First version of the scRNA-seq analysis pipeline (up until differential expression).

09-Single-cell_analysis/Makefile

+INPUT_FOLDER=/home/users/ltranchevent/Data/GeneDER/Original/
+OUTPUT_FOLDER=/home/users/ltranchevent/Data/GeneDER/Analysis/09/
+CODE_FOLDER=/home/users/ltranchevent/Projects/GeneDER/Analysis/09-Single-cell_analysis/
+
+clean:
+	@rm -rf *~
+clean_outputs:
+	@rm -rf ${OUTPUT_FOLDER}/*
+analyse:
+	@sbatch ${CODE_FOLDER}analyse.sh

09-Single-cell_analysis/README.md

+# Objectives
+The objectives of this step is to analyse the single-cell data (PD versus control) for male and female samples.
+
+# Details and instructions
+
+# Prerequisites
+A prerequisite is to have the scRNA data ready in the project data folder.
\ No newline at end of file

09-Single-cell_analysis/analyse.sh

+#!/bin/bash -l
+#SBATCH -J geneder:09:scRNA
+#SBATCH --mail-type=all
+#SBATCH --mail-user=leon-charles.tranchevent@uni.lu
+#SBATCH -N 1
+#SBATCH --ntasks-per-socket=14
+#SBATCH --ntasks-per-node=28
+#SBATCH -c 1
+#SBATCH --mem=32GB
+#SBATCH --time=0-02:00:00
+#SBATCH -p batch
+#SBATCH --qos=normal
+
+echo "== Starting run at $(date)"
+echo "== Job ID: ${SLURM_JOBID}"
+echo "== Node list: ${SLURM_NODELIST}"
+echo "== Submit dir. : ${SLURM_SUBMIT_DIR}"
+echo ""
+
+# Defining global parameters.
+OUTPUT_FOLDER=/home/users/ltranchevent/Data/GeneDER/Analysis/09/
+CODE_FOLDER=/home/users/ltranchevent/Projects/GeneDER/Analysis/09-Single-cell_analysis/
+
+# Loading modules.
+module load lang/R/3.6.2-foss-2019b-bare
+
+# Load configuration
+source ../libs/conf/confSH.sh
+create_variables ../Confs/datasets_config.yml
+
+# We get the Ensembl and HGNC data
+wget -O ${OUTPUT_FOLDER}mitochondrial_genes.tsv 'http://www.ensembl.org/biomart/martservice?query=<?xml version="1.0" encoding="UTF-8"?><!DOCTYPE Query><Query  virtualSchemaName = "default" formatter = "TSV" header = "0" uniqueRows = "0" count = "" datasetConfigVersion = "0.6" ><Dataset name = "hsapiens_gene_ensembl" interface = "default" ><Filter name = "chromosome_name" value = "MT"/><Attribute name = "ensembl_gene_id" /></Dataset></Query>'
+wget -O ${OUTPUT_FOLDER}ribosomalrna_genes.tsv  'https://www.genenames.org/cgi-bin/genegroup/download?id=848&type=branch'
+
+# For all scRNA datasets
+#nbScDatasets=${#scdatasets__dataset_name[@]}
+#for (( i=0; i<$nbScDatasets; i++ ))
+#do
+	i=1
+	datasetName=${scdatasets__dataset_name[$i]}
+	echo "== Job $i started (${datasetName}) =="
+	rm -rf ${OUTPUT_FOLDER}${datasetName}/
+	mkdir ${OUTPUT_FOLDER}${datasetName}/
+	Rscript --vanilla ${CODE_FOLDER}analyse.R ${datasetName} > ${OUTPUT_FOLDER}${datasetName}/analysis_log.out 2> ${OUTPUT_FOLDER}${datasetName}/analysis_log.err
+	echo "== Job $i ended (${datasetName}) =="
+#done
+
+# Moving the slurm log file to data
+mv ${CODE_FOLDER}/slurm-*out ${OUTPUT_FOLDER}/

09-Single-cell_analysis/local_config.yml

+local_data_dir: !!str '09/'
+local_code_dir: !!str '09-Single-cell_analysis/'

Confs/datasets_config.yml

@@ -247,3 +247,8 @@ datasets:
     has_age: 'TRUE'
     tissue: iPSC-DA
     quality_score: 1.0 # Was NA
+scdatasets:
+  -
+    dataset_name: GSE157783
+  -
+    dataset_name: GSE157783s