From 199fc7289d2780471397098578c0c51329378b8d Mon Sep 17 00:00:00 2001
From: MaxUlysse <max.u.garcia@gmail.com>
Date: Wed, 22 May 2019 15:37:49 +0200
Subject: [PATCH 01/11] add tiddit to container

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

diff --git a/environment.yml b/environment.yml
index 891322f26e..023b057811 100644
--- a/environment.yml
+++ b/environment.yml
@@ -26,5 +26,6 @@ dependencies:
   - samtools=1.9
   - snpeff=4.3.1t
   - strelka=2.9.10
+  - tiddit=2.6.0
   - vcfanno=0.3.1
   - vcftools=0.1.16

From a385337162428ef7e0180b6430a9f3fd9a30951e Mon Sep 17 00:00:00 2001
From: MaxUlysse <max.u.garcia@gmail.com>
Date: Wed, 22 May 2019 15:37:58 +0200
Subject: [PATCH 02/11] add process for TIDDIT

---
 main.nf | 57 +++++++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 49 insertions(+), 8 deletions(-)

diff --git a/main.nf b/main.nf
index 44cbb28c91..a7e1506074 100644
--- a/main.nf
+++ b/main.nf
@@ -50,12 +50,14 @@ def helpMessage() {
                                     Available: Mapping, Recalibrate, VariantCalling, Annotate
                                     Default: Mapping
         --targetBED                 Target BED file for targeted or whole exome sequencing
-        --tools                     Specify tools to use for variant calling
+        --tools                     Specify tools to use for variant calling:
                                     Available: ASCAT, ControlFREEC, FreeBayes, HaplotypeCaller
-                                    Manta, mpileup, MuTect2, Strelka
+                                    Manta, mpileup, MuTect2, Strelka, TIDDIT
+                                    or for annotation:
+                                    snpEff, VEP
                                     Default: HaplotypeCaller, Manta, Strelka
         --annotateTools             Specify from which tools Sarek will annotate VCF, only for step annotate
-                                    Available: HaplotypeCaller, Manta, MuTect2, Strelka
+                                    Available: HaplotypeCaller, Manta, MuTect2, Strelka, TIDDIT
 
     References                      If not specified in the configuration file or you wish to overwrite any of the references.
         --acLoci                    acLoci file
@@ -792,7 +794,7 @@ bamRecal = bamRecal.dump(tag:'BAM')
 // Manta will be run in Germline mode, or in Tumor mode depending on status
 // HaplotypeCaller and Strelka will be run for Normal and Tumor samples
 
-(bamMantaSingle, bamStrelkaSingle, bamRecalAllTemp, bamRecalAll) = bamRecal.into(4)
+(bamMantaSingle, bamStrelkaSingle, bamTIDDIT, bamRecalAll, bamRecalAllTemp) = bamRecal.into(5)
 
 // To speed Variant Callers up we are chopping the reference into smaller pieces
 // Do variant calling by this intervals, and re-merge the VCFs
@@ -975,6 +977,40 @@ process MantaSingle {
 
 vcfMantaSingle = vcfMantaSingle.dump(tag:'Single Manta')
 
+// STEP TIDDIT
+
+process TIDDIT {
+    tag {idSample}
+
+    publishDir "${params.outdir}/VariantCalling/${idSample}/TIDDIT", mode: params.publishDirMode
+
+    publishDir params.outdir, mode: params.publishDirMode,
+        saveAs: {
+            if (it == "TIDDIT_${idSample}.vcf") "VariantCalling/${idSample}/TIDDIT/${it}"
+            else "Reports/${idSample}/TIDDIT/${it}"
+        }
+
+    input:
+        set idPatient, idSample, file(bam), file(bai) from bamTIDDIT
+        set file(genomeFile), file(genomeIndex) from Channel.value([
+            referenceMap.genomeFile,
+            referenceMap.genomeIndex
+        ])
+
+    output:
+        set val("TIDDIT"), idPatient, idSample, file("*.vcf") into vcfTIDDIT
+        set file("*."), file("*.") into tidditOut
+
+    when: 'tiddit' in tools
+
+    script:
+    """
+    tiddit --sv -o TIDDIT_${idSample}.vcf --bam ${bam} --ref ${genomeFile}
+    """
+}
+
+vcfTIDDIT = vcfTIDDIT.dump(tag:'TIDDIT')
+
 /*
 ================================================================================
                              SOMATIC VARIANT CALLING
@@ -1104,7 +1140,7 @@ process ConcatVCF {
     // we have this funny *_* pattern to avoid copying the raw calls to publishdir
         set variantCaller, idPatient, idSample, file("*_*.vcf.gz"), file("*_*.vcf.gz.tbi") into vcfConcatenated
 
-    when: ('haplotypecaller' in tools || 'mutect2' in tools || 'freebayes' in tools)
+    when: 'haplotypecaller' in tools || 'mutect2' in tools || 'freebayes' in tools
 
     script:
     if (variantCaller == 'HaplotypeCallerGVCF') outputFile = "HaplotypeCaller_${idSample}.g.vcf"
@@ -1191,7 +1227,7 @@ process Manta {
     options = params.targetBED ? "--exome --callRegions call_targets.bed.gz" : ""
     """
     ${beforeScript}
-        configManta.py \
+    configManta.py \
         --normalBam ${bamNormal} \
         --tumorBam ${bamTumor} \
         --reference ${genomeFile} \
@@ -1391,7 +1427,7 @@ process Mpileup {
     output:
         set idPatient, idSample, file("${intervalBed.baseName}_${idSample}.pileup.gz") into mpileupMerge
 
-    when: ('controlfreec' in tools || 'mpileup' in tools)
+    when: 'controlfreec' in tools || 'mpileup' in tools
 
     script:
     """
@@ -1417,7 +1453,7 @@ process MergeMpileup {
     output:
         set idPatient, idSample, file("${idSample}.pileup.gz") into mpileupOut
 
-    when: ('controlfreec' in tools || 'mpileup' in tools)
+    when: 'controlfreec' in tools || 'mpileup' in tools
 
     script:
     """
@@ -1581,6 +1617,10 @@ vcfKeep = Channel.empty().mix(
     vcfStrelkaBPSNVS.map {
         variantcaller, idPatient, idSample, vcf, tbi ->
         [variantcaller, idSample, vcf[1]]
+    },
+    vcfTIDDIT.map {
+        variantcaller, idPatient, idSample, vcf, tbi ->
+        [variantcaller, idSample, vcf]
     })
 
 (vcfBCFtools, vcfVCFtools, vcfAnnotation) = vcfKeep.into(3)
@@ -2192,6 +2232,7 @@ def defineToolList() {
         'mutect2',
         'snpeff',
         'strelka',
+        'tiddit',
         'vep'
     ]
 }

From 1fc66547b35a3e4896abfa9c6b590b97549f1186 Mon Sep 17 00:00:00 2001
From: MaxUlysse <max.u.garcia@gmail.com>
Date: Wed, 22 May 2019 16:14:03 +0200
Subject: [PATCH 03/11] update TIDDIT to 2.7.1

---
 environment.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/environment.yml b/environment.yml
index 023b057811..2ef20b6310 100644
--- a/environment.yml
+++ b/environment.yml
@@ -26,6 +26,6 @@ dependencies:
   - samtools=1.9
   - snpeff=4.3.1t
   - strelka=2.9.10
-  - tiddit=2.6.0
+  - tiddit=2.7.1
   - vcfanno=0.3.1
   - vcftools=0.1.16

From 05d155d213cb318e69c12495086a9ab2763a9849 Mon Sep 17 00:00:00 2001
From: MaxUlysse <max.u.garcia@gmail.com>
Date: Fri, 2 Aug 2019 10:16:37 +0200
Subject: [PATCH 04/11] fix merge issues

---
 main.nf | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/main.nf b/main.nf
index 8856fdf63f..07ab375805 100644
--- a/main.nf
+++ b/main.nf
@@ -49,31 +49,21 @@ def helpMessage() {
         --step                      Specify starting step
                                     Available: Mapping, Recalibrate, VariantCalling, Annotate
                                     Default: Mapping
-<<<<<<< HEAD
-        --targetBED                 Target BED file for targeted or whole exome sequencing
         --tools                     Specify tools to use for variant calling:
                                     Available: ASCAT, ControlFREEC, FreeBayes, HaplotypeCaller
                                     Manta, mpileup, MuTect2, Strelka, TIDDIT
-                                    or for annotation:
-                                    snpEff, VEP
-                                    Default: HaplotypeCaller, Manta, Strelka
-        --annotateTools             Specify from which tools Sarek will annotate VCF, only for step annotate
-                                    Available: HaplotypeCaller, Manta, MuTect2, Strelka, TIDDIT
-=======
-        --tools                     Specify tools to use for variant calling, and annotation
-                                    Available: ASCAT, ControlFREEC, FreeBayes, HaplotypeCaller
-                                    Manta, mpileup, MuTect2, Strelka, snpEff, VEP, merge
+                                    and/or for annotation:
+                                    snpEff, VEP, merge
                                     Default: None
         --skip                      Specify which QC tools to skip when running Sarek
                                     Available: bamQC, BCFtools, FastQC, MultiQC, samtools, vcftools, versions
                                     Default: None
         --annotateTools             Specify from which tools Sarek will look for VCF files to annotate, only for step annotate
-                                    Available: HaplotypeCaller, Manta, MuTect2, Strelka
+                                    Available: HaplotypeCaller, Manta, MuTect2, Strelka, TIDDIT
                                     Default: None
         --annotation_cache          Enable the use of cache for annotation, to be used with --snpEff_cache and/or --vep_cache
         --snpEff_cache              Specity the path to snpEff cache, to be used with --annotation_cache
         --vep_cache                 Specity the path to VEP cache, to be used with --annotation_cache
->>>>>>> upstream/dev
 
     References                      If not specified in the configuration file or you wish to overwrite any of the references.
         --acLoci                    acLoci file

From 9f464064d1935ae0aef7da30b8a1931a30a3ead3 Mon Sep 17 00:00:00 2001
From: MaxUlysse <max.u.garcia@gmail.com>
Date: Fri, 2 Aug 2019 10:20:13 +0200
Subject: [PATCH 05/11] feat: add tests for TIDDIT

---
 scripts/run_tests.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/scripts/run_tests.sh b/scripts/run_tests.sh
index 43661935ed..46d85d17f6 100755
--- a/scripts/run_tests.sh
+++ b/scripts/run_tests.sh
@@ -88,7 +88,7 @@ fi
 
 if [[ ALL,SOMATIC =~ $TEST ]]
 then
-  OPTIONS="--tools FreeBayes,HaplotypeCaller,Manta,Strelka,Mutect2"
+  OPTIONS="--tools FreeBayes,HaplotypeCaller,Manta,Strelka,TIDDIT,Mutect2"
   if [[ $OFFLINE == false ]]
   then
     run_sarek ${OPTIONS}
@@ -100,7 +100,7 @@ fi
 
 if [[ ALL,TARGETED =~ $TEST ]]
 then
-  OPTIONS="--tools FreeBayes,HaplotypeCaller,Manta,Strelka,Mutect2"
+  OPTIONS="--tools FreeBayes,HaplotypeCaller,Manta,Strelka,TIDDIT,Mutect2"
   if [[ $OFFLINE == false ]]
   then
     run_sarek ${OPTIONS} --targetBED https://github.com/nf-core/test-datasets/raw/sarek/testdata/target.bed
@@ -135,7 +135,7 @@ fi
 
 if [[ MULTIPLE =~ $TEST ]]
 then
-  OPTIONS="--tools FreeBayes,HaplotypeCaller,Manta,Strelka,Mutect2,snpEff,VEP,merge"
+  OPTIONS="--tools FreeBayes,HaplotypeCaller,Manta,Strelka,TIDDIT,Mutect2,snpEff,VEP,merge"
   if [[ $OFFLINE == false ]]
   then
     run_sarek ${OPTIONS} --sample https://github.com/nf-core/test-datasets/raw/sarek/testdata/tsv/tiny-multiple-https.tsv

From 22ca372c6a7208553954b77d11ef3c45ab8647c9 Mon Sep 17 00:00:00 2001
From: MaxUlysse <max.u.garcia@gmail.com>
Date: Mon, 5 Aug 2019 17:06:42 +0200
Subject: [PATCH 06/11] feat: update CHANGELOG

---
 CHANGELOG.md | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 910f48ef5b..a5cf4380c2 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,13 +12,13 @@ Initial release of `nf-core/sarek`, created with the [nf-core](http://nf-co.re/)
 ### `Added`
 
 - [#2](https://github.com/nf-core/sarek/pull/2) - Create `nf-core/sarek` `environment.yml` file
-- [#2](https://github.com/nf-core/sarek/pull/2), [#3](https://github.com/nf-core/sarek/pull/3), [#4](https://github.com/nf-core/sarek/pull/4), [#5](https://github.com/nf-core/sarek/pull/5), [#7](https://github.com/nf-core/sarek/pull/7), [#9](https://github.com/nf-core/sarek/pull/9), [#11](https://github.com/nf-core/sarek/pull/11), [#12](https://github.com/nf-core/sarek/pull/12) - Add CI for `nf-core/sarek`
+- [#2](https://github.com/nf-core/sarek/pull/2), [#3](https://github.com/nf-core/sarek/pull/3), [#4](https://github.com/nf-core/sarek/pull/4), [#5](https://github.com/nf-core/sarek/pull/5), [#7](https://github.com/nf-core/sarek/pull/7), [#9](https://github.com/nf-core/sarek/pull/9), [#10](https://github.com/nf-core/sarek/pull/10), [#11](https://github.com/nf-core/sarek/pull/11), [#12](https://github.com/nf-core/sarek/pull/12) - Add CI for `nf-core/sarek`
 - [#3](https://github.com/nf-core/sarek/pull/3) - Add preprocessing to `nf-core/sarek`
 - [#4](https://github.com/nf-core/sarek/pull/4) - Add variant calling to `nf-core/sarek` with `HaplotypeCaller`, and single mode `Manta` and `Strelka`
 - [#5](https://github.com/nf-core/sarek/pull/5) - Add variant calling to `nf-core/sarek` with `Manta`, `Strelka`, `Strelka Best Practices`, `MuTecT2`, `FreeBayes`, `ASCAT`, `ControlFREEC`
 - [#6](https://github.com/nf-core/sarek/pull/6) - Add default containers for annotation to `nf-core/sarek`
-- [#7](https://github.com/nf-core/sarek/pull/7) - Add annotation
 - [#7](https://github.com/nf-core/sarek/pull/7) - Add MultiQC
+- [#7](https://github.com/nf-core/sarek/pull/7) - Add annotation
 - [#7](https://github.com/nf-core/sarek/pull/7) - Add social preview image in `png` and `svg` format
 - [#7](https://github.com/nf-core/sarek/pull/7), [#8](https://github.com/nf-core/sarek/pull/8), [#11](https://github.com/nf-core/sarek/pull/11) - Add helper script `run_tests.sh` to run different tests
 - [#7](https://github.com/nf-core/sarek/pull/7), [#8](https://github.com/nf-core/sarek/pull/8), [#9](https://github.com/nf-core/sarek/pull/9) - Add automatic build of specific containers for annotation for `GRCh37`, `GRCh38` and `GRCm38` using `CircleCI`
@@ -26,23 +26,24 @@ Initial release of `nf-core/sarek`, created with the [nf-core](http://nf-co.re/)
 - [#7](https://github.com/nf-core/sarek/pull/7), [#9](https://github.com/nf-core/sarek/pull/9), [#11](https://github.com/nf-core/sarek/pull/11), [#12](https://github.com/nf-core/sarek/pull/12) - Add helper script `download_image.sh` to download containers for testing
 - [#8](https://github.com/nf-core/sarek/pull/8) - Add test configation for easier testing
 - [#9](https://github.com/nf-core/sarek/pull/9), [#11](https://github.com/nf-core/sarek/pull/11) - Add scripts for `ASCAT`
+- [#10](https://github.com/nf-core/sarek/pull/10) - Add `TIDDIT` to detect structural variants
 - [#11](https://github.com/nf-core/sarek/pull/11) - Add automatic build of specific containers for annotation for `CanFam3.1` using `CircleCI`
 - [#11](https://github.com/nf-core/sarek/pull/11), [#12](https://github.com/nf-core/sarek/pull/12) - Add posters and abstracts
-- [#12](https://github.com/nf-core/sarek/pull/12) - Use `label` for processes configation
-- [#12](https://github.com/nf-core/sarek/pull/12) - Add helper scripts `filter_locifile.py` and `selectROI.py`
 - [#12](https://github.com/nf-core/sarek/pull/12) - Add helper script `make_snapshot.sh` to make an archive for usage on a secure cluster
+- [#12](https://github.com/nf-core/sarek/pull/12) - Add helper scripts `filter_locifile.py` and `selectROI.py`
+- [#12](https://github.com/nf-core/sarek/pull/12) - Use `label` for processes configation
 - [#13](https://github.com/nf-core/sarek/pull/13) - Add Citation documentation
 - [#13](https://github.com/nf-core/sarek/pull/13) - Add `BamQC` process
 - [#13](https://github.com/nf-core/sarek/pull/13) - Add `CompressVCFsnpEff` and `CompressVCFvep` processes
 - [#18](https://github.com/nf-core/sarek/pull/18) - Add `--no-reports` option for tests + add snpEff,VEP,merge to MULTIPLE test
-- [#18](https://github.com/nf-core/sarek/pull/18) - Add possibility to download other genome for `sareksnpeff` and `sarekvep` containers
-- [#18](https://github.com/nf-core/sarek/pull/18) - Add params `--skip` to skip specified QC tools
 - [#18](https://github.com/nf-core/sarek/pull/18) - Add logo to MultiQC report
+- [#18](https://github.com/nf-core/sarek/pull/18) - Add params `--skip` to skip specified QC tools
+- [#18](https://github.com/nf-core/sarek/pull/18) - Add possibility to download other genome for `sareksnpeff` and `sarekvep` containers
 - [#20](https://github.com/nf-core/sarek/pull/20) - Add `markdownlint` config file
 
 ### `Changed`
 
-- [#1](https://github.com/nf-core/sarek/pull/1), [#2](https://github.com/nf-core/sarek/pull/2), [#3](https://github.com/nf-core/sarek/pull/3), [#4](https://github.com/nf-core/sarek/pull/4), [#5](https://github.com/nf-core/sarek/pull/5), [#6](https://github.com/nf-core/sarek/pull/6), [#7](https://github.com/nf-core/sarek/pull/7), [#8](https://github.com/nf-core/sarek/pull/8), [#9](https://github.com/nf-core/sarek/pull/9), [#11](https://github.com/nf-core/sarek/pull/11), [#12](https://github.com/nf-core/sarek/pull/12), [#18](https://github.com/nf-core/sarek/pull/18), [#20](https://github.com/nf-core/sarek/pull/20) - Update docs
+- [#1](https://github.com/nf-core/sarek/pull/1), [#2](https://github.com/nf-core/sarek/pull/2), [#3](https://github.com/nf-core/sarek/pull/3), [#4](https://github.com/nf-core/sarek/pull/4), [#5](https://github.com/nf-core/sarek/pull/5), [#6](https://github.com/nf-core/sarek/pull/6), [#7](https://github.com/nf-core/sarek/pull/7), [#8](https://github.com/nf-core/sarek/pull/8), [#9](https://github.com/nf-core/sarek/pull/9), [#10](https://github.com/nf-core/sarek/pull/10), [#11](https://github.com/nf-core/sarek/pull/11), [#12](https://github.com/nf-core/sarek/pull/12), [#18](https://github.com/nf-core/sarek/pull/18), [#20](https://github.com/nf-core/sarek/pull/20) - Update docs
 - [#4](https://github.com/nf-core/sarek/pull/4) - Update `cancerit-allelecount` from `2.1.2` to `4.0.2`
 - [#4](https://github.com/nf-core/sarek/pull/4) - Update `gatk4` from `4.1.1.0` to `4.1.2.0`
 - [#7](https://github.com/nf-core/sarek/pull/7) - `--sampleDir` is now deprecated, use `--sample` instead

From 3da452dbd6c8b14a224024e241ce446571a0b298 Mon Sep 17 00:00:00 2001
From: MaxUlysse <max.u.garcia@gmail.com>
Date: Tue, 6 Aug 2019 11:49:18 +0200
Subject: [PATCH 07/11] feat: Add documentation for TIDDIT

---
 docs/containers.md |  2 ++
 docs/output.md     | 32 ++++++++++++++++++++++++++++++--
 2 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/docs/containers.md b/docs/containers.md
index fd5de52105..20d7ee30e0 100644
--- a/docs/containers.md
+++ b/docs/containers.md
@@ -32,6 +32,7 @@ For annotation, the main container can be used, but the cache has to be download
 - Contain **[samtools][samtools-link]** 1.9
 - Contain **[snpEff][snpeff-link]** 4.3.1t
 - Contain **[Strelka2][strelka-link]** 2.9.10
+- Contain **[TIDDIT][tiddit-link]** 2.7.1
 - Contain **[VCFanno][vcfanno-link]** 0.3.1
 - Contain **[VCFtools][vcftools-link]** 0.1.16
 - Contain **[VEP][vep-link]** 96.0
@@ -111,6 +112,7 @@ The `environment.yml` file can easilly be modified if particular versions of too
 [sareksnpeff-docker-badge]: https://img.shields.io/docker/automated/nfcore/sareksnpeff.svg
 [sareksnpeff-docker-link]: https://hub.docker.com/r/nfcore/sareksnpeff
 [strelka-link]: https://github.com/Illumina/strelka
+[tiddit-link]: https://github.com/SciLifeLab/TIDDIT
 [vcfanno-link]: https://github.com/brentp/vcfanno
 [vcftools-link]: https://vcftools.github.io/index.html
 [vep-link]: https://github.com/Ensembl/ensembl-vep
diff --git a/docs/output.md b/docs/output.md
index 105010936c..5e26d8cee0 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -24,6 +24,7 @@ The pipeline processes data using the following steps:
         * [`Strelka2`](#Strelka2)
     * Structural variants
         * [`Manta`](#Manta)
+        * [`TIDDIT`](#TIDDIT)
     * Sample heterogeneity, ploidy and CNVs
         * `alleleCounter`
         * [`ConvertAlleleCounts`](#ConvertAlleleCounts)
@@ -48,6 +49,7 @@ The pipeline processes data using the following steps:
         * [`MultiQC`](#MultiQC)
 
 ## Preprocessing
+
 Sarek preprocesses raw FastQ files or unmapped BAM files, based on [GATK best practices](https://software.broadinstitute.org/gatk/best-practices/).
 
 BAM files with Recalibration tables can also be used as an input to start with the recalibration of said BAM files, for more information see [TSV files output information](#TSV-files)
@@ -79,6 +81,7 @@ For all samples:
   * BAM file and index
 
 ### TSV files
+
 The TSV files are autogenerated and can be used by Sarek for further processing and/or variant calling.
 
 For further reading and documentation see the [input documentation](https://github.com/nf-core/sarek/blob/master/docs/input.md).
@@ -89,14 +92,16 @@ For all samples:
 * `duplicateMarked.tsv` and `recalibrated.tsv`
   * TSV files to start Sarek from `recalibration` or `variantcalling` steps.
 * `duplicateMarked_[SAMPLE].tsv` and `recalibrated_[SAMPLE].tsv`
-    * TSV files to start Sarek from `recalibration` or `variantcalling` steps for a specific sample.
+  * TSV files to start Sarek from `recalibration` or `variantcalling` steps for a specific sample.
 
 ## Variant Calling
+
 All the results regarding variant-calling are collected in this directory.
 
 Recalibrated BAM files can also be used as an input to start the Variant Calling, for more information see [TSV files output information](#TSV-files)
 
 ### FreeBayes
+
 [FreeBayes](https://github.com/ekg/freebayes) is a Bayesian genetic variant detector designed to find small polymorphisms, specifically SNPs, indels, MNPs, and complex events smaller than the length of a short-read sequencing alignment..
 
 For further reading and documentation see the [FreeBayes manual](https://github.com/ekg/freebayes/blob/master/README.md#user-manual-and-guide).
@@ -108,6 +113,7 @@ For a Tumor/Normal pair only:
   * VCF with Tabix index
 
 ### HaplotypeCaller
+
 [GATK HaplotypeCaller](https://github.com/broadinstitute/gatk) calls germline SNPs and indels via local re-assembly of haplotypes.
 
 Germline calls are provided for all samples, to able comparison of both tumor and normal for possible mixup.
@@ -121,6 +127,7 @@ For all samples:
   * VCF with Tabix index
 
 ### GenotypeGVCFs
+
 [GATK GenotypeGVCFs](https://github.com/broadinstitute/gatk) performs joint genotyping on one or more samples pre-called with HaplotypeCaller.
 
 Germline calls are provided for all samples, to able comparison of both tumor and normal for possible mixup.
@@ -134,6 +141,7 @@ For all samples:
   * VCF with Tabix index
 
 ### MuTect2
+
 [GATK MuTect2](https://github.com/broadinstitute/gatk) calls somatic SNVs and indels via local assembly of haplotypes.
 
 For further reading and documentation see the [MuTect2 manual](https://software.broadinstitute.org/gatk/documentation/tooldocs/4.1.2.0/org_broadinstitute_hellbender_tools_walkers_mutect_Mutect2.php).
@@ -144,7 +152,22 @@ For a Tumor/Normal pair only:
 * `MuTect2_[TUMORSAMPLE]_vs_[NORMALSAMPLE].vcf.gz` and `MuTect2_[TUMORSAMPLE]_vs_[NORMALSAMPLE].vcf.gz.tbi`
   * VCF with Tabix index
 
+### TIDDIT
+
+[TIDDIT](https://github.com/SciLifeLab/TIDDIT)identifies intra and inter-chromosomal translocations, deletions, tandem-duplications and inversions.
+
+Germline calls are provided for all samples, to able comparison of both tumor and normal for possible mixup.
+
+For further reading and documentation see the [TIDDIT manual](https://github.com/SciLifeLab/TIDDIT/blob/master/README.md).
+
+For all samples:
+**Output directory: `results/VariantCalling/[SAMPLE]/TIDDIT`**
+
+* `TIDDIT_[SAMPLE].g.vcf.gz` and `TIDDIT_[SAMPLE].g.vcf.gz.tbi`
+  * VCF with Tabix index
+
 ### Strelka2
+
 [Strelka2](https://github.com/Illumina/strelka) is a fast and accurate small variant caller optimized for analysis of germline variation in small cohorts and somatic variation in tumor/normal sample pairs.
 
 For further reading and documentation see the [Strelka2 user guide](https://github.com/Illumina/strelka/blob/v2.9.x/docs/userGuide/README.md).
@@ -167,15 +190,17 @@ For a Tumor/Normal pair:
 
 Using [Strelka Best Practices](https://github.com/Illumina/strelka/blob/v2.9.x/docs/userGuide/README.md#somatic-configuration-example) with the `candidateSmallIndels` from `Manta`:
 **Output directory: `results/VariantCalling/[TUMOR_vs_NORMAL]/Strelka`**
+
 * `StrelkaBP_[TUMORSAMPLE]_vs_[NORMALSAMPLE]_somatic_indels.vcf.gz` and `StrelkaBP_[TUMORSAMPLE]_vs_[NORMALSAMPLE]_somatic_indels.vcf.gz.tbi`
   * VCF with Tabix index
 * `StrelkaBP_[TUMORSAMPLE]_vs_[NORMALSAMPLE]_somatic_snvs.vcf.gz` and `StrelkaBP_[TUMORSAMPLE]_vs_[NORMALSAMPLE]_somatic_snvs.vcf.gz.tbi`
   * VCF with Tabix index
 
 ### Manta
+
 [Manta](https://github.com/Illumina/manta) calls structural variants (SVs) and indels from mapped paired-end sequencing reads.
 It is optimized for analysis of germline variation in small sets of individuals and somatic variation in tumor/normal sample pairs.
-`Manta` provides a candidate list for small indels also that can be fed to `Strelka` following [Strelka Best Practices](https://github.com/Illumina/strelka/blob/v2.9.x/docs/userGuide/README.md#somatic-configuration-example.
+`Manta` provides a candidate list for small indels also that can be fed to `Strelka` following [Strelka Best Practices](https://github.com/Illumina/strelka/blob/v2.9.x/docs/userGuide/README.md#somatic-configuration-example).
 
 For further reading and documentation see the [Manta user guide](https://github.com/Illumina/manta/blob/master/docs/userGuide/README.md).
 
@@ -188,10 +213,12 @@ For all samples:
   * VCF with Tabix index
 
 For Normal sample only:
+
 * `Manta_[NORMALSAMPLE].diploidSV.vcf.gz` and `Manta_[NORMALSAMPLE].diploidSV.vcf.gz.tbi`
   * VCF with Tabix index
 
 For a Tumor sample only:
+
 * `Manta_[TUMORSAMPLE].tumorSV.vcf.gz` and `Manta_[TUMORSAMPLE].tumorSV.vcf.gz.tbi`
   * VCF with Tabix index
 
@@ -208,6 +235,7 @@ For a Tumor/Normal pair only:
   * VCF with Tabix index
 
 ### ConvertAlleleCounts
+
 [ConvertAlleleCounts](https://github.com/nf-core/sarek/blob/master/bin/convertAlleleCounts.r) is a R-script for converting output from AlleleCount to BAF and LogR values.
 
 For a Tumor/Normal pair only:

From e79211ce87fa32f5c3309bb858cca6bd0d235149 Mon Sep 17 00:00:00 2001
From: MaxUlysse <max.u.garcia@gmail.com>
Date: Tue, 6 Aug 2019 11:51:53 +0200
Subject: [PATCH 08/11] fix: arrange TIDDIT output

---
 main.nf | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/main.nf b/main.nf
index 07ab375805..b8b1dd7102 100644
--- a/main.nf
+++ b/main.nf
@@ -967,7 +967,7 @@ process MantaSingle {
         ])
 
     output:
-        set val("Manta"), idPatient, idSample,  file("*.vcf.gz"), file("*.vcf.gz.tbi") into vcfMantaSingle
+        set val("Manta"), idPatient, idSample, file("*.vcf.gz"), file("*.vcf.gz.tbi") into vcfMantaSingle
 
     when: 'manta' in tools
 
@@ -1025,14 +1025,18 @@ process TIDDIT {
         ])
 
     output:
-        set val("TIDDIT"), idPatient, idSample, file("*.vcf") into vcfTIDDIT
-        set file("*."), file("*.") into tidditOut
+        set val("TIDDIT"), idPatient, idSample, file("*.vcf.gz"), file("*.tbi") into vcfTIDDIT
+        set file("TIDDIT_${idSample}.ploidy.tab"), file("TIDDIT_${idSample}.signals.tab") into tidditOut
 
     when: 'tiddit' in tools
 
     script:
     """
-    tiddit --sv -o TIDDIT_${idSample}.vcf --bam ${bam} --ref ${genomeFile}
+    tiddit --sv -o TIDDIT_${idSample} --bam ${bam} --ref ${genomeFile}
+
+    bgzip --threads ${task.cpus} -c TIDDIT_${idSample}.vcf > TIDDIT_${idSample}.vcf.gz
+
+    tabix TIDDIT_${idSample}.vcf.gz
     """
 }
 
@@ -1396,7 +1400,7 @@ alleleCounterOut = alleleCountOutNormal.combine(alleleCountOutTumor)
 
 alleleCounterOut = alleleCounterOut.map {
     idPatientNormal, idSampleNormal, alleleCountOutNormal,
-    idPatientTumor,  idSampleTumor,  alleleCountOutTumor ->
+    idPatientTumor, idSampleTumor, alleleCountOutTumor ->
     [idPatientNormal, idSampleNormal, idSampleTumor, alleleCountOutNormal, alleleCountOutTumor]
 }
 
@@ -1525,7 +1529,7 @@ mpileupOut = mpileupOutNormal.combine(mpileupOutTumor)
 
 mpileupOut = mpileupOut.map {
     idPatientNormal, idSampleNormal, mpileupOutNormal,
-    idPatientTumor,  idSampleTumor,  mpileupOutTumor ->
+    idPatientTumor, idSampleTumor, mpileupOutTumor ->
     [idPatientNormal, idSampleNormal, idSampleTumor, mpileupOutNormal, mpileupOutTumor]
 }
 
@@ -1862,7 +1866,7 @@ process VEP {
     }
 
     input:
-        set variantCaller,  idSample, file(vcf), file(idx) from vcfVep
+        set variantCaller, idSample, file(vcf), file(idx) from vcfVep
         file dataDir from Channel.value(params.vep_cache ? file(params.vep_cache) : "null")
         val cache_version from Channel.value(params.genomes[params.genome].vepCacheVersion)
         set file(cadd_WG_SNVs), file(cadd_WG_SNVs_tbi), file(cadd_InDels), file(cadd_InDels_tbi) from Channel.value([
@@ -1925,7 +1929,7 @@ process VEPmerge {
     }
 
     input:
-        set variantCaller,  idSample, file(vcf), file(idx) from compressVCFsnpEffOut
+        set variantCaller, idSample, file(vcf), file(idx) from compressVCFsnpEffOut
         file dataDir from Channel.value(params.vep_cache ? file(params.vep_cache) : "null")
         val cache_version from Channel.value(params.genomes[params.genome].vepCacheVersion)
         set file(cadd_WG_SNVs), file(cadd_WG_SNVs_tbi), file(cadd_InDels), file(cadd_InDels_tbi) from Channel.value([

From a64aef875b45ed86cec95bfb081c0c82fd7d5ad2 Mon Sep 17 00:00:00 2001
From: MaxUlysse <max.u.garcia@gmail.com>
Date: Tue, 6 Aug 2019 12:44:32 +0200
Subject: [PATCH 09/11] feat: filter out low quality calls from TIDDIT

---
 main.nf | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/main.nf b/main.nf
index b8b1dd7102..35d743a470 100644
--- a/main.nf
+++ b/main.nf
@@ -1026,7 +1026,7 @@ process TIDDIT {
 
     output:
         set val("TIDDIT"), idPatient, idSample, file("*.vcf.gz"), file("*.tbi") into vcfTIDDIT
-        set file("TIDDIT_${idSample}.ploidy.tab"), file("TIDDIT_${idSample}.signals.tab") into tidditOut
+        set file("TIDDIT_${idSample}.old.vcf"), file("TIDDIT_${idSample}.ploidy.tab"), file("TIDDIT_${idSample}.signals.tab"), file("TIDDIT_${idSample}.wig"), file("TIDDIT_${idSample}.gc.wig") into tidditOut
 
     when: 'tiddit' in tools
 
@@ -1034,6 +1034,10 @@ process TIDDIT {
     """
     tiddit --sv -o TIDDIT_${idSample} --bam ${bam} --ref ${genomeFile}
 
+    cp TIDDIT_${idSample}.vcf TIDDIT_${idSample}.old.vcf
+
+    grep -E "#|PASS" TIDDIT_${idSample}.vcf > TIDDIT_${idSample}.vcf
+
     bgzip --threads ${task.cpus} -c TIDDIT_${idSample}.vcf > TIDDIT_${idSample}.vcf.gz
 
     tabix TIDDIT_${idSample}.vcf.gz

From e24688cfa8fe17bda327ecbcd91c0eb16edbc18c Mon Sep 17 00:00:00 2001
From: MaxUlysse <max.u.garcia@gmail.com>
Date: Tue, 6 Aug 2019 12:44:45 +0200
Subject: [PATCH 10/11] feat: complete TIDDIT docs

---
 docs/output.md | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/docs/output.md b/docs/output.md
index 5e26d8cee0..3d8a44fd48 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -157,14 +157,25 @@ For a Tumor/Normal pair only:
 [TIDDIT](https://github.com/SciLifeLab/TIDDIT)identifies intra and inter-chromosomal translocations, deletions, tandem-duplications and inversions.
 
 Germline calls are provided for all samples, to able comparison of both tumor and normal for possible mixup.
+Low quality calls are removed internally, to simplify processing of variant calls but they are saved by Sarek.
 
 For further reading and documentation see the [TIDDIT manual](https://github.com/SciLifeLab/TIDDIT/blob/master/README.md).
 
 For all samples:
 **Output directory: `results/VariantCalling/[SAMPLE]/TIDDIT`**
 
-* `TIDDIT_[SAMPLE].g.vcf.gz` and `TIDDIT_[SAMPLE].g.vcf.gz.tbi`
+* `TIDDIT_[SAMPLE].vcf.gz` and `TIDDIT_[SAMPLE].vcf.gz.tbi`
   * VCF with Tabix index
+* `TIDDIT_[SAMPLE].signals.tab`
+  * tab file describing coverage across the genome, binned per 50 bp
+* `TIDDIT_[SAMPLE].ploidy.tab`
+  * tab file describing the estimated ploïdy and coverage across each contig
+* `TIDDIT_[SAMPLE].old.vcf`
+  * VCF including the low qualiy calls
+* `TIDDIT_[SAMPLE].wig`
+  * wiggle file containing coverage across the genome, binned per 50 bp
+* `TIDDIT_[SAMPLE].gc.wig`
+  * wiggle file containing fraction of gc content, binned per 50 bp
 
 ### Strelka2
 

From a8c02cf65f1794d548bc0901f8e735819640c653 Mon Sep 17 00:00:00 2001
From: MaxUlysse <max.u.garcia@gmail.com>
Date: Tue, 6 Aug 2019 15:11:11 +0200
Subject: [PATCH 11/11] fix: syntac error, bad grep

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

diff --git a/main.nf b/main.nf
index 35d743a470..5c2f6325d9 100644
--- a/main.nf
+++ b/main.nf
@@ -1034,9 +1034,9 @@ process TIDDIT {
     """
     tiddit --sv -o TIDDIT_${idSample} --bam ${bam} --ref ${genomeFile}
 
-    cp TIDDIT_${idSample}.vcf TIDDIT_${idSample}.old.vcf
+    mv TIDDIT_${idSample}.vcf TIDDIT_${idSample}.old.vcf
 
-    grep -E "#|PASS" TIDDIT_${idSample}.vcf > TIDDIT_${idSample}.vcf
+    grep -E "#|PASS" TIDDIT_${idSample}.old.vcf > TIDDIT_${idSample}.vcf
 
     bgzip --threads ${task.cpus} -c TIDDIT_${idSample}.vcf > TIDDIT_${idSample}.vcf.gz