Mercurial > repos > mingchen0919 > rmarkdown_i_adhore
changeset 0:9755ce6ac4d5 draft
planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_i_adhore commit b6ef011f29d6c75775be9cc0e0abe53e19981d1d-dirty
| author | mingchen0919 |
|---|---|
| date | Tue, 08 Aug 2017 12:53:57 -0400 |
| parents | |
| children | fd719a0a6b26 |
| files | README.md i-adhore.xml i_adhore_configure.Rmd i_adhore_configure_render.R |
| diffstat | 4 files changed, 276 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.md Tue Aug 08 12:53:57 2017 -0400 @@ -0,0 +1,2 @@ +# i-adhore tool +A galaxy tool for generating configuration file for i-adhore analysis.
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/i-adhore.xml Tue Aug 08 12:53:57 2017 -0400 @@ -0,0 +1,93 @@ +<tool id="i_adhore" name="i-adhore" version="0.1"> + <requirement type="package" version="1.20.0">r-getopt</requirement> + <requirement type="package" version="1.2">r-rmarkdown</requirement> + <description>Generate i-adhore configure file</description> + <stdio> + <exit_code range="1:" /> + <exit_code range=":-1" /> + <regex match="Error:" /> + <regex match="Exception:" /> + </stdio> + <command><![CDATA[ + + Rscript '${__tool_directory__}/i_adhore_configure_render.R' + + ## 1. input data + -e $echo + + #set $g_analysis_files = '' + #for $g in $genomes + #if str($g.genome_name) + #set $analysis_files = [] + #for $file in $g.analysis_files.to_dataset_instances($g.analysis_files) + #set $analysis_files += [$file.__str__] + #end for + #set g_analysis_files += str($g.genome_name) + ':' + ','.join($analysis_files) + ';' + #end if + #end for + -G '$g_analysis_files' + + -b $blast_table + -g $gap_size + -c $cluster_gap + -q $q_value + -p $prob_cutoff + -a $anchor_points + -m $alignment_method + -l $level2only + -T $table_type + -h $multi_hypothesis_correction + + ## 2. output report and file directory + -x $i_adhore_configure_txt + -o $i_adhore_configure + -d $i_adhore_configure.files_path + + ## 3. Rmd templates in the tool directory + -t '${__tool_directory__}/i_adhore_configure.Rmd' + + + ]]></command> + <inputs> + <repeat name="genomes" title="genome" min="1"> + <param name="genome_name" type="text" value="" label="Specify genome name" /> + <param name="analysis_files" type="data" format="txt" multiple="true" label="analysis files (.lst or .txt files)" /> + </repeat> + <param name="blast_table" type="data" format="csv" multiple="false" label="blast table (.csv file)" /> + <param name="gap_size" type="text" value="30" label="gap size" /> + <param name="cluster_gap" type="text" value="35" label="cluster gap" /> + <param name="q_value" type="text" value="0.75" label="q value" /> + <param name="prob_cutoff" type="text" value="0.01" label="probability cutoff" /> + <param name="anchor_points" type="text" value="3" label="anchor_points" /> + <param name="alignment_method" type="text" value="gg4" label="alignment method" /> + <param name="level2only" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="level 2 only" /> + <param name="table_type" type="text" value="family" label="table type" /> + <param name="multi_hypothesis_correction" type="text" value="FDR" label="multiple hypothesis correction" /> + + <param type="boolean" name="echo" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Display analysis code in report?" /> + </inputs> + <outputs> + <data name="i_adhore_configure" format="html" label="i-adhore configure report" /> + <data name="i_adhore_configure_txt" format="txt" label="i-adhore configure file" /> + </outputs> + <citations> + <citation type="bibtex"> + @article{allaire2016rmarkdown, + title={rmarkdown: Dynamic Documents for R, 2016}, + author={Allaire, J and Cheng, Joe and Xie, Yihui and McPherson, Jonathan and Chang, Winston and Allen, Jeff and Wickham, Hadley and Atkins, Aron and Hyndman, Rob}, + journal={R package version 0.9}, + volume={6}, + year={2016} + } + </citation> + <citation type="bibtex"> + @book{xie2015dynamic, + title={Dynamic Documents with R and knitr}, + author={Xie, Yihui}, + volume={29}, + year={2015}, + publisher={CRC Press} + } + </citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/i_adhore_configure.Rmd Tue Aug 08 12:53:57 2017 -0400 @@ -0,0 +1,79 @@ +--- +title: 'i-adhore: generate i-adhore config file' +output: + html_document: + number_sections: true + toc: true + theme: cosmo + highlight: tango +--- + +```{r setup, include=FALSE, warning=FALSE, message=FALSE} +knitr::opts_chunk$set(echo = ECHO) +``` + +# Genomes and analysis files + +```{r} +g_analysis_files_set = strsplit(opt$g_analysis_file, ';')[[1]] +g_analysis_files_list = list() +# for(i in g_analysis_files_set) { +# genome = strsplit(i, ':')[[1]][1] +# analysis_files = strsplit(i, ':')[[1]][2] %>% +# strsplit(',') %>% `[[`(1) %>% +# (function(x){ +# paste0(1:length(x),' ', x) +# }) +# g_analysis_files_list[[genome]] = analysis_files +# } +for(i in g_analysis_files_set) { + genome = strsplit(i, ':')[[1]][1] + analysis_files = strsplit(i, ':')[[1]][2] %>% + strsplit(',') %>% `[[`(1) %>% + laply(.fun = function(x){ + file_name = strsplit(x, '/')[[1]] %>% tail(1) + file_name = strsplit(file_name, '\\.')[[1]][1] + paste0(file_name, ' ', x) + }) + g_analysis_files_list[[genome]] = c( + 'name' = paste0('genome=', strsplit(i, ':')[[1]][1]), + 'analysis_files' = analysis_files + ) + print(paste0('genome=', strsplit(i, ':')[[1]][1])) + print(analysis_files) +} +``` + +# Other parameters + +```{r} +params = c( + 'blast table' = opt$blast_table, + 'output_path' = opt$i_adhore_configure_dir, + 'gap_size' = opt$gap_size, + 'cluster_gap' = opt$cluster_gap, + 'q_value' = opt$q_value, + 'prob_cutoff' = opt$prob_cutoff, + 'anchor_points' = opt$anchor_points, + 'level_2_only' = opt$level2only, + 'table_type' = opt$table_type, + 'multi_hypothesis_correction' = opt$multi_hypothesis_correction +) + +df = data.frame(name = names(params), + value = params) +knitr::kable(df) +``` + + +```{r echo=FALSE} +# generate i_adhore_configure.txt file +lines = c(unlist(g_analysis_files_list), + ' ', + paste0(df$name, '=', df$value), + 'CompareAligners') +fileConn = file('I_ADHORE_CONFIGURE_TXT') +writeLines(lines, con = fileConn) +``` + +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/i_adhore_configure_render.R Tue Aug 08 12:53:57 2017 -0400 @@ -0,0 +1,102 @@ + +##======= Handle arguments from command line ======== +# setup R error handline to go to stderr +options(show.error.messages=FALSE, +error=function(){ + cat(geterrmessage(), file=stderr()) + quit("no", 1, F) +}) + +# we need that to not crash galaxy with an UTF8 error on German LC settings. +loc = Sys.setlocale("LC_MESSAGES", "en_US.UTF-8") + +# suppress warning +options(warn = -1) + +options(stringsAsFactors=FALSE, useFancyQuotes=FALSE) +args = commandArgs(trailingOnly=TRUE) + +suppressPackageStartupMessages({ + library(getopt) + library(tools) +}) + +# column 1: the long flag name +# column 2: the short flag alias. A SINGLE character string +# column 3: argument mask +# 0: no argument +# 1: argument required +# 2: argument is optional +# column 4: date type to which the flag's argument shall be cast. +# possible values: logical, integer, double, complex, character. +spec_list=list() + + +##------- 1. input data --------------------- +spec_list$ECHO = c('echo', 'e', '1', 'character') +spec_list$G_ANALYSIS_FILES = c('g_analysis_files', 'G', '1', 'character') +spec_list$BLAST_TABLE = c('blast_table', 'b', '1', 'character') +spec_list$GAP_SIZE = c('gap_size', 'g', '1', 'character') +spec_list$CLUSTER_GAP = c('cluster_gap', 'c', '1', 'character') +spec_list$Q_VALUE = c('q_value', 'q', '1', 'character') +spec_list$PROB_CUTOFF = c('prob_cutoff', 'p', '1', 'character') +spec_list$ANCHOR_POINTS = c('anchor_points', 'a', '1', 'character') +spec_list$ALIGNMENT_METHOD = c('alignment_method', 'm', '1', 'character') +spec_list$LEVEL2ONLY = c('level2only', 'l', '1', 'character') +spec_list$TABLE_TYPE = c('table_type', 'T', '1', 'character') +spec_list$MULTI_HYPOTHESIS_CORRECTION = c('multi_hypothesis_correction', 'h', '1', 'character') + + +##--------2. output report and report site directory -------------- +spec_list$I_ADHORE_CONFIGURE_TXT = c('i_adhore_configure_txt', 'x', '1', 'character') +spec_list$OUTPUT_HTML = c('i_adhore_configure_html', 'o', '1', 'character') +spec_list$OUTPUT_DIR = c('i_adhore_configure_dir', 'd', '1', 'character') + + +##--------3. Rmd templates sitting in the tool directory ---------- +spec_list$I_ADHORE_CONFIGURE_RMD = c('i_adhore_configure_rmd', '-t', '1', 'character') + + +spec = t(as.data.frame(spec_list)) +opt = getopt(spec) +# arguments are accessed by long flag name (the first column in the spec matrix) +# NOT by element name in the spec_list +# example: opt$help, opt$expression_file +##====== End of arguments handling ========== + +#------ Load libraries --------- +library(rmarkdown) +library(plyr) +library(dplyr) + + +#----- 1. create the report directory ------------------------ +system(paste0('mkdir -p ', opt$i_adhore_configure_dir)) +# set working directory to output files directory +setwd(opt$i_adhore_configure_dir) + + +#----- 2. generate Rmd files with Rmd templates -------------- +# a. templates without placeholder variables: +# copy templates from tool directory to the working directory. +# b. templates with placeholder variables: +# substitute variables with user input values and place them in the working directory. + + +#----- 01 i_adhore_configure.Rmd ----------------------- +readLines(opt$i_adhore_configure_rmd) %>% + (function(x) { + gsub('ECHO', opt$echo, x) + }) %>% + (function(x) { + gsub('I_ADHORE_CONFIGURE_TXT', opt$i_adhore_configure_txt, x) + }) %>% + (function(x) { + fileConn = file('i_adhore_configure.Rmd') + writeLines(x, con=fileConn) + close(fileConn) + }) + + +#------ 3. render all Rmd files -------- +render('i_adhore_configure.Rmd', output_file = opt$i_adhore_configure_html)