[med-svn] [roary] 01/03: Imported Upstream version 3.6.1+dfsg
Sascha Steinbiss
sascha at steinbiss.name
Wed Apr 20 09:35:17 UTC 2016
This is an automated email from the git hooks/post-receive script.
sascha-guest pushed a commit to branch master
in repository roary.
commit f30f1b004cfbc3fa87a8b314df63598c5d89e641
Author: Sascha Steinbiss <sascha at steinbiss.name>
Date: Wed Apr 20 09:24:01 2016 +0000
Imported Upstream version 3.6.1+dfsg
---
.gitignore | 1 -
bin/roary-create_pan_genome_plots.R | 59 ++++++++++++++++++++++++++++++++
bin/roary-pan_genome_reorder_spreadsheet | 19 ++++++++++
bin/roary-query_pan_genome | 19 ++++++++++
dist.ini | 2 +-
5 files changed, 98 insertions(+), 2 deletions(-)
diff --git a/.gitignore b/.gitignore
index 5a1d3b0..660798c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -33,4 +33,3 @@ set_difference_unique_set_two_reannotated
extras/
bin/shred_assemblies
Bio-Roary-*
-Roary-*
diff --git a/bin/roary-create_pan_genome_plots.R b/bin/roary-create_pan_genome_plots.R
new file mode 100755
index 0000000..8bf392e
--- /dev/null
+++ b/bin/roary-create_pan_genome_plots.R
@@ -0,0 +1,59 @@
+#!/usr/bin/env Rscript
+# ABSTRACT: Create R plots
+# PODNAME: create_plots.R
+# Take the output files from the pan genome pipeline and create nice plots.
+library(ggplot2)
+
+
+mydata = read.table("number_of_new_genes.Rtab")
+boxplot(mydata, data=mydata, main="Number of new genes",
+ xlab="No. of genomes", ylab="No. of genes",varwidth=TRUE, ylim=c(0,max(mydata)), outline=FALSE)
+
+mydata = read.table("number_of_conserved_genes.Rtab")
+boxplot(mydata, data=mydata, main="Number of conserved genes",
+ xlab="No. of genomes", ylab="No. of genes",varwidth=TRUE, ylim=c(0,max(mydata)), outline=FALSE)
+
+mydata = read.table("number_of_genes_in_pan_genome.Rtab")
+boxplot(mydata, data=mydata, main="No. of genes in the pan-genome",
+ xlab="No. of genomes", ylab="No. of genes",varwidth=TRUE, ylim=c(0,max(mydata)), outline=FALSE)
+
+mydata = read.table("number_of_unique_genes.Rtab")
+boxplot(mydata, data=mydata, main="Number of unique genes",
+ xlab="No. of genomes", ylab="No. of genes",varwidth=TRUE, ylim=c(0,max(mydata)), outline=FALSE)
+
+mydata = read.table("blast_identity_frequency.Rtab")
+plot(mydata,main="Number of blastp hits with different percentage identity", xlab="Blast percentage identity", ylab="No. blast results")
+
+
+library(ggplot2)
+conserved = colMeans(read.table("number_of_conserved_genes.Rtab"))
+total = colMeans(read.table("number_of_genes_in_pan_genome.Rtab"))
+
+genes = data.frame( genes_to_genomes = c(conserved,total),
+ genomes = c(c(1:length(conserved)),c(1:length(conserved))),
+ Key = c(rep("Conserved genes",length(conserved)), rep("Total genes",length(total))) )
+
+ggplot(data = genes, aes(x = genomes, y = genes_to_genomes, group = Key, linetype=Key)) +geom_line()+
+theme_classic() +
+ylim(c(1,max(total)))+
+xlim(c(1,length(total)))+
+xlab("No. of genomes") +
+ylab("No. of genes")+ theme_bw(base_size = 16) + theme(legend.justification=c(0,1),legend.position=c(0,1))+
+ggsave(filename="conserved_vs_total_genes.png", scale=1)
+
+######################
+
+unique_genes = colMeans(read.table("number_of_unique_genes.Rtab"))
+new_genes = colMeans(read.table("number_of_new_genes.Rtab"))
+
+genes = data.frame( genes_to_genomes = c(unique_genes,new_genes),
+ genomes = c(c(1:length(unique_genes)),c(1:length(unique_genes))),
+ Key = c(rep("Unique genes",length(unique_genes)), rep("New genes",length(new_genes))) )
+
+ggplot(data = genes, aes(x = genomes, y = genes_to_genomes, group = Key, linetype=Key)) +geom_line()+
+theme_classic() +
+ylim(c(1,max(unique_genes)))+
+xlim(c(1,length(unique_genes)))+
+xlab("No. of genomes") +
+ylab("No. of genes")+ theme_bw(base_size = 16) + theme(legend.justification=c(1,1),legend.position=c(1,1))+
+ggsave(filename="unique_vs_new_genes.png", scale=1)
diff --git a/bin/roary-pan_genome_reorder_spreadsheet b/bin/roary-pan_genome_reorder_spreadsheet
new file mode 100755
index 0000000..f436248
--- /dev/null
+++ b/bin/roary-pan_genome_reorder_spreadsheet
@@ -0,0 +1,19 @@
+#!/usr/bin/env perl
+
+package Bio::Roary::Main::RoaryReorderSpreadsheet;
+
+# ABSTRACT: Take in a tree and a spreadsheet and output a reordered spreadsheet
+# PODNAME: pan_genome_reorder_spreadsheet
+
+=head1 SYNOPSIS
+
+Take in a tree and a spreadsheet and output a reordered spreadsheet
+
+=cut
+
+use Cwd qw(abs_path);
+BEGIN { unshift( @INC, abs_path('./lib') ) }
+BEGIN { unshift( @INC, abs_path('./t/lib') ) }
+use Bio::Roary::CommandLine::RoaryReorderSpreadsheet;
+
+Bio::Roary::CommandLine::RoaryReorderSpreadsheet->new(args => \@ARGV, script_name => $0)->run;
diff --git a/bin/roary-query_pan_genome b/bin/roary-query_pan_genome
new file mode 100755
index 0000000..0e62826
--- /dev/null
+++ b/bin/roary-query_pan_genome
@@ -0,0 +1,19 @@
+#!/usr/bin/env perl
+
+package Bio::Roary::Main::QueryRoary;
+
+# ABSTRACT: Take in a groups file and the protein fasta files and output selected data
+# PODNAME: query_pan_genome
+
+=head1 SYNOPSIS
+
+Take in a groups file and the protein fasta files and output selected data
+
+=cut
+
+use Cwd qw(abs_path);
+BEGIN { unshift( @INC, abs_path('./lib') ) }
+BEGIN { unshift( @INC, abs_path('./t/lib') ) }
+use Bio::Roary::CommandLine::QueryRoary;
+
+Bio::Roary::CommandLine::QueryRoary->new(args => \@ARGV, script_name => $0)->run;
diff --git a/dist.ini b/dist.ini
index 1131967..ee8e8a3 100644
--- a/dist.ini
+++ b/dist.ini
@@ -1,5 +1,5 @@
name = Bio-Roary
-version = 3.6.0
+version = 3.6.1
author = Andrew J. Page <ap13 at sanger.ac.uk>
license = GPL_3
copyright_holder = Wellcome Trust Sanger Institute
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-med/roary.git
More information about the debian-med-commit
mailing list