Merge pull request #750 from maxplanck-ie/develop

Develop

.ci_stuff/test_dag.sh

@@ -181,6 +181,8 @@ WC=`ChIP-seq -d allelic_BAM_input --sampleSheet .ci_stuff/test_sampleSheet.tsv -
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 331 ]; then exit 1 ; fi
 
 # mRNA-seq
+WC=`mRNA-seq -i PE_input -o output --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 882 ]; then exit 1 ; fi
 WC=`mRNA-seq -i PE_input -o output --sampleSheet .ci_stuff/test_sampleSheet.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 892 ]; then exit 1 ; fi
 WC=`mRNA-seq -i PE_input -o output --rMats --sampleSheet .ci_stuff/test_sampleSheet.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
@@ -211,6 +213,8 @@ if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 659 ]; then exit 1 ; fi
 WC=`mRNA-seq --mode alignment,alignment-free -i PE_input -o output --rMats --sampleSheet .ci_stuff/test_sampleSheet_multiComp.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 867 ]; then exit 1 ; fi
 #allelic
+WC=`mRNA-seq -m allelic-mapping,deepTools_qc -i PE_input -o output --snakemakeOptions " --dryrun --conda-prefix /tmp" --VCFfile allelic_input/file.vcf.gz --strains strain1,strain2 .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 1360 ]; then exit 1 ; fi
 WC=`mRNA-seq -m allelic-mapping,deepTools_qc -i PE_input -o output --sampleSheet .ci_stuff/test_sampleSheet.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" --VCFfile allelic_input/file.vcf.gz --strains strain1,strain2 .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 1370 ]; then exit 1 ; fi
 WC=`mRNA-seq -m allelic-mapping,deepTools_qc -i PE_input -o output --sampleSheet .ci_stuff/test_sampleSheet.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" --SNPfile allelic_input/snpfile.txt --NMaskedIndex allelic_input/Ngenome .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
@@ -219,6 +223,8 @@ WC=`mRNA-seq -m allelic-mapping,deepTools_qc -i PE_input -o output --sampleSheet
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 1370 ]; then exit 1 ; fi
 
 # noncoding-RNA-seq
+WC=`noncoding-RNA-seq -i PE_input -o output --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 717 ]; then exit 1 ; fi
 WC=`noncoding-RNA-seq -i PE_input -o output --sampleSheet .ci_stuff/test_sampleSheet.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 733 ]; then exit 1 ; fi
 WC=`noncoding-RNA-seq -i SE_input -o output --sampleSheet .ci_stuff/test_sampleSheet.tsv --snakemakeOptions " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee >(cat 1>&2) | grep -v "Conda environment" | sed '/^\s*$/d' | wc -l`

conda-recipe/meta.yaml

@@ -1,6 +1,6 @@
 package:
   name: snakepipes
-  version: 2.4.2
+  version: 2.4.3
 
 source:
   path: ../

docs/content/News.rst

@@ -1,6 +1,15 @@
 snakePipes News
 ===============
 
+snakePipes 2.4.3
+----------------
+
+* Fixed noncoding-RNA-seq workflow without sample sheet.
+* Updated links to prebuilt indices on zenodo.
+* Fixed read length estimation for rMats.
+* Cutadapt is set as default read trimming program for both noncoding-RNA-seq and mRNA-seq workflows.
+
+
 snakePipes 2.4.2
 ----------------
 

docs/content/setting_up.rst

@@ -34,7 +34,7 @@ The easiest way to install snakePipes is via our conda channel. The following co
 
 .. code:: bash
 
-    conda create -n snakePipes -c mpi-ie -c conda-forge -c bioconda snakePipes==2.4.2
+    conda create -n snakePipes -c mpi-ie -c conda-forge -c bioconda snakePipes==2.4.3
 
 This way, the software used within snakePipes do not conflict with the software pre-installed on your terminal or in your python environment.
 
@@ -192,10 +192,10 @@ Download premade indices
 
 For the sake of convenience, we provide premade indices for the following organisms:
 
- - `Human (GRCh38, Gencode release 29) <https://zenodo.org/record/2650763>`__
- - `Mouse (GRCm38/mm10, Gencode release m19) <https://zenodo.org/record/4020455>`__
- - `Mouse (GRCm37/mm9, Gencode release 1) <https://zenodo.org/record/2650849>`__
- - `Fruit fly (dm6, Ensembl release 94) <https://zenodo.org/record/2650762>`__
+ - `Human (GRCh38, Gencode release 29) <https://zenodo.org/record/4471116>`__
+ - `Mouse (GRCm38/mm10, Gencode release m19) <https://zenodo.org/record/4468065>`__
+ - `Mouse (GRCm37/mm9, Gencode release 1) <https://zenodo.org/record/4478284>`__
+ - `Fruit fly (dm6, Ensembl release 94) <https://zenodo.org/record/4478414>`__
 
 To use these, simply download and extract them. You will then need to modify the provided YAML file to indicate exactly where the indices are located (i.e., replace ``/data/processing/ryan`` with whatever is appropriate).
 

docs/index.rst

@@ -34,7 +34,7 @@ Quick start
 
 .. code:: bash
 
-    conda create -n snakePipes -c mpi-ie -c conda-forge -c bioconda snakePipes==2.4.2
+    conda create -n snakePipes -c mpi-ie -c conda-forge -c bioconda snakePipes==2.4.3
 
 * You can update snakePipes to the latest version available on conda with:
 

snakePipes/__init__.py

@@ -1 +1 @@
-__version__ = '2.4.2'
+__version__ = '2.4.3'

snakePipes/shared/rules/rMats.multipleComp.snakefile

@@ -64,7 +64,7 @@ rule rMats:
         TMPDIR={params.tempDir}
         MYTEMP=$(mktemp -d ${{TMPDIR:-/tmp}}/snakepipes.XXXXXXXXXX);
         set +o pipefail;
-        readLen=$(samtools view {params.s1} | awk \'{{print length($10)}}\' | head -10000 | awk \'{{ sum += $1 }} END {{ if (NR > 0) print sum / NR }}\')
+        readLen=$(samtools view {params.s1} | awk \'{{print length($10)}}\' | head -10000 | awk \'{{ sum += $1 }} END {{ if (NR > 0) print int(sum / NR) }}\')
         rmats.py --gtf {params.gtf} --b1 {input.b1} --b2 {input.b2} --od {params.od} --tmp $MYTEMP -t {params.end} --libType {params.libType} --readLength $readLen --variable-read-length --nthread {threads} --tstat {threads} 2> {log};
         rm -rf $MYTEMP
 """

snakePipes/shared/rules/rMats.singleComp.snakefile

@@ -44,7 +44,7 @@ rule rMats:
         TMPDIR={params.tempDir}
         MYTEMP=$(mktemp -d ${{TMPDIR:-/tmp}}/snakepipes.XXXXXXXXXX);
         set +o pipefail;
-        readLen=$(samtools view {params.s1} | awk \'{{print length($10)}}\' | head -10000 | awk \'{{ sum += $1 }} END {{ if (NR > 0) print sum / NR }}\')
+        readLen=$(samtools view {params.s1} | awk \'{{print length($10)}}\' | head -10000 | awk \'{{ sum += $1 }} END {{ if (NR > 0) print int(sum / NR) }}\')
         rmats.py --gtf {params.gtf} --b1 {input.b1} --b2 {input.b2} --od {params.od} --tmp $MYTEMP -t {params.end} --libType {params.libType} --readLength $readLen --variable-read-length --nthread {threads} --tstat {threads} 2> {log};
         rm -rf $MYTEMP
 """

snakePipes/shared/rules/rMats.snakefile

@@ -39,6 +39,6 @@ rule rMats:
     conda: CONDA_RNASEQ_ENV
     shell:"""
         set +o pipefail;
-        readLen=$(samtools view {params.s1} | awk \'{{print length($10)}}\' | head -10000 | awk \'{{ sum += $1 }} END {{ if (NR > 0) print sum / NR }}\')
+        readLen=$(samtools view {params.s1} | awk \'{{print length($10)}}\' | head -10000 | awk \'{{ sum += $1 }} END {{ if (NR > 0) print int(sum / NR) }}\')
         rmats.py --gtf {params.gtf} --b1 {input.b1} --b2 {input.b2} --od {params.od} --tmp {params.tempDir} -t {params.end} --libType {params.libType} --readLength $readLen --variable-read-length --nthread {threads} --tstat {threads} 2> {log}
 """

snakePipes/shared/rules/tecounts.snakefile

@@ -183,16 +183,17 @@ def get_outdir(folder_name,sampleSheet):
     sample_name = os.path.splitext(os.path.basename(str(sampleSheet)))[0]
     return("{}_{}".format(folder_name, sample_name))
 
-rule split_sampleSheet:
-    input:
-        sampleSheet = sampleSheet
-    output:
-        splitSheets = os.path.join("splitSampleSheets",os.path.splitext(os.path.basename(str(sampleSheet)))[0]+".{compGroup}.tsv")
-    params:
-        splitSheetPfx = os.path.join("splitSampleSheets",os.path.splitext(os.path.basename(str(sampleSheet)))[0])
-    run:
-        if isMultipleComparison:
-            cf.splitSampleSheet(input.sampleSheet,params.splitSheetPfx)
+if sampleSheet:
+    rule split_sampleSheet:
+        input:
+            sampleSheet = sampleSheet
+        output:
+            splitSheets = os.path.join("splitSampleSheets",os.path.splitext(os.path.basename(str(sampleSheet)))[0]+".{compGroup}.tsv")
+        params:
+            splitSheetPfx = os.path.join("splitSampleSheets",os.path.splitext(os.path.basename(str(sampleSheet)))[0])
+        run:
+            if isMultipleComparison:
+                cf.splitSampleSheet(input.sampleSheet,params.splitSheetPfx)
 
 
 # TODO: topN, FDR

snakePipes/workflows/noncoding-RNA-seq/defaults.yaml

@@ -32,7 +32,7 @@ pairedEnd: True
 downsample:
 ## Options for trimming
 trim: False
-trimmer: fastp
+trimmer: cutadapt
 trimmerOptions:
 ## further options
 mode: alignment,deepTools_qc