point(size = 1.5, alpha = 0.9) +
labs(
title = paste("Gene Expression on Chromosome 21"),
x = "Chromosome Position (bp)",
y = "Relative Expression Level (log2)",
color =NULL
) +
scale_y_continuous(limits = c(-1, 1.5), breaks = seq(-1.5, 1.5, by = 0.5)) +
scale_x_continuous(expand = c(0, 0),
limits = c(0, max(plot_combined_data_long$gene_end) + 1e7),
breaks = seq(from = 0, to = max(plot_combined_data_long$gene_end)+1e7, by = 10000000),
labels = c("0", "10,000,000", "20,000,000", "30,000,000", "40,000,000", "50,000,000")) +
scale_color_manual(values = c("8p Proband" = "steelblue", "Trisomy 21" = "firebrick")) +
expand_limits(x = 0, y = -1.5) +
theme_classic() +
coord_cartesian(clip = "off") +
theme(
text = element_text(family = "Arial", face = "bold"),
plot.title = element_text(size = 28, face = "bold", hjust = 0.5, family = "Arial"),
axis.title = element_text(size = 20, family = "Arial"),
axis.text = element_text(size = 18, family = "Arial"),
axis.title.x = element_text(margin = margin(t = 20)),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
legend.text = element_text(size = 16, family = "Arial")
)
print(plot_object)
# ggsave(
# filename = paste("CHR21_gene_expression_plot_log2_TS21vsDS_PROvsREV.png"),
# plot = plot_object,
# width = 18, # Adjust the width to make the canvas longer
# height = 6, # Adjust the height to control the aspect ratio
# dpi = 300, # Set the resolution to 300 dpi
# bg = "transparent"
# )
mean_values_GSE185192 <- gene.deldup.tmm.plot.relative.TS.GSE185192 %>%
summarize(DS_mean_log2 = mean(DS, na.rm = TRUE),
TS_mean_log2 = mean(TS, na.rm = TRUE)) %>%
mutate(abs_fold_change = 2^(TS_mean_log2 - DS_mean_log2))
mean_values_GSE185192| DS_mean_log2 | TS_mean_log2 | abs_fold_change |
|---|---|---|
| 3.411458 | 4.034069 | 1.539659 |
filtering out 8p and chr21 genes
# PRO vs REV 8p
PRO_REV_8P_table <- contr.rev$top_tags$table %>%
filter(gene_biotype == "protein_coding", gene_chr %in% c(1:22,"X","Y"))
# TS vs DS 21
TS_DS_21_table <- contr$top_tags$table %>%
filter(gene_biotype == "protein_coding", gene_chr %in% c(1:22,"X","Y"))
# write_csv(contr$top_tags$table %>% dplyr::filter(FDR <= 0.05), "DEgenes_Trisomy21.csv")
dim(TS_DS_21_table)## [1] 14038 15dim(PRO_REV_8P_table)## [1] 13212 15region_counts21 <- TS_DS_21_table %>%
mutate(region = gene_chr) %>%
group_by(region) %>%
summarise(
total_genes = n(),
de_count = sum(FDR <= 0.05),
.groups = "drop"
) %>%
mutate(fraction = de_count / total_genes) %>%
mutate(region = factor(region, levels = c(as.character(1:22), "X", "Y")))
ggplot(region_counts21, aes(x = region, y = fraction)) +
geom_col(width = 0.7) +
geom_text(
aes(label = scales::percent(fraction, accuracy = 0.1)),
vjust = -0.5,
size = 3
) +
scale_y_continuous(
labels = scales::percent,
expand = expansion(mult = c(0, 0.1))
) +
labs(
title = "DE Genes per Chromosome",
subtitle = "TS vs DS (FDR <= 0.05, protein-coding)",
x = "Chromosome",
y = "Fraction DE"
) +
theme_classic(base_family = "Arial") +
theme(
plot.title = element_text(size = 20, face = "bold", hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
axis.title = element_text(size = 14, face = "bold"),
axis.text = element_text(size = 14),
axis.text.x = element_text(hjust = 1),
panel.grid = element_blank()
)
## 8p
region_counts8p <- PRO_REV_8P_table %>%
mutate(region = gene_chr) %>%
group_by(region) %>%
summarise(
total_genes = n(),
de_count = sum(FDR <= 0.05),
.groups = "drop"
) %>%
mutate(fraction = de_count / total_genes) %>%
mutate(region = factor(region, levels = c(as.character(1:22), "X", "Y")))
ggplot(region_counts8p, aes(x = region, y = fraction)) +
geom_col(width = 0.7) +
geom_text(
aes(label = scales::percent(fraction, accuracy = 0.1)),
vjust = -0.5,
size = 3
) +
scale_y_continuous(
labels = scales::percent,
expand = expansion(mult = c(0, 0.1))
) +
labs(
title = "DE Genes per Chromosome - 8p",
subtitle = "PRO vs REV (FDR <= 0.05, protein-coding)",
x = "Chromosome",
y = "Fraction DE"
) +
theme_classic(base_family = "Arial") +
theme(
plot.title = element_text(size = 20, face = "bold", hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
axis.title = element_text(size = 14, face = "bold"),
axis.text = element_text(size = 14),
axis.text.x = element_text(hjust = 1),
panel.grid = element_blank()
)
merged_FC <- inner_join(TS_DS_21_table %>%
dplyr::select(-c(gene_name, gene_chr, gene_start, gene_end,gene_strand,gene_length, gene_description, gene_biotype, tf_family)),
PRO_REV_8P_table, by = "gene_id", suffix = c("_21", "_8p"))
# # export as background for enrichr
# write.table(
# merged_FC$gene_name,
# file = "co-detected.txt",
# quote = FALSE,
# row.names = FALSE,
# col.names = FALSE
# )Figure 5C
# Spearman
spearman_r <- cor(merged_FC$logFC_21,
merged_FC$logFC_8p,
use = "complete.obs",
method = "spearman")
spearman_r## [1] 0.2731122spearman_test <- cor.test(merged_FC$logFC_21,
merged_FC$logFC_8p,
use = "complete.obs",
method = "spearman")## Warning in cor.test.default(merged_FC$logFC_21, merged_FC$logFC_8p, use =
## "complete.obs", : Cannot compute exact p-value with tiesspearman_test##
## Spearman's rank correlation rho
##
## data: merged_FC$logFC_21 and merged_FC$logFC_8p
## S = 2.7373e+11, p-value < 2.2e-16
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## 0.2731122Figure 5D
total21.filtered <- TS_DS_21_table %>%
dplyr::filter(
gene_chr != "21",
!gene_id %in% combined_genes$ensembl_gene_id
)
total8p.filtered <- PRO_REV_8P_table %>%
dplyr::filter(
gene_chr != "21",
!gene_id %in% combined_genes$ensembl_gene_id
)
merged_FC_filtered <- merged_FC %>%
dplyr::filter(
gene_chr != "21",
!gene_id %in% combined_genes$ensembl_gene_id
)
## protein coding gene
up_21 <- total21.filtered %>%
dplyr::filter(FDR <= 0.05 & logFC > 0) %>%
pull(gene_name)
up_8p <- total8p.filtered %>%
dplyr::filter(FDR <= 0.05, logFC > 0) %>%
pull(gene_name)
# Negative logFC (downregulated)
down_21 <- total21.filtered %>%
dplyr::filter(FDR <= 0.05, logFC < 0) %>%
pull(gene_name)
down_8p <- total8p.filtered %>%
dplyr::filter(FDR <= 0.05, logFC < 0) %>%
pull(gene_name)
# Upregulated (positive logFC)
upregulated_intersected_genes <- intersect(up_21, up_8p)
# Downregulated (negative logFC)
downregulated_intersected_genes <- intersect(down_21, down_8p)
cat("exclude 21 and 8p genes:")## exclude 21 and 8p genes:cat("Upregulated:", length(upregulated_intersected_genes),
"\nDownregulated:", length(downregulated_intersected_genes), "\n")## Upregulated: 263
## Downregulated: 269# write.table(
# upregulated_intersected_genes,
# file = "enrichr_upregulated_both_filtered.txt",
# quote = FALSE,
# row.names = FALSE,
# col.names = FALSE
# )
#
# write.table(
# downregulated_intersected_genes,
# file = "enrichr_downregulated_both_filtered.txt",
# quote = FALSE,
# row.names = FALSE,
# col.names = FALSE
# )
#
# write.table(
# merged_FC_filtered$gene_name,
# file = "co-detected_filtered.txt",
# quote = FALSE,
# row.names = FALSE,
# col.names = FALSE
# )
# hypergeometric test
N <- nrow(merged_FC_filtered) # total number of genes in merged dataset
# Upregulated in 21 that are in merged_FC
K <- sum(up_21 %in% merged_FC_filtered$gene_name)
# Upregulated in 8p that are in merged_FC
n <- sum(up_8p %in% merged_FC_filtered$gene_name)
# Shared upregulated genes that are also in merged_FC
x <- sum(upregulated_intersected_genes %in% merged_FC_filtered$gene_name)
# Run hypergeometric test
p_value <- phyper(q = x - 1, m = K, n = N - K, k = n, lower.tail = FALSE)
# Hypergeometric test (greater tail = enrichment)
p_value <- phyper(q = x - 1, m = K, n = N - K, k = n, lower.tail = FALSE)
cat("N (total tested genes):", N, "\n",
"K (DE up in dataset 21):", K, "\n",
"n (DE up in dataset 8p):", n, "\n",
"x (co-upregulated):", x, "\n")## N (total tested genes): 12869
## K (DE up in dataset 21): 1623
## n (DE up in dataset 8p): 972
## x (co-upregulated): 263# "N (total tested genes): 12869
# K (DE up in dataset 21): 1623
# n (DE up in dataset 8p): 972
# x (co-upregulated): 263
# "
print(p_value)## [1] 5.901803e-37venn_data <- c(
"Invdupdel(8p)" = n-x,
"Trisomy 21" = K-x,
"Invdupdel(8p)&Trisomy 21" = x
)
venn_euler <- euler(venn_data)
p <- plot(
venn_euler,
fills = c(
met.brewer("Hiroshige", n = 10)[3],
met.brewer("Hiroshige", n = 10)[7]
),
labels = list(font = 1, cex = 0),
alpha = 0.7
)
# png("euler_plot_up.png", width = 1500, height = 1200, res = 300)
# grid::grid.newpage()
# # Draw the plot
# grid::grid.draw(p)
#
# # Close the file
# dev.off()
# hypergeometric test
N <- nrow(merged_FC_filtered) # total genes (universe)
# Upregulated in 21 that are in merged_FC
K <- sum(down_21 %in% merged_FC_filtered$gene_name)
# Upregulated in 8p that are in merged_FC
n <- sum(down_8p%in% merged_FC_filtered$gene_name)
# Shared upregulated genes that are also in merged_FC
x <- sum(downregulated_intersected_genes %in% merged_FC_filtered$gene_name)
# Hypergeometric test (greater tail = enrichment)
p_value <- phyper(q = x - 1, m = K, n = N - K, k = n, lower.tail = FALSE)
cat("N (total tested genes):", N, "\n",
"K (DE down in dataset 21):", K, "\n",
"n (DE down in dataset 8p):", n, "\n",
"x (co-downregulated):", x, "\n")## N (total tested genes): 12869
## K (DE down in dataset 21): 1783
## n (DE down in dataset 8p): 1153
## x (co-downregulated): 269# "N (total tested genes): 12869
# K (DE down in dataset 21): 1783
# n (DE down in dataset 8p): 1153
# x (co-downregulated): 269
# "
print(p_value)## [1] 5.388227e-20venn_data <- c(
"Invdupdel(8p)" = n-x,
"Trisomy 21" = K-x,
"Invdupdel(8p)&Trisomy 21" = x
)
venn_euler <- euler(venn_data)
p <- plot(
venn_euler,
fills = c(
met.brewer("Hiroshige", n = 10)[3],
met.brewer("Hiroshige", n = 10)[7]
),
labels = list(font = 1, cex = 0),
alpha = 0.7
)
# png("euler_plot_down.png", width = 1500, height = 1200, res = 300)
# grid::grid.newpage()
# # Draw the plot
# grid::grid.draw(p)
# # Close the file
# dev.off()upregulated_8p_not_21 <- setdiff(up_8p, up_21)[setdiff(up_8p, up_21) %in% merged_FC_filtered$gene_name]
cat("Upregulated in 8p but not in 21:", length(upregulated_8p_not_21), " (FDR <= 0.05) \n")## Upregulated in 8p but not in 21: 709 (FDR <= 0.05)downregulated_8p_not_21 <- setdiff(down_8p, down_21)[setdiff(down_8p, down_21) %in% merged_FC_filtered$gene_name]
cat("Downregulated in 8p but not in 21:", length(downregulated_8p_not_21), " (FDR <= 0.05) \n")## Downregulated in 8p but not in 21: 884 (FDR <= 0.05)# write.table(
# upregulated_8p_not_21,
# file = "enrichr_upregulated_8p_not_21_filtered.txt",
# quote = FALSE,
# row.names = FALSE,
# col.names = FALSE
# )
#
# write.table(
# downregulated_8p_not_21,
# file = "enrichr_downregulated_8p_not_21_filtered.txt",
# quote = FALSE,
# row.names = FALSE,
# col.names = FALSE
# )
upregulated_21_not_8p <- setdiff(up_21, up_8p)[setdiff(up_21, up_8p) %in% merged_FC_filtered$gene_name]
cat("Upregulated in 21 but not in 8p:", length(upregulated_21_not_8p), " (FDR <= 0.05) \n")## Upregulated in 21 but not in 8p: 1360 (FDR <= 0.05)downregulated_21_not_8p <- setdiff(down_21, down_8p)[setdiff(down_21, down_8p) %in% merged_FC_filtered$gene_name]
cat("Downregulated in 21 but not in 8p:", length(downregulated_21_not_8p), " (FDR <= 0.05) \n")## Downregulated in 21 but not in 8p: 1514 (FDR <= 0.05)# write.table(
# upregulated_21_not_8p,
# file = "enrichr_upregulated_21_not_8p_filtered.txt",
# quote = FALSE,
# row.names = FALSE,
# col.names = FALSE
# )
#
# write.table(
# downregulated_21_not_8p,
# file = "enrichr_downregulated_21_not_8p_filtered.txt",
# quote = FALSE,
# row.names = FALSE,
# col.names = FALSE
# )overlapping_genes <- intersect(protein_coding_genes_del$ensembl_gene_id, protein_coding_genes_dup$ensembl_gene_id)
if (length(overlapping_genes) > 0) {
cat("Genes present in both regions:\n")
print(overlapping_genes)
} else {
cat("No genes are present in both the deletion and duplication regions.\n")
}## No genes are present in both the deletion and duplication regions.Session Info and Citations
sessionInfo()## R version 4.4.1 (2024-06-14)
## Platform: aarch64-apple-darwin20
## Running under: macOS 15.6
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/lib/libRlapack.dylib; LAPACK version 3.12.0
##
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## time zone: America/Los_Angeles
## tzcode source: internal
##
## attached base packages:
## [1] grid stats4 stats graphics grDevices utils datasets
## [8] methods base
##
## other attached packages:
## [1] ggthemes_5.1.0 eulerr_7.0.2 MetBrewer_0.2.0
## [4] gt_0.11.1 gtsummary_2.0.4 ggrepel_0.9.6
## [7] scales_1.3.0 biomaRt_2.60.1 msigdbr_7.5.1
## [10] enrichplot_1.24.4 org.Hs.eg.db_3.19.1 AnnotationDbi_1.66.0
## [13] IRanges_2.38.1 S4Vectors_0.42.1 Biobase_2.64.0
## [16] BiocGenerics_0.50.0 clusterProfiler_4.12.6 edgeR_4.2.2
## [19] limma_3.60.6 lubridate_1.9.3 forcats_1.0.0
## [22] stringr_1.5.1 dplyr_1.1.4 purrr_1.0.2
## [25] readr_2.1.5 tidyr_1.3.1 tibble_3.2.1
## [28] ggplot2_3.5.1 tidyverse_2.0.0 readxl_1.4.3
##
## loaded via a namespace (and not attached):
## [1] RColorBrewer_1.1-3 rstudioapi_0.17.1 jsonlite_1.8.9
## [4] magrittr_2.0.3 farver_2.1.2 rmarkdown_2.28
## [7] fs_1.6.5 zlibbioc_1.50.0 vctrs_0.6.5
## [10] memoise_2.0.1 ggtree_3.12.0 progress_1.2.3
## [13] htmltools_0.5.8.1 curl_5.2.3 cellranger_1.1.0
## [16] gridGraphics_0.5-1 sass_0.4.9 bslib_0.8.0
## [19] plyr_1.8.9 httr2_1.0.5 cachem_1.1.0
## [22] igraph_2.1.1 lifecycle_1.0.4 pkgconfig_2.0.3
## [25] Matrix_1.7-1 R6_2.5.1 fastmap_1.2.0
## [28] gson_0.1.0 GenomeInfoDbData_1.2.12 digest_0.6.37
## [31] aplot_0.2.3 colorspace_2.1-1 patchwork_1.3.0
## [34] RSQLite_2.3.7 labeling_0.4.3 filelock_1.0.3
## [37] fansi_1.0.6 timechange_0.3.0 httr_1.4.7
## [40] polyclip_1.10-7 compiler_4.4.1 bit64_4.5.2
## [43] withr_3.0.2 BiocParallel_1.38.0 viridis_0.6.5
## [46] DBI_1.2.3 highr_0.11 ggforce_0.4.2
## [49] R.utils_2.12.3 MASS_7.3-61 rappdirs_0.3.3
## [52] tools_4.4.1 ape_5.8 scatterpie_0.2.4
## [55] R.oo_1.26.0 glue_1.8.0 nlme_3.1-166
## [58] GOSemSim_2.30.2 polylabelr_0.3.0 shadowtext_0.1.4
## [61] reshape2_1.4.4 fgsea_1.30.0 generics_0.1.3
## [64] gtable_0.3.6 tzdb_0.4.0 R.methodsS3_1.8.2
## [67] data.table_1.16.2 hms_1.1.3 xml2_1.3.6
## [70] tidygraph_1.3.1 utf8_1.2.4 XVector_0.44.0
## [73] pillar_1.9.0 vroom_1.6.5 babelgene_22.9
## [76] yulab.utils_0.1.7 splines_4.4.1 tweenr_2.0.3
## [79] BiocFileCache_2.12.0 treeio_1.28.0 lattice_0.22-6
## [82] bit_4.5.0 tidyselect_1.2.1 GO.db_3.19.1
## [85] locfit_1.5-9.10 Biostrings_2.72.1 knitr_1.48
## [88] gridExtra_2.3 xfun_0.48 graphlayouts_1.2.0
## [91] statmod_1.5.0 stringi_1.8.4 UCSC.utils_1.0.0
## [94] lazyeval_0.2.2 ggfun_0.1.7 yaml_2.3.10
## [97] evaluate_1.0.1 codetools_0.2-20 ggraph_2.2.1
## [100] qvalue_2.36.0 ggplotify_0.1.2 cli_3.6.3
## [103] munsell_0.5.1 jquerylib_0.1.4 Rcpp_1.0.13
## [106] GenomeInfoDb_1.40.1 dbplyr_2.5.0 png_0.1-8
## [109] parallel_4.4.1 blob_1.2.4 prettyunits_1.2.0
## [112] DOSE_3.30.5 viridisLite_0.4.2 tidytree_0.4.6
## [115] crayon_1.5.3 rlang_1.1.4 cowplot_1.1.3
## [118] fastmatch_1.1-4 KEGGREST_1.44.1packages_in_use <- c( names( sessionInfo()$otherPkgs ) )
the_citations_list <- lapply( X=packages_in_use, FUN=citation)
the_citations_list## [[1]]
## To cite package 'ggthemes' in publications use:
##
## Arnold J (2024). _ggthemes: Extra Themes, Scales and Geoms for
## 'ggplot2'_. R package version 5.1.0,
## <https://CRAN.R-project.org/package=ggthemes>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {ggthemes: Extra Themes, Scales and Geoms for 'ggplot2'},
## author = {Jeffrey B. Arnold},
## year = {2024},
## note = {R package version 5.1.0},
## url = {https://CRAN.R-project.org/package=ggthemes},
## }
##
## [[2]]
## To cite use of the eulerr R package in publications, please use:
##
## Larsson J (2024). _eulerr: Area-Proportional Euler and Venn Diagrams
## with Ellipses_. R package version 7.0.2,
## <https://CRAN.R-project.org/package=eulerr>.
##
## To cite the methodology behind eulerr in publications, please use:
##
## Larsson J, Gustafsson P (2018). "A Case Study in Fitting
## Area-Proportional Euler Diagrams with Ellipses Using eulerr." In
## _Proceedings of International Workshop on Set Visualization and
## Reasoning_, volume 2116, 84-91.
## <https://cran.r-project.org/package=eulerr>.
##
## To see these entries in BibTeX format, use 'print(<citation>,
## bibtex=TRUE)', 'toBibtex(.)', or set
## 'options(citation.bibtex.max=999)'.
##
## [[3]]
## To cite package 'MetBrewer' in publications use:
##
## Mills BR (2022). _MetBrewer: Color Palettes Inspired by Works at the
## Metropolitan Museum of Art_. R package version 0.2.0,
## <https://CRAN.R-project.org/package=MetBrewer>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {MetBrewer: Color Palettes Inspired by Works at the Metropolitan Museum of
## Art},
## author = {Blake Robert Mills},
## year = {2022},
## note = {R package version 0.2.0},
## url = {https://CRAN.R-project.org/package=MetBrewer},
## }
##
## ATTENTION: This citation information has been auto-generated from the
## package DESCRIPTION file and may need manual editing, see
## 'help("citation")'.
##
## [[4]]
## To cite package 'gt' in publications use:
##
## Iannone R, Cheng J, Schloerke B, Hughes E, Lauer A, Seo J, Brevoort
## K, Roy O (2024). _gt: Easily Create Presentation-Ready Display
## Tables_. R package version 0.11.1,
## <https://CRAN.R-project.org/package=gt>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {gt: Easily Create Presentation-Ready Display Tables},
## author = {Richard Iannone and Joe Cheng and Barret Schloerke and Ellis Hughes and Alexandra Lauer and JooYoung Seo and Ken Brevoort and Olivier Roy},
## year = {2024},
## note = {R package version 0.11.1},
## url = {https://CRAN.R-project.org/package=gt},
## }
##
## [[5]]
## To cite gtsummary in publications use:
##
## Sjoberg DD, Whiting K, Curry M, Lavery JA, Larmarange J. Reproducible
## summary tables with the gtsummary package. The R Journal
## 2021;13:570–80. https://doi.org/10.32614/RJ-2021-053.
##
## A BibTeX entry for LaTeX users is
##
## @Article{gtsummary,
## author = {Daniel D. Sjoberg and Karissa Whiting and Michael Curry and Jessica A. Lavery and Joseph Larmarange},
## title = {Reproducible Summary Tables with the gtsummary Package},
## journal = {{The R Journal}},
## year = {2021},
## url = {https://doi.org/10.32614/RJ-2021-053},
## doi = {10.32614/RJ-2021-053},
## volume = {13},
## issue = {1},
## pages = {570-580},
## }
##
## [[6]]
## To cite package 'ggrepel' in publications use:
##
## Slowikowski K (2024). _ggrepel: Automatically Position
## Non-Overlapping Text Labels with 'ggplot2'_. R package version 0.9.6,
## <https://CRAN.R-project.org/package=ggrepel>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {ggrepel: Automatically Position Non-Overlapping Text Labels with
## 'ggplot2'},
## author = {Kamil Slowikowski},
## year = {2024},
## note = {R package version 0.9.6},
## url = {https://CRAN.R-project.org/package=ggrepel},
## }
##
## [[7]]
## To cite package 'scales' in publications use:
##
## Wickham H, Pedersen T, Seidel D (2023). _scales: Scale Functions for
## Visualization_. R package version 1.3.0,
## <https://CRAN.R-project.org/package=scales>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {scales: Scale Functions for Visualization},
## author = {Hadley Wickham and Thomas Lin Pedersen and Dana Seidel},
## year = {2023},
## note = {R package version 1.3.0},
## url = {https://CRAN.R-project.org/package=scales},
## }
##
## [[8]]
## To cite the biomaRt package in publications use:
##
## Mapping identifiers for the integration of genomic datasets with the
## R/Bioconductor package biomaRt. Steffen Durinck, Paul T. Spellman,
## Ewan Birney and Wolfgang Huber, Nature Protocols 4, 1184-1191 (2009).
##
## BioMart and Bioconductor: a powerful link between biological
## databases and microarray data analysis. Steffen Durinck, Yves Moreau,
## Arek Kasprzyk, Sean Davis, Bart De Moor, Alvis Brazma and Wolfgang
## Huber, Bioinformatics 21, 3439-3440 (2005).
##
## To see these entries in BibTeX format, use 'print(<citation>,
## bibtex=TRUE)', 'toBibtex(.)', or set
## 'options(citation.bibtex.max=999)'.
##
## [[9]]
## To cite package 'msigdbr' in publications use:
##
## Dolgalev I (2022). _msigdbr: MSigDB Gene Sets for Multiple Organisms
## in a Tidy Data Format_. R package version 7.5.1,
## <https://CRAN.R-project.org/package=msigdbr>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {msigdbr: MSigDB Gene Sets for Multiple Organisms in a Tidy Data Format},
## author = {Igor Dolgalev},
## year = {2022},
## note = {R package version 7.5.1},
## url = {https://CRAN.R-project.org/package=msigdbr},
## }
##
## [[10]]
## To cite package 'enrichplot' in publications use:
##
## Yu G (2024). _enrichplot: Visualization of Functional Enrichment
## Result_. doi:10.18129/B9.bioc.enrichplot
## <https://doi.org/10.18129/B9.bioc.enrichplot>, R package version
## 1.24.4, <https://bioconductor.org/packages/enrichplot>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {enrichplot: Visualization of Functional Enrichment Result},
## author = {Guangchuang Yu},
## year = {2024},
## note = {R package version 1.24.4},
## url = {https://bioconductor.org/packages/enrichplot},
## doi = {10.18129/B9.bioc.enrichplot},
## }
##
## [[11]]
## To cite package 'org.Hs.eg.db' in publications use:
##
## Carlson M (2024). _org.Hs.eg.db: Genome wide annotation for Human_. R
## package version 3.19.1.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {org.Hs.eg.db: Genome wide annotation for Human},
## author = {Marc Carlson},
## year = {2024},
## note = {R package version 3.19.1},
## }
##
## ATTENTION: This citation information has been auto-generated from the
## package DESCRIPTION file and may need manual editing, see
## 'help("citation")'.
##
## [[12]]
## To cite package 'AnnotationDbi' in publications use:
##
## Pagès H, Carlson M, Falcon S, Li N (2024). _AnnotationDbi:
## Manipulation of SQLite-based annotations in Bioconductor_.
## doi:10.18129/B9.bioc.AnnotationDbi
## <https://doi.org/10.18129/B9.bioc.AnnotationDbi>, R package version
## 1.66.0, <https://bioconductor.org/packages/AnnotationDbi>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {AnnotationDbi: Manipulation of SQLite-based annotations in Bioconductor},
## author = {Hervé Pagès and Marc Carlson and Seth Falcon and Nianhua Li},
## year = {2024},
## note = {R package version 1.66.0},
## url = {https://bioconductor.org/packages/AnnotationDbi},
## doi = {10.18129/B9.bioc.AnnotationDbi},
## }
##
## ATTENTION: This citation information has been auto-generated from the
## package DESCRIPTION file and may need manual editing, see
## 'help("citation")'.
##
## [[13]]
## To cite package 'IRanges' in publications use:
##
## Lawrence M, Huber W, Pag\`es H, Aboyoun P, Carlson M, et al. (2013)
## Software for Computing and Annotating Genomic Ranges. PLoS Comput
## Biol 9(8): e1003118. doi:10.1371/journal.pcbi.1003118
##
## A BibTeX entry for LaTeX users is
##
## @Article{,
## title = {Software for Computing and Annotating Genomic Ranges},
## author = {Michael Lawrence and Wolfgang Huber and Herv\'e Pag\`es and Patrick Aboyoun and Marc Carlson and Robert Gentleman and Martin Morgan and Vincent Carey},
## year = {2013},
## journal = {{PLoS} Computational Biology},
## volume = {9},
## issue = {8},
## doi = {10.1371/journal.pcbi.1003118},
## url = {http://www.ploscompbiol.org/article/info%3Adoi%2F10.1371%2Fjournal.pcbi.1003118},
## }
##
## [[14]]
## To cite package 'S4Vectors' in publications use:
##
## Pagès H, Lawrence M, Aboyoun P (2024). _S4Vectors: Foundation of
## vector-like and list-like containers in Bioconductor_.
## doi:10.18129/B9.bioc.S4Vectors
## <https://doi.org/10.18129/B9.bioc.S4Vectors>, R package version
## 0.42.1, <https://bioconductor.org/packages/S4Vectors>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {S4Vectors: Foundation of vector-like and list-like containers in
## Bioconductor},
## author = {Hervé Pagès and Michael Lawrence and Patrick Aboyoun},
## year = {2024},
## note = {R package version 0.42.1},
## url = {https://bioconductor.org/packages/S4Vectors},
## doi = {10.18129/B9.bioc.S4Vectors},
## }
##
## [[15]]
## To cite package 'Biobase' in publications use:
##
## Orchestrating high-throughput genomic analysis with Bioconductor. W.
## Huber, V.J. Carey, R. Gentleman, ..., M. Morgan Nature Methods,
## 2015:12, 115.
##
## A BibTeX entry for LaTeX users is
##
## @Article{,
## author = {W. Huber and V. J. Carey and R. Gentleman and S. Anders and M. Carlson and B. S. Carvalho and H. C. Bravo and S. Davis and L. Gatto and T. Girke and R. Gottardo and F. Hahne and K. D. Hansen and R. A. Irizarry and M. Lawrence and M. I. Love and J. MacDonald and V. Obenchain and A. K. {Ole's} and H. {Pag`es} and A. Reyes and P. Shannon and G. K. Smyth and D. Tenenbaum and L. Waldron and M. Morgan},
## title = {{O}rchestrating high-throughput genomic analysis with {B}ioconductor},
## journal = {Nature Methods},
## year = {2015},
## volume = {12},
## number = {2},
## pages = {115--121},
## url = {http://www.nature.com/nmeth/journal/v12/n2/full/nmeth.3252.html},
## }
##
## [[16]]
## To cite package 'BiocGenerics' in publications use:
##
## Orchestrating high-throughput genomic analysis with Bioconductor. W.
## Huber, V.J. Carey, R. Gentleman, ..., M. Morgan Nature Methods,
## 2015:12, 115.
##
## A BibTeX entry for LaTeX users is
##
## @Article{,
## author = {{Huber} and {W.} and {Carey} and V. J. and {Gentleman} and {R.} and {Anders} and {S.} and {Carlson} and {M.} and {Carvalho} and B. S. and {Bravo} and H. C. and {Davis} and {S.} and {Gatto} and {L.} and {Girke} and {T.} and {Gottardo} and {R.} and {Hahne} and {F.} and {Hansen} and K. D. and {Irizarry} and R. A. and {Lawrence} and {M.} and {Love} and M. I. and {MacDonald} and {J.} and {Obenchain} and {V.} and {{Ole's}} and A. K. and {{Pag`es}} and {H.} and {Reyes} and {A.} and {Shannon} and {P.} and {Smyth} and G. K. and {Tenenbaum} and {D.} and {Waldron} and {L.} and {Morgan} and {M.}},
## title = {{O}rchestrating high-throughput genomic analysis with {B}ioconductor},
## journal = {Nature Methods},
## year = {2015},
## volume = {12},
## number = {2},
## pages = {115--121},
## url = {http://www.nature.com/nmeth/journal/v12/n2/full/nmeth.3252.html},
## }
##
## [[17]]
## Please cite S. Xu (2024) for using clusterProfiler. In addition, please
## cite G. Yu (2010) when using GOSemSim, G. Yu (2015) when using DOSE and
## G. Yu (2015) when using ChIPseeker.
##
## S Xu, E Hu, Y Cai, Z Xie, X Luo, L Zhan, W Tang, Q Wang, B Liu, R
## Wang, W Xie, T Wu, L Xie, G Yu. Using clusterProfiler to characterize
## multiomics data. Nature Protocols. 2024,
## doi:10.1038/s41596-024-01020-z
##
## T Wu, E Hu, S Xu, M Chen, P Guo, Z Dai, T Feng, L Zhou, W Tang, L
## Zhan, X Fu, S Liu, X Bo, and G Yu. clusterProfiler 4.0: A universal
## enrichment tool for interpreting omics data. The Innovation. 2021,
## 2(3):100141
##
## Guangchuang Yu, Li-Gen Wang, Yanyan Han and Qing-Yu He.
## clusterProfiler: an R package for comparing biological themes among
## gene clusters. OMICS: A Journal of Integrative Biology 2012,
## 16(5):284-287
##
## To see these entries in BibTeX format, use 'print(<citation>,
## bibtex=TRUE)', 'toBibtex(.)', or set
## 'options(citation.bibtex.max=999)'.
##
## [[18]]
## See Section 1.2 in the User's Guide for more detail about how to cite
## the different edgeR pipelines.
##
## Chen Y, Chen L, Lun ATL, Baldoni PL, Smyth GK (2024). edgeR 4.0:
## powerful differential analysis of sequencing data with expanded
## functionality and improved support for small counts and larger
## datasets. bioRxiv doi: 10.1101/2024.01.21.576131
##
## Chen Y, Lun ATL, Smyth GK (2016). From reads to genes to pathways:
## differential expression analysis of RNA-Seq experiments using
## Rsubread and the edgeR quasi-likelihood pipeline. F1000Research 5,
## 1438
##
## McCarthy DJ, Chen Y and Smyth GK (2012). Differential expression
## analysis of multifactor RNA-Seq experiments with respect to
## biological variation. Nucleic Acids Research 40(10), 4288-4297
##
## Robinson MD, McCarthy DJ and Smyth GK (2010). edgeR: a Bioconductor
## package for differential expression analysis of digital gene
## expression data. Bioinformatics 26(1), 139-140
##
## To see these entries in BibTeX format, use 'print(<citation>,
## bibtex=TRUE)', 'toBibtex(.)', or set
## 'options(citation.bibtex.max=999)'.
##
## [[19]]
## To cite package 'limma' in publications use:
##
## Ritchie, M.E., Phipson, B., Wu, D., Hu, Y., Law, C.W., Shi, W., and
## Smyth, G.K. (2015). limma powers differential expression analyses for
## RNA-sequencing and microarray studies. Nucleic Acids Research 43(7),
## e47.
##
## A BibTeX entry for LaTeX users is
##
## @Article{,
## author = {Matthew E Ritchie and Belinda Phipson and Di Wu and Yifang Hu and Charity W Law and Wei Shi and Gordon K Smyth},
## title = {{limma} powers differential expression analyses for {RNA}-sequencing and microarray studies},
## journal = {Nucleic Acids Research},
## year = {2015},
## volume = {43},
## number = {7},
## pages = {e47},
## doi = {10.1093/nar/gkv007},
## }
##
## [[20]]
## To cite lubridate in publications use:
##
## Garrett Grolemund, Hadley Wickham (2011). Dates and Times Made Easy
## with lubridate. Journal of Statistical Software, 40(3), 1-25. URL
## https://www.jstatsoft.org/v40/i03/.
##
## A BibTeX entry for LaTeX users is
##
## @Article{,
## title = {Dates and Times Made Easy with {lubridate}},
## author = {Garrett Grolemund and Hadley Wickham},
## journal = {Journal of Statistical Software},
## year = {2011},
## volume = {40},
## number = {3},
## pages = {1--25},
## url = {https://www.jstatsoft.org/v40/i03/},
## }
##
## [[21]]
## To cite package 'forcats' in publications use:
##
## Wickham H (2023). _forcats: Tools for Working with Categorical
## Variables (Factors)_. R package version 1.0.0,
## <https://CRAN.R-project.org/package=forcats>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {forcats: Tools for Working with Categorical Variables (Factors)},
## author = {Hadley Wickham},
## year = {2023},
## note = {R package version 1.0.0},
## url = {https://CRAN.R-project.org/package=forcats},
## }
##
## [[22]]
## To cite package 'stringr' in publications use:
##
## Wickham H (2023). _stringr: Simple, Consistent Wrappers for Common
## String Operations_. R package version 1.5.1,
## <https://CRAN.R-project.org/package=stringr>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {stringr: Simple, Consistent Wrappers for Common String Operations},
## author = {Hadley Wickham},
## year = {2023},
## note = {R package version 1.5.1},
## url = {https://CRAN.R-project.org/package=stringr},
## }
##
## [[23]]
## To cite package 'dplyr' in publications use:
##
## Wickham H, François R, Henry L, Müller K, Vaughan D (2023). _dplyr: A
## Grammar of Data Manipulation_. R package version 1.1.4,
## <https://CRAN.R-project.org/package=dplyr>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {dplyr: A Grammar of Data Manipulation},
## author = {Hadley Wickham and Romain François and Lionel Henry and Kirill Müller and Davis Vaughan},
## year = {2023},
## note = {R package version 1.1.4},
## url = {https://CRAN.R-project.org/package=dplyr},
## }
##
## [[24]]
## To cite package 'purrr' in publications use:
##
## Wickham H, Henry L (2023). _purrr: Functional Programming Tools_. R
## package version 1.0.2, <https://CRAN.R-project.org/package=purrr>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {purrr: Functional Programming Tools},
## author = {Hadley Wickham and Lionel Henry},
## year = {2023},
## note = {R package version 1.0.2},
## url = {https://CRAN.R-project.org/package=purrr},
## }
##
## [[25]]
## To cite package 'readr' in publications use:
##
## Wickham H, Hester J, Bryan J (2024). _readr: Read Rectangular Text
## Data_. R package version 2.1.5,
## <https://CRAN.R-project.org/package=readr>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {readr: Read Rectangular Text Data},
## author = {Hadley Wickham and Jim Hester and Jennifer Bryan},
## year = {2024},
## note = {R package version 2.1.5},
## url = {https://CRAN.R-project.org/package=readr},
## }
##
## [[26]]
## To cite package 'tidyr' in publications use:
##
## Wickham H, Vaughan D, Girlich M (2024). _tidyr: Tidy Messy Data_. R
## package version 1.3.1, <https://CRAN.R-project.org/package=tidyr>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {tidyr: Tidy Messy Data},
## author = {Hadley Wickham and Davis Vaughan and Maximilian Girlich},
## year = {2024},
## note = {R package version 1.3.1},
## url = {https://CRAN.R-project.org/package=tidyr},
## }
##
## [[27]]
## To cite package 'tibble' in publications use:
##
## Müller K, Wickham H (2023). _tibble: Simple Data Frames_. R package
## version 3.2.1, <https://CRAN.R-project.org/package=tibble>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {tibble: Simple Data Frames},
## author = {Kirill Müller and Hadley Wickham},
## year = {2023},
## note = {R package version 3.2.1},
## url = {https://CRAN.R-project.org/package=tibble},
## }
##
## [[28]]
## To cite ggplot2 in publications, please use
##
## H. Wickham. ggplot2: Elegant Graphics for Data Analysis.
## Springer-Verlag New York, 2016.
##
## A BibTeX entry for LaTeX users is
##
## @Book{,
## author = {Hadley Wickham},
## title = {ggplot2: Elegant Graphics for Data Analysis},
## publisher = {Springer-Verlag New York},
## year = {2016},
## isbn = {978-3-319-24277-4},
## url = {https://ggplot2.tidyverse.org},
## }
##
## [[29]]
## To cite package 'tidyverse' in publications use:
##
## Wickham H, Averick M, Bryan J, Chang W, McGowan LD, François R,
## Grolemund G, Hayes A, Henry L, Hester J, Kuhn M, Pedersen TL, Miller
## E, Bache SM, Müller K, Ooms J, Robinson D, Seidel DP, Spinu V,
## Takahashi K, Vaughan D, Wilke C, Woo K, Yutani H (2019). "Welcome to
## the tidyverse." _Journal of Open Source Software_, *4*(43), 1686.
## doi:10.21105/joss.01686 <https://doi.org/10.21105/joss.01686>.
##
## A BibTeX entry for LaTeX users is
##
## @Article{,
## title = {Welcome to the {tidyverse}},
## author = {Hadley Wickham and Mara Averick and Jennifer Bryan and Winston Chang and Lucy D'Agostino McGowan and Romain François and Garrett Grolemund and Alex Hayes and Lionel Henry and Jim Hester and Max Kuhn and Thomas Lin Pedersen and Evan Miller and Stephan Milton Bache and Kirill Müller and Jeroen Ooms and David Robinson and Dana Paige Seidel and Vitalie Spinu and Kohske Takahashi and Davis Vaughan and Claus Wilke and Kara Woo and Hiroaki Yutani},
## year = {2019},
## journal = {Journal of Open Source Software},
## volume = {4},
## number = {43},
## pages = {1686},
## doi = {10.21105/joss.01686},
## }
##
## [[30]]
## To cite package 'readxl' in publications use:
##
## Wickham H, Bryan J (2023). _readxl: Read Excel Files_. R package
## version 1.4.3, <https://CRAN.R-project.org/package=readxl>.
##
## A BibTeX entry for LaTeX users is
##
## @Manual{,
## title = {readxl: Read Excel Files},
## author = {Hadley Wickham and Jennifer Bryan},
## year = {2023},
## note = {R package version 1.4.3},
## url = {https://CRAN.R-project.org/package=readxl},
## }