Package 'OrnTx'

Align RNA-seq reads using STAR

Description

Aligns FASTQ files to a reference genome using STAR and generates ReadsPerGene.out.tab count files compatible with importCustomAtlas(). Requires STAR to be installed.

Usage

alignReads(
  fastq_dir,
  index_dir,
  output_dir = "aligned",
  paired = TRUE,
  threads = 16L,
  ram_gb = 60,
  strandedness = "reverse"
)

Arguments

fastq_dir	Directory containing cleaned FASTQ files.
index_dir	Path to STAR genome index directory.
output_dir	Directory for alignment output.
paired	Logical. TRUE for paired-end (default).
threads	Threads per sample (default 16).
ram_gb	RAM for BAM sorting in GB (default 60).
strandedness	Library strandedness (default "reverse").

Value

Invisibly returns paths to count files.

Examples

checkTools()
## Not run: 
alignReads(
  fastq_dir  = "clean_reads/",
  index_dir  = "star_index/",
  output_dir = "aligned/"
)

## End(Not run)

---

Annotate DE results

Description

Adds locus names to DE results from runDE().

Usage

annotateDEResults(de_results, species = "Rosa chinensis")

Arguments

de_results	data.frame from runDE() with a gene_id column.
species	Character. Default "Rosa chinensis".

Value

data.frame with locus_name and gene_biotype columns added.

Examples

data("rosa_example", package = "OrnTx")
de <- runDE(rosa_example,
            design   = ~ tissue_simple,
            contrast = c("tissue_simple", "petal", "abscission zone"))
head(annotateDEResults(de))

---

Annotate gene IDs with Rosa chinensis locus information

Description

Maps generic gene IDs (gene0, gene1, etc.) from the RchiOBHm-V2 reference genome to official Rosa chinensis locus names and gene biotype information.

Usage

annotateGenes(gene_ids, species = "Rosa chinensis")

Arguments

gene_ids	Character vector of gene IDs to annotate (e.g., c("gene24707", "gene47555")).
species	Character. Currently supports "Rosa chinensis".

Value

A data.frame with columns:

• gene_id — input gene ID

• locus_name — official RchiOBHm-V2 locus name

• gene_biotype — gene type (protein_coding, lncRNA, etc.)

Examples

ann <- annotateGenes(c("gene10715", "gene21520", "gene37167"))
print(ann)

---

Annotate gene IDs using NCBI functional annotation

Description

Adds functional product descriptions to DE results when gene IDs are in NCBI LOC format (e.g., LOC112190511). This complements annotateGenes() which works with RchiOBHm locus names.

Usage

annotateWithNCBI(de_results)

Arguments

de_results

A data.frame with a gene_id column containing NCBI LOC gene identifiers.

Value

The input data.frame with product column added.

Examples

data(rose_ncbi_annotation)
head(rose_ncbi_annotation)

data(rosa_ncbi_annotation)
de <- data.frame(gene_id = rose_ncbi_annotation$ncbi_gene_id[1:5],
                 log2FoldChange = rnorm(5))
annotateWithNCBI(de)

---

Annotate DE results with trait information

Description

Identifies known floriculture trait genes in differential expression results.

Usage

annotateWithTraits(
  de_results,
  trait = "all",
  species = "all",
  gene_col = NULL,
  mapping = NULL
)

Arguments

de_results	A data.frame from runDE().
trait	Trait categories to check, or 'all'.
species	Species for evidence filtering, or 'all'.
gene_col	Optional column name containing gene symbols.
mapping	Optional data.frame with gene_id and arabidopsis_id columns for ortholog-based matching.

Value

A data.frame with the original columns plus additional trait annotation columns merged from the floriculture trait database.

Examples

color_genes <- getFlowerGenes(trait = 'flower_color')
head(color_genes[, c('gene_symbol', 'pathway')])

  de <- data.frame(
    gene_id        = c('CHS', 'CHI', 'F3H', 'gene001'),
    log2FoldChange = c(2.1, 1.8, 1.5, -0.3),
    significant    = c(TRUE, TRUE, TRUE, FALSE)
  )
  annotateWithTraits(de, trait = 'flower_color', gene_col = 'gene_id')

---

Build an expression atlas from count data

Description

Build an expression atlas from count data

Usage

buildAtlas(se, group_var = "stage", assay_name = "counts")

Arguments

se	A SummarizedExperiment object from importRosaCounts()
group_var	Column name in colData for grouping samples
assay_name	Which assay to use (default "counts")

Value

A SummarizedExperiment with atlas slot

Examples

library(OrnTx)
data(rosa_example)
se_norm <- normalizeCounts(rosa_example, method = "CPM")

---

Build STAR genome index

Description

Builds a STAR genome index from FASTA and GTF. Required once per genome. Requires STAR to be installed.

Usage

buildGenomeIndex(
  genome_fasta,
  gtf_file,
  index_dir = "star_index",
  threads = 16L,
  ram_gb = 60,
  sa_index_nbases = 13L
)

Arguments

genome_fasta	Path to reference genome FASTA file.
gtf_file	Path to genome annotation GTF file.
index_dir	Output directory for genome index.
threads	Threads for index building (default 16).
ram_gb	Available RAM in GB (default 60).
sa_index_nbases	SA index parameter (default 13).

Value

Invisibly returns the index directory path.

Examples

checkTools()
## Not run: 
buildGenomeIndex(
  genome_fasta = "rosa_genome.fna",
  gtf_file     = "rosa_annotation.gtf",
  index_dir    = "star_index/"
)

## End(Not run)

---

Build Rosa chinensis Expression Atlas

Description

Build Rosa chinensis Expression Atlas

Usage

buildRosaAtlas(
  counts_dir,
  metadata_file,
  strandedness = "reverse",
  min_samples = 10
)

Arguments

counts_dir	Path to directory containing ReadsPerGene.out.tab files
metadata_file	Path to SraRunTable.txt
strandedness	One of "reverse", "forward", "unstranded"
min_samples	Minimum samples a gene must be expressed in

Value

A SummarizedExperiment object

Examples

ann <- getRosaAnnotation()
nrow(ann)
## Not run: 
se <- buildRosaAtlas(
  counts_dir    = "path/to/counts",
  metadata_file = "path/to/SraRunTable.txt"
)

## End(Not run)

---

Check which RNA-seq tools are available

Description

Checks fastp, STAR, fasterq-dump availability.

Usage

checkTools()

Value

Named logical vector of tool availability.

Examples

checkTools()

---

Download RNA-seq data from NCBI SRA

Description

Downloads SRA files and converts to FASTQ using fasterq-dump or direct AWS S3 download.

Usage

downloadSRA(
  accessions,
  output_dir = "raw_reads",
  threads = 4L,
  compress = TRUE,
  method = c("aws", "fasterq-dump")
)

Arguments

accessions	Character vector of SRA run accessions.
output_dir	Directory to save FASTQ files.
threads	Threads for fasterq-dump (default 4).
compress	Compress output with gzip (default TRUE).
method	"fasterq-dump" or "aws" (direct S3, faster).

Value

Invisibly returns paths to downloaded FASTQ files.

Examples

checkTools()
## Not run: 
downloadSRA(
  accessions = c("SRR10160942", "SRR10160944"),
  output_dir = "raw_reads/",
  threads    = 4
)

## End(Not run)

---

Find orthologs in floriculture trait database

Description

Maps gene symbols or Arabidopsis IDs to curated trait gene information.

Usage

findOrthologs(gene_ids, id_type = c("symbol", "arabidopsis"), species = "any")

Arguments

gene_ids	Character vector of gene IDs to query.
id_type	One of "symbol" or "arabidopsis".
species	Source species (informational).

Value

A data.frame of matched trait genes.

Examples

findOrthologs(c("CHS", "DFR", "ANS"), id_type = "symbol")

---

Floriculture Trait Gene Database

Description

A curated database of 64 genes associated with economically important floriculture traits, anchored to Arabidopsis thaliana gene IDs to enable cross-species queries regardless of annotation quality. Covers flower color, floral scent, senescence/vase life, floral development, and transcriptional regulation.

Usage

data(floriculture_traits)

Format

A data frame with 64 rows and 9 variables:

gene_symbol

Gene symbol (e.g., "CHS", "DFR", "FT")

arabidopsis_id

Arabidopsis thaliana AGI locus ID

trait

Specific trait subcategory

trait_category

Broad trait category

pathway

Biochemical pathway name

rose_evidence

Evidence level in Rosa chinensis

marigold_evidence

Evidence level in Tagetes erecta

key_pmid

Key PubMed reference ID

Value

A data.frame with 64 rows and columns including gene symbol, trait category, Arabidopsis ortholog, and Rosa chinensis gene ID.

Source

Literature-curated from published floriculture transcriptomics studies. See key_pmid column for references.

---

Get curated floriculture trait gene sets

Description

Returns curated gene sets anchored to Arabidopsis orthologs for cross-species trait analysis.

Usage

getFlowerGenes(trait = "all", species = "all", evidence = "all")

Arguments

trait	Character. One of "flower_color", "scent", "senescence", "development", "regulatory", or "all".
species	Character. "Rosa chinensis", "Tagetes erecta", or "all".
evidence	Character. "Strong", "Moderate", "Weak", or "all".

Value

A data.frame of curated trait genes.

Examples

color_genes <- getFlowerGenes(trait = "flower_color")
head(color_genes)

---

Get Rosa chinensis annotation database

Description

Returns the complete built-in annotation table for Rosa chinensis RchiOBHm-V2 genome containing 51,302 genes.

Usage

getRosaAnnotation()

Value

A data.frame with columns gene_id, locus_name, gene_biotype.

Examples

ann <- getRosaAnnotation()
head(ann)
nrow(ann)

---

Import count data from any RNA-seq tool

Description

Accepts count matrices from STAR, featureCounts, HTSeq, Salmon, or any pre-loaded matrix. Unlike importCustomAtlas() which reads STAR output files, this function works with already-loaded matrices or files from any quantification tool.

Usage

importCountMatrix(
  counts,
  metadata,
  species = "Unknown species",
  file_format = "auto",
  sample_col = NULL,
  min_count = 5L,
  min_samples = 3L
)

Arguments

counts	File path or pre-loaded matrix/data.frame with genes as rows and samples as columns.
metadata	Data.frame with sample metadata. Row names or first column must match column names of counts.
species	Scientific name of the plant species.
file_format	One of "auto", "STAR", "featureCounts", "HTSeq", "Salmon", "matrix". Default "auto" detects format.
sample_col	Column in metadata containing sample IDs.
min_count	Minimum count for filtering (default 5).
min_samples	Minimum samples expressing gene (default 3).

Value

A SummarizedExperiment object.

Examples

counts <- matrix(rpois(500, 10), nrow=50, ncol=10)
rownames(counts) <- paste0("gene", 1:50)
colnames(counts) <- paste0("sample", 1:10)
meta <- data.frame(Sample = colnames(counts),
                   tissue = rep(c("petal","leaf"), 5))
se <- importCountMatrix(counts, meta,
  species = "Rosa chinensis", sample_col = "Sample")

---

Import RNA-seq data from any plant species into OrnTx

Description

A universal import function that accepts STAR ReadsPerGene.out.tab files from any plant species. Unlike buildRosaAtlas() which is Rosa chinensis specific, this function works for any plant species including ornamental flowers, fruit crops, vegetables, and model plants.

Usage

importCustomAtlas(
  counts_dir,
  metadata_file,
  species = "Unknown species",
  sample_col = NULL,
  strandedness = c("reverse", "forward", "unstranded"),
  min_count = 5L,
  min_samples = 3L,
  annotation_file = NULL,
  sep = ","
)

Arguments

counts_dir	Character. Path to directory containing ReadsPerGene.out.tab files from STAR alignment.
metadata_file	Character. Path to a CSV or TSV file with sample metadata. Must have a column matching sample IDs. See Details.
species	Character. Scientific name of the plant species, e.g., "Chrysanthemum morifolium", "Tagetes erecta".
sample_col	Character. Column name in metadata containing sample IDs that match count file names (default "Run").
strandedness	Character. Library strandedness: "reverse" (most dUTP libraries, default), "forward", or "unstranded".
min_count	Integer. Minimum count threshold for filtering (default 5).
min_samples	Integer. Minimum number of samples a gene must be expressed in (default 3).
annotation_file	Character. Optional path to GTF/GFF file for gene name annotation. If provided, gene IDs are mapped to gene names automatically.
sep	Character. Metadata file separator: "," for CSV (default) or "\t" for TSV.

Details

The metadata file should contain one row per sample with at minimum a column of sample IDs matching the count file names. For example, if count files are named Sample1_ReadsPerGene.out.tab and Sample2_ReadsPerGene.out.tab, the metadata must have a column containing Sample1 and Sample2.

Recommended metadata columns for ornamental plant studies:

• tissue - tissue type (petal, leaf, root, etc.)

• dev_stage - developmental stage

• cultivar - cultivar or accession name

• treatment - experimental treatment

• replicate - biological replicate number

Value

A SummarizedExperiment object with:

• assays: raw counts matrix

• colData: sample metadata

• rowData: gene annotation (if GTF provided)

• metadata: species name and import parameters

Examples

# Check available tools
ann <- getRosaAnnotation()
nrow(ann)
## Not run: 
# Example 1: Chrysanthemum morifolium
se <- importCustomAtlas(
  counts_dir    = "path/to/chrysanthemum/counts/",
  metadata_file = "chrysanthemum_metadata.csv",
  species       = "Chrysanthemum morifolium",
  strandedness  = "reverse"
)

# Example 2: Tagetes erecta (marigold)
se <- importCustomAtlas(
  counts_dir    = "path/to/marigold/counts/",
  metadata_file = "marigold_metadata.csv",
  species       = "Tagetes erecta",
  annotation_file = "marigold_genome.gtf"
)

# Example 3: Any plant species
se <- importCustomAtlas(
  counts_dir    = "path/to/counts/",
  metadata_file = "metadata.csv",
  species       = "Tulipa gesneriana"
)

# After import - standard analysis works identically
se_norm <- normalizeCounts(se, method = "CPM")
plotPCA(se_norm, color_by = "tissue")
runDE(se, design = ~ tissue,
      contrast = c("tissue", "petal", "leaf"))

## End(Not run)

---

Import STAR count files into OrnTx

Description

Import STAR count files into OrnTx

Usage

importRosaCounts(file_paths, col_data, strandedness = "reverse")

Arguments

file_paths	Named character vector of paths to ReadsPerGene.out.tab files.
col_data	A data.frame with sample metadata.
strandedness	One of "reverse", "forward", "unstranded".

Value

A SummarizedExperiment object.

Examples

ann <- getRosaAnnotation()
head(ann)
## Not run: 
files <- c(Sample1 = "path/to/sample1/ReadsPerGene.out.tab")
importRosaCounts(files, col_data = metadata)

## End(Not run)

---

Marigold Carotenoid Gene Mapping

Description

A curated mapping of Tagetes erecta gene IDs to carotenoid biosynthesis gene symbols and Arabidopsis orthologs. Based on differential expression analysis between orange (V-01) and yellow (V-01M) flower color genotypes.

Usage

data(marigold_carotenoid_genes)

Format

A data frame with 4 rows and 3 variables:

gene_id

Tagetes erecta gene ID (QVD17 format)

gene_symbol

Carotenoid gene symbol (CCS, BCH, LCYe, PSY)

arabidopsis_id

Arabidopsis thaliana ortholog AGI ID

Value

A data.frame containing carotenoid biosynthesis gene identifiers and annotations for Tagetes erecta.

Source

Differential expression analysis of NCBI BioProject PRJNA562616 using OrnTx runDE().

---

Normalize count data

Description

Normalize count data

Usage

normalizeCounts(se, method = c("CPM", "TMM", "DESeq2_vst"), design = ~1)

Arguments

se	A SummarizedExperiment object.
method	One of "CPM", "TMM", or "DESeq2_vst".
design	Optional formula for DESeq2 methods.

Value

SummarizedExperiment with normalized assay added.

Examples

data(rosa_example)
se_norm <- normalizeCounts(rosa_example, method = "CPM")

---

OrnTx ggplot2 theme

Description

OrnTx ggplot2 theme

Usage

ornTheme(base_size = 12)

Arguments

base_size

Base font size

Value

A ggplot2 theme

Examples

p <- ggplot2::ggplot(data.frame(x=1:5, y=1:5),
       ggplot2::aes(x, y)) + ornTheme()
print(p)

---

Plot expression atlas heatmap

Description

Plot expression atlas heatmap

Usage

plotAtlas(atlas, top_n = 50, title = "Expression Atlas")

Arguments

atlas	A SummarizedExperiment from buildAtlas()
top_n	Number of top variable genes to show
title	Plot title

Value

A ggplot2 heatmap object

Examples

data(rosa_example)
se_norm <- normalizeCounts(rosa_example, method = 'CPM')
atlas <- buildAtlas(se_norm, group_var = 'tissue_simple',
                    assay_name = 'CPM')
plotAtlas(atlas, top_n = 30, title = 'Rosa chinensis Atlas')

data(rosa_example)
se_norm <- normalizeCounts(rosa_example, method = "CPM")
atlas <- buildAtlas(se_norm, group_var = "tissue_simple",
                    assay_name = "CPM")
plotAtlas(atlas, top_n = 30, title = "Rosa chinensis Atlas")

---

PCA plot of expression data

Description

PCA plot of expression data

Usage

plotPCA(
  se,
  assay_name = "counts",
  color_by = "stage",
  shape_by = NULL,
  label_points = TRUE
)

Arguments

se	A SummarizedExperiment object
assay_name	Which assay to use
color_by	Column in colData for point color
shape_by	Column in colData for point shape
label_points	Show sample labels

Value

A ggplot2 PCA plot

Examples

data(rosa_example)
se_norm <- normalizeCounts(rosa_example, method = "CPM")

---

Volcano plot of DE results

Description

Volcano plot of DE results

Usage

plotVolcano(
  de_results,
  alpha = 0.05,
  lfc_threshold = 1,
  top_n = 20,
  title = "Volcano Plot"
)

Arguments

de_results	Data.frame from runDE()
alpha	Significance threshold
lfc_threshold	LFC threshold
top_n	Number of genes to label
title	Plot title

Value

A ggplot2 volcano plot

Examples

data(rosa_example)
results <- runDE(rosa_example, design = ~ tissue_simple,
  contrast = c('tissue_simple', 'petal', 'abscission zone'))
plotVolcano(results, title = 'Petal vs AZ')

data(rosa_example)
results <- runDE(rosa_example,
  design   = ~ tissue_simple,
  contrast = c("tissue_simple", "petal", "abscission zone"))
plotVolcano(results, title = "Petal vs Abscission Zone")

---

Rosa chinensis Gene Annotation Database

Description

A curated annotation table mapping generic gene IDs from the RchiOBHm-V2 reference genome to official Rosa chinensis locus names and gene biotype classifications.

Usage

data(rosa_annotation)

Format

A data frame with 51,302 rows and 3 variables:

gene_id

Generic gene identifier (e.g., "gene0", "gene1")

locus_name

Official RchiOBHm-V2 locus name

gene_biotype

Gene biotype (protein_coding, lncRNA, etc.)

Value

A data.frame with gene annotation data for Rosa chinensis, including gene IDs, symbols, descriptions, and chromosomal coordinates.

Source

NCBI RefSeq GCF_002994745.2 (RchiOBHm-V2)

References

Hibrand Saint-Oyant L, et al. (2018) Nature Plants 4: 473-484.

---

Rosa chinensis Example Expression Dataset

Description

A small subset of the OrnTx Rosa chinensis expression atlas for use in package examples and testing. Contains 500 highly variable genes across 6 samples: 3 petal and 3 abscission zone.

Usage

data(rosa_example)

Format

A SummarizedExperiment with 500 genes x 6 samples.

assays

counts: raw read counts matrix

colData

sample metadata including tissue_simple

Value

A SummarizedExperiment object with 6 RNA-seq samples (3 petal, 3 abscission zone) from Rosa chinensis.

Source

NCBI SRA BioProjects PRJNA562083 and PRJNA594099

---

Rosa chinensis NCBI Functional Annotation

Description

Functional annotation for 30,924 Rosa chinensis genes from the NCBI RefSeq annotation of the RchiOBHm-V2 reference genome (GCF_002994745.2). Contains gene product descriptions extracted from the genomic GTF file. Gene IDs use NCBI LOC format (e.g., LOC112190511).

Usage

data(rose_ncbi_annotation)

Format

A data frame with 30,924 rows and 2 variables:

ncbi_gene_id

NCBI gene identifier (LOC format)

product

Gene product description from NCBI annotation

Value

A data.frame with NCBI-sourced gene annotation for Rosa chinensis, including RefSeq IDs and functional descriptions.

Source

NCBI RefSeq GCF_002994745.2 (RchiOBHm-V2) GTF annotation. https://www.ncbi.nlm.nih.gov/datasets/genome/GCF_002994745.2/

---

Differential Expression Analysis

Description

Differential Expression Analysis

Usage

runDE(
  se,
  design = ~tissue_clean,
  contrast = NULL,
  alpha = 0.05,
  lfc_threshold = 1
)

Arguments

se	A SummarizedExperiment object
design	Formula for experimental design
contrast	Character vector of length 3
alpha	Significance threshold
lfc_threshold	Minimum log2 fold change

Value

A data.frame of DE results

Examples

data(rosa_example)
results <- runDE(rosa_example,
  design   = ~ tissue_simple,
  contrast = c("tissue_simple", "petal", "abscission zone"))

---

Run complete RNA-seq pipeline from FASTQ to SummarizedExperiment

Description

Convenience wrapper running the complete OrnTx pipeline: QC (fastp) -> Alignment (STAR) -> Import -> Normalize. For SRA download first, use downloadSRA() separately. Requires fastp and STAR installed (Linux/macOS/HPC only).

Usage

runFullPipeline(
  fastq_dir,
  genome_fasta,
  gtf_file,
  metadata_file,
  species = "Unknown species",
  work_dir = "ornAtlas_pipeline",
  threads = 16L,
  strandedness = "reverse",
  paired = TRUE,
  skip_qc = FALSE,
  skip_index = FALSE
)

Arguments

fastq_dir	Directory containing raw FASTQ files.
genome_fasta	Path to reference genome FASTA.
gtf_file	Path to genome annotation GTF.
metadata_file	Path to sample metadata CSV/TSV.
species	Scientific name of the plant species.
work_dir	Working directory for intermediate files.
threads	Threads for alignment (default 16).
strandedness	Library strandedness (default "reverse").
paired	Logical. Paired-end data (default TRUE).
skip_qc	Logical. Skip fastp QC step (default FALSE).
skip_index	Logical. Skip index building if built.

Value

A CPM-normalized SummarizedExperiment.

Examples

checkTools()
## Not run: 
se <- runFullPipeline(
  fastq_dir     = "raw_reads/",
  genome_fasta  = "rosa_genome.fna",
  gtf_file      = "rosa_annotation.gtf",
  metadata_file = "metadata.csv",
  species       = "Rosa chinensis",
  threads       = 16
)
plotPCA(se, color_by = "tissue")

## End(Not run)

---

Quality control of FASTQ files using fastp

Description

Runs fastp QC on FASTQ files. Supports paired and single-end data. Requires fastp to be installed.

Usage

runQC(
  input_dir,
  output_dir = "clean_reads",
  paired = TRUE,
  threads = 4L,
  min_length = 36L,
  quality = 20L
)

Arguments

input_dir	Directory containing raw FASTQ files.
output_dir	Directory for clean FASTQ output.
paired	Logical. TRUE for paired-end (default).
threads	Threads per sample (default 4).
min_length	Minimum read length after trimming (default 36).
quality	Minimum base quality score (default 20).

Value

Invisibly returns paths to cleaned FASTQ files.

Examples

checkTools()
## Not run: 
runQC(input_dir="raw_reads/", output_dir="clean_reads/")

## End(Not run)

---

Standardize developmental stage vocabulary

Description

Harmonizes inconsistent developmental stage names across studies into a controlled vocabulary. Solves the problem of "bud", "Bud", "floral bud", "Stage 1" all meaning the same thing in different publications.

Usage

standardizeStage(stage_vector)

Arguments

stage_vector

Character vector of stage names to standardize.

Value

Character vector of standardized stage names.

Examples

raw_stages <- c("bud", "Bud", "floral bud", "Stage 1",
                "open flower", "OF", "full bloom", "senescent")
standardizeStage(raw_stages)

---