利用R包ggmsa进行多序列比对

## 1.设置当前工作目录

setwd("./ggmsa")

## 2.安装和导入R包

# install.packages("ggmsa")

library(ggmsa)

library(ggplot2)

## 3.R包简要信息

help(package = "ggmsa")

# Package: ggmsa

# Title: Plot Multiple Sequence Alignment using 'ggplot2'

# Version: 0.0.4

# Authors@R: c( person("Guangchuang", "Yu", email = "guangchuangyu@gmail.com", role = c("aut", "cre"), comment = c(ORCID = "0000-0002-6485-8781")),

# person("Lang", "Zhou", email = "nyzhoulang@gmail.com", role = "aut"),

# person("Huina", "Huang", email = "1185796994@qq.com", role = "ctb"))

# Description: Supports visualizing multiple sequence alignment of DNA and protein sequences using 'ggplot2'. It supports a number of colour schemes, including Chemistry, Clustal, Shapely, Taylor and Zappo. Multiple sequence alignment can easily be combined with other 'ggplot2' plots, such as aligning a phylogenetic tree produced by 'ggtree' with multiple sequence alignment.

# Depends: R (>= 3.5.0)

# Imports: Biostrings, ggplot2, magrittr, tidyr, utils, stats, stringr

# Suggests: ape, cowplot, ggtree, knitr, methods, seqmagick

# License: Artistic-2.0

# Encoding: UTF-8

# LazyData: true

# RoxygenNote: 7.1.0

# VignetteBuilder: knitr

# NeedsCompilation: no

# Packaged: 2020-05-28 08:15:32 UTC; ygc

# Author: Guangchuang Yu [aut, cre] (<https://orcid.org/0000-0002-6485-8781>),

# Lang Zhou [aut],

# Huina Huang [ctb]

# Maintainer: Guangchuang Yu <guangchuangyu@gmail.com>

# Repository: CRAN

# Date/Publication: 2020-05-28 10:50:10 UTC

# Built: R 3.6.3; ; 2020-05-29 14:03:22 UTC; windows

ls(package:ggmsa)

# [1] "available_colors" "available_fonts" "available_msa"

# [4] "facet_msa" "geom_asterisk" "geom_GC"

# [7] "geom_msa" "geom_seed" "geom_seqlogo"

# [10] "ggmotif" "ggmsa" "tidy_msa"

## 4.测试

# Plot multiple sequence alignment using ggplot2 with multiple color schemes supported.

# Supports visualizing multiple sequence alignment of DNA and protein sequences using ggplot2 It supports a number of colour schemes, including Chemistry, Clustal, Shapely, Taylor and Zappo. Multiple sequence alignment can easily be combined with other ‘ggplot2’ plots, such as aligning a phylogenetic tree produced by ‘ggtree’ with multiple sequence alignment.

### 4.1 Load sample data

# Three sample data are shipped with the ggmsa package. Note that ggmsa supports not only fasta files but other objects as well. available_msa()can be used to list MSA objects currently available.

available_msa()

# files currently available:

# .fasta

# XStringSet objects from 'Biostrings' package:

# DNAStringSet RNAStringSet AAStringSet BStringSet DNAMultipleAlignment RNAMultipleAlignment AAMultipleAlignment

# bin objects from 'seqmagick' package:

# DNAbin AAbin

protein_sequences <- system.file("extdata", "sample.fasta", package = "ggmsa")

miRNA_sequences <- system.file("extdata", "seedSample.fa", package = "ggmsa")

nt_sequences <- system.file("extdata", "LeaderRepeat_All.fa", package = "ggmsa")

path.package("ggmsa")

# [1] "C:/Users/lenovo/Documents/R/win-library/3.6/ggmsa"

# Visualizing Multiple Sequence Alignments #

### 4.2 The most simple code to use ggmsa:

?ggmsa

#@ 简单绘制

ggmsa(protein_sequences, start = 265, end = 300)

#@ 调整参数，实现个性化绘制多序列比对图

ggmsa(protein_sequences, start = 265, end = 300, font = "TimesNewRoman", color = "Clustal", char_width = 0.8, none_bg = T, seq_name = T)

ggmsa(protein_sequences, start = 265, end = 300, font = "TimesNewRoman", color = "Chemistry_AA", char_width = 0.8, none_bg = F)

# Colour Schemes #

available_colors()

# color schemes for nucleotide sequences currently available:

# Chemistry_NT Shapely_NT Taylor_NT Zappo_NT

# color schemes for AA sequences currently available:

# Clustal Chemistry_AA Shapely_AA Zappo_AA Taylor_AA

### 4.3 Clustal X Colour Scheme(Default)

#@ This is an emulation of the default colourscheme used for alignments in Clustal X, a graphical interface for the ClustalW multiple sequence alignment program. Each residue in the alignment is assigned a colour if the amino acid profile of the alignment at that position meets some minimum criteria specific for the residue type.

ggmsa(protein_sequences, start = 320, end = 360, color = "Clustal")

### 4.4 Color by Chemistry

#@ Amino acids are colored according to their side chain chemistry:

ggmsa(protein_sequences, start = 320, end = 360, color = "Chemistry_AA")

### 4.5 Color by Shapely

#@ This color scheme matches the RasMol amino acid and RasMol nucleotide color schemes, which are, in turn, based on Robert Fletterick’s “Shapely models”.

ggmsa(protein_sequences, start = 320, end = 360, color = "Shapely_AA")

### 4.6 Color by Taylor

#@ This color scheme is taken from Taylor(Taylor 1997) and is also used in JalView(Waterhouse et al. 2009).

ggmsa(protein_sequences, start = 320, end = 360, color = "Taylor_AA")

### 4.7 Color by Zappo

#@ This scheme colors residues according to their physico-chemical properties, and is also used in JalView(Waterhouse et al. 2009).

ggmsa(protein_sequences, start = 320, end = 360, color = "Zappo_AA")

### 4.8 Font

#@ Several classic font for MSA are shipped in the package. In the same ways, you can use available_fonts() to list font currently available

available_fonts()

# font families currently available:

# helvetical mono TimesNewRoman DroidSansMono

# helvetical

ggmsa(protein_sequences, start = 320, end = 360, font = "helvetical", color = "Chemistry_AA")

# TimesNewRoman

ggmsa(protein_sequences, start = 320, end = 360, font = "TimesNewRoman", color = "Chemistry_AA")

# DroidSansMono

ggmsa(protein_sequences, start = 320, end = 360, font = "DroidSansMono", color = "Chemistry_AA")

#@ If you specify font = NULL, only tiles will be plot.

ggmsa(protein_sequences, start = 320, end = 360, font = NULL, color = "Chemistry_AA", seq_name = F)

ggmsa(protein_sequences, start = 320, end = 360, font = NULL, color = "Chemistry_AA", seq_name = T)

### 4.9 Characters width

#@ Characters width can be specified by char_width. Defaults is 0.9.

ggmsa(protein_sequences, start = 320, end = 360, char_width = 0.5, color = "Chemistry_AA")

### 4.10 Background

#@ Background can be specified by none_bg. If none_bg = TRUE, only the character will be plot.

ggmsa(protein_sequences, start = 320, end = 360, none_bg = TRUE) + theme_void()

### 4.11 Position Highligthed

#@ Position Highligthed can be specified by posHighligthed. The none_bg = FALSE when you specified position Highligthed by posHighligthed

# 不连续高亮

ggmsa(protein_sequences, 164, 213, color = "Chemistry_AA",

posHighligthed = c(185, 190))

ggmsa(protein_sequences, 164, 213, color = "Chemistry_AA", posHighligthed = c(180, 190, 200))

# 连续高亮

ggmsa(protein_sequences, 164, 213, color = "Chemistry_AA",

posHighligthed = c(180:200))

### 4.12 Sequence names

#@ Sequence names Defaults is ‘NULL’ which indicates that the sequence name is displayed when font = NULL, but ‘font = char’ will not be displayed. If seq_name = TRUE the sequence name will be displayed when you need it.

ggmsa(protein_sequences, 164, 213, color = "Chemistry_AA", seq_name = TRUE)

#2 If seq_name = FALSE the sequence name will not be displayed in any case.

ggmsa(protein_sequences, 164, 213, font = NULL, color = "Chemistry_AA", seq_name = FALSE)

## 5.结束

# RUNRPTEST("./ggmsa", rpackage = "ggmsa",install_method = "website", rpackage_repository = "cran")

sessionInfo()

# R version 3.6.3 (2020-02-29)

# Platform: x86_64-w64-mingw32/x64 (64-bit)

# Running under: Windows 10 x64 (build 18363)

# Matrix products: default

# locale:

# [1] LC_COLLATE=Chinese (Simplified)_China.936

# [2] LC_CTYPE=Chinese (Simplified)_China.936

# [3] LC_MONETARY=Chinese (Simplified)_China.936

# [4] LC_NUMERIC=C

# [5] LC_TIME=Chinese (Simplified)_China.936

# attached base packages:

# [1] stats graphics grDevices utils datasets methods

# [7] base

# other attached packages:

# [1] ggplot2_3.3.0 ggmsa_0.0.4

# loaded via a namespace (and not attached):

# [1] Rcpp_1.0.4.6 pillar_1.4.4 compiler_3.6.3

# [4] XVector_0.26.0 tools_3.6.3 zlibbioc_1.32.0

# [7] digest_0.6.25 packrat_0.5.0 lifecycle_0.2.0

# [10] tibble_3.0.1 gtable_0.3.0 pkgconfig_2.0.3

# [13] rlang_0.4.6 rstudioapi_0.11 seqmagick_0.1.3

# [16] parallel_3.6.3 withr_2.2.0 dplyr_0.8.5

# [19] stringr_1.4.0 Biostrings_2.54.0 S4Vectors_0.24.3

# [22] vctrs_0.3.0 IRanges_2.20.2 stats4_3.6.3

# [25] grid_3.6.3 tidyselect_1.1.0 glue_1.4.1

# [28] R6_2.4.1 purrr_0.3.4 tidyr_1.1.0

# [31] farver_2.0.3 magrittr_1.5 scales_1.1.1

# [34] ellipsis_0.3.1 BiocGenerics_0.32.0 assertthat_0.2.1

# [37] colorspace_1.4-1 labeling_0.3 stringi_1.4.6

# [40] munsell_0.5.0 crayon_1.3.4

#@ 两篇参考文献，有兴趣的同学读一下

# Taylor, W R. 1997. “Residual Colours: A Proposal for Aminochromography.” Protein Eng 10 (7): 743–46.

# Waterhouse, A. M., J. B. Procter, D. M. Martin, M Clamp, and G. J. Barton. 2009. “Jalview Version 2–a Multiple Sequence Alignment Editor and Analysis Workbench.” Bioinformatics 25 (9): 1189.