Merge pull request #432 from maxplanck-ie/develop

Release 1.2.1

.ci_stuff/test_dag.sh

@@ -55,11 +55,11 @@ touch /tmp/genes.gtf /tmp/genome.fa /tmp/genome.fa.fai
 WC=`DNA-mapping -i PE_input -o output --tempdir /tmp .ci_stuff/organism.yaml --snakemake_options " --dryrun --conda-prefix /tmp" | tee /dev/stderr | grep -v "Conda environment" | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 734 ]; then exit 1 ; fi
 WC=`DNA-mapping -i PE_input -o output --tempdir /tmp .ci_stuff/organism.yaml --snakemake_options " --dryrun --conda-prefix /tmp" --trim --mapq 20 --dedup --properpairs | tee /dev/stderr | grep -v "Conda environment" | wc -l`
-if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 936 ]; then exit 1 ; fi
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 802 ]; then exit 1 ; fi
 WC=`DNA-mapping -i SE_input -o output --tempdir /tmp .ci_stuff/organism.yaml --snakemake_options " --dryrun --conda-prefix /tmp" | tee /dev/stderr | grep -v "Conda environment" | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 684 ]; then exit 1 ; fi
 WC=`DNA-mapping -i SE_input -o output --tempdir /tmp .ci_stuff/organism.yaml --snakemake_options " --dryrun --conda-prefix /tmp" --trim --mapq 20 --dedup --properpairs | tee /dev/stderr | grep -v "Conda environment" | wc -l`
-if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 820 ]; then exit 1 ; fi
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 752 ]; then exit 1 ; fi
 
 # ChIP-seq
 WC=`ChIP-seq -d BAM_input --tempdir /tmp --snakemake_options " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml .ci_stuff/ChIP.sample_config.yaml | tee /dev/stderr | grep -v "Conda environment" | wc -l`
@@ -81,19 +81,19 @@ if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 889 ]; then exit 1 ; fi
 WC=`RNA-seq -i PE_input -o output --tempdir /tmp --snakemake_options " --dryrun --conda-prefix /tmp" -m "alignment" .ci_stuff/organism.yaml | tee /dev/stderr | grep -v "Conda environment" | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 578 ]; then exit 1 ; fi
 WC=`RNA-seq -i PE_input -o output --tempdir /tmp --snakemake_options " --dryrun --conda-prefix /tmp" -m "alignment,deepTools_qc" --trim .ci_stuff/organism.yaml | tee /dev/stderr | grep -v "Conda environment" | wc -l`
-if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 1052 ]; then exit 1 ; fi
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 918 ]; then exit 1 ; fi
 WC=`RNA-seq -i SE_input -o output --tempdir /tmp --snakemake_options " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee /dev/stderr | grep -v "Conda environment" | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 828 ]; then exit 1 ; fi
 WC=`RNA-seq -i SE_input -o output --tempdir /tmp --snakemake_options " --dryrun --conda-prefix /tmp" -m "alignment" .ci_stuff/organism.yaml | tee /dev/stderr | grep -v "Conda environment" | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 528 ]; then exit 1 ; fi
 WC=`RNA-seq -i SE_input -o output --tempdir /tmp --snakemake_options " --dryrun --conda-prefix /tmp" -m "alignment,deepTools_qc" --trim .ci_stuff/organism.yaml | tee /dev/stderr | grep -v "Conda environment" | wc -l`
-if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 925 ]; then exit 1 ; fi
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 857 ]; then exit 1 ; fi
 
 # HiC - fails
 WC=`HiC -i PE_input -o output --tempdir /tmp --snakemake_options " --dryrun --conda-prefix /tmp" .ci_stuff/organism.yaml | tee /dev/stderr | grep -v "Conda environment" | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 522 ]; then exit 1 ; fi
 WC=`HiC -i PE_input -o output --tempdir /tmp --snakemake_options " --dryrun --conda-prefix /tmp" --trim .ci_stuff/organism.yaml | tee /dev/stderr | grep -v "Conda environment" | wc -l`
-if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 724 ]; then exit 1 ; fi
+if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 590 ]; then exit 1 ; fi
 WC=`HiC -i PE_input -o output --tempdir /tmp --snakemake_options " --dryrun --conda-prefix /tmp" --enzyme DpnII .ci_stuff/organism.yaml | tee /dev/stderr | grep -v "Conda environment" | wc -l`
 if [ ${PIPESTATUS[0]} -ne 0 ] || [ $WC -ne 522 ]; then exit 1 ; fi
 WC=`HiC -i PE_input -o output --tempdir /tmp --snakemake_options " --dryrun --conda-prefix /tmp" --noTAD .ci_stuff/organism.yaml | tee /dev/stderr | grep -v "Conda environment" | wc -l`

conda-recipe/meta.yaml

@@ -1,6 +1,6 @@
 package:
   name: snakepipes
-  version: 1.2.0
+  version: 1.2.1
 
 source:
   path: ../

docs/content/News.rst

@@ -1,6 +1,15 @@
 snakePipes News
 ===============
 
+snakePipes 1.2.1
+----------------
+
+ * Fixed a typo in ``createIndices``.
+ * Implemented complex experimental design in RNAseq (differential gene expression), ChIP/ATACseq (differential binding).
+ * Fixed an issue with ggplot2 and log transformation in RNAseq report Rmd.
+ * fastqc folder is created and its content will be added to multiqc only if fastqc flag is called.
+ * fastqc-trimmed folder is created and its content will be added to multiqc only if both fastqc and trim flags are called. 
+
 snakePipes 1.2.0
 ----------------
 
@@ -40,7 +49,7 @@ snakePipes 1.1.0
    * Automatic reports are generated in every folder containing results of statistical analysis (single CpG stats, metilene DMR stats, user interval aggregate stats), as long as sample sheet is provided.
    * R sessionInfo() is now printed at the end of the statistical analysis.
 
- * scRNAseq: 
+ * scRNAseq:
 
    * An extention to the pipeline now takes the processed csv file from Results folder as input and runs cell filtering with a range of total transcript thresholds using monocle and subsequently runs clustering, produces tsne visualizations, calculates top 2 and top10 markers per cluster and produces heatmap visualizations for these using monocle/seurat. If the skipRaceID flag is set to False (default), all of the above are also executed using RaceID.
    * Stats reports were implemented for RaceID and Monocle/Seurat so that folders Filtered_cells_RaceID and Filtered_cells_monocle now contain a Stats_report.html.
@@ -49,7 +58,7 @@ snakePipes 1.1.0
 
  * all sample sheets now need to have a "name" and a "condition" column, that was not consistent before
  * consistent --sampleSheet [FILE] options to invoke differential analysis mode (RNA-seq, ChIP-seq, ATAC-seq), --DE/--DB were dropped
- 
+
 snakePipes 1.0.0 (king cobra) released
 --------------------------------------
 

docs/content/setting_up.rst

@@ -8,7 +8,7 @@ Unlike many other pipelines, setting up snakePipes is easy! All you need is a *l
 Installing conda with python3
 -----------------------------
 
-Follow the instructions `here <https://conda.io/docs/user-guide/install/index.html>`__ to install either
+Follow the instructions `here <https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html>`__ to install either
 miniconda or anaconda. A minimal version (miniconda) is enough for snakePipes. Get the miniconda installer `here <https://conda.io/miniconda.html>`__.
 
 After installation, check your python path and version :
@@ -38,6 +38,8 @@ The easiest way to install snakePipes is via our conda channel. The following co
 
 This way, the software used within snakePipes do not conflict with the software pre-installed on your terminal or in your python environment.
 
+.. note:: This might take a few minutes depending on the access to conda channels.
+
 Development installation
 ~~~~~~~~~~~~~~~~~~~~~~~~
 

snakePipes/__init__.py

@@ -1 +1 @@
-__version__ = '1.2.0'
+__version__ = '1.2.1'

snakePipes/shared/defaults.yaml

@@ -6,8 +6,7 @@
 # Note that due to limitations in yaml.dump, only very basic structures are
 # permitted here.
 ################################################################################
-#snakemake_options: ' --use-conda --conda-prefix /package/anaconda3/envs/ '
-snakemake_options: ' --use-conda --conda-prefix /data/processing/sikora/snakePipes_envs '
+snakemake_options: ' --use-conda --conda-prefix /package/anaconda3/envs/ '
 tempdir: /data/extended/
 # The following are only needed if you use the --emailAddress option
 smtpServer:

snakePipes/shared/rscripts/DESeq2.R

@@ -65,6 +65,7 @@ sampleInfo$condition <- relevel(sampleInfo$condition, ref = as.character(sampleI
 #    sampleInfo[grepl("^[0-9]", sampleInfo$name),]$name <- paste0("X", sampleInfo[grepl("^[0-9]", sampleInfo$name),]$name)
 #}
 sampleInfo$name <- make.names(sampleInfo$name)
+rownames(sampleInfo)<-sampleInfo$name
 
 ## ~~~~~~ 2. Check if data is in proper order  ~~~~~
 if(isTRUE(tximport)) {

snakePipes/shared/rscripts/DESeq2Report.Rmd

@@ -467,7 +467,7 @@ plotCounts_gg <- function(i, dds, intgroup) {
         data <- cbind(data, data.frame('group' = group))
     }
 
-    ggplot(data, aes(x = group, y = count)) + geom_jitter(width=0.2) + ylab('Normalized count') + ggtitle(i) + coord_trans(y = "log10") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
+    ggplot(data, aes(x = group, y = log10(count))) + geom_jitter(width=0.2) + ylab('Log10(Normalized count + 0.5)') + ggtitle(i) + theme(axis.text.x = element_text(angle = 90, hjust = 1))
 }
 for(i in head(features, nBestFeatures)) {
     print(plotCounts_gg(i, dds = dds, intgroup = intgroup[2:length(intgroup)]))

snakePipes/shared/rules/createIndices.snakefile

@@ -126,7 +126,7 @@ rule makeKnownSpliceSites:
     conda: CONDA_RNASEQ_ENV
     threads: 10
     shell: """
-        hista2_extract_splice_sites.py {input} > {output}
+        hisat2_extract_splice_sites.py {input} > {output}
         """
 
 

snakePipes/shared/rules/envs/atac_seq.yaml

@@ -10,4 +10,3 @@ dependencies:
  - gawk = 4.2.1
  - r-kernsmooth = 2.23_15
  - r-statmod = 1.4.30
- - bioconductor-genomeinfodbdata

snakePipes/shared/rules/multiQC.snakefile

@@ -10,7 +10,7 @@ def multiqc_input_check(return_value):
 
     if not pipeline=="scrna-seq" and ("fromBam" not in globals() or not fromBam):
         if paired:
-            if trim:
+            if trim and fastqc:
                 infiles.append( expand("FastQC_trimmed/{sample}{read}_fastqc.html", sample = samples, read = reads) )
                 indir += " FastQC_trimmed "
                 infiles.append( expand(fastq_dir+"/{sample}{read}.fastq.gz", sample = samples, read = reads) )
@@ -19,7 +19,7 @@ def multiqc_input_check(return_value):
                 infiles.append( expand("FastQC/{sample}{read}_fastqc.html", sample = samples, read = reads) )
                 indir +=" FastQC "
         else:
-            if trim:
+            if trim and fastqc:
                 infiles.append( expand("FastQC_trimmed/{sample}"+reads[0]+"_fastqc.html", sample = samples) )
                 indir += " FastQC_trimmed "
                 infiles.append( expand(fastq_dir+"/{sample}"+reads[0]+".fastq.gz", sample = samples) )
@@ -62,10 +62,12 @@ def multiqc_input_check(return_value):
         if trim:
             infiles.append( expand("FastQC_trimmed/{sample}"+reads[0]+"_fastqc.html", sample = samples) )
             indir += " FastQC_trimmed "
+        else:
+            infiles.append( expand("FastQC/{sample}{read}_fastqc.html", sample = samples, read = reads) )
+            indir +=" FastQC "
+
         infiles.append( expand(fastq_dir+"/{sample}"+reads[0]+".fastq.gz", sample = samples) )
         indir += fastq_dir + " "
-        infiles.append( expand("FastQC/{sample}{read}_fastqc.html", sample = samples, read = reads) )
-        indir +=" FastQC "
         infiles.append( expand(mapping_prg+"/{sample}.bam", sample = samples) +
         expand("Sambamba/{sample}.markdup.txt", sample = samples) +
         expand("deepTools_qc/estimateReadFiltering/{sample}_filtering_estimation.txt", sample=samples))

snakePipes/workflows/RNA-seq/internals.snakefile

@@ -2,6 +2,7 @@ import glob
 import os
 import subprocess
 import re
+import sys
 
 
 ## Main variables ##############################################################