Upload New File

Codes/CNV_Analyses.slurm

+#!/bin/bash
+#SBATCH --job-name=CNVs
+#SBATCH --output=/shared/home/righettin/Analyses/slurm_outputs/CNVs.out
+#SBATCH --error=/shared/home/righettin/Analyses/slurm_outputs/CNVs.error
+#SBATCH --cpus-per-task=48
+#SBATCH --nodes=1
+
+# Define paths
+root_dir="/shared/home/righettin/Analyses/CNV_estimates"
+analysis_dir="$root_dir/analysis"
+genes_id2name="/shared/home/righettin/Data/References/hg38/geneID2name_hg38_Apr24.tsv"
+paralogs="/shared/home/righettin/Data/References/hg38/paralogs_hg38_Apr24.txt"
+
+# 1) Concatenate all CNV estimates in a single file
+echo "1) Concatenating all CNV estimates in a single file:"
+
+output_file="$analysis_dir/AllGenomes.type.nobl.cnv"
+genomes_list="$analysis_dir/genomes.type.list"
+> $output_file   # Create an empty output file
+while read genome_id; do
+    cat $root_dir/$genome_id.nobl.cnv.tsv >> $output_file
+done < $genomes_list
+
+echo "All CNV estimates have been concatenated to ${output_file}."
+
+# 2) Remove decimal places from the fifth column
+echo "2) Removing decimal places from the fifth column of $output_file:"
+
+# Using awk to remove decimal places (".1" to ".9") from the fifth column
+awk -F'\t' '{sub(/\.[0-9]+/, "", $5)}1' OFS='\t' "$output_file" > "${output_file}.tmp"
+mv "${output_file}.tmp" "$output_file"
+
+echo "Decimal places removed from the fifth column of $output_file."
+
+# 3) Compute Gene Matrix
+echo "3) Computing Gene Matrix for all genomes:"
+
+python3 /shared/home/righettin/Scripts/CNV_scripts/computeGeneMatrix.py -t $output_file -d $genes_id2name -p $paralogs > $analysis_dir/AllGenomes.type.nobl.cnv.matrix.ALL.tsv
+
+echo "Gene Matrix for all genomes computed and saved as $analysis_dir/AllGenomes.type.nobl.cnv.matrix.ALL.tsv."
+echo "Since this contains all genes, it can be filtered to retain only genes that have a gain or a loss in at least one archaic genome compared to the human reference:"
+
+python /shared/home/righettin/Scripts/CNV_scripts/computeGeneMatrix.py -t $output_file -d $genes_id2name -p $paralogs |
+awk 'NR==1{print;next} {for(i=5;i<=NF;i++){ if($i/$4<0.5||$i/$4>1.5){print;next} }}' > $analysis_dir/AllGenomes.type.nobl.cnv.matrix.tsv
+
+echo "Results are in $analysis_dir/AllGenomes.type.nobl.cnv.matrix.tsv."