sync

bin/bioformat-utils/bam2cram.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+
+bam_list="$1"
+output_dir="$2"
+
+if [ ! -f "$bam_list" ]; then
+    echo "BAM file list not found: $bam_list"
+    exit 1
+fi
+
+if [ ! -d "$output_dir" ]; then
+    mkdir -p "$output_dir" || { echo "Failed to create output directory: $output_dir"; exit 1; }
+fi
+
+convert_to_cram() {
+    bam_file="$1"
+    output_dir="$2"
+    out_file="$output_dir"/"$(basename "${bam_file%.bam}.cram")"
+    samtools view -C -T /fs/s6k/groups/agmedgen/KOL_UOL/reference_GRCh38/Homo_sapiens/GATK/GRCh38/Sequence/WholeGenomeFasta/Homo_sapiens_assembly38.fasta -o "$out_file" "$bam_file"
+    echo "Converted $bam_file to $out_file"
+}
+
+export -f convert_to_cram
+
+parallel -a "$bam_list" -j8 convert_to_cram {} "$output_dir"
+~                                                            

bin/bioformat-utils/run_bam2cram.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+
+#SBATCH --job-name=bam2cram
+#SBATCH --nodes 8
+#SBATCH --ntasks=8
+#SBATCH --cpus-per-task 24
+#SBATCH --time 3-0
+#SBATCH --output=slurm.%j.out
+#SBATCH --error=slurm.%j.err
+#SBATCH --mail-type=END,FAIL
+#SBATCH --mail-user=your@email.de
+#SBATCH --partition rosa.p
+
+
+module load hpc-env/13.1
+module load SAMtools
+ml parallel/20230822-GCCcore-13.1.0
+ml HTSlib
+ml Python
+
+
+script="bam2cram.sh"
+cram_list="bamlist.txt"
+output_dir="/your/folder/converted_files"
+
+"$script" "$cram_list" "$output_dir"