config_DAS_Tool_vamb.yaml

# base output directory. Will create direcrorties within for each sample you do this for
outdir_base: binning_das_tool 
# sample file: three column tsv, with paired end reads specified with commas
# SAMPLE_NAME    ASSEMBLY   READS1,READS2
sample_file: binning_input.txt
# mean read length
read_length: 150
###########################
# vamb configs
###########################
contigs: contigs.txt
sample_data: samples2data.txt
index_size: 3G
minimap_mem: 15gb
minimap_ppn: 10
vamb_mem: 10gb
vamb_ppn: 10
checkm_mem: 25gb
checkm_ppn: 10
vamb_params: -o _ -m 2000 --minfasta 500000
vamb_preload: 
###########################
# kraken2 database to use for classification
# default is genbank_genome_chromosome_scaffold - high memory, high sensitivity, lower specificity
# also available refseq: /labs/asbhatt/data/program_indices/kraken2/kraken_custom_jan2020/refseq
kraken2db: /labs/asbhatt/data/program_indices/kraken2/kraken_custom_jan2020/genbank_genome_chromosome_scaffold/
# are we using a non-standard (non ncbi) taxonomy
custom_taxonomy: False
# Working with long reads from Nanopore? Experimental implementation in the DAS_tool workflow
long_read: False
# to speedup execution time, can skip searching for samples that already finished 
# this will prevent them from being included in the final table, though
skip_finished: False