Type: Package
Title: Visualizing the Elements Within Bio-Sequences
Version: 1.0.3
Maintainer: Shiqi Zhao <zhaosq89@163.com>
Description: Visualizing the types and distribution of elements within bio-sequences. At the same time, We have developed a geom layer, geom_rrect(), that can generate rounded rectangles. No external references are used in the development of this package.
Encoding: UTF-8
License: Artistic-2.0
Language: en-US
RoxygenNote: 7.2.3
Repository: CRAN
Imports: dplyr, ggplot2, httr, RColorBrewer, seqinr, stringr, tidyr, magrittr, ggtree, treeio, ggh4x, shiny
NeedsCompilation: no
Packaged: 2025-04-11 15:17:07 UTC; zhaoshiqi
Author: Shiqi Zhao ORCID iD [aut, cre, cph]
Date/Publication: 2025-04-11 16:30:02 UTC

BioVizSeq shiny app start function.

Description

BioVizSeq shiny app start function.

Usage

biovizseq()

Value

Shinyapp: BioVizSeq shiny app.

Author(s)

Shiqi Zhao

Examples

# 1. Library BioVizSeq package
library(BioVizSeq)

cdd_plot

Description

Visualization of domain in CDD file

Usage

cdd_plot(
  cdd_file,
  fasta_file,
  the_order = NULL,
  domain_select = NULL,
  shape = "RoundRect",
  r = 0.3,
  legend_size = 15,
  domain_color = NULL
)

Arguments

cdd_file

The path of cdd file.

fasta_file

The path of fasta file.

the_order

The path of order file. A List of Gene ID , One ID Per Line.

domain_select

The domain ID which you want to align with.

shape

RoundRect or Rect.

r

The radius of rounded corners.

legend_size

The size of legend.

domain_color

The color set of domain.

Value

p

Author(s)

Shiqi Zhao

Examples

hitdata_path <- system.file("extdata", "hitdata.txt", package = "BioVizSeq")
fa_path <- system.file("extdata", "idpep.fa", package = "BioVizSeq")
cdd_plot(hitdata_path, fa_path)

order_path <- system.file("extdata", "order.csv", package = "BioVizSeq")
cdd_plot(hitdata_path, fa_path, the_order = order_path)

cdd_to_loc

Description

Extract the location information of domain from cdd file

Usage

cdd_to_loc(cdd_file)

Arguments

cdd_file

CDD file.

Value

data.frame

Author(s)

Shiqi Zhao

Examples

hitdata_path <- system.file("extdata", "hitdata.txt", package = "BioVizSeq")
cdd_file <- readLines(hitdata_path)
domain_loc <- cdd_to_loc(cdd_file)

combi_p

Description

Get ggplot2 files to facilitate free combination in patchwork

Usage

combi_p(
  tree_path,
  gff_path = NULL,
  meme_path = NULL,
  pfam_path = NULL,
  cdd_path = NULL,
  fa_path = NULL,
  smart_path = FALSE,
  plantcare_path = NULL,
  promoter_length = NULL,
  renamefile = NULL,
  groupfile = NULL,
  shape = "RoundRect",
  r = 0.3,
  legend_size = 6
)

Arguments

tree_path

The path of tree file (.newick).

gff_path

The path of .gff/gtf file.

meme_path

The path of .meme/mast file.

pfam_path

The path of pfam result file (.tsv).

cdd_path

The path of cdd result file (.txt).

fa_path

The path of protein file (.fa/fasta).

smart_path

Do SMART or not. (TRUE or FALSE)

plantcare_path

The path of plantcare file (.tab).

promoter_length

The length of promoter.

renamefile

Rename file. Two cols: new_name and old_name.

groupfile

Group information. Two cols: label and Group.

shape

RoundRect or Rect.

r

The radius of rounded corners.

legend_size

The size of legend.

Value

list

Author(s)

Shiqi Zhao

Examples

tree_path <- system.file("extdata", "idpep.nwk", package = "BioVizSeq")
plot_file <- combi_p(tree_path)

fastaleng

Description

Statistical sequence length

Usage

fastaleng(fasta_file)

Arguments

fasta_file

The path of protein fasta file.

Value

data.frame

Author(s)

Shiqi Zhao

Examples

fasta_path <- system.file("extdata", "idpep.fa", package = "BioVizSeq") 
fastaleng(fasta_path)

geom_rrect

Description

Rounded rectangle

Usage

geom_rrect(
  mapping = NULL,
  data = NULL,
  stat = "identity",
  position = "identity",
  r = 0.2,
  ...,
  na.rm = FALSE,
  show.legend = NA,
  inherit.aes = TRUE
)

Arguments

mapping

Set of aesthetic mappings created by aes. If specified and inherit.aes = TRUE (the default), it is combined with the default mapping at the top level of the plot. You must supply mapping if there is no plot mapping.

data

A data.frame, or other object, will override the plot data. All objects will be fortified to produce a data frame.

stat

Name of stat to modify data.

position

The position adjustment to use for overlapping points on this layer.

r

The radius of rounded corners.

...

additional parameter, e.g. color, linewidth, alpha.

na.rm

If "FALSE" (default), missing values are removed with a warning. If "TRUE", missing values are silently removed, logical.

show.legend

Whether to show legend, logical.

inherit.aes

Whether to inherit aesthetic mappings, logical, defaults to "TRUE".

Details

draws rounded rectangle by using the locations of the four corners (xmin, xmax, ymin and ymax) like geom_rect().

Value

ggplot object

Aesthetics

geom_rrect() understands the following aesthetics (required aesthetics are in bold):

Learn more about setting these aesthetics in vignette("ggplot2-specs").

Author(s)

Shiqi Zhao

Examples

library(ggplot2)
df <- data.frame(
 xmin = c(1, 2, 3),
 xmax = c(2, 3, 4),
 ymin = c(1, 2, 3),
 ymax = c(2, 3, 4),
 category = c("A", "B", "C")
 )
 
 p <- ggplot(df) +
   geom_rrect(aes(xmin = xmin, xmax = xmax, 
              ymin = ymin, ymax = ymax, fill = category), 
             r = 0.4, linewidth = 1, colour = "black") 
 
 print(p)

gff_plot

Description

Visualization of element in gff or gtf file

Usage

gff_plot(
  gff_file,
  the_order = NULL,
  shape = "Rect",
  r = 0.3,
  legend_size = 15,
  element_color = NULL
)

Arguments

gff_file

The path of gff file.

the_order

The path of order of mRNA. It is also the mRNA you want to showcase. A List of Gene ID , One ID Per Line.

shape

RoundRect or Rect.

r

The radius of rounded corners.

legend_size

The size of legend.

element_color

The color set of element.

Value

p

Author(s)

Shiqi Zhao

Examples

gff_path <- system.file("extdata", "test.gff", package = "BioVizSeq")
gff_plot(gff_path)

gff_to_loc

Description

Extract the location information of element from gff or gtf file

Usage

gff_to_loc(gff_data, mRNA_ID = NULL)

Arguments

gff_data

gff file.

mRNA_ID

The mRNA you selected. If NULL, it means selecting all mRNAs.

Value

list

Author(s)

Shiqi Zhao

Examples


gff_path <- system.file("extdata", "test.gff", package = "BioVizSeq")
gff_data <- read.table(gff_path, header = FALSE, sep = '\t')
gff_loc <- gff_to_loc(gff_data)

ID_path <- system.file("extdata", "ID_select.csv", package = "BioVizSeq")
mRNA_ID <- readLines(ID_path) 
gff_loc <- gff_to_loc(gff_data, mRNA_ID=mRNA_ID)

Global Variables Declaration

Description

Global Variables

Details

This block declares global variables to avoid R CMD check warnings.

meme_plot

Description

Visualization of motif in meme file or mast file

Usage

meme_plot(
  meme_file,
  the_order = NULL,
  motif_select = NULL,
  shape = "RoundRect",
  show_motif_id = FALSE,
  r = 0.3,
  legend_size = 15,
  motif_color = NULL
)

Arguments

meme_file

The path of meme file or mast file.

the_order

The path of order file. A List of Gene ID , One ID Per Line.

motif_select

The motif ID which you want to align with.

shape

RoundRect or Rect.

show_motif_id

Display the name of the motif.

r

The radius of rounded corners.

legend_size

The size of legend.

motif_color

The color set of motif.

Value

p

Author(s)

Shiqi Zhao

Examples

mast_path <- system.file("extdata", "mast.xml", package = "BioVizSeq")
meme_plot(mast_path)

meme_plot(mast_path, motif_select="1", show_motif_id = TRUE)

order_path <- system.file("extdata", "order.csv", package = "BioVizSeq")
meme_plot(mast_path, the_order=order_path, motif_select="1")

meme_seq

Description

Get motif sequence from meme file or mast file

Usage

meme_seq(meme_file)

Arguments

meme_file

The path of meme file or mast file.

Value

data.frame

Author(s)

Shiqi Zhao

Examples

mast_path <- system.file("extdata", "mast.xml", package = "BioVizSeq")
mast_file <- readLines(mast_path)
motifseq<- meme_seq(mast_file)

meme_to_loc

Description

Extract the location information of motif from mast or meme file

Usage

meme_to_loc(motif_file)

Arguments

motif_file

The motif data of mast or meme file.

Value

list

Author(s)

Shiqi Zhao

Examples


mast_path <- system.file("extdata", "mast.xml", package = "BioVizSeq") 
mast_file <- readLines(mast_path)
motif_loc <- meme_to_loc(mast_file)

motif_plot

Description

Draws multiple rounded rectangle.

Usage

motif_plot(
  motif_loc,
  gene_length,
  the_order = NULL,
  motif_select = NULL,
  shape = "RoundRect",
  show_motif_id = FALSE,
  r = 0.3,
  legend_size = 15,
  motif_color = NULL
)

Arguments

motif_loc

A data.frame contains for columuns: ID, motif, start, end.

gene_length

A data.fram of the length of biosequences. Two columns: ID, length.

the_order

A List of Gene ID , One ID Per Line.

motif_select

The motif ID which you want to align with.

shape

RoundRect or Rect.

show_motif_id

Display the name of the motif.

r

The radius of rounded corners.

legend_size

The size of legend.

motif_color

The color set of motif.

Details

motif_plot() draws multiple rounded rectangle to represent the above elements of biosequences, but not limited to biosequences

Value

p

Author(s)

Shiqi Zhao

Examples

df <- data.frame(
 ID = rep(c("geneA", "geneB", "geneC"), each = 3),
 motif = rep(c("1", "2", "3"), times = 3),
 start = c(1, 3, 6, 1, 6, 10, 10, 7, 17),
 end = c(3, 5, 11, 3, 8, 15, 12, 9, 22)
 )
 
 length_data <- data.frame(
 ID = c("geneA", "geneB", "geneC"),
 length = c(15, 27, 30)
 )
 
 order_data <- c("geneB", "geneA", "geneC")
 
 motif_plot(df, length_data)
 motif_plot(df, length_data, the_order = order_data)

pfam_plot

Description

Visualization of domain in pfam result file

Usage

pfam_plot(
  pfam_file,
  the_order = NULL,
  domain_select = NULL,
  shape = "RoundRect",
  r = 0.3,
  legend_size = 15,
  domain_color = NULL
)

Arguments

pfam_file

The path of meme file or mast file.

the_order

The path of order file. A List of Gene ID , One ID Per Line.

domain_select

The domain ID which you want to align with.

shape

RoundRect or Rect.

r

The radius of rounded corners.

legend_size

The size of legend.

domain_color

The color set of domain.

Value

p

Author(s)

Shiqi Zhao

Examples

pfam_path <- system.file("extdata", "iprscan.tsv", package = "BioVizSeq")
order_path <- system.file("extdata", "order.csv", package = "BioVizSeq")
pfam_plot(pfam_path)
pfam_plot(pfam_path, the_order=order_path)

pfam_to_loc

Description

Extract the location information of domain from pfam result

Usage

pfam_to_loc(pfam_data)

Arguments

pfam_data

The result file (.tsv) of pfam (via InterPro).

Value

list

Author(s)

Shiqi Zhao

Examples

pfam_path <- system.file("extdata", "iprscan.tsv", package = "BioVizSeq")
pfam_file <- read.table(pfam_path, sep='\t', header = FALSE)
motif_loc <- pfam_to_loc(pfam_file)

plantcare_classify

Description

Classify the functions of cis element from Plantcare

Usage

plantcare_classify(plantcare_file)

Arguments

plantcare_file

The result file (.tab) of Plantcare.

Value

data.frame

Author(s)

Shiqi Zhao

Examples

plantcare_path <- system.file("extdata", "plantCARE_output.tab", package = "BioVizSeq") 
plantcare_file <- read.table(plantcare_path, header = FALSE, sep = '\t', quote="")
plantcare_data <- plantcare_classify(plantcare_file)

plantcare_plot

Description

Visualization of cis-element in plantcare result file

Usage

plantcare_plot(
  plantcare_file,
  promoter_length = 2000,
  the_order = NULL,
  shape = "Rect",
  r = 6,
  legend_size = 15,
  element_color = NULL
)

Arguments

plantcare_file

The path of plantcare result file (.tab).

promoter_length

The promoter length.

the_order

The path of order file. A List of Gene ID , One ID Per Line.

shape

RoundRect or Rect.

r

The radius of rounded corners.

legend_size

The size of legend.

element_color

The color set of cis-element.

Value

p

Author(s)

Shiqi Zhao

Examples

plantcare_path <- system.file("extdata", "plantCARE_output.tab", package = "BioVizSeq") 
plantcare_plot(plantcare_path, promoter_length = 2000)

plantcare_plot1

Description

Heatmap of the number of cis-element in plantcare result file

Usage

plantcare_plot1(plantcare_file, the_order = NULL)

Arguments

plantcare_file

The path of plantcare result file (.tab).

the_order

The path of order file. A List of Gene ID , One ID Per Line.

Value

p

Author(s)

Shiqi Zhao

Examples

plantcare_path <- system.file("extdata", "plantCARE_output.tab", package = "BioVizSeq") 
plantcare_plot1(plantcare_path)

plantcare_plot2

Description

Bar plot1 of the number of cis-element in plantcare result file

Usage

plantcare_plot2(plantcare_file, the_order = NULL)

Arguments

plantcare_file

The path of plantcare result file (.tab).

the_order

The path of order file. A List of Gene ID , One ID Per Line.

Value

p

Author(s)

Shiqi Zhao

Examples

plantcare_path <- system.file("extdata", "plantCARE_output.tab", package = "BioVizSeq") 
plantcare_plot2(plantcare_path)

plantcare_plot3

Description

Bar plot2 of the number of cis-element in plantcare result file

Usage

plantcare_plot3(plantcare_file, the_order = NULL)

Arguments

plantcare_file

The path of plantcare result file (.tab).

the_order

The path of order file. A List of Gene ID , One ID Per Line.

Value

p

Author(s)

Shiqi Zhao

Examples

plantcare_path <- system.file("extdata", "plantCARE_output.tab", package = "BioVizSeq") 
plantcare_plot3(plantcare_path)

plantcare_statistic1

Description

Count the number of cis element from Plantcare for heatmap

Usage

plantcare_statistic1(plantcare_data)

Arguments

plantcare_data

The result of plantcare_classify().

Value

data.frame

Author(s)

Shiqi Zhao

Examples

plantcare_path <- system.file("extdata", "plantCARE_output.tab", package = "BioVizSeq") 
plantcare_file <- read.table(plantcare_path, header = FALSE, sep = '\t', quote="")
plantcare_data <- plantcare_classify(plantcare_file)
statistic_data1 <- plantcare_statistic1(plantcare_data)

plantcare_statistic2

Description

Count the number of cis element from Plantcare for Bar chart

Usage

plantcare_statistic2(plantcare_data)

Arguments

plantcare_data

The result of plantcare_classify().

Value

data.frame

Author(s)

Shiqi Zhao

Examples

plantcare_path <- system.file("extdata", "plantCARE_output.tab", package = "BioVizSeq") 
plantcare_file <- read.table(plantcare_path, header = FALSE, sep = '\t', quote="")
plantcare_data <- plantcare_classify(plantcare_file)
statistic_data2 <- plantcare_statistic2(plantcare_data)

plantcare_to_loc

Description

Extract the location information of cis-element from Plantcare

Usage

plantcare_to_loc(plantcare_data)

Arguments

plantcare_data

The result of plantcare_classify().

Value

data.frame

Author(s)

Shiqi Zhao

Examples

plantcare_path <- system.file("extdata", "plantCARE_output.tab", package = "BioVizSeq") 
plantcare_file <- read.table(plantcare_path, header = FALSE, sep = '\t', quote="")
plantcare_data <- plantcare_classify(plantcare_file)
plantcare_loc <- plantcare_to_loc(plantcare_data)

smart_plot

Description

Visualization of domain in SMART result file

Usage

smart_plot(
  fasta_file,
  the_order = NULL,
  domain_select = NULL,
  shape = "RoundRect",
  r = 0.3,
  legend_size = 15,
  domain_color = NULL
)

Arguments

fasta_file

The path of protein fasta file.

the_order

The path of order file. A List of Gene ID , One ID Per Line.

domain_select

The domain ID which you want to align with.

shape

RoundRect or Rect.

r

The radius of rounded corners.

legend_size

The size of legend.

domain_color

The color set of domain.

Value

p

Author(s)

Shiqi Zhao

smart_to_loc

Description

Extract the location information of domain from SMART result

Usage

smart_to_loc(input_file, do_pfam = TRUE)

Arguments

input_file

The path of potein fasta file.

do_pfam

Include the pfam domain or not.

Value

list

Author(s)

Shiqi Zhao

upload_fa_to_plantcare

Description

Upload the promoter file to Plantcare database

Usage

upload_fa_to_plantcare(fasta_file, email)

Arguments

fasta_file

The path of promoter file.

email

e-mail address.

Details

Due to the file size limitation of plantcare on fasta, upload_fa_to_plantcare() first splits fasta file. Then uploads the splited fasta files to the plantcare database, and automatically returns the results to the email provided by the user.

upload_fa_to_plantcare("the path/test.fasta", "your e-mail address")

Value

plantcare_result

Author(s)

Shiqi Zhao