diff --git a/CHANGELOG b/CHANGELOG deleted file mode 100644 index 4e3bf78140804a7928e50aa24aa709f5dd6617ef..0000000000000000000000000000000000000000 --- a/CHANGELOG +++ /dev/null @@ -1,2 +0,0 @@ -- All files uploaded to new repository "ONT_pilot_gitlab" for the ONT analyses -- Snakefile updated with correct paths for short-read mapping against IGC and HG38 reference databases \ No newline at end of file diff --git a/config/CONFIG_original.yaml b/config/CONFIG_original.yaml deleted file mode 100644 index 64492e3200327ff4dd2a96edb452786dfbecd39e..0000000000000000000000000000000000000000 --- a/config/CONFIG_original.yaml +++ /dev/null @@ -1,148 +0,0 @@ -steps: "assembly_annotation metaT" -# steps: "assembly_annotation mmseq metaT mapping binning taxonomy" -data_dir: "data" -results_dir: "results" -db_dir: "dbs" -runs: - first: "S1_SizeSelected" - second: "S3_Gtube" -# third: "20181108_0827_test" -barcodes: ["barcode06", "barcode07", "barcode08", "barcode09", "barcode10"] -assemblers: ["flye"] -p7zip: - bin: "/home/users/claczny/apps/software/p7zip_16.02/bin/7za" - threads: 4 -ont_fast5_api: - single_to_multi_fast5: - bin: "single_to_multi_fast5" - batch: 8000 - threads: 8 -flowcell: "FLO-MIN106" -kit: "SQK-LSK109" -#barcodes: ["barcode06", "barcode07", "barcode08", "barcode09", "barcode10"] -barcodes: ["barcode07"] -guppy_cpu: - path: "/scratch/users/claczny/ont/apps/software/ont-guppy-cpu-3.1.5_linux64/bin" - bin: "/scratch/users/claczny/ont/apps/software/ont-guppy-cpu-3.1.5_linux64/bin/guppy_basecaller" - version: "cpu-3.1.5" - config: "dna_r9.4.1_450bps_modbases_dam-dcm-cpg_hac.cfg" - cpu_threads: 28 -guppy_gpu: - path: "/home/users/sbusi/apps/ont-guppy/bin" - bin: "set +u; source ~/.bashrc; set -u; ml compiler/LLVM system/CUDA && /home/users/sbusi/apps/ont-guppy/bin/guppy_basecaller" - version: "3.6.0+98ff765" - config: "dna_r9.4.1_450bps_modbases_dam-dcm-cpg_hac.cfg" - hac_config: "dna_r9.4.1_450bps_hac.cfg" - records_per_fastq: 8000 - chunk_size: 1000 - chunks_per_runner: 1000 - num_callers: 4 - runners_per_device: 2 - gpu_device: "cuda:0" - cpu_threads: 28 -guppy_barcoder: - path: "/home/users/sbusi/apps/ont-guppy/bin" - bin: "set +u; source ~/.bashrc; set -u; ml compiler/LLVM system/CUDA && /home/users/sbusi/apps/ont-guppy/bin/guppy_barcoder" - version: "3.4.5+fb1fbfb" - records_per_fastq: 8000 - threads: 8 -nanostats: -short_reads_prefix: "/scratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/data/raw/short_reads" -#short_reads_prefix: "/mnt/isilon/projects/lcsb_sequencing/transfer/bioecosystem/Rashi/2019/Apr/fastq" -metaT_prefix: "/scratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/data/metaT" -fastp: - min_length: 40 -minimap2: - threads: 16 -igc: - uri: "parrot.genomics.cn/gigadb/pub/10.5524/100001_101000/100064/1.GeneCatalogs/IGC.fa.gz" -hg38: - uri: "ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/405/GCF_000001405.38_GRCh38.p12/GCF_000001405.38_GRCh38.p12_genomic.fna.gz" -genomecov: - bin: "bedtools genomecov" -compute_avg_coverage: - bin: "scripts/coverage.awk" -bwa: - threads: 24 - long_reads_index: - opts: "-aY -A 5 -B 11 -O 2,1 -E 4,3 -k 8 -W 16 -w 40 -r 1 -D 0 -y 20 -L 30,30 -T 2.5" -samtools: - sort: - threads: 4 - chunk_size: "4G" - view: - threads: 4 -flye: - bin: "flye" - threads: 27 - genome_size: "1g" -operams: - bin: "set +u; source ~/.bashrc; set -u; ml lang/Perl lang/R && perl /scratch/users/claczny/ont/apps/software/OPERA-MS/OPERA-MS.pl" - threads: 28 -megahit: - threads: 28 -nonpareil: - memory: 4096 - threads: 14 -medaka: - threads: 28 -racon: - threads: 28 -rebaler: - threads: 28 -diamond: - threads: 28 - db: "/mnt/isilon/projects/ecosystem_biology/NOMIS/DIAMOND/new_nr.dmnd" -metaspades: - threads: 28 -mmseq2: - threads: 24 -# Define sample names -#samples: ["flye", "megahit", "metaspades_hybrid"] -# samples: ["flye", "megahit"] -# samples: ["metaspades_hybrid"] -binning_samples: ["flye", "megahit", "bwa_sr_metaspades_hybrid", "bwa_lr_metaspades_hybrid", "bwa_merged_metaspades_hybrid", "mmi_sr_metaspades_hybrid", "mmi_lr_metaspades_hybrid", "mmi_merged_metaspades_hybrid"] - -# Hybrid assembler -hybrid_assembler: "metaspades_hybrid" - -# Directory where fastq files are -#data_dir: "/scratch/users/sbusi/ONT/cedric_ont_basecalling/Binning" - -# Directory to save the output to -#results_dir: "/scratch/users/sbusi/ONT/cedric_ont_basecalling/Binning" - -# Number of cpus or threads to use -threads: 28 - -# Path to the the 140GB Kraken2 database -kraken2_database: "/scratch/users/bkunath/Kraken2/maxikraken2_1903_140GB/" - -# Path to DAS_Tool -DAS_Tool: - path: "/home/users/sbusi/apps/DAS_Tool-master" - bin: "/home/users/sbusi/apps/DAS_Tool-master/src/" - -# Path to DAS_Tool database -dastool_database: "/home/users/sbusi/apps/DAS_Tool-master/db/" - -# Mapping options -bwa: - threads: 24 - long_reads_index: - opts: "-aY -A 5 -B 11 -O 2,1 -E 4,3 -k 8 -W 16 -w 40 -r 1 -D 0 -y 20 -L 30,30 -T 2.5" -samtools: - sort: - threads: 4 - chunk_size: "4G" - view: - threads: 4 -minimap2: - threads: 24 - -# Path to GTDBTK database -GTDBTK: - DATA: "/home/users/sbusi/apps/db/gtdbtk/release89" - -# Rscript path -Rscript: "/home/users/sbusi/apps/miniconda3/envs/dastool/bin/"