# Location of BacQuerya_processing repository relative to the Snakefile

BacQuerya_location: .

# whether this run is building the reference information for a species ("reference") or processing new isolates ("query")

# unless you are adding a new species to the indices, this has to be "query"

run_type: reference

skip_NCBI: False

skip_ENA: True

skip_genes: False

# needed for a "reference" run. Tells snakemake to add gene information merged together from all runs to the elastic gene index

index_genes: False

index_sequences: False #construct COBS index for genes

index_isolates: False

# whether we are indexing the GPS data or not

GPS: False

# whether we are indexing the ESC data or not

ESC: False

# name of GPS/ESC metadata json

supplementaryMetadataJSON: ESC_metadata.json

# multiprocessing option

n_cpu: 8

# options for extract_entrez_information

extract_entrez_information:

accession_file: NCBI_requested_accessions.txt

email: empty

assembly: assembly-stats

gff: annotation

genome: genome

# options to extract sequence reads

extract_read_metadata:

accession_file: ESC_ENA_Accessions.txt

# options for single_meryl_dbs

single_meryl_dbs:

single_files: meryl_single_files

assembly_txt_file: meryl_single_files/assembly_str.txt

# options for merge_single_meryl_dbs

merge_single_meryl_dbs:

merged_db_folder: meryl_merged_files

# options for run_merqury

run_merqury:

merqury_output: merqury_output

# options for extract_assembly_stats

extract_assembly_stats:

index_file: index_values.json

# options for index_isolate_attributes

index_isolate_attributes:

index: isolate_index

# options for index_gene_features

index_sequences:

kmer_length: 31

gene_type: gene

elasticSearchIndex: gene_index

assembly_type: assembly