Skip to content
Snippets Groups Projects
Commit d5917fb4 authored by Susheel Busi's avatar Susheel Busi
Browse files

added the proper environments for mapping and binning

parent a6594d5e
No related branches found
No related tags found
1 merge request!44Work
Hide whitespace changes
Inline Side-by-side
envs/CONFIG.yaml 0 → 100644
+ 147
− 0
View file @ d5917fb4
data_dir: "data"
results_dir: "results"
db_dir: "dbs"
runs:
first: "20181106_1450_noselection_sizeselection"
second: "20181107_0906_same"
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-LSK108"
#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: "3.4.5+fb1fbfb"
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/claczny/ont/fecal_pilot/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/metaT/2018_GDB"
#samples: ["Kapa1_MG_S18", "Kapa2_MG_S19", "NEB1_MG_S16", "NEB2_MG_S17", "NEBmod1_MG_Rashi_S22", "NEBmod2_MG_Rashi_S23"]
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"]
# 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/"
envs/binning_config.yaml 0 → 100755
+ 51
− 0
View file @ d5917fb4
# Define sample names
# samples: ["flye", "megahit", "metaspades"]
# samples: ["flye", "megahit"]
samples: ["metaspades"]
binning_samples: ["flye", "megahit", "bwa_sr_metaspades", "bwa_lr_metaspades", "bwa_merged_metaspades", "mmi_sr_metaspades", "mmi_lr_metaspades", "mmi_merged_metaspades"]
# 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 anvio
anvio:
path: "/home/users/sbusi/apps/miniconda3/envs/conda_env/bin"
bin: "/home/users/sbusi/apps/miniconda3/envs/conda_env/bin/anvio"
# 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/"
envs/config.yaml 0 → 100755
+ 98
− 0
View file @ d5917fb4
data_dir: "data"
results_dir: "results"
db_dir: "dbs"
runs:
first: "20181106_1450_noselection_sizeselection"
second: "20181107_0906_same"
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-LSK108"
#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: "3.4.5+fb1fbfb"
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/claczny/ont/fecal_pilot/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/metaT/2018_GDB"
samples: ["Kapa1_MG_S18", "Kapa2_MG_S19", "NEB1_MG_S16", "NEB2_MG_S17", "NEBmod1_MG_Rashi_S22", "NEBmod2_MG_Rashi_S23"]
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
envs/flye_megahit_binning_config.yaml 0 → 100755
+ 43
− 0
View file @ d5917fb4
# Define sample names
# samples: ["flye", "megahit", "metaspades"]
samples: ["flye", "megahit"]
#samples: ["metaspades"]
# 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 anvio
anvio:
path: "/home/users/sbusi/apps/miniconda3/envs/conda_env/bin"
bin: "/home/users/sbusi/apps/miniconda3/envs/conda_env/bin/anvio"
# 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
envs/metaspades_binning_config.yaml 0 → 100755
+ 43
− 0
View file @ d5917fb4
# Define sample names
# samples: ["flye", "megahit", "metaspades"]
# samples: ["flye", "megahit"]
samples: ["metaspades"]
# 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 anvio
anvio:
path: "/home/users/sbusi/apps/miniconda3/envs/conda_env/bin"
bin: "/home/users/sbusi/apps/miniconda3/envs/conda_env/bin/anvio"
# 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
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment