added smRNAseq workflow

.ci_stuff/organism.yaml

@@ -20,3 +20,4 @@ extended_coding_regions_gtf: ".ci_stuff/gencode/m9/genes.slop.gtf"
 blacklist_bed: ".ci_stuff/DKFZ/GRCm38_General_readAttractingRegions.UseThisOne.bed"
 ignoreForNormalization: "MT X Y JH584299.1 GL456233.1 JH584301.1 GL456211.1 GL456350.1 JH584293.1 GL456221.1 JH584297.1 JH584296.1 GL456354.1 JH584294.1 JH584298.1 JH584300.1 GL456219.1 GL456210.1 JH584303.1 JH584302.1 GL456212.1 JH584304.1 GL456379.1 GL456216.1 GL456393.1 GL456366.1 GL456367.1 GL456239.1 GL456213.1 GL456383.1 GL456385.1 GL456360.1 GL456378.1 GL456389.1 GL456372.1 GL456370.1 GL456381.1 GL456387.1 GL456390.1 GL456394.1 GL456392.1 GL456382.1 GL456359.1 GL456396.1 GL456368.1 JH584292.1 JH584295.1"
 rmsk_file: "/tmp/rmsk.txt"
+tesmall_db: "/tmp/genomes/"

README.md

@@ -18,7 +18,8 @@ snakePipes are flexible and powerful workflows built using [snakemake](https://g
 - ATACseq*  
 - scRNAseq  
 - HiC  
-- makePairs*  
+- makePairs*
+- smRNAseq
 - Whole Genome Bisulfite Seq/WGBS  
 
 (* also available in allele-specific mode)

pyproject.toml

@@ -12,6 +12,7 @@ keywords = [
     "ChIPSeq",
     "mRNAseq",
     "ncRNAseq",
+    "smRNAseq",
     "ATACseq",
     "scRNAseq",
     "WGBS / Bisulfite seq",
@@ -37,7 +38,10 @@ dependencies = [
     "thefuzz",
     "pyyaml >= 5.1",
     "snakemake-executor-plugin-cluster-generic >= 1.0.9",
-    "graphviz"
+    "graphviz",
+    "matplotlib",
+    "numpy",
+    "seaborn"
 ]
 
 [project.optional-dependencies]
@@ -70,6 +74,7 @@ DNAmapping = "snakePipes.workflows.DNAmapping.DNAmapping:main"
 HiC = "snakePipes.workflows.HiC.HiC:main"
 makePairs = "snakePipes.workflows.makePairs.makePairs:main"
 mRNAseq = "snakePipes.workflows.mRNAseq.mRNAseq:main"
+smRNAseq = "snakePipes.workflows.smRNAseq.smRNAseq:main"
 ncRNAseq = "snakePipes.workflows.ncRNAseq.ncRNAseq:main"
 preprocessing = "snakePipes.workflows.preprocessing.preprocessing:main"
 scRNAseq = "snakePipes.workflows.scRNAseq.scRNAseq:main"

snakePipes/common_functions.py

@@ -40,6 +40,7 @@ def set_env_yamls():
             'CONDA_RMD_ENV': 'envs/rmarkdown.yaml',
             'CONDA_PREPROCESSING_ENV': 'envs/preprocessing.yaml',
             'CONDA_NONCODING_RNASEQ_ENV': 'envs/noncoding.yaml',
+            'CONDA_SMRNA_ENV': 'envs/smrna.yaml',
             'CONDA_SAMBAMBA_ENV': 'envs/sambamba.yaml',
             'CONDA_pysam_ENV': 'envs/pysam.yaml',
             'CONDA_SEACR_ENV': 'envs/chip_seacr.yaml',

snakePipes/shared/defaults.yaml

@@ -1,22 +1,15 @@
-################################################################################
-# This file should hold values that should be present in ALL workflows
-# Note that due to limitations in yaml.dump, only very basic structures are
-# permitted here.
-################################################################################
+condaEnvDir: /localenv/navandar/SnakePipes/
+configMode: manual
+emailSender: null
+max_thread: 25
+oldConfig: null
+onlySSL: false
+organismsDir: shared/organisms
+smtpPassword: null
+smtpPort: 0
+smtpServer: null
+smtpUsername: null
 snakemakeOptions: ''
-organismsDir: 'shared/organisms'
-snakemakeProfile: 'shared/profiles/local'
+snakemakeProfile: shared/profiles/snakepipes_genericprofile
 tempDir: /scratch/local
-# The following are only needed if you use the --emailAddress option
-smtpServer:
-smtpPort: 0
-onlySSL: False
-emailSender:
-smtpUsername:
-smtpPassword:
-# maximum number of threads to be used
-max_thread: 25
-#print tools versions
-toolsVersion: True
-oldConfig:
-configMode: manual
+toolsVersion: true

snakePipes/shared/organisms/mm10_gencodeM19.yaml

@@ -16,3 +16,4 @@ extended_coding_regions_gtf: "/data/repository/organisms/GRCm38_ensembl/gencode/
 blacklist_bed: "/data/repository/organisms/GRCm38_ensembl/DKFZ/GRCm38_General_readAttractingRegions.UseThisOne.bed"
 ignoreForNormalization: "MT X Y JH584299.1 GL456233.1 JH584301.1 GL456211.1 GL456350.1 JH584293.1 GL456221.1 JH584297.1 JH584296.1 GL456354.1 JH584294.1 JH584298.1 JH584300.1 GL456219.1 GL456210.1 JH584303.1 JH584302.1 GL456212.1 JH584304.1 GL456379.1 GL456216.1 GL456393.1 GL456366.1 GL456367.1 GL456239.1 GL456213.1 GL456383.1 GL456385.1 GL456360.1 GL456378.1 GL456389.1 GL456372.1 GL456370.1 GL456381.1 GL456387.1 GL456390.1 GL456394.1 GL456392.1 GL456382.1 GL456359.1 GL456396.1 GL456368.1 JH584292.1 JH584295.1"
 rmsk_file: '/data/repository/organisms/GRCm38_ensembl/UCSC/mm10/rmsk.txt'
+tesmall_db: "/data/repository/organisms/GRCm38_ensembl/TEsmall/mm10/genomes/"

snakePipes/shared/profiles/snakepipes_genericprofile/config.yaml

@@ -1,51 +1,101 @@
-executor: cluster-generic
-cluster-generic-submit-cmd:
-  "mkdir -p logs/{rule};\
-  module load slurm && sbatch \
-    --partition={resources.partition} \
-    --cpus-per-task={threads} \
-    --mem-per-cpu={resources.mem} \
-    --job-name=snakePipes_{rule}-{wildcards} \
-    --output=logs/{rule}/{rule}-{wildcards}-%j.out \
-    --time={resources.time} \
-    --parsable"
-jobs: 20
-conda-prefix: /localenv/$USER/anaconda/snakepipes-envs
-use-conda: True
+cluster-generic-cancel-cmd: ccancel.sh
+cluster-generic-submit-cmd: mkdir -p logs/{rule};module load slurm && sbatch --partition={resources.partition}
+  --cpus-per-task={threads} --mem-per-cpu={resources.mem} --job-name=snakePipes_{rule}-{wildcards}
+  --output=logs/{rule}/{rule}-{wildcards}-%j.out --time={resources.time} --parsable
 conda-frontend: conda
-cluster-generic-cancel-cmd: "ccancel.sh"
-latency-wait: 300
+conda-prefix: /localenv/navandar/SnakePipes/
 default-resources:
   mem: 10G
-  time: 1440
   partition: bioinfo
+  time: 1440
+executor: cluster-generic
+jobs: 20
+latency-wait: 300
 set-resources:
-  annotation_bed2fasta:
-    mem: 4G
+  ATAC_qc:
+    mem: 2G
   AlevinForVelocity:
     mem: 10G
-  ATAC_qc:
+  BAMsort_allelic:
+    mem: 3G
+  Bowtie2:
+    mem: 4G
+  CSAW:
+    mem: 30G
+  CollectAlignmentSummaryMetrics:
     mem: 2G
+  CollectInsertSizeMetrics:
+    mem: 1G
+  CpG_report:
+    mem: 6G
+  CpG_stats:
+    mem: 30G
+  DESeq2:
+    mem: 5G
+  DESeq2_Salmon_allelic:
+    mem: 3G
+  DESeq2_Salmon_basic:
+    mem: 3G
+  DSS:
+    mem: 10G
+  DepthOfCov:
+    mem: 3G
+  DepthOfCovGenome:
+    mem: 3G
+  FASTQdownsample:
+    mem: 4G
+  Genrich_peaks:
+    mem: 20G
+  HISAT2:
+    mem: 6G
+  MACS2:
+    mem: 8G
+  SEACR_peaks_lenient:
+    mem: 20G
+  SEACR_peaks_stringent:
+    mem: 10G
+  STAR:
+    mem: 6G
+  STAR_allele:
+    mem: 30G
+  STARsolo:
+    mem: 6G
+  STARsolo_raw_to_seurat:
+    mem: 10G
+  SalmonAlevin:
+    mem: 10G
+  SalmonIndex:
+    mem: 3G
+  SalmonQuant:
+    mem: 2G
+  Salmon_TPM:
+    mem: 5G
+  Salmon_counts:
+    mem: 5G
+  Salmon_index_joint_fa:
+    mem: 6G
+  TEcounts:
+    mem: 16G
+  annotation_bed2fasta:
+    mem: 4G
   bamCoverage:
     mem: 5G
+  bamCoverage_RPKM:
+    mem: 5G
   bamCoverage_coverage:
     mem: 5G
   bamCoverage_filtered:
     mem: 5G
   bamCoverage_raw:
     mem: 5G
-  bamCoverage_RPKM:
-    mem: 5G
   bamCoverage_unique_mappings:
     mem: 5G
   bamPE_fragment_size:
     mem: 10G
-  BAMsort_allelic:
-    mem: 3G
-  Bowtie2:
-    mem: 4G
   bowtie2Index:
     mem: 10G
+  build_matrix:
+    mem: 9G
   bwa:
     mem: 4G
   bwaIndex:
@@ -56,76 +106,44 @@ set-resources:
     mem: 90G
   bwameth:
     mem: 3G
-  bwamethIndex:
-    mem: 20G
   bwameth2Index:
     mem: 120G
-  build_matrix:
-    mem: 9G
+  bwamethIndex:
+    mem: 20G
   call_tads:
     mem: 3G
   cellsort_bam:
     mem: 10G
   clumpify:
     mem: 2G
-  CollectAlignmentSummaryMetrics:
-    mem: 2G
-  CollectInsertSizeMetrics:
-    mem: 1G
   correct_matrix:
     mem: 7G
-  CpG_report:
-    mem: 6G
-  CpG_stats:
-    mem: 30G
-  create_annotation_bed:
-    mem: 4G
   createGenomeFasta:
     mem: 20G
-  CSAW:
-    mem: 30G
+  create_annotation_bed:
+    mem: 4G
   create_snpgenome:
     mem: 30G
-  DepthOfCov:
-    mem: 3G
-  DepthOfCovGenome:
-    mem: 3G
-  DESeq2:
-    mem: 5G
-  DESeq2_Salmon_basic:
-    mem: 3G
-  DESeq2_Salmon_allelic:
-    mem: 3G
   diagnostic_plot:
     mem: 2G
   dmrseq:
     mem: 10G
   downloadGTF:
     mem: 20G
-  DSS:
-    mem: 10G
   fastaDict:
     mem: 4G
-  FASTQdownsample:
-    mem: 4G
   filterBW:
     mem: 6G
+  filterCoveragePerScaffolds:
+    mem: 6G
   filter_reads:
     mem: 3G
   filter_reads_umi:
     mem: 10G
-  filterCoveragePerScaffolds:
-    mem: 6G
-  Genrich_peaks:
-    mem: 20G
-  HISAT2:
-    mem: 6G
   hisat2Index:
     mem: 2G
   histoneHMM:
     mem: 4G
-  MACS2:
-    mem: 8G
   make2bit:
     mem: 8G
   map_fastq_single_end:
@@ -140,8 +158,6 @@ set-resources:
     mem: 6G
   namesort_bams:
     mem: 6G
-  plot_heatmap_cov_CSAW:
-    mem: 5G
   plotCorrelation_pearson:
     mem: 3G
   plotCorrelation_pearson_allelic:
@@ -162,59 +178,36 @@ set-resources:
     mem: 4G
   plot_heatmap_CSAW_up:
     mem: 10G
+  plot_heatmap_cov_CSAW:
+    mem: 5G
   prepForMetilene:
     mem: 3G
   produceReport:
     mem: 20G
   run_eisaR:
     mem: 30G
-  Salmon_counts:
-    mem: 5G
-  Salmon_index_joint_fa:
-    mem: 6G
-  SalmonAlevin:
-    mem: 10G
-  SalmonIndex:
-    mem: 3G
-  SalmonQuant:
-    mem: 2G
-  Salmon_TPM:
-    mem: 5G
+  sambamaba_sort_hic_r1:
+    mem: 4G
+  sambamaba_sort_hic_r2:
+    mem: 4G
   sambamba_flagstat:
     mem: 3G
   sambamba_flagstat_sorted:
     mem: 3G
   sambamba_markdup:
     mem: 4G
-  sambamaba_sort_hic_r1:
-    mem: 4G
-  sambamaba_sort_hic_r2:
-    mem: 4G
-  SEACR_peaks_lenient:
-    mem: 20G
-  SEACR_peaks_stringent:
-    mem: 10G
   sleuth_Salmon:
     mem: 4G
   sleuth_SalmonAllelic:
     mem: 10G
   snp_split:
     mem: 25G
-  STAR:
-    mem: 6G
-  STAR_allele:
-    mem: 30G
-  star_index:
-    mem: 15G
   starIndex:
     mem: 8G
-  STARsolo:
-    mem: 6G
-  STARsolo_raw_to_seurat:
-    mem: 10G
-  TEcounts:
-    mem: 16G
+  star_index:
+    mem: 15G
   velo_to_sce:
     mem: 30G
   velocyto:
     mem: 20G
+use-conda: true