Merge pull request #14 from PatrickRWright/dev

2.1.2

CopraRNA2.pl

@@ -6,7 +6,7 @@
 use Getopt::Long;
 use Cwd 'abs_path'; ## edit 2.0.5.1
 
-# CopraRNA 2.1.1
+# CopraRNA 2.1.2
 
  # License: MIT
 
@@ -95,6 +95,8 @@
 
 #### changelog
 
+# v2.1.2   : added R downstream ooi false positive removal
+#
 # v2.1.1   : added input exceptions
 #            DAVID python code now py2 and py3 compatible
 #            changed coloring in evolutionary heatmap
@@ -170,6 +172,7 @@
 my $verbose = 0; ## edit 2.0.5.1
 my $noclean = 0; ## edit 2.0.5.1
 my $websrv = 0; ## edit 2.0.5.1
+my $ooi_filt = 0; ## for copraRNA2_ooi_post_filtering.R
 my $pvalcutoff = 0.15; # p-value cutoff for CopraRNA 2 // ## edit 2.0.5.1
 my $topcount = 200; # amount of top predictions // ## edit 2.0.5.1
 my $root = 1; # root function to apply to the weights // ## edit 2.0.5.1
@@ -202,12 +205,13 @@
     'enrich:i'		=> \$enrich, # functional enrichment needs to be specifically turned on // also how many top preds to use for enrichment 
     'root:i'		=> \$root, # root function to apply to the weights ## edit 2.0.5.1
     'cons:i'		=> \$cons, # consensus mode / 0=off, 1=ooi_cons, 2=overall_cons ## edit 2.0.6
+    'ooifilt:f'		=> \$ooi_filt, # for copraRNA2_ooi_post_filtering.R
 );
 
 
 if ($help) { ## edit 2.0.4 // added  help and getopt
 
-print "\nCopraRNA 2.1.1\n\n",
+print "\nCopraRNA 2.1.2\n\n",
 
 "CopraRNA is a tool for sRNA target prediction. It computes whole genome target predictions\n",
 "by combination of distinct whole genome IntaRNA predictions. As input CopraRNA requires\n",
@@ -249,6 +253,7 @@
 " --noclean                 switch to prevent removal of temporary files (def:off)\n",  ## edit 2.0.5.1
 " --enrich                  if entered then DAVID-WS functional enrichment is calculated with given amount of top predictions (def:off)\n",  ## edit 2.0.5.1
 " --nooi                    if set then the CopraRNA2 prediction mode is set not to focus on the organism of interest (def:off)\n",  ## edit 2.0.6
+" --ooifilt                 post processing filter for organism of interest p-value 0=off (def:0)\n",
 " --root                    specifies root function to apply to the weights (def:1)\n",
 " --topcount                specifies the amount of top predictions to return and use for the extended regions plots (def:200)\n\n", ## edit 2.0.6
 
@@ -278,6 +283,9 @@
 chomp $count_fa;
 die("\nError: The input file ($sRNAs_fasta) seems to contain less than 3 sequences!\n\n") unless($count_fa>2);
 
+# check for ooifilt <=1 and >= 0
+die("\nError: ooifilt needs to be specified between 0 and 1. You set $ooi_filt\n\n") unless ($ooi_filt>=0 and $ooi_filt<=1);
+
 # create warning for non empty run dir
 my @dir_files = <*>; ## edit 2.0.5.1
 my $file_count = scalar(@dir_files); ## edit 2.0.5.1
@@ -351,7 +359,8 @@
     print WRITETOOPTIONS "enrich:" . $enrich . "\n";
     print WRITETOOPTIONS "noclean:" . $noclean . "\n";
     print WRITETOOPTIONS "cons:" . $cons . "\n"; ## edit 2.0.6
-    print WRITETOOPTIONS "version:CopraRNA 2.1.1\n";  ## edit 2.0.4.2
+    print WRITETOOPTIONS "ooifilt:" . $ooi_filt . "\n"; ## 
+    print WRITETOOPTIONS "version:CopraRNA 2.1.2\n";  ## edit 2.0.4.2
 close WRITETOOPTIONS;
 # end write options
 
@@ -511,6 +520,17 @@
         system "mv all_predictions/CopraRNA_result.csv .";
         system "mv all_predictions/coprarna_websrv_table.csv ." if ($websrv);
     }
+
+    # make an archive for the Rdata files
+    unless ($cop1) {
+        system "mkdir Rdata";
+        system "mv consensus_positions.Rdata Rdata";
+        system "mv conservation_table.Rdata Rdata";
+        system "mv interaction_positions.Rdata Rdata";
+    }
+
+    # zip evo_alignments folder to reduce file number
+    system "if [ -d evo_alignments ]; then zip -rmq evo_alignments evo_alignments 2>&1; fi";
 
     # remove weights.warning if its empty
     system "rm weights.warning" if (-z "weights.warning");

README.md

@@ -1,4 +1,4 @@
-# CopraRNA [![GitHub](https://img.shields.io/github/tag/PatrickRWright/CopraRNA.svg)](https://github.com/PatrickRWright/CopraRNA)  [![Bioconda](https://anaconda.org/bioconda/coprarna/badges/version.svg)](https://anaconda.org/bioconda/coprarna) [![Docker Repository on Quay](https://quay.io/repository/biocontainers/coprarna/status "Docker Repository on Quay")](https://quay.io/repository/repository/biocontainers/coprarna)
+# CopraRNA [![GitHub](https://img.shields.io/github/tag/PatrickRWright/CopraRNA.svg)](https://github.com/PatrickRWright/CopraRNA/releases)  [![Bioconda](https://anaconda.org/bioconda/coprarna/badges/version.svg)](https://anaconda.org/bioconda/coprarna) [![Docker Repository on Quay](https://quay.io/repository/biocontainers/coprarna/status "Docker Repository on Quay")](https://quay.io/repository/biocontainers/coprarna)
 ![CopraRNA](https://raw.githubusercontent.com/PatrickRWright/CopraRNA/master/copra_sRNA.jpg "CopraRNA")
 
 **Phylogenetic target prediction for prokaryotic *trans*-acting small RNAs**
@@ -13,7 +13,8 @@ for any character and X stands for a digit between 0 and 9). Depending on sequen
 or longer to compute. In most cases it is significantly faster. It is suggested to run CopraRNA
 on a machine with at least 8 GB of memory.
 
-Please note: Version 2.1.1 is currently experimental and changes are actively being pushed.
+CopraRNA produces a lot of file I/O. It is suggested to run CopraRNA in a dedicated
+empty directory to avoid unexpected behavior.
 
 For testing or ad hoc use of CopraRNA, you can use its webinterface at the
 
@@ -47,8 +48,9 @@ The following topics are covered by this documentation:
 <a name="install" />
 # Installation
 
-In order to use CopraRNA you can either install it directly via conda or
-clone this github repository and install the dependencies individually.
+In order to use CopraRNA you can either [install it directly via conda](#instconda) or
+clone this github repository and install the dependencies individually. 
+It is also possible to run CopraRNA [via a provided Docker container](#biocontainer).
 
 <br /><br />
 <a name="deps" />
@@ -115,7 +117,7 @@ source activate coprarnaenv
 
 ## Usage via biocontainer (docker)
 
-CopraRNA can be retrieved and used as docker container with all dependencies via [docker](https://docs.docker.com/engine/installation/). Once you have docker installed simply type:
+CopraRNA can be retrieved and used as docker container with all dependencies via [docker](https://docs.docker.com/engine/installation/). Once you have docker installed simply type (with changed version):
 ```bash
        docker run -i -t quay.io/biocontainers/coprarna:2.1.0--0 /bin/bash
 ```
@@ -162,6 +164,7 @@ The following options are available:
 - `--noclean` : switch to prevent removal of temporary files (def:off)
 - `--enrich` : if entered then DAVID-WS functional enrichment is calculated with given amount of top predictions (def:off)
 - `--nooi` : if set then the CopraRNA2 prediction mode is set not to focus on the organism of interest (def:off)
+- `--ooifilt` : post processing filter for organism of interest p-value 0=off (def:0)
 - `--root` : specifies root function to apply to the weights (def:1)
 - `--topcount` : specifies the amount of top predictions to return and use for the extended regions plots (def:200)
 
@@ -179,7 +182,7 @@ cd run
 ```
 Here you can execute build_kegg2refseq.pl 
 ```bash
-./build_kegg2refseq.pl 
+../build_kegg2refseq.pl 
 ```
 which will download prokaryotes.txt from the
 NCBI and process it into the files CopraRNA_available_organisms.txt and kegg2refseqnew.csv.