Merge pull request #54 from cancerit/feature/bwamem2

Feature/bwamem2

.travis.yml

@@ -26,3 +26,4 @@ script:
  - docker run -t --rm pcap-core bam_stats --version
  - docker run -t --rm pcap-core mismatchQc --version
  - docker run -t --rm pcap-core bwa_mem.pl --version
+ - docker run -t --rm pcap-core merge_or_mark.pl --version

CHANGES.md

@@ -1,5 +1,9 @@
 # CHANGES
 
+## NEXT
+
+* Adds basic `merge_or_mark.pl` script for merging data generated by `bwa_mem.pl`.
+
 ## 4.4.1
 
 * `bamToBw.pl` correct to send stdout/err to file when threads are active.
@@ -144,13 +148,13 @@ Handle recent changes to BioPerl structure
 ## 3.1.0
 
 * Use BWA default for `-T` previously hard coded to `-T 0`.
-  *  Can be passed through `bwa_mem.pl` other ags to bwa via the `-b` option.
-*  Fix `bam2bedgraph` compilation since changes to underlying libraries
-*  `bamToBw.pl` - expose read flag filters
-*  Drop dependancy on `Bio::DB::HTS INSTALL.pl` as can't fix to known good version.
-*  Added travis CI
-*  Add support for output directly to CRAM
-*  `bwa` version upgraded to [0.7.15](https://github.com/lh3/bwa/releases/tag/v0.7.15)
+  * Can be passed through `bwa_mem.pl` other ags to bwa via the `-b` option.
+* Fix `bam2bedgraph` compilation since changes to underlying libraries
+* `bamToBw.pl` - expose read flag filters
+* Drop dependancy on `Bio::DB::HTS INSTALL.pl` as can't fix to known good version.
+* Added travis CI
+* Add support for output directly to CRAM
+* `bwa` version upgraded to [0.7.15](https://github.com/lh3/bwa/releases/tag/v0.7.15)
 
 ## 3.0.0
 
@@ -170,16 +174,16 @@ Handle recent changes to BioPerl structure
 ## 2.0.0
 
 * bwa_mem.pl
-    * allow user to specify BWA mapping parameters
-    * now accepts CRAM as input
+  * allow user to specify BWA mapping parameters
+  * now accepts CRAM as input
 * bamToBw.pl - now accepts CRAM as input.
 * bam_stats - Adds 2 new stats:
-    * `#_mapped_pairs`
-    * `#_inter_chr_pairs`
+  * `#_mapped_pairs`
+  * `#_inter_chr_pairs`
 * Dependancy changes
-    * __WARNING__: ensure all related tools handle these updates
-    * [samtools](https://github.com/samtools/samtools/releases), now only uses htslib based versions (1.3+, handling deprecated use of sort)
-    * [Bio::DB::HTS](http://search.cpan.org/~rishidev/Bio-DB-HTS/lib/Bio/DB/HTS.pm) htslib bindings replacing Bio::DB::Sam
+  * __WARNING__: ensure all related tools handle these updates
+  * [samtools](https://github.com/samtools/samtools/releases), now only uses htslib based versions (1.3+, handling deprecated use of sort)
+  * [Bio::DB::HTS](http://search.cpan.org/~rishidev/Bio-DB-HTS/lib/Bio/DB/HTS.pm) htslib bindings replacing Bio::DB::Sam
 
 ## 1.14.0
 
@@ -225,8 +229,8 @@ Handle recent changes to BioPerl structure
 ## 1.5.4
 
 * bam_stats C
-    * Reference file parameter is now optional to replicate bam_stats.pl functionality.
-    * Warnings in help, and when a cram file is given as reference from header may not be found, and bam stats will fail.
+  * Reference file parameter is now optional to replicate bam_stats.pl functionality.
+  * Warnings in help, and when a cram file is given as reference from header may not be found, and bam stats will fail.
 
 ## 1.5.3
 
@@ -235,9 +239,9 @@ Handle recent changes to BioPerl structure
 
 ## 1.5.2
 
-bamToBw.pl fixes
-* Pull actual binaries from jkent_util not html page associated
-* process name corrections in bamToBw.pm command line args
+* bamToBw.pl fixes
+  * Pull actual binaries from jkent_util not html page associated
+  * process name corrections in bamToBw.pm command line args
 
 ## 1.5.1
 
@@ -305,16 +309,16 @@ and potentially unstable in future.
 ## 1.0.2
 
 * Upgrade install to pull biobambam 0.0.138
-    * fastqtobam option 'pairedfile' for where readnames don't have trailing '/1' or '/2'.
-    * fastqtobam option to relax qscore validation without turning off... careful
+  * fastqtobam option 'pairedfile' for where readnames don't have trailing '/1' or '/2'.
+  * fastqtobam option to relax qscore validation without turning off... careful
 * Upgrade install to pull BWA 0.7.8
-    * performance improvements for short read alignment (100bp)
+  * performance improvements for short read alignment (100bp)
 
 ## 1.0.1
 
 * Upgrade install to pull biobambam 0.0.135
-    * fastqtobam supports Casava v1.8
-    * bamsort supports NM/MD correction during sam->bam/merge process
+  * fastqtobam supports Casava v1.8
+  * bamsort supports NM/MD correction during sam->bam/merge process
 * Minor enhancement to BAS reader module.
 * Sample name from command line passed through to SM of RG header in bwa_mem.pl
 * SRA.pm - check that rg id is unique within run of code (thanks to Junjun Zhang)

Dockerfile

@@ -2,8 +2,10 @@ FROM quay.io/wtsicgp/cgpbigwig:1.1.0 as builder
 
 USER  root
 
-ARG VER_BBB2="2.0.87-release-20180301132713"
-ARG VER_BIODBHTS="2.10"
+ARG BBB2_URL="https://gitlab.com/german.tischler/biobambam2/uploads/178774a8ece96d2201fcd0b5249884c7/biobambam2-2.0.146-release-20191030105216-x86_64-linux-gnu.tar.xz"
+ARG BWAMEM2_URL="https://github.com/bwa-mem2/bwa-mem2/releases/download/v2.0pre2/bwa-mem2-2.0pre2_x64-linux.tar.bz2"
+ARG STADEN="https://iweb.dl.sourceforge.net/project/staden/staden/2.0.0b11/staden-2.0.0b11-2016-linux-x86_64.tar.gz"
+ARG VER_BIODBHTS="3.01"
 ARG VER_BWA="v0.7.17"
 ARG VER_HTSLIB="1.9"
 ARG VER_SAMTOOLS="1.9"
@@ -60,10 +62,10 @@ LABEL maintainer="cgphelp@sanger.ac.uk"\
       description="pcap-core"
 
 ENV OPT /opt/wtsi-cgp
-ENV PATH $OPT/bin:$OPT/biobambam2/bin:$PATH
+ENV PATH $OPT/bin:$OPT/biobambam2/bin:$OPT/scramble/bin:$PATH
 ENV PATH $OPT/bin:$PATH
 ENV PERL5LIB $OPT/lib/perl5
-ENV LD_LIBRARY_PATH $OPT/lib
+ENV LD_LIBRARY_PATH $OPT/lib:$OPT/scramble/lib
 ENV LC_ALL C
 
 RUN apt-get -yq update
@@ -80,6 +82,8 @@ zlib1g \
 liblzma5 \
 libncurses5 \
 p11-kit \
+libcurl3 \
+moreutils \
 unattended-upgrades && \
 unattended-upgrade -d -v && \
 apt-get remove -yq unattended-upgrades && \

INSTALL.md

@@ -63,7 +63,8 @@ apt-get -yqq install \
     lsof \
     time \
     libgd-perl \
-    psmisc
+    psmisc \
+    moreutils
 ```
 
 ### Amazon Linux AMI

Makefile.PL

@@ -29,6 +29,7 @@ WriteMakefile(
   EXE_FILES     => [qw( bin/bwa_aln.pl
                         bin/bwa_mem.pl
                         bin/bamToBw.pl
+                        bin/merge_or_mark.pl
                         bin/xam_coverage_bins.pl )],
   PREREQ_PM     => {
                      'Module::Build' => 0.42,

bin/bwa_mem.pl

@@ -2,7 +2,7 @@
 
 ##########LICENCE##########
 # PCAP - NGS reference implementations and helper code for the ICGC/TCGA Pan-Cancer Analysis Project
-# Copyright (C) 2014-2018 ICGC PanCancer Project
+# Copyright (C) 2014-2020 ICGC PanCancer Project
 #
 # This program is free software; you can redistribute it and/or
 # modify it under the terms of the GNU General Public License
@@ -52,7 +52,7 @@
   my $options = setup();
 
  	my $threads = PCAP::Threaded->new($options->{'threads'});
-	&PCAP::Threaded::disable_out_err if(!exists $options->{'index'} && $options->{'threads'} == 1);
+  &PCAP::Threaded::disable_out_err if(exists $options->{'index'});
 
   # register processes
 	$threads->add_function('split', \&PCAP::Bwa::split_in);
@@ -98,8 +98,8 @@ sub setup {
               'm|man' => \$opts{'m'},
               'v|version' => \$opts{'v'},
               'j|jobs' => \$opts{'jobs'},
-              't|threads=i' => \$opts{'threads'},
-              'mt|map_threads=i' => \$opts{'map_threads'},
+              't|threads:i' => \$opts{'threads'},
+              'mt|map_threads:i' => \$opts{'map_threads'},
               'r|reference=s' => \$opts{'reference'},
               'o|outdir=s' => \$opts{'outdir'},
               's|sample=s' => \$opts{'sample'},
@@ -125,9 +125,6 @@ sub setup {
     exit 0;
   }
 
-  my $version = PCAP::Bwa::bwa_version();
-  die "bwa mem can only be used with bwa version 0.7+, the version found in path is: $version\n" unless(version->parse($version) >= version->parse('0.7.0'));
-
   # then check for no args:
   my $defined;
   for(keys %opts) { $defined++ if(defined $opts{$_}); }