From d248e7ce20ce59bf63ccfd713870d7dbe0498a24 Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Thu, 9 Aug 2018 14:39:49 +0200
Subject: [PATCH 01/32] First efforts to generate bigWig files

---
 main.nf | 38 ++++++++++++++++++--------------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/main.nf b/main.nf
index 9098207b2..5433c37f5 100644
--- a/main.nf
+++ b/main.nf
@@ -675,7 +675,7 @@ if(params.aligner == 'hisat2'){
         file wherearemyfiles
 
         output:
-        file "${hisat2_bam.baseName}.sorted.bam" into bam_count, bam_rseqc, bam_preseq, bam_markduplicates, bam_featurecounts, bam_stringtieFPKM, bam_forSubsamp, bam_skipSubsamp
+        file "${hisat2_bam.baseName}.sorted.bam" into bam_count, bam_rseqc, bam_preseq, bam_markduplicates, bam_featurecounts, bam_stringtieFPKM, bam_for_genebody, bam_skipSubsamp
         file "where_are_my_files.txt"
 
         script:
@@ -748,31 +748,30 @@ process rseqc {
     """
 }
 
+
 /*
- * Step 4.1 Subsample the BAM files if necessary
- */
-bam_forSubsamp
-    .filter { it.size() > params.subsampFilesizeThreshold }
-    .map { [it, params.subsampFilesizeThreshold / it.size() ] }
-    .set{ bam_forSubsampFiltered }
-bam_skipSubsamp
-    .filter { it.size() <= params.subsampFilesizeThreshold }
-    .set{ bam_skipSubsampFiltered }
-process bam_subsample {
+ * Step 4.1 Rseqc create BigWig coverage 
+ */ 
+
+process createBigWig {
     tag "${bam.baseName - '.sorted'}"
+    publishDir "${params.outdir}/bigwig", mode: 'copy'
 
-    input:
-    set file(bam), val(fraction) from bam_forSubsampFiltered
+    when:
+    !params.skip_qc && !params.skip_genebody_coverage
+
+    input: 
+    file bam from bam_for_genebody
 
     output:
-    file "*_subsamp.bam" into bam_subsampled
+    file "*.bigwig" into bigwig_for_genebody
 
     script:
     """
-    samtools view -s $fraction -b $bam | samtools sort -o ${bam.baseName}_subsamp.bam
+    samtools index $bam
+    bamCoverage -b $bam -p ${task.cpus} -o $bam.bigwig
     """
 }
-
 /*
  * Step 4.2 Rseqc genebody_coverage
  */
@@ -791,7 +790,7 @@ process genebody_coverage {
     !params.skip_qc && !params.skip_genebody_coverage
 
     input:
-    file bam from bam_subsampled.concat(bam_skipSubsampFiltered)
+    file bigwig from bigwig_for_genebody
     file bed12 from bed_genebody_coverage.collect()
 
     output:
@@ -799,9 +798,8 @@ process genebody_coverage {
 
     script:
     """
-    samtools index $bam
-    geneBody_coverage.py \\
-        -i $bam \\
+    geneBody_coverage2.py \\
+        -i $bigwig \\
         -o ${bam.baseName}.rseqc \\
         -r $bed12
     mv log.txt ${bam.baseName}.rseqc.log.txt

From 9fbefcba560e1340814ad42e04b8637478c448bf Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Thu, 9 Aug 2018 14:42:47 +0200
Subject: [PATCH 02/32] Add deeptools as dependency

---
 environment.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/environment.yml b/environment.yml
index 1f9d5c554..7ec37e097 100644
--- a/environment.yml
+++ b/environment.yml
@@ -24,3 +24,4 @@ dependencies:
   - subread=1.6.1
   - multiqc=1.5
   - gffread=0.9.9
+  - deeptools=3.1.1

From 16bab7f0ad4ee23d79e1fa9508d0db2a1b06a86c Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Thu, 9 Aug 2018 14:45:51 +0200
Subject: [PATCH 03/32] Fix subsampling steps in RNAseq

---
 main.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/main.nf b/main.nf
index 5433c37f5..517c3a15d 100644
--- a/main.nf
+++ b/main.nf
@@ -592,7 +592,7 @@ if(params.aligner == 'star'){
     star_aligned
         .filter { logs, bams -> check_log(logs) }
         .flatMap {  logs, bams -> bams }
-    .into { bam_count; bam_rseqc; bam_preseq; bam_markduplicates; bam_featurecounts; bam_stringtieFPKM; bam_forSubsamp; bam_skipSubsamp }
+    .into { bam_count; bam_rseqc; bam_preseq; bam_markduplicates; bam_featurecounts; bam_stringtieFPKM; bam_for_genebody }
 }
 
 
@@ -675,7 +675,7 @@ if(params.aligner == 'hisat2'){
         file wherearemyfiles
 
         output:
-        file "${hisat2_bam.baseName}.sorted.bam" into bam_count, bam_rseqc, bam_preseq, bam_markduplicates, bam_featurecounts, bam_stringtieFPKM, bam_for_genebody, bam_skipSubsamp
+        file "${hisat2_bam.baseName}.sorted.bam" into bam_count, bam_rseqc, bam_preseq, bam_markduplicates, bam_featurecounts, bam_stringtieFPKM, bam_for_genebody
         file "where_are_my_files.txt"
 
         script:

From 88cfb2972cf901fa1bca8b042099a60ed631814c Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Thu, 9 Aug 2018 14:46:49 +0200
Subject: [PATCH 04/32] Add createBigWig to base.config

---
 conf/base.config | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/conf/base.config b/conf/base.config
index 24fa6dce0..a80593342 100644
--- a/conf/base.config
+++ b/conf/base.config
@@ -61,6 +61,12 @@ process {
     time = { check_max( 7.h * task.attempt, 'time' ) }
     errorStrategy = { task.exitStatus in [143,137] ? 'retry' : 'ignore' }
   }
+  withName:createBigWig {
+    cpus = { check_max( 8 * task.attempt, 'cpus' ) }
+    memory = { check_max( 32.GB * task.attempt, 'memory' ) }
+    time = { check_max( 7.h * task.attempt, 'time' ) }
+    errorStrategy = { task.exitStatus in [143,137] ? 'retry' : 'ignore' }
+  }
   withName:genebody_coverage {
     cpus = { check_max( 1 * task.attempt, 'cpus' ) }
     memory = { check_max( 32.GB * task.attempt, 'memory' ) }

From 5801cca7ce825ce2c1dacec76ac196a55b3842b6 Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Thu, 9 Aug 2018 14:48:13 +0200
Subject: [PATCH 05/32] Probably missing collect

---
 main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.nf b/main.nf
index 517c3a15d..2611eea6c 100644
--- a/main.nf
+++ b/main.nf
@@ -790,7 +790,7 @@ process genebody_coverage {
     !params.skip_qc && !params.skip_genebody_coverage
 
     input:
-    file bigwig from bigwig_for_genebody
+    file bigwig from bigwig_for_genebody.collect()
     file bed12 from bed_genebody_coverage.collect()
 
     output:

From 36059f9ec72a77e203877c77d6b4df63fa2aabf2 Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Thu, 9 Aug 2018 15:01:00 +0200
Subject: [PATCH 06/32] Fix suffix

---
 main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.nf b/main.nf
index 2611eea6c..86924526d 100644
--- a/main.nf
+++ b/main.nf
@@ -769,7 +769,7 @@ process createBigWig {
     script:
     """
     samtools index $bam
-    bamCoverage -b $bam -p ${task.cpus} -o $bam.bigwig
+    bamCoverage -b $bam -p ${task.cpus} -o ${bam.baseName - 'sorted'}.bigwig
     """
 }
 /*

From c1f36aa17c268d3c82a3ccb1a4fd593538628c92 Mon Sep 17 00:00:00 2001
From: jun-wan <jun.wang@scilifelab.se>
Date: Fri, 10 Aug 2018 10:37:51 +0200
Subject: [PATCH 07/32] Fix rnaseq pipeline crashes with large input files; Add
 sequencing center in BAM

---
 conf/base.config | 18 +++++++++++++++---
 main.nf          | 10 ++++++++--
 2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/conf/base.config b/conf/base.config
index c239d8972..25482a38f 100644
--- a/conf/base.config
+++ b/conf/base.config
@@ -41,9 +41,11 @@ process {
     time = { check_max( 8.h * task.attempt, 'time' ) }
   }
   $star {
-    cpus = { check_max( 10 * task.attempt, 'cpus' ) }
+    cpus = 10 
     memory = { check_max( 80.GB * task.attempt, 'memory' ) }
     time = { check_max( 8.h * task.attempt, 'time' ) }
+    errorStrategy = { task.exitStatus in [1,143,137,104] ? 'retry' : 'terminate' }
+    maxRetries = 2
   }
   $hisat2Align {
     cpus = { check_max( 8 * task.attempt, 'cpus' ) }
@@ -71,12 +73,22 @@ process {
     errorStrategy = { task.exitStatus in [143,137] ? 'retry' : 'ignore' }
   }
   $markDuplicates {
-    cpus = { check_max( 2 * task.attempt, 'cpus' ) }
+    cpus = 2 
     memory = { check_max( 16.GB * task.attempt, 'memory' ) }
+    errorStrategy = { task.exitStatus in [1,143,137] ? 'retry' : 'terminate' }
+    maxRetries = 3
   }
   $dupradar {
-    cpus = { check_max( 2 * task.attempt, 'cpus' ) }
+    cpus = 1
+    memory = { check_max( 16.GB * task.attempt, 'memory' ) }
+    errorStrategy = { task.exitStatus in [1,143,137,139] ? 'retry' : 'terminate' }
+    maxRetries = 3
+  }
+  $featureCounts {
+    cpus = 2
     memory = { check_max( 16.GB * task.attempt, 'memory' ) }
+    errorStrategy = { task.exitStatus in [1,143,137,134,104] ? 'retry' : 'terminate' }
+    maxRetries = 3
   }
   $sample_correlation {
     cpus = { check_max( 2 * task.attempt, 'cpus' ) }
diff --git a/main.nf b/main.nf
index e47e1d7c0..d3a50aed7 100644
--- a/main.nf
+++ b/main.nf
@@ -100,6 +100,7 @@ params.hisat2_index = params.genome ? params.genomes[ params.genome ].hisat2 ?:
 params.multiqc_config = "$baseDir/assets/multiqc_config.yaml"
 params.email = false
 params.plaintext_email = false
+params.seqCenter = false
 
 mdsplot_header = file("$baseDir/assets/mdsplot_header.txt")
 heatmap_header = file("$baseDir/assets/heatmap_header.txt")
@@ -529,6 +530,7 @@ if(params.aligner == 'star'){
         script:
         prefix = reads[0].toString() - ~/(_R1)?(_trimmed)?(_val_1)?(\.fq)?(\.fastq)?(\.gz)?$/
         def avail_mem = task.memory == null ? '' : "--limitBAMsortRAM ${task.memory.toBytes() - 100000000}"
+        RG = params.seqCenter ? "--outSAMattrRGline ID:$prefix 'CN:$params.seqCenter'" : ''
         """
         STAR --genomeDir $index \\
             --sjdbGTFfile $gtf \\
@@ -539,7 +541,8 @@ if(params.aligner == 'star'){
             --outSAMtype BAM SortedByCoordinate $avail_mem \\
             --readFilesCommand zcat \\
             --runDirPerm All_RWX \\
-            --outFileNamePrefix $prefix
+            --outFileNamePrefix $prefix \\
+            $RG
         """
     }
     // Filter removes all 'aligned' channels that fail the check
@@ -579,6 +582,7 @@ if(params.aligner == 'hisat2'){
         script:
         index_base = hs2_indices[0].toString() - ~/.\d.ht2/
         prefix = reads[0].toString() - ~/(_R1)?(_trimmed)?(_val_1)?(\.fq)?(\.fastq)?(\.gz)?$/
+        RG = params.seqCenter ? "--rg-id ${prefix} --rg 'CN:${params.seqCenter}'" : ''
         def rnastrandness = ''
         if (forward_stranded && !unstranded){
             rnastrandness = params.singleEnd ? '--rna-strandness F' : '--rna-strandness FR'
@@ -595,6 +599,7 @@ if(params.aligner == 'hisat2'){
                    --met-stderr \\
                    --new-summary \\
                    --summary-file ${prefix}.hisat2_summary.txt \\
+                   $RG \\
                    | samtools view -bS -F 4 -F 256 - > ${prefix}.bam
             """
         } else {
@@ -610,6 +615,7 @@ if(params.aligner == 'hisat2'){
                    --met-stderr \\
                    --new-summary \\
                    --summary-file ${prefix}.hisat2_summary.txt \\
+                   $RG \\
                    | samtools view -bS -F 4 -F 8 -F 256 - > ${prefix}.bam
             """
         }
@@ -800,7 +806,7 @@ process markDuplicates {
         avail_mem = task.memory.toGiga()
     }
     """
-    picard MarkDuplicates \\
+    picard -Xmx${avail_mem}g MarkDuplicates \\
         INPUT=$bam \\
         OUTPUT=${bam.baseName}.markDups.bam \\
         METRICS_FILE=${bam.baseName}.markDups_metrics.txt \\

From 86387c729dd2326d0d78d0b875b5ea6822e32a2a Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Fri, 10 Aug 2018 11:09:46 +0200
Subject: [PATCH 08/32] Back to old Dockerfile syntax

---
 Dockerfile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Dockerfile b/Dockerfile
index d4fdb9492..d6d7de824 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -4,4 +4,5 @@ LABEL authors="phil.ewels@scilifelab.se" \
     description="Docker image containing all requirements for the nfcore/rnaseq pipeline"
 
 COPY environment.yml /
-RUN conda env update -n root -f /environment.yml && conda clean -a
+RUN conda env create -f /environment.yml && conda clean -a
+ENV PATH /opt/conda/envs/nfcore-rnaseq-1.0dev/bin:$PATH
\ No newline at end of file

From 7d25565a45780d76c8e801f59a97e6c63ae444c9 Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Fri, 10 Aug 2018 11:10:54 +0200
Subject: [PATCH 09/32] Removed bigwig from basename - its not bam anymore

---
 main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.nf b/main.nf
index 86924526d..0a33327b7 100644
--- a/main.nf
+++ b/main.nf
@@ -776,7 +776,7 @@ process createBigWig {
  * Step 4.2 Rseqc genebody_coverage
  */
 process genebody_coverage {
-    tag "${bam.baseName - '.sorted'}"
+    tag "${bigwig.baseName - '.bigwig'}"
        publishDir "${params.outdir}/rseqc" , mode: 'copy',
         saveAs: {filename ->
             if (filename.indexOf("geneBodyCoverage.curves.pdf") > 0)       "geneBodyCoverage/$filename"

From c47ca5ac3d26bea1e6f572edbbf1013292e89ef4 Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Sat, 11 Aug 2018 00:16:21 +0200
Subject: [PATCH 10/32] Little update for environment

---
 environment.yml | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/environment.yml b/environment.yml
index daa8eae3b..3078fdefa 100644
--- a/environment.yml
+++ b/environment.yml
@@ -8,10 +8,10 @@ channels:
 dependencies:
   - conda-forge::openjdk=8.0.144 # Needed for FastQC - conda build hangs without this
   - fastqc=0.11.7
-  - trim-galore=0.5
+  - trim-galore=0.5.0
   - star=2.6.0c
   - hisat2=2.1.0
-  - picard=2.18.7
+  - picard=2.18.11
   - bioconductor-dupradar=1.8.0
   - conda-forge::r-data.table=1.11.4
   - conda-forge::r-gplots=3.0.1
@@ -21,7 +21,7 @@ dependencies:
   - rseqc=2.6.4
   - samtools=1.9
   - stringtie=1.3.4
-  - subread=1.6.1
+  - subread=1.6.2
   - gffread=0.9.9
   - deeptools=3.1.1
   - multiqc=1.6
\ No newline at end of file

From 4d8e91df21bdc2d5dee71f7ca5ecc4b3c3f63c59 Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Sat, 11 Aug 2018 00:20:23 +0200
Subject: [PATCH 11/32] Just remove sorted suffix

---
 main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.nf b/main.nf
index 0a33327b7..339c198e9 100644
--- a/main.nf
+++ b/main.nf
@@ -776,7 +776,7 @@ process createBigWig {
  * Step 4.2 Rseqc genebody_coverage
  */
 process genebody_coverage {
-    tag "${bigwig.baseName - '.bigwig'}"
+    tag "${bigwig.baseName - '.sorted'}"
        publishDir "${params.outdir}/rseqc" , mode: 'copy',
         saveAs: {filename ->
             if (filename.indexOf("geneBodyCoverage.curves.pdf") > 0)       "geneBodyCoverage/$filename"

From 7808e62b688453973dee6090ba5d3521da9c8d3e Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Sat, 11 Aug 2018 00:28:53 +0200
Subject: [PATCH 12/32] Remove entire suffix

---
 main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.nf b/main.nf
index 339c198e9..562dccf3b 100644
--- a/main.nf
+++ b/main.nf
@@ -754,7 +754,7 @@ process rseqc {
  */ 
 
 process createBigWig {
-    tag "${bam.baseName - '.sorted'}"
+    tag "${bam.baseName}"
     publishDir "${params.outdir}/bigwig", mode: 'copy'
 
     when:

From 8c1a4a693bde976dfc4b0552028c26a9c39f9485 Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Sat, 11 Aug 2018 10:55:17 +0200
Subject: [PATCH 13/32] Fixing baseName usage

---
 main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.nf b/main.nf
index 562dccf3b..489343016 100644
--- a/main.nf
+++ b/main.nf
@@ -769,7 +769,7 @@ process createBigWig {
     script:
     """
     samtools index $bam
-    bamCoverage -b $bam -p ${task.cpus} -o ${bam.baseName - 'sorted'}.bigwig
+    bamCoverage -b $bam -p ${task.cpus} -o ${bam.baseName}.bigwig
     """
 }
 /*

From 3442d2555e25f2610349b12cfa99f8a571cccedb Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Sat, 11 Aug 2018 11:00:55 +0200
Subject: [PATCH 14/32] Don't remove sorted

---
 main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.nf b/main.nf
index 489343016..5f87e7c34 100644
--- a/main.nf
+++ b/main.nf
@@ -776,7 +776,7 @@ process createBigWig {
  * Step 4.2 Rseqc genebody_coverage
  */
 process genebody_coverage {
-    tag "${bigwig.baseName - '.sorted'}"
+    tag "${bigwig.baseName}"
        publishDir "${params.outdir}/rseqc" , mode: 'copy',
         saveAs: {filename ->
             if (filename.indexOf("geneBodyCoverage.curves.pdf") > 0)       "geneBodyCoverage/$filename"

From 140d7a2f844bb6a905b103dab94882c94b7aa4cf Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Sat, 11 Aug 2018 11:01:29 +0200
Subject: [PATCH 15/32] Theres no bam

---
 main.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/main.nf b/main.nf
index 5f87e7c34..824988e7a 100644
--- a/main.nf
+++ b/main.nf
@@ -800,9 +800,9 @@ process genebody_coverage {
     """
     geneBody_coverage2.py \\
         -i $bigwig \\
-        -o ${bam.baseName}.rseqc \\
+        -o ${bigwig.baseName}.rseqc \\
         -r $bed12
-    mv log.txt ${bam.baseName}.rseqc.log.txt
+    mv log.txt ${bigwig.baseName}.rseqc.log.txt
     """
 }
 

From 16fab8a3d55b02e4cc865b52f0ac87dbef716af8 Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Sat, 11 Aug 2018 11:16:45 +0200
Subject: [PATCH 16/32] remove collect

---
 main.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/main.nf b/main.nf
index 824988e7a..a40da659b 100644
--- a/main.nf
+++ b/main.nf
@@ -754,7 +754,7 @@ process rseqc {
  */ 
 
 process createBigWig {
-    tag "${bam.baseName}"
+    tag "${bam.baseName - 'sortedByCoord.out'}"
     publishDir "${params.outdir}/bigwig", mode: 'copy'
 
     when:
@@ -790,7 +790,7 @@ process genebody_coverage {
     !params.skip_qc && !params.skip_genebody_coverage
 
     input:
-    file bigwig from bigwig_for_genebody.collect()
+    file bigwig from bigwig_for_genebody
     file bed12 from bed_genebody_coverage.collect()
 
     output:

From 8575d4eece402e9a1d7bf4f1c318fb0ecae2e54e Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Sat, 11 Aug 2018 12:15:45 +0200
Subject: [PATCH 17/32] Add travis_wait / hopefully no more timeouts

---
 .travis.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.travis.yml b/.travis.yml
index c7b117c85..efee5c0f8 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -28,6 +28,6 @@ script:
   # Lint the pipeline code
   - "nf-core lint ${TRAVIS_BUILD_DIR}"
   # Run, build reference genome with STAR
-  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker
+  - travis_wait 40 nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker
   # Run, build reference genome with HISAT2
-  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --aligner hisat2
+  - travis_wait 40 nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --aligner hisat2

From ee627490b5f2101c6e2a6d752fe65ade72682c7c Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Sat, 11 Aug 2018 15:08:09 +0200
Subject: [PATCH 18/32] Moving the log not required anymore

---
 main.nf | 1 -
 1 file changed, 1 deletion(-)

diff --git a/main.nf b/main.nf
index a40da659b..8485cf14f 100644
--- a/main.nf
+++ b/main.nf
@@ -802,7 +802,6 @@ process genebody_coverage {
         -i $bigwig \\
         -o ${bigwig.baseName}.rseqc \\
         -r $bed12
-    mv log.txt ${bigwig.baseName}.rseqc.log.txt
     """
 }
 

From fdd7ad60ea31706b7184918fd9343678bd072096 Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Sat, 11 Aug 2018 20:29:16 +0200
Subject: [PATCH 19/32] Still need a txt extension though

---
 main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.nf b/main.nf
index 8485cf14f..83dc3a275 100644
--- a/main.nf
+++ b/main.nf
@@ -800,7 +800,7 @@ process genebody_coverage {
     """
     geneBody_coverage2.py \\
         -i $bigwig \\
-        -o ${bigwig.baseName}.rseqc \\
+        -o ${bigwig.baseName}.rseqc.txt \\
         -r $bed12
     """
 }

From 76044e0bb72e0ab931ae99a9b4b1f50d4d7fd06d Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Sun, 12 Aug 2018 21:58:35 +0200
Subject: [PATCH 20/32] Remove travis wait

---
 .travis.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.travis.yml b/.travis.yml
index efee5c0f8..c7b117c85 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -28,6 +28,6 @@ script:
   # Lint the pipeline code
   - "nf-core lint ${TRAVIS_BUILD_DIR}"
   # Run, build reference genome with STAR
-  - travis_wait 40 nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker
+  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker
   # Run, build reference genome with HISAT2
-  - travis_wait 40 nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --aligner hisat2
+  - nextflow run ${TRAVIS_BUILD_DIR} -profile test,docker --aligner hisat2

From 4822d1b21eb1fac38b20c5005377868cd8d78aec Mon Sep 17 00:00:00 2001
From: jun-wan <jun.wang@scilifelab.se>
Date: Mon, 13 Aug 2018 11:23:36 +0200
Subject: [PATCH 21/32] update default seeting in base.config and minor changes
 in main.nf

---
 conf/base.config | 43 +++++++++++++++----------------------------
 main.nf          | 14 ++++++--------
 2 files changed, 21 insertions(+), 36 deletions(-)

diff --git a/conf/base.config b/conf/base.config
index 25482a38f..ab73dae76 100644
--- a/conf/base.config
+++ b/conf/base.config
@@ -13,90 +13,77 @@ process {
 
   container = params.container
 
-  cpus = { check_max( 1 * task.attempt, 'cpus' ) }
+  cpus = { check_max( 2, 'cpus' ) }
   memory = { check_max( 8.GB * task.attempt, 'memory' ) }
   time = { check_max( 2.h * task.attempt, 'time' ) }
 
-  errorStrategy = { task.exitStatus in [143,137] ? 'retry' : 'terminate' }
-  maxRetries = 1
+  errorStrategy = { task.exitStatus in [1,143,137,104,134,139] ? 'retry' : 'terminate' }
+  maxRetries = 3
   maxErrors = '-1'
 
   // Process-specific resource requirements
   $makeSTARindex {
-    cpus = { check_max( 10 * task.attempt, 'cpus' ) }
+    cpus = { check_max( 10, 'cpus' ) }
     memory = { check_max( 80.GB * task.attempt, 'memory' ) }
     time = { check_max( 5.h * task.attempt, 'time' ) }
   }
   $makeHISATindex {
-    cpus = { check_max( 10 * task.attempt, 'cpus' ) }
+    cpus = { check_max( 10, 'cpus' ) }
     memory = { check_max( 80.GB * task.attempt, 'memory' ) }
     time = { check_max( 5.h * task.attempt, 'time' ) }
   }
   $fastqc {
-    errorStrategy = { task.exitStatus in [143,137] ? 'retry' : 'ignore' }
+    errorStrategy = 'ignore'
   }
   $trim_galore {
-    cpus = { check_max( 2 * task.attempt, 'cpus' ) }
     memory = { check_max( 16.GB * task.attempt, 'memory' ) }
     time = { check_max( 8.h * task.attempt, 'time' ) }
   }
   $star {
-    cpus = 10 
+    cpus = { check_max (10, 'cpus')}
     memory = { check_max( 80.GB * task.attempt, 'memory' ) }
     time = { check_max( 8.h * task.attempt, 'time' ) }
-    errorStrategy = { task.exitStatus in [1,143,137,104] ? 'retry' : 'terminate' }
-    maxRetries = 2
   }
   $hisat2Align {
-    cpus = { check_max( 8 * task.attempt, 'cpus' ) }
+    cpus = { check_max( 8, 'cpus' ) }
     memory = { check_max( 64.GB * task.attempt, 'memory' ) }
     time = { check_max( 8.h * task.attempt, 'time' ) }
   }
   $hisat2_sortOutput {
-    cpus = { check_max( 4 * task.attempt, 'cpus' ) }
+    cpus = { check_max( 4, 'cpus' ) }
     memory = { check_max( 32.GB * task.attempt, 'memory' ) }
     time = { check_max( 8.h * task.attempt, 'time' ) }
   }
   $rseqc {
-    cpus = { check_max( 8 * task.attempt, 'cpus' ) }
+    cpus = { check_max( 8, 'cpus' ) }
     memory = { check_max( 32.GB * task.attempt, 'memory' ) }
     time = { check_max( 7.h * task.attempt, 'time' ) }
-    errorStrategy = { task.exitStatus in [143,137] ? 'retry' : 'ignore' }
+    errorStrategy = 'ignore'
   }
   $genebody_coverage {
-    cpus = { check_max( 1 * task.attempt, 'cpus' ) }
+    cpus = { check_max( 1, 'cpus' ) }
     memory = { check_max( 32.GB * task.attempt, 'memory' ) }
     time = { check_max( 7.h * task.attempt, 'time' ) }
-    errorStrategy = { task.exitStatus in [143,137] ? 'retry' : 'ignore' }
   }
   $preseq {
-    errorStrategy = { task.exitStatus in [143,137] ? 'retry' : 'ignore' }
+    errorStrategy = 'ignore'
   }
   $markDuplicates {
-    cpus = 2 
     memory = { check_max( 16.GB * task.attempt, 'memory' ) }
-    errorStrategy = { task.exitStatus in [1,143,137] ? 'retry' : 'terminate' }
-    maxRetries = 3
   }
   $dupradar {
-    cpus = 1
+    cpus = { check_max( 1, 'cpus' ) }
     memory = { check_max( 16.GB * task.attempt, 'memory' ) }
-    errorStrategy = { task.exitStatus in [1,143,137,139] ? 'retry' : 'terminate' }
-    maxRetries = 3
   }
   $featureCounts {
-    cpus = 2
     memory = { check_max( 16.GB * task.attempt, 'memory' ) }
-    errorStrategy = { task.exitStatus in [1,143,137,134,104] ? 'retry' : 'terminate' }
-    maxRetries = 3
   }
   $sample_correlation {
-    cpus = { check_max( 2 * task.attempt, 'cpus' ) }
     memory = { check_max( 16.GB * task.attempt, 'memory' ) }
   }
   $multiqc {
     memory = { check_max( 2.GB * task.attempt, 'memory' ) }
-    errorStrategy = { task.exitStatus in [143,137] ? 'retry' : 'ignore' }
+    errorStrategy = 'ignore'
   }
   $get_software_versions {
     memory = { check_max( 2.GB, 'memory' ) }
diff --git a/main.nf b/main.nf
index d3a50aed7..1e0138b22 100644
--- a/main.nf
+++ b/main.nf
@@ -64,6 +64,7 @@ def helpMessage() {
       --clusterOptions              Extra SLURM options, used in conjunction with Uppmax.config
       --maxMultiqcEmailFileSize     Theshold size for MultiQC report to be attached in notification email. If file generated by pipeline exceeds the threshold, it will not be attached (Default: 25MB)
       -name                         Name for the pipeline run. If not specified, Nextflow will automatically generate a random mnemonic.
+      --seqCenter                   Add sequencing center in @RG line of output BAM header
 
     AWSBatch options:
       --awsqueue                    The AWSBatch JobQueue that needs to be set when running on AWSBatch
@@ -530,7 +531,7 @@ if(params.aligner == 'star'){
         script:
         prefix = reads[0].toString() - ~/(_R1)?(_trimmed)?(_val_1)?(\.fq)?(\.fastq)?(\.gz)?$/
         def avail_mem = task.memory == null ? '' : "--limitBAMsortRAM ${task.memory.toBytes() - 100000000}"
-        RG = params.seqCenter ? "--outSAMattrRGline ID:$prefix 'CN:$params.seqCenter'" : ''
+        def seqCenter = params.seqCenter ? "--outSAMattrRGline ID:$prefix 'CN:$params.seqCenter'" : ''
         """
         STAR --genomeDir $index \\
             --sjdbGTFfile $gtf \\
@@ -541,8 +542,7 @@ if(params.aligner == 'star'){
             --outSAMtype BAM SortedByCoordinate $avail_mem \\
             --readFilesCommand zcat \\
             --runDirPerm All_RWX \\
-            --outFileNamePrefix $prefix \\
-            $RG
+            --outFileNamePrefix $prefix $seqCenter \\
         """
     }
     // Filter removes all 'aligned' channels that fail the check
@@ -582,7 +582,7 @@ if(params.aligner == 'hisat2'){
         script:
         index_base = hs2_indices[0].toString() - ~/.\d.ht2/
         prefix = reads[0].toString() - ~/(_R1)?(_trimmed)?(_val_1)?(\.fq)?(\.fastq)?(\.gz)?$/
-        RG = params.seqCenter ? "--rg-id ${prefix} --rg 'CN:${params.seqCenter}'" : ''
+        def seqCenter = params.seqCenter ? "--rg-id ${prefix} --rg CN:${params.seqCenter.replaceAll("\\s","_")}" : ''
         def rnastrandness = ''
         if (forward_stranded && !unstranded){
             rnastrandness = params.singleEnd ? '--rna-strandness F' : '--rna-strandness FR'
@@ -598,8 +598,7 @@ if(params.aligner == 'hisat2'){
                    -p ${task.cpus} \\
                    --met-stderr \\
                    --new-summary \\
-                   --summary-file ${prefix}.hisat2_summary.txt \\
-                   $RG \\
+                   --summary-file ${prefix}.hisat2_summary.txt $seqCenter \\
                    | samtools view -bS -F 4 -F 256 - > ${prefix}.bam
             """
         } else {
@@ -614,8 +613,7 @@ if(params.aligner == 'hisat2'){
                    -p ${task.cpus} \\
                    --met-stderr \\
                    --new-summary \\
-                   --summary-file ${prefix}.hisat2_summary.txt \\
-                   $RG \\
+                   --summary-file ${prefix}.hisat2_summary.txt $seqCenter \\
                    | samtools view -bS -F 4 -F 8 -F 256 - > ${prefix}.bam
             """
         }

From 8dbe57c25ba3e290fe67a9748ecf387cd6a3ce26 Mon Sep 17 00:00:00 2001
From: jun-wan <jun.wang@scilifelab.se>
Date: Tue, 14 Aug 2018 13:19:37 +0200
Subject: [PATCH 22/32] Fix syntax error from the Travis CI test

---
 main.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/main.nf b/main.nf
index 02de02bc9..11af7ab88 100644
--- a/main.nf
+++ b/main.nf
@@ -577,7 +577,7 @@ if(params.aligner == 'star'){
         script:
         prefix = reads[0].toString() - ~/(_R1)?(_trimmed)?(_val_1)?(\.fq)?(\.fastq)?(\.gz)?$/
         def avail_mem = task.memory == null ? '' : "--limitBAMsortRAM ${task.memory.toBytes() - 100000000}"
-        def seqCenter = params.seqCenter ? "--outSAMattrRGline ID:$prefix 'CN:$params.seqCenter'" : ''
+        seqCenter = params.seqCenter ? "--outSAMattrRGline ID:$prefix 'CN:$params.seqCenter'" : ''
         """
         STAR --genomeDir $index \\
             --sjdbGTFfile $gtf \\
@@ -628,7 +628,7 @@ if(params.aligner == 'hisat2'){
         script:
         index_base = hs2_indices[0].toString() - ~/.\d.ht2/
         prefix = reads[0].toString() - ~/(_R1)?(_trimmed)?(_val_1)?(\.fq)?(\.fastq)?(\.gz)?$/
-        def seqCenter = params.seqCenter ? "--rg-id ${prefix} --rg CN:${params.seqCenter.replaceAll("\\s","_")}" : ''
+        seqCenter = params.seqCenter ? "--rg-id ${prefix} --rg CN:${params.seqCenter.replaceAll('\\s','_')}" : ''
         def rnastrandness = ''
         if (forward_stranded && !unstranded){
             rnastrandness = params.singleEnd ? '--rna-strandness F' : '--rna-strandness FR'

From 92cade7c081e3be16f2a0553d29aab6dd2062786 Mon Sep 17 00:00:00 2001
From: Phil Ewels <phil.ewels@scilifelab.se>
Date: Thu, 16 Aug 2018 13:26:40 +0200
Subject: [PATCH 23/32] Pull upstream and fix conflicts

---
 conf/base.config |  9 ---------
 nextflow.config  | 15 +++++++++++----
 2 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/conf/base.config b/conf/base.config
index 48a59fdf1..c78239b5b 100644
--- a/conf/base.config
+++ b/conf/base.config
@@ -32,9 +32,6 @@ process {
     memory = { check_max( 80.GB * task.attempt, 'memory' ) }
     time = { check_max( 5.h * task.attempt, 'time' ) }
   }
-  withName:fastqc {
-    errorStrategy = 'ignore'
-  }
   withName:trim_galore {
     memory = { check_max( 16.GB * task.attempt, 'memory' ) }
     time = { check_max( 8.h * task.attempt, 'time' ) }
@@ -64,16 +61,12 @@ process {
     cpus = { check_max( 8 * task.attempt, 'cpus' ) }
     memory = { check_max( 32.GB * task.attempt, 'memory' ) }
     time = { check_max( 7.h * task.attempt, 'time' ) }
-    errorStrategy = { task.exitStatus in [143,137] ? 'retry' : 'ignore' }
   }
   withName:genebody_coverage {
     cpus = { check_max( 1, 'cpus' ) }
     memory = { check_max( 32.GB * task.attempt, 'memory' ) }
     time = { check_max( 7.h * task.attempt, 'time' ) }
   }
-  withName:preseq {
-    errorStrategy = 'ignore'
-  }
   withName:markDuplicates {
     memory = { check_max( 16.GB * task.attempt, 'memory' ) }
   }
@@ -99,7 +92,6 @@ process {
   withName:workflow_summary_mqc {
     memory = { check_max( 2.GB, 'memory' ) }
     cache = false
-    executor = 'local'
     errorStrategy = 'ignore'
   }
 }
@@ -110,5 +102,4 @@ params {
   max_cpus = 16
   max_time = 240.h
   igenomes_base = 's3://ngi-igenomes/igenomes/'
-  maxMultiqcEmailFileSize = 25.MB
 }
diff --git a/nextflow.config b/nextflow.config
index 9de09a9b6..c3a7316da 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -21,23 +21,30 @@ params {
   unstranded = false
   splicesites = false
   outdir = './results'
-  hisatBuildMemory = 200 // Required amount of memory in GB to build HISAT2 index with splice sites
-  subsampFilesizeThreshold = 10000000000 // Don't subsample BAMs for RSeQC gene_body_coverage if less than this
   saveReference = false
   saveTrimmed = false
   saveAlignedIntermediates = false
   singleEnd = false
   reads = "data/*{1,2}.fastq.gz"
   outdir = './results'
+
   // Custom trimming options
   clip_r1 = 0
   clip_r2 = 0
   three_prime_clip_r1 = 0
   three_prime_clip_r2 = 0
-  sampleLevel = false
-  clusterOptions = false
+
+  // AWS Batch
   awsqueue = false
   awsregion = 'eu-west-1'
+
+  // Defaults
+  sampleLevel = false
+  clusterOptions = false
+  hisatBuildMemory = 200 // Required amount of memory in GB to build HISAT2 index with splice sites
+  subsampFilesizeThreshold = 10000000000 // Don't subsample BAMs for RSeQC gene_body_coverage if less than this
+  maxMultiqcEmailFileSize = 25.MB
+  readPaths = null
   tracedir = "${params.outdir}/pipeline_info"
 }
 

From 42bea74bbc80f83861a0b37c05d6e51a165e01a3 Mon Sep 17 00:00:00 2001
From: Phil Ewels <phil.ewels@scilifelab.se>
Date: Thu, 16 Aug 2018 13:31:00 +0200
Subject: [PATCH 24/32] Get the linting tests to pass

---
 .travis.yml     | 31 ++++++++++++++++++-------------
 Dockerfile      |  2 +-
 README.md       |  2 +-
 Singularity     |  8 ++++++--
 environment.yml |  4 ++--
 nextflow.config |  8 +++++---
 6 files changed, 33 insertions(+), 22 deletions(-)

diff --git a/.travis.yml b/.travis.yml
index c7b117c85..d99bbd9fc 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,28 +1,33 @@
 sudo: required
-language: java
+language: python
 jdk: openjdk8
 services: docker
+python: '3.6'
+cache: pip
+matrix:
+  fast_finish: true
 
-before_install: docker pull nfcore/rnaseq:latest
+before_install:
+  # PRs to master are only ok if coming from dev branch
+  - '[ $TRAVIS_PULL_REQUEST = "false" ] || [ $TRAVIS_BRANCH != "master" ] || ([ $TRAVIS_PULL_REQUEST_SLUG = $TRAVIS_REPO_SLUG ] && [ $TRAVIS_PULL_REQUEST_BRANCH = "dev" ])'
+  # Pull the docker image first so the test doesn't wait for this
+  - docker pull nfcore/rnaseq
+  # Fake the tag locally so that the pipeline runs properly
+  - docker tag nfcore/rnaseq nfcore/rnaseq:latest
 
 install:
   # Install Nextflow
-  - mkdir /tmp/nextflow
-  - cd /tmp/nextflow
+  - mkdir /tmp/nextflow && cd /tmp/nextflow
   - wget -qO- get.nextflow.io | bash
   - sudo ln -s /tmp/nextflow/nextflow /usr/local/bin/nextflow
   # Install nf-core/tools
-  - git clone https://github.com/nf-core/tools.git /tmp/nf-core-tools
-  - cd /tmp/nf-core-tools
-  - pip install --user -e .
-  # Make test directories
-  - mkdir ${TRAVIS_BUILD_DIR}/tests
-  - cd ${TRAVIS_BUILD_DIR}/tests
-
+  - pip install nf-core
+  # Reset
+  - mkdir ${TRAVIS_BUILD_DIR}/tests && cd ${TRAVIS_BUILD_DIR}/tests
 
 env:
-  - NXF_VER=0.30.1
-  - ''
+  - NXF_VER='0.31.1' # Specify a minimum NF version that should be tested and work
+  - NXF_VER='' # Plus: get the latest NF version and check that it works
 
 script:
   # Lint the pipeline code
diff --git a/Dockerfile b/Dockerfile
index d6d7de824..7e7bb43c7 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -5,4 +5,4 @@ LABEL authors="phil.ewels@scilifelab.se" \
 
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
-ENV PATH /opt/conda/envs/nfcore-rnaseq-1.0dev/bin:$PATH
\ No newline at end of file
+ENV PATH /opt/conda/envs/nf-core-rnaseq-1.0dev/bin:$PATH
diff --git a/README.md b/README.md
index 2cedeabd0..3a769ec03 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 # ![nfcore/rnaseq](docs/images/nfcore-rnaseq_logo.png)
 
 [![Build Status](https://travis-ci.org/nf-core/rnaseq.svg?branch=master)](https://travis-ci.org/nf-core/rnaseq)
-[![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A50.30.1-brightgreen.svg)](https://www.nextflow.io/)
+[![Nextflow](https://img.shields.io/badge/nextflow-%E2%89%A50.31.1-brightgreen.svg)](https://www.nextflow.io/)
 [![Gitter](https://img.shields.io/badge/gitter-%20join%20chat%20%E2%86%92-4fb99a.svg)](https://gitter.im/nf-core/Lobby)
 
 [![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg)](http://bioconda.github.io/)
diff --git a/Singularity b/Singularity
index d286cbf35..ce0b0f59e 100644
--- a/Singularity
+++ b/Singularity
@@ -3,12 +3,16 @@ Bootstrap:docker
 
 %labels
     MAINTAINER Phil Ewels <phil.ewels@scilifelab.se>
-    DESCRIPTION Container image containing all requirements for the nf-core/rnaseq pipeline
+    DESCRIPTION Singularity image containing all requirements for nf-core/rnaseq pipeline
     VERSION 1.0dev
 
+%environment
+    PATH=/opt/conda/envs/nf-core-rnaseq-1.0dev/bin:$PATH
+    export PATH
+
 %files
     environment.yml /
 
 %post
-    /opt/conda/bin/conda env update -n root -f /environment.yml
+    /opt/conda/bin/conda env create -f /environment.yml
     /opt/conda/bin/conda clean -a
diff --git a/environment.yml b/environment.yml
index 3078fdefa..8b8966a22 100644
--- a/environment.yml
+++ b/environment.yml
@@ -1,6 +1,6 @@
 # You can use this file to create a conda environment for this pipeline:
 #   conda env create -f environment.yml
-name: nfcore-rnaseq-1.0dev
+name: nf-core-rnaseq-1.0dev
 channels:
   - bioconda
   - conda-forge
@@ -24,4 +24,4 @@ dependencies:
   - subread=1.6.2
   - gffread=0.9.9
   - deeptools=3.1.1
-  - multiqc=1.6
\ No newline at end of file
+  - multiqc=1.6
diff --git a/nextflow.config b/nextflow.config
index c3a7316da..8b5837ab0 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -10,8 +10,6 @@
 
 // Global default params, used in configs
 params {
-  version = '1.0dev' //Pipeline version
-  nf_required_version = '0.30.1' //Minimum version of Nextflow required
   container = 'nfcore/rnaseq:latest' // Container slug. Stable releases should specify release tag!
 
   // Pipeline Options
@@ -137,9 +135,13 @@ dag {
 }
 
 manifest {
-  homePage = 'https://github.com/nf-core/rnaseq'
+  name = 'nf-core/rnaseq'
   description = 'Nextflow RNA-Seq analysis pipeline, part of the nf-core community.'
+  homePage = 'https://github.com/nf-core/rnaseq'
+  author = 'Phil Ewels, Rickard Hammarén'
+  pipelineVersion = '1.0dev'
   mainScript = 'main.nf'
+  nextflowVersion = '>=0.31.1'
 }
 
 // Function to ensure that resource requirements don't go beyond

From a484c3e8b9c4b7e74f9dc9d24e3095a99f827e61 Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Thu, 16 Aug 2018 13:33:15 +0200
Subject: [PATCH 25/32] Update STAR version to latest (fixing segfaults)

---
 environment.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/environment.yml b/environment.yml
index 3078fdefa..1414a8d94 100644
--- a/environment.yml
+++ b/environment.yml
@@ -9,7 +9,7 @@ dependencies:
   - conda-forge::openjdk=8.0.144 # Needed for FastQC - conda build hangs without this
   - fastqc=0.11.7
   - trim-galore=0.5.0
-  - star=2.6.0c
+  - star=2.6.1a
   - hisat2=2.1.0
   - picard=2.18.11
   - bioconductor-dupradar=1.8.0
@@ -24,4 +24,4 @@ dependencies:
   - subread=1.6.2
   - gffread=0.9.9
   - deeptools=3.1.1
-  - multiqc=1.6
\ No newline at end of file
+  - multiqc=1.6

From d648825f12e3969f8485e1fd6217382a0d5fe150 Mon Sep 17 00:00:00 2001
From: Phil Ewels <phil.ewels@scilifelab.se>
Date: Thu, 16 Aug 2018 13:37:52 +0200
Subject: [PATCH 26/32] Switch from old nextflow & pipeline param usage to new
 manifest.

---
 Singularity |  2 +-
 main.nf     | 40 +++++++---------------------------------
 2 files changed, 8 insertions(+), 34 deletions(-)

diff --git a/Singularity b/Singularity
index ce0b0f59e..86630108d 100644
--- a/Singularity
+++ b/Singularity
@@ -3,7 +3,7 @@ Bootstrap:docker
 
 %labels
     MAINTAINER Phil Ewels <phil.ewels@scilifelab.se>
-    DESCRIPTION Singularity image containing all requirements for nf-core/rnaseq pipeline
+    DESCRIPTION Singularity image containing all requirements for the nf-core/rnaseq pipeline
     VERSION 1.0dev
 
 %environment
diff --git a/main.nf b/main.nf
index acd1cedd9..2dc83ed23 100644
--- a/main.nf
+++ b/main.nf
@@ -15,7 +15,7 @@
 def helpMessage() {
     log.info"""
     ===================================
-     nfcore/rnaseq  ~  version ${params.version}
+     nfcore/rnaseq  ~  version ${manifest.pipelineVersion}
     ===================================
     Usage:
 
@@ -246,7 +246,7 @@ log.info """=======================================================
     | \\| |       \\__, \\__/ |  \\ |___     \\`-._,-`-,
                                           `._,._,\'
 
- nf-core/rnaseq : RNA-Seq Best Practice v${params.version}
+ nf-core/rnaseq : RNA-Seq Best Practice v${manifest.pipelineVersion}
 ======================================================="""
 def summary = [:]
 summary['Run Name']     = custom_runName ?: workflow.runName
@@ -296,20 +296,6 @@ log.info summary.collect { k,v -> "${k.padRight(15)}: $v" }.join("\n")
 log.info "========================================="
 
 
-// Check that Nextflow version is up to date enough
-// try / throw / catch works for NF versions < 0.25 when this was implemented
-try {
-    if( ! nextflow.version.matches(">= $params.nf_required_version") ){
-        throw GroovyException('Nextflow version too old')
-    }
-} catch (all) {
-    log.error "====================================================\n" +
-              "  Nextflow version $params.nf_required_version required! You are running v$workflow.nextflow.version.\n" +
-              "  Pipeline execution will continue, but things may break.\n" +
-              "  Please run `nextflow self-update` to update Nextflow.\n" +
-              "============================================================"
-}
-
 // Show a big error message if we're running on the base config and an uppmax cluster
 if( workflow.profile == 'standard'){
     if ( "hostname".execute().text.contains('.uppmax.uu.se') ) {
@@ -754,8 +740,8 @@ process rseqc {
 
 
 /*
- * Step 4.1 Rseqc create BigWig coverage 
- */ 
+ * Step 4.1 Rseqc create BigWig coverage
+ */
 
 process createBigWig {
     tag "${bam.baseName - 'sortedByCoord.out'}"
@@ -764,7 +750,7 @@ process createBigWig {
     when:
     !params.skip_qc && !params.skip_genebody_coverage
 
-    input: 
+    input:
     file bam from bam_for_genebody
 
     output:
@@ -1052,7 +1038,7 @@ process get_software_versions {
 
     script:
     """
-    echo $params.version &> v_ngi_rnaseq.txt
+    echo $manifest.pipelineVersion &> v_ngi_rnaseq.txt
     echo $workflow.nextflow.version &> v_nextflow.txt
     fastqc --version &> v_fastqc.txt
     cutadapt --version &> v_cutadapt.txt
@@ -1167,7 +1153,7 @@ workflow.onComplete {
       subject = "[nfcore/rnaseq] FAILED: $workflow.runName"
     }
     def email_fields = [:]
-    email_fields['version'] = params.version
+    email_fields['version'] = manifest.pipelineVersion
     email_fields['runName'] = custom_runName ?: workflow.runName
     email_fields['success'] = workflow.success
     email_fields['dateComplete'] = workflow.complete
@@ -1253,18 +1239,6 @@ workflow.onComplete {
 
     log.info "[nfcore/rnaseq] Pipeline Complete"
 
-    try {
-        if( ! nextflow.version.matches(">= $params.nf_required_version") ){
-            throw GroovyException('Nextflow version too old')
-        }
-    } catch (all) {
-        log.error "====================================================\n" +
-                  "  Nextflow version $params.nf_required_version required! You are running v$workflow.nextflow.version.\n" +
-                  "  Please be extra careful with pipeline results.\n" +
-                  "  Run `nextflow self-update` to update Nextflow.\n" +
-                  "============================================================"
-    }
-
     if(!workflow.success){
         if( workflow.profile == 'standard'){
             if ( "hostname".execute().text.contains('.uppmax.uu.se') ) {

From cfadba521f0a0dbb300edfdb442fb145f1b304b1 Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Fri, 17 Aug 2018 14:28:50 +0200
Subject: [PATCH 27/32] Fix containsKey if no genome is used

---
 main.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/main.nf b/main.nf
index acd1cedd9..6dff222b1 100644
--- a/main.nf
+++ b/main.nf
@@ -95,8 +95,8 @@ if (params.help){
 }
 
 // Check if genome exists in the config file
-if (!params.genomes.containsKey(params.genome) && params.genome) {
-  exit 1, "The provided genome '${params.genome}' is not available in the iGenomes file. Currently the available genomes are ${params.genomes.keySet().join(", ")}"
+if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) {
+    exit 1, "The provided genome '${params.genome}' is not available in the iGenomes file. Currently the available genomes are ${params.genomes.keySet().join(", ")}"
   }
 
 // Configurable variables

From 499f202bab1a0073d05ccdc5a8754a840888f5c0 Mon Sep 17 00:00:00 2001
From: Phil Ewels <phil.ewels@scilifelab.se>
Date: Fri, 17 Aug 2018 15:19:07 +0200
Subject: [PATCH 28/32] Remove manifest.pipelineVersion from main.nf

Hopefully we can go back to only using this in a future version of nextflow.
---
 main.nf         | 21 ++++++++++++++-------
 nextflow.config |  5 ++++-
 2 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/main.nf b/main.nf
index 2dc83ed23..5a8eefa45 100644
--- a/main.nf
+++ b/main.nf
@@ -13,10 +13,17 @@
 */
 
 def helpMessage() {
-    log.info"""
-    ===================================
-     nfcore/rnaseq  ~  version ${manifest.pipelineVersion}
-    ===================================
+    log.info """
+    =======================================================
+                                              ,--./,-.
+              ___     __   __   __   ___     /,-._.--~\'
+        |\\ | |__  __ /  ` /  \\ |__) |__         }  {
+        | \\| |       \\__, \\__/ |  \\ |___     \\`-._,-`-,
+                                              `._,._,\'
+
+     nf-core/rnaseq : RNA-Seq Best Practice v${params.pipelineVersion}
+    =======================================================
+    
     Usage:
 
     The typical command for running the pipeline is as follows:
@@ -246,7 +253,7 @@ log.info """=======================================================
     | \\| |       \\__, \\__/ |  \\ |___     \\`-._,-`-,
                                           `._,._,\'
 
- nf-core/rnaseq : RNA-Seq Best Practice v${manifest.pipelineVersion}
+ nf-core/rnaseq : RNA-Seq Best Practice v${params.pipelineVersion}
 ======================================================="""
 def summary = [:]
 summary['Run Name']     = custom_runName ?: workflow.runName
@@ -1038,7 +1045,7 @@ process get_software_versions {
 
     script:
     """
-    echo $manifest.pipelineVersion &> v_ngi_rnaseq.txt
+    echo $params.pipelineVersion &> v_ngi_rnaseq.txt
     echo $workflow.nextflow.version &> v_nextflow.txt
     fastqc --version &> v_fastqc.txt
     cutadapt --version &> v_cutadapt.txt
@@ -1153,7 +1160,7 @@ workflow.onComplete {
       subject = "[nfcore/rnaseq] FAILED: $workflow.runName"
     }
     def email_fields = [:]
-    email_fields['version'] = manifest.pipelineVersion
+    email_fields['version'] = params.pipelineVersion
     email_fields['runName'] = custom_runName ?: workflow.runName
     email_fields['success'] = workflow.success
     email_fields['dateComplete'] = workflow.complete
diff --git a/nextflow.config b/nextflow.config
index 8b5837ab0..d6e923b5b 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -44,6 +44,8 @@ params {
   maxMultiqcEmailFileSize = 25.MB
   readPaths = null
   tracedir = "${params.outdir}/pipeline_info"
+  // TODO: Remove this if/when we can. See https://github.com/nextflow-io/nextflow/issues/840
+  pipelineVersion = '1.0dev'
 }
 
 profiles {
@@ -139,7 +141,8 @@ manifest {
   description = 'Nextflow RNA-Seq analysis pipeline, part of the nf-core community.'
   homePage = 'https://github.com/nf-core/rnaseq'
   author = 'Phil Ewels, Rickard Hammarén'
-  pipelineVersion = '1.0dev'
+  // TODO: Define only here if/when we can. See https://github.com/nextflow-io/nextflow/issues/840
+  pipelineVersion = params.pipelineVersion
   mainScript = 'main.nf'
   nextflowVersion = '>=0.31.1'
 }

From d4b504906f8aa6a8e7c722887be6d9493eafa0c5 Mon Sep 17 00:00:00 2001
From: Phil Ewels <phil.ewels@scilifelab.se>
Date: Mon, 20 Aug 2018 16:30:23 +0200
Subject: [PATCH 29/32] Bump version number to v1.0 and write changelog

---
 .travis.yml     |  2 +-
 CHANGELOG.md    | 43 ++++++++++++++++++++++++++++++++++++++++---
 Dockerfile      |  2 +-
 Singularity     |  4 ++--
 environment.yml |  2 +-
 nextflow.config |  5 +++--
 6 files changed, 48 insertions(+), 10 deletions(-)

diff --git a/.travis.yml b/.travis.yml
index d99bbd9fc..ba99d8215 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -13,7 +13,7 @@ before_install:
   # Pull the docker image first so the test doesn't wait for this
   - docker pull nfcore/rnaseq
   # Fake the tag locally so that the pipeline runs properly
-  - docker tag nfcore/rnaseq nfcore/rnaseq:latest
+  - docker tag nfcore/rnaseq nfcore/rnaseq:1.0
 
 install:
   # Install Nextflow
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8c2a40096..4880f5608 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,42 @@
-## nf-core/rnaseq v1.0dev
-This release marks the point where the pipeline was moved from SciLifeLab/NGI-RNAseq
-over to the new nf-core community, at nf-core/rnaseq.
+# nf-core/rnaseq
+
+## [Version 1.0](https://github.com/nf-core/rnaseq/releases/tag/1.0) - 2018-08-20
+
+This release marks the point where the pipeline was moved from [SciLifeLab/NGI-RNAseq](https://github.com/SciLifeLab/NGI-RNAseq)
+over to the new [nf-core](http://nf-co.re/) community, at [nf-core/rnaseq](https://github.com/nf-core/rnaseq).
 
 View the previous changelog at [SciLifeLab/NGI-RNAseq/CHANGELOG.md](https://github.com/SciLifeLab/NGI-RNAseq/blob/master/CHANGELOG.md)
+
+In addition to porting to the new nf-core community, the pipeline has had a number of major changes in this version.
+There have been 157 commits by 16 different contributors coving 70 different files in the pipeline: 7,357 additions and 8,236 deletions!
+
+In summary, the main changes are:
+
+* Rebranding and renaming throughout the pipeline to nf-core
+* Updating many parts of the pipeline config and style to meet nf-core standards
+* Support for GFF files in addition to GTF files
+    * Just use `--gff` instead of `--gtf` when specifying a file path
+* New command line options to skip various quality control steps
+* More safety checks when launching a pipeline
+    * Several new sanity checks - for example, that the specified reference genome exists
+* Improved performance with memory usage (especially STAR and Picard)
+* New BigWig file outputs for plotting coverage across the genome
+* Refactored gene body coverage calculation, now much faster and using much less memory
+* Bugfixes in the MultiQC process to avoid edge cases where it wouldn't run
+* MultiQC report now automatically attached to the email sent when the pipeline completes
+* New testing method, with data on GitHub
+    * Now run pipeline with `-profile test` instead of using bash scripts
+* Rewritten continuous integration tests with Travis CI
+* New explicit support for Singularity containers
+* Improved MultiQC support for DupRadar and featureCounts
+    * Now works for all users instead of just NGI Stockholm
+* New configuration for use on AWS batch
+* Updated config syntax to support latest versions of Nextflow
+* Built-in support for a number of new local HPC systems
+    * CCGA, GIS, UCT HEX, updates to UPPMAX, CFC, BINAC, Hebbe, c3se
+* Slightly improved documentation (more updates to come)
+* Updated software packages
+
+...and many more minor tweaks.
+
+Thanks to everyone who has worked on this release!
diff --git a/Dockerfile b/Dockerfile
index 7e7bb43c7..431bc2793 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -5,4 +5,4 @@ LABEL authors="phil.ewels@scilifelab.se" \
 
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
-ENV PATH /opt/conda/envs/nf-core-rnaseq-1.0dev/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-rnaseq-1.0/bin:\$PATH
diff --git a/Singularity b/Singularity
index 86630108d..fd55e6532 100644
--- a/Singularity
+++ b/Singularity
@@ -4,10 +4,10 @@ Bootstrap:docker
 %labels
     MAINTAINER Phil Ewels <phil.ewels@scilifelab.se>
     DESCRIPTION Singularity image containing all requirements for the nf-core/rnaseq pipeline
-    VERSION 1.0dev
+    VERSION 1.0
 
 %environment
-    PATH=/opt/conda/envs/nf-core-rnaseq-1.0dev/bin:$PATH
+    PATH=/opt/conda/envs/nf-core-rnaseq-1.0/bin:\$PATH
     export PATH
 
 %files
diff --git a/environment.yml b/environment.yml
index 6b613db65..6f78e33ea 100644
--- a/environment.yml
+++ b/environment.yml
@@ -1,6 +1,6 @@
 # You can use this file to create a conda environment for this pipeline:
 #   conda env create -f environment.yml
-name: nf-core-rnaseq-1.0dev
+name: nf-core-rnaseq-1.0
 channels:
   - bioconda
   - conda-forge
diff --git a/nextflow.config b/nextflow.config
index d6e923b5b..50aa65607 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -10,10 +10,11 @@
 
 // Global default params, used in configs
 params {
-  container = 'nfcore/rnaseq:latest' // Container slug. Stable releases should specify release tag!
+  container = 'nfcore/rnaseq:1.0' // Container slug. Stable releases should specify release tag!
 
   // Pipeline Options
   aligner = 'star'
+  genome = false
   forward_stranded = false
   reverse_stranded = false
   unstranded = false
@@ -45,7 +46,7 @@ params {
   readPaths = null
   tracedir = "${params.outdir}/pipeline_info"
   // TODO: Remove this if/when we can. See https://github.com/nextflow-io/nextflow/issues/840
-  pipelineVersion = '1.0dev'
+  pipelineVersion = '1.0'
 }
 
 profiles {

From 0d0dab91b12b4c85cbdcbd9d5df49ee9e94858dd Mon Sep 17 00:00:00 2001
From: Phil Ewels <phil.ewels@scilifelab.se>
Date: Mon, 20 Aug 2018 16:40:22 +0200
Subject: [PATCH 30/32] Changelog typo fixed

---
 CHANGELOG.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 4880f5608..8b41e1d39 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,7 +8,7 @@ over to the new [nf-core](http://nf-co.re/) community, at [nf-core/rnaseq](https
 View the previous changelog at [SciLifeLab/NGI-RNAseq/CHANGELOG.md](https://github.com/SciLifeLab/NGI-RNAseq/blob/master/CHANGELOG.md)
 
 In addition to porting to the new nf-core community, the pipeline has had a number of major changes in this version.
-There have been 157 commits by 16 different contributors coving 70 different files in the pipeline: 7,357 additions and 8,236 deletions!
+There have been 157 commits by 16 different contributors covering 70 different files in the pipeline: 7,357 additions and 8,236 deletions!
 
 In summary, the main changes are:
 

From 3197bddf55e94ef6957509519cb97338889c4cb6 Mon Sep 17 00:00:00 2001
From: Phil Ewels <phil.ewels@scilifelab.se>
Date: Mon, 20 Aug 2018 17:09:22 +0200
Subject: [PATCH 31/32] Remove cheeky backslashes that crept in after version
 bump

---
 Dockerfile  | 2 +-
 Singularity | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index 431bc2793..1c7574a5d 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -5,4 +5,4 @@ LABEL authors="phil.ewels@scilifelab.se" \
 
 COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
-ENV PATH /opt/conda/envs/nf-core-rnaseq-1.0/bin:\$PATH
+ENV PATH /opt/conda/envs/nf-core-rnaseq-1.0/bin:$PATH
diff --git a/Singularity b/Singularity
index fd55e6532..fa004de48 100644
--- a/Singularity
+++ b/Singularity
@@ -7,7 +7,7 @@ Bootstrap:docker
     VERSION 1.0
 
 %environment
-    PATH=/opt/conda/envs/nf-core-rnaseq-1.0/bin:\$PATH
+    PATH=/opt/conda/envs/nf-core-rnaseq-1.0/bin:$PATH
     export PATH
 
 %files

From 0fe8b6cb7439567722809d68ab97f1faefd3e18b Mon Sep 17 00:00:00 2001
From: Alexander Peltzer <alexander.peltzer@uni-tuebingen.de>
Date: Mon, 20 Aug 2018 17:45:31 +0200
Subject: [PATCH 32/32] Add missing deepTools output for MultiQC/Report

---
 bin/scrape_software_versions.py | 2 ++
 main.nf                         | 1 +
 2 files changed, 3 insertions(+)

diff --git a/bin/scrape_software_versions.py b/bin/scrape_software_versions.py
index ba6e83ed5..eb7eb55c5 100755
--- a/bin/scrape_software_versions.py
+++ b/bin/scrape_software_versions.py
@@ -14,6 +14,7 @@
     'Picard MarkDuplicates': ['v_markduplicates.txt', r"([\d\.]+)-SNAPSHOT"],
     'Samtools': ['v_samtools.txt', r"samtools (\S+)"],
     'featureCounts': ['v_featurecounts.txt', r"featureCounts v(\S+)"],
+    'deepTools': ['v_deeptools.txt', r"bamCoverage (\S+)"],
     'StringTie': ['v_stringtie.txt', r"(\S+)"],
     'Preseq': ['v_preseq.txt', r"Version: (\S+)"],
     'RSeQC': ['v_rseqc.txt', r"read_duplication.py ([\d\.]+)"],
@@ -32,6 +33,7 @@
 results['featureCounts'] = '<span style="color:#999999;\">N/A</span>'
 results['StringTie'] = '<span style="color:#999999;\">N/A</span>'
 results['Preseq'] = '<span style="color:#999999;\">N/A</span>'
+results['deepTools'] = '<span style="color:#999999;\">N/A</span>'
 results['RSeQC'] = '<span style="color:#999999;\">N/A</span>'
 results['MultiQC'] = '<span style="color:#999999;\">N/A</span>'
 
diff --git a/main.nf b/main.nf
index 68afeca2b..a1abc371c 100644
--- a/main.nf
+++ b/main.nf
@@ -1055,6 +1055,7 @@ process get_software_versions {
     stringtie --version &> v_stringtie.txt
     preseq &> v_preseq.txt
     read_duplication.py --version &> v_rseqc.txt
+    echo \$(bamCoverage --version 2>&1) > v_deeptools.txt
     featureCounts -v &> v_featurecounts.txt
     picard MarkDuplicates --version &> v_markduplicates.txt  || true
     samtools --version &> v_samtools.txt