Multi-platform profiling reveals host- and cell -type-specific pseudorabies virus gene expression.
Paper
Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC
The paper is loaded when this pane is shown.
The authors' code
R · 162 lines · 5.9 KB · MIT
- cover_dt_weighted <- function(dt,
- weight_col = NULL,
- by = c("seqnames", "strand", "sample"),
- return = c("rle", "pos"),
- nworkers = 1L,
- # zero-fill options
- include_zero = FALSE,
- contigs_dt = NULL,
- contig_seq_col = "seqnames",
- contig_start_col = "start",
- contig_end_col = "end") {
- stopifnot(all(c("seqnames","strand","start","end","sample") %in% names(dt)))
- return <- match.arg(return)
- setDT(dt)
- # Coerce to ints & numeric weight
- dt[, `:=`(start = as.integer(start), end = as.integer(end))]
- if (!is.null(weight_col)) {
- stopifnot(weight_col %in% names(dt))
- set(dt, j = weight_col, value = as.numeric(dt[[weight_col]]))
- }
- if (is.null(weight_col)) {
- dt[, `__w__` := 1.0]
- on.exit(dt[, `__w__` := NULL], add = TRUE)
- weight_col <- "__w__"
- }
- # Drop 0 / NA / non-finite weights early
- dt <- dt[is.finite(get(weight_col)) & get(weight_col) != 0]
- # Safe +1 with overflow guard
- add1 <- function(x) {
- y <- x + 1L
- y[is.na(x)] <- NA_integer_
- y[ y < x ] <- .Machine$integer.max
- y
- }
- make_runs <- function(x, bycols, wcol) {
- # Weighted events per group: +w at start, -w at end+1
- ev <- x[, {
- w <- get(wcol)
- .(pos = c(start, add1(end)),
- delta = c(w, -w))
- }, by = bycols]
- # Combine same-position events
- ev <- ev[, .(delta = sum(delta)), by = c(bycols, "pos")]
- # Order by group columns and position
- do.call(setorder, c(list(ev), as.list(c(bycols, "pos"))))
- # Weighted coverage via cumsum of deltas per group
- ev[, cov := cumsum(delta), by = bycols]
- ev[, next_pos := shift(pos, type = "lead"), by = bycols]
- runs <- ev[!is.na(next_pos) & cov > 0,
- .(start = pos, end = next_pos - 1L, count = cov),
- by = bycols]
- runs[]
- }
- # Compute positive-coverage runs
- if (nrow(dt) == 0L) {
- runs <- data.table(matrix(ncol = length(by) + 3L, nrow = 0L))
- setnames(runs, c(by, "start", "end", "count"))
- } else if (nworkers > 1L) {
- requireNamespace("future.apply", quietly = TRUE)
- requireNamespace("future", quietly = TRUE)
- split_dt <- split(dt, by = by, drop = TRUE, keep.by = TRUE)
- oplan <- NULL
- if (!inherits(future::plan(), "multiprocess")) {
- oplan <- future::plan(future::multisession, workers = nworkers)
- on.exit({ if (!is.null(oplan)) future::plan(oplan) }, add = TRUE)
- }
- parts <- future.apply::future_lapply(
- split_dt, make_runs, bycols = by, wcol = weight_col, future.seed = TRUE
- )
- runs <- rbindlist(parts, use.names = TRUE)
- } else {
- runs <- make_runs(dt, by, weight_col)
- }
- # === Zero-fill RLE based on contig spans ===
- if (isTRUE(include_zero)) {
- stopifnot(!is.null(contigs_dt),
- all(c(contig_seq_col, contig_start_col, contig_end_col) %in% names(contigs_dt)))
- g0 <- unique(as.data.table(contigs_dt)[,
- .(seqnames = get(contig_seq_col),
- g_start = as.integer(get(contig_start_col)),
- g_end = as.integer(get(contig_end_col)))
- ])
- # Expand contigs across any missing by-columns using dt's uniques
- comb_list <- list(seqnames = unique(g0$seqnames))
- for (col in setdiff(by, "seqnames")) {
- if (col %in% names(contigs_dt)) comb_list[[col]] <- unique(contigs_dt[[col]])
- else comb_list[[col]] <- unique(dt[[col]])
- }
- comb <- do.call(CJ, c(comb_list, list(unique = TRUE)))
- contigs_exp <- g0[comb, on = "seqnames", nomatch = 0L]
- # Groups with no positive runs -> full-length zero run
- runs_keys <- unique(runs[, ..by])
- missing_groups <- contigs_exp[!runs_keys, on = by]
- zero_missing <- if (nrow(missing_groups)) {
- missing_groups[, .(start = g_start, end = g_end, count = 0.0), by = by]
- } else data.table(matrix(ncol = length(by) + 3L, nrow = 0L))
- if (nrow(zero_missing)) setnames(zero_missing, c(by, "start", "end", "count"))
- # For groups with positives, add leading/trailing and between-run zeros
- if (nrow(runs)) {
- runs2 <- contigs_exp[runs, on = by]
- # g_start/g_end now available per group
- zeros_between <- runs2[, {
- sd <- copy(.SD)
- setorder(sd, start, end)
- gs <- g_start[1L]; ge <- g_end[1L]
- out <- vector("list", 3L)
- k <- 0L
- if (nrow(sd) && sd$start[1L] > gs) { k <- k + 1L; out[[k]] <- data.table(start = gs, end = sd$start[1L] - 1L, count = 0.0) }
- if (nrow(sd) > 1L) {
- gaps_s <- sd$end[-.N] + 1L
- gaps_e <- sd$start[-1L] - 1L
- sel <- gaps_s <= gaps_e
- if (any(sel)) { k <- k + 1L; out[[k]] <- data.table(start = gaps_s[sel], end = gaps_e[sel], count = 0.0) }
- }
- if (nrow(sd) && sd$end[.N] < ge) { k <- k + 1L; out[[k]] <- data.table(start = sd$end[.N] + 1L, end = ge, count = 0.0) }
- if (k) rbindlist(out[1:k]) else data.table(start = integer(), end = integer(), count = numeric())
- }, by = by]
- runs <- rbindlist(list(runs, zeros_between, zero_missing), use.names = TRUE, fill = TRUE)
- } else {
- runs <- zero_missing
- }
- if (nrow(runs)) do.call(setorder, c(list(runs), as.list(c(by, "start", "end"))))
- }
- #
- runs <- runs[, .(seqnames, strand, sample, start, end, count)]
- #
- if (return == "rle") {
- setcolorder(runs, c(by, setdiff(names(runs), by)))
- return(runs[])
- }
- # Per-position expansion (row-wise, length-safe). This will also include zeros if include_zero=TRUE.
- runs[, {
- pos_list <- Map(seq.int, start, end)
- .(pos = unlist(pos_list, use.names = FALSE),
- count = rep.int(count, lengths(pos_list)))
- }, by = by]
- }
ExDT2cov.R at commit aeb8421, under MIT · at the source
Overview
- Department of Medical Biology, Albert Szent-Györgyi Medical School, University of Szeged, Szeged, Hungary
- Department of Physiology, Anatomy and Neuroscience, Faculty of Science and Informatics, University of Szeged, 6726 Szeged, Hungary
Abstract
Pseudorabies virus (PRV) is an alphaherpesvirus that follows a conserved immediate-early → early → late transcriptional cascade, yet how this program adapts to diverse cell types is unclear. We profiled PRV transcription in four permissive cell lines—two epithelial (porcine kidney PK-15 and rat kidney NRK), one glial (rat glioma C6), and one neuron-like (rat PC-12)—at six time points (1–12 h post-infection). Host-dependent differences peaked early in infection, particularly for the regulators ie180, ep0, and us1. ie180 showed strong species bias, with high expression in PK-15 but minimal in rodent lines, whereas ep0 and us1 varied quantitatively by cell type, with C6 and PC-12 showing marked early us1 activation. Combining long-read direct cDNA and direct RNA sequencing with 5′-capped CAGE-seq resolved viral transcription boundaries and identified 94 previously unannotated transcripts, including 5′ UTR isoforms, polygenic RNAs, and noncoding transcripts. Differential transcript usage analysis revealed extensive isoform remodeling across conditions, with late infection showing shifts from long or polygenic isoforms toward shorter forms. Together, these results provide the first multi-host, isoform-resolved temporal atlas of PRV transcription and show that the canonical cascade is conserved yet quantitatively tuned by host species and cell-type background.
Supplementary Information: The online version contains supplementary material available at 10.1038/
Reproduced under the paper's license (CC BY), from the paper cited above.
Repositories
Its files are read in the Code ↔ Paper reader above.
Balays/Rlyeh
aeb8421bc29070fa130d6266c927d7e1c5df64c6, 7 February 2026Availability: 1 check, the latest on 28 September 2026: the link answers
- 28 September 2026: the link answers
44 files
- R/
ExDT2cov.R , R, 162 lines - R/
ExDT2cov.Rmd , R, 405 lines - R/
add.correct.ends.R , R, 21 lines - R/
add_rightmost_non.NA_col , R, 21 lines.R - R/
cigar.sum.R , R, 9 lines - R/
cov.from.bam.R , R, 122 lines - R/
cov.from.bam.multi.R , R, 216 lines - R/
dt.from.PS.R , R, 68 lines - R/
dt.from.bam.R , R, 46 lines - R/
dt.slpitcol.R , R, 25 lines - R/
export_functions.R , R, 71 lines - R/
feature.OV.from.polyC.TR , R, 102 lines.R - R/
filt_bamfiles_to_contig. , R, 48 linesR - R/
filter.and.import.bams.R , R, 161 lines - R/
foverlaps2.R , R, 29 lines - R/
foverlaps3.R , R, 69 lines - R/
foverlaps4.R , R, 155 lines - R/
genome_plot.data.R , R, 44 lines - R/
geom_gene_rect.R , R, 58 lines - R/
get.best.aln.R , R, 125 lines - R/
get_intervals.R , R, 56 lines - R/
get_top_taxa.R , R, 68 lines - R/
get_vis_intervals.R , R, 56 lines - R/
gggenome.from.df.R , R, 48 lines - R/
idxstats.bams.R , R, 29 lines - R/
make_read_plot_data.R , R, 243 lines - R/
mapping.eval.R , R, 129 lines - R/
merge2.R , R, 30 lines - R/
merge_list.R , R, 45 lines - R/
misc.functions.R , R, 36 lines - R/
misc_functions.R , R, 21 lines - R/
ov.from.bam2.R , R, 102 lines - R/
ov.from.bam3.R , R, 103 lines - R/
paste_columns_dt.R , R, 32 lines - R/
plot.genome.and.TXs.R , R, 93 lines - R/
plot.genome.region.R , R, 1,170 lines - R/
plot_transcripts.R , R, 614 lines - R/
rename_bamfiles.R , R, 15 lines - R/
replace_NA_taxa.R , R, 44 lines - R/
tax_glom_fast2.R , R, 144 lines - R/
unsummarize.R , R, 28 lines - R/
window_cov.R , R, 139 lines - bash/
count_tags_in_bam.sh , Shell, 38 lines - LICENSE, License, 21 lines
Balays/VALAR-PRV-MDBIO-4cell
Availability: 1 check, the latest on 28 September 2026: the link is dead
- 28 September 2026: the link is dead
Code availability
All R scripts that were used for the downstream analysis are available at the GitHub repository: https://
Reproduced under the paper's license (CC BY), from the paper cited above.
Tracing map
Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.
What the map holds:
- 2 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
- 43 scripts, each with its path and the digest of its content;
- no match between paragraphs and code yet;
- neither the text of the paper nor the code itself.
Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.
Data
No dataset and no data link were found in the paper.
Data availability
The fastq files from all sequencing were uploaded to European Nucleotide Archive (ENA), under the project id PRJEB60055.
Reproduced under the paper's license (CC BY), from the paper cited above.
Versions
The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.
Version 1, 28 September 2026: the first record
Recorded: type, language, journal, volume, issue, pages, dates, 9 authors, 3 keywords, 10 MeSH terms, 1 funder, 51 references.
Cite
This paper
Kakuk, B., Csabai, Z., Deim, Z., Torma, G., Fülöp, Á., Nagy, G. Á., Dani, V. É., Tombácz, D., & Boldogkői, Z. (2026). Multi-platform profiling reveals host- and cell -type-specific pseudorabies virus gene expression. Scientific reports, 16(1), 15297. https://
BibTeX
@article{kakuk2026multi,
author = {Kakuk, Balázs and Csabai, Zsolt and Deim, Zoltán and Torma, Gábor and Fülöp, Ádám and Nagy, Gergely Ármin and Dani, Virág Éva and Tombácz, Dóra and Boldogkői, Zsolt},
title = {{Multi-platform profiling reveals host- and cell -type-specific pseudorabies virus gene expression}},
journal = {Scientific reports},
year = {2026},
month = apr,
volume = {16},
number = {1},
pages = {15297},
publisher = {Nature Publishing Group},
issn = {2045-2322},
doi = {10.1038/
url = {https://
pmid = {41922589},
pmcid = {PMC13181115}
}
RIS
TY - JOUR
AU - Kakuk, Balázs
AU - Csabai, Zsolt
AU - Deim, Zoltán
AU - Torma, Gábor
AU - Fülöp, Ádám
AU - Nagy, Gergely Ármin
AU - Dani, Virág Éva
AU - Tombácz, Dóra
AU - Boldogkői, Zsolt
TI - Multi-platform profiling reveals host- and cell -type-specific pseudorabies virus gene expression
T2 - Scientific reports
J2 - Sci Rep
PY - 2026
DA - 2026/
VL - 16
IS - 1
SP - 15297
SN - 2045-2322
PB - Nature Publishing Group
DO - 10.1038/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.1038/
"type": "article-journal",
"title": "Multi-platform profiling reveals host- and cell -type-specific pseudorabies virus gene expression",
"container-title": "Scientific reports",
"author": [
{
"family": "Kakuk",
"given": "Balázs"
},
{
"family": "Csabai",
"given": "Zsolt"
},
{
"family": "Deim",
"given": "Zoltán"
},
{
"family": "Torma",
"given": "Gábor"
},
{
"family": "Fülöp",
"given": "Ádám"
},
{
"family": "Nagy",
"given": "Gergely Ármin"
},
{
"family": "Dani",
"given": "Virág Éva"
},
{
"family": "Tombácz",
"given": "Dóra"
},
{
"family": "Boldogkői",
"given": "Zsolt"
}
],
"container-title-short":
"volume": "16",
"issue": "1",
"page": "15297",
"DOI": "10.1038/
"PMID": "41922589",
"PMCID": "PMC13181115",
"ISSN": "2045-2322",
"publisher": "Nature Publishing Group",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
1
]
]
}
}
The tracing map gets a citation of its own once an author has validated it and it has a DOI.
Similar papers
The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.
- [1] doi:10.1016/j.xgen.2025.101101 [code]
- Transcript-guided targeted cell enrichment for scalable single-nucleus RNA sequencing.Journal: Cell genomicsIn common: SAMtools, igraph, cowplot, 3 other tools, genetics / omics, cellular / molecular, 2 references
- [2] doi:10.1016/j.xgen.2025.101079 [code]
- Incomplete lineage sorting of segmental duplications defines the human chromosome 2 fusion site early during African great ape speciation.Journal: Cell genomicsIn common: SAMtools, igraph, cowplot, 3 other tools, cellular / molecular, 2 references
- [3] doi:10.1038/s41467-025-65712-0 [code]
- Multimodal single cell analyses reveal gene networks of planarian stem cell differentiation.Journal: Nature communicationsIn common: SAMtools, igraph, cowplot, 3 other tools, genetics / omics, cellular / molecular, 2 references
- [4] doi:10.1371/journal.pone.0266405 [code]
- Analysis of modular gene co-expression networks reveals molecular pathways underlying Alzheimer's disease and progressive supranuclear palsy.Journal: PloS oneIn common: SAMtools, igraph, cowplot, 3 other tools, cellular / molecular, 1 reference
- [5] doi:10.1038/s41467-024-47945-7 [code]
- A human neural crest model reveals the developmental impact of neuroblastoma-associated
chromosomal aberrations. Journal: Nature communicationsIn common: SAMtools, igraph, cowplot, 3 other tools, genetics / omics, other condition, 1 reference - [6] doi:10.1038/s41467-024-49608-z [code]
- A multiomic atlas of the aging hippocampus reveals molecular changes in response to environmental enrichment.Journal: Nature communicationsIn common: SAMtools, cowplot, data.table, 2 other tools, genetics / omics, cellular / molecular, 2 references
- [7] doi:10.1038/s41467-025-58293-5 [code]
- Alternative splicing across the C. elegans nervous system.Journal: Nature communicationsIn common: SAMtools, igraph, cowplot, 2 other tools, genetics / omics, cellular / molecular, 2 references
- [8] doi:10.1038/s41467-026-70382-7 [code]
- Identification of cis-regulatory elements provides insights into tissue-specific gene regulation in the sheep genome.Journal: Nature communicationsIn common: SAMtools, cowplot, data.table, 2 other tools, genetics / omics, cellular / molecular, 2 references
- [9] doi:10.1093/bioinformatics/btae549 [code]
- Scywalker: scalable end-to-end data analysis workflow for long-read single-cell transcriptome sequencing.Journal: Bioinformatics (Oxford, England)In common: SAMtools, ggplot2, tidyverse, genetics / omics, 3 references
- [10] doi:10.1038/s41593-024-01636-0 [code]
- Analysis of gene expression in the postmortem brain of neurotypical Black Americans reveals contributions of genetic ancestry.Journal: Nature neuroscienceIn common: SAMtools, igraph, data.table, 2 other tools, genetics / omics, cellular / molecular, 1 reference
Contribute
The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.
Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Validate its tracing map
You validate the map as this page shows it: 2 repositories of the authors' code, each at its verified commit and with its license, 43 scripts, and 0 matches between paragraphs and code (see the Code and Map sections). It then receives a DOI on Zenodo, with you (your ORCID iD) and OSCR as its creators; the code itself is not deposited.
The map's fingerprint: sha256:051e13507d0b27a2…
Add the badge to the code's README
If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.
Markdown
<!-- oscr-badge:start -->
[](https://openscicode.org/badge/doi/10.1038/s41598-026-45990-4)
<!-- oscr-badge:end -->reStructuredText
.. oscr-badge:start
.. image:: https://openscicode.org/badge/doi/10.1038/s41598-026-45990-4.svg
:target: https://openscicode.org/badge/doi/10.1038/s41598-026-45990-4
:alt: OSCR
.. oscr-badge:endHTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.1038/s41598-026-45990-4"><img src="https://openscicode.org/badge/doi/10.1038/s41598-026-45990-4.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".
- Balays/Rlyeh on GitHub (add a README there)
- Balays/VALAR-PRV-MDBIO-4cell on GitHub (add a README there)
If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge page.
Request its removal
To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).
Discussion, reproductions, activity
Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.
Report a mismatch between the code and the paper · Report a code error (signed in)
Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.
Report a reproduction failure (signed in)
Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
