Merge branch 'main' of github.com:boulardlab/3t-seq

Dockerfile

@@ -184,5 +184,4 @@ RUN mamba env create --prefix /conda-envs/346c7adef34200145d01dda184ac25b8 --fil
     mamba env create --prefix /conda-envs/b93daf96b2454232db6380819bb61725 --file /conda-envs/b93daf96b2454232db6380819bb61725/environment.yaml && \
     mamba env create --prefix /conda-envs/2473cc7cad71f946585d67bc0fc276d6 --file /conda-envs/2473cc7cad71f946585d67bc0fc276d6/environment.yaml && \
     mamba env create --prefix /conda-envs/3674dd77e0957c12c05158a88113106a --file /conda-envs/3674dd77e0957c12c05158a88113106a/environment.yaml && \
-    mamba clean --all -y && \
-    update-ca-certificates
+    mamba clean --all -y

config/config-GSE130735.yaml

@@ -0,0 +1,49 @@
+sequencing_libraries:
+  - name: GSE130735
+    protocol: pe
+    # "sample_sheet" is a csv mapping FILENAMES without extensions to GENOTYPE
+    # E.g.
+    #  Name,Filename,Genotype
+    #  s01,some_complicate_filename_s01,WT
+    #  s02,some_complicate_filename_s02,WT
+    #  s03,some_complicate_filename_s03,KO
+    #  s04,some_complicate_filename_s04,KO    
+    sample_sheet: resources/sample-sheet.csv
+    trimmomatic: "ILLUMINACLIP:$CONDA_PREFIX/share/trimmomatic/adapters/TruSeq3-PE.fa:1:15:10 SLIDINGWINDOW:8:22 MAXINFO:20:0.6 LEADING:22 TRAILING:20 MINLEN:50"
+    star: "--seedSearchStartLmax 30 --outFilterMismatchNoverReadLmax 0.04 --winAnchorMultimapNmax 40"
+    bamCoverage: "--binSize 10 --normalizeUsing None"
+    deseq2:
+      test: Wald
+      variable: genotype
+      reference_level: WT
+
+
+disable_TE_analysis: false
+disable_tRNA_analysis: false
+
+globals:
+  # <reads_folder>/<library-name> is the expected pattern
+  reads_folder: ../reads/
+
+  results_folder: results/
+  qc_folder: results/qc
+  log_folder: results/log
+  references_folder: references
+  tmp_folder: /tmp
+  analysis_folder: results/analysis
+
+genome:
+  label: mm10
+  annotation_type: mgi
+
+  # URL for genome fasta file
+  fasta_url: GRCm38.primary_assembly.genome.fa
+
+  # URL for genome GTF file
+  gtf_url: MGI_mod.gff3
+
+  # URL to GtRNAdb files
+  gtrnadb_url: http://gtrnadb.ucsc.edu/genomes/eukaryota/Mmusc10/mm10-tRNAs.tar.gz
+
+deseq2:
+  working_directory: .

profile/slurm-GSE130735/config.yaml

@@ -0,0 +1,46 @@
+rerun-triggers:
+  - input
+  - mtime
+  - params
+  - software-env
+
+max-status-checks-per-second: 1
+seconds-between-status-checks: 30
+max-jobs-per-second: 1
+
+# let Snakemake submit up to 100 jobs at the time
+jobs: 100
+
+# Wait up to 2 minutes for files to appear on file system
+# This is to handle latency on some shared file systems
+latency-wait: 120
+
+# If a job fails, let Snakemake retry running it up to 2 times
+retries: 2
+
+default-resources:
+  - "slurm_account=boulard" # this is the default account for billing of used resources
+  - "slurm_partition=htc-el8" # this is the default partition jobs should be submitted to
+
+set-resources:
+  # this syntax manipulates specific resources for specific rules
+  - "starTE_random:runtime=2880" # runtime
+  - "star:mem_mb=128000" # memory
+  - "starTE_random:mem_mb=256334" # memory
+  - "starTE_multihit:mem_mb=256334" # memory
+  - "star:slurm_partition=bigmem" # Cluster partition
+  - "starTE_random:slurm_partition=bigmem" # Cluster partition
+  - "starTE_multihit:slurm_partition=bigmem" # Cluster partition
+  - "trimmomatic_pe:runtime=10080"
+  - "multiqc_star:runtime=60"
+  - "fastqc_markdup:runtime=30"
+
+# Manipulate the number of cores allocated to a specific rule
+set-threads:
+  - "fastqc_raw=16"
+  - "star=32"
+  - "starTE_random=32"
+  - "starTE_multihit=32"
+  - "star_genome_preparation=32"
+  - "trimmomatic_pe=16"
+  - "trimmomatic_se=16"