Initialize a new project database

Usage

new_db(
  db_path = "./.sqlite",
  mapping_fn = NULL,
  mapping_id = "ID",
  mapping_taxon = "Taxon",
  genetic_code = NULL,
  assemble_cpus = 6,
  assemble_memory = 24,
  assembler = "GetOrganelle",
  seeds_db =
    "https://raw.githubusercontent.com/smithsonian/MitoPilot/main/ref_dbs/getOrganelle/seeds/fish_mito_seeds.fasta",
  labels_db =
    "https://raw.githubusercontent.com/smithsonian/MitoPilot/main/ref_dbs/getOrganelle/labels/fish_mito_labels.fasta",
  getOrganelle = paste("-F 'anonym'", "-R 10 -k '21,45,65,85,105,115'",
    "--larger-auto-ws", "--expected-max-size 20000", "--target-genome-size 16500"),
  mitofinder_db =
    "https://raw.githubusercontent.com/Smithsonian/MitoPilot/refs/heads/main/ref_dbs/MitoFinder/NC_002333_Danio_rerio.gb",
  mitofinder = paste("--megahit"),
  max_paths = 10,
  max_scaffolds = 10,
  min_assembly_length = 500,
  annotate_cpus = 6,
  annotate_memory = 36,
  annotate_ref_db = "Chordata",
  annotate_ref_dir =
    "https://raw.githubusercontent.com/Smithsonian/MitoPilot/refs/heads/main/ref_dbs/Mitos2",
  mitos_opts = "--intron 0 --oril 0",
  trnaScan_opts = "-M vert -X 20",
  arwen_opts = "-mtx",
  aragorn_opts = "-m -gcstd",
  curate_cpus = 4,
  curate_memory = 8,
  curate_target = "fish_mito",
  curate_ref_db = "Metazoa_RefSeq235",
  max_blast_hits = 10,
  linear_complete = FALSE,
  curate_params = NULL,
  orf_cpus = 4,
  orf_memory = 8,
  orffinder_opts = "-s 1",
  orf_min_len = 300,
  orf_max_overlap = 0.1
)

Arguments

db_path: Path to the new database file
mapping_fn: Path to the mapping CSV file. Must contain columns "ID", "Taxon, "R1", and "R2"
mapping_id: Column name of the mapping file to use as the primary key
mapping_taxon: Column name of the mapping file containing a Taxonomic identifier (eg, species name)
genetic_code: Optional NCBI translation table override. Default `NULL` auto-selects from the curation ruleset (`curate_target`); a number sets an override on the default curate_opts set. https://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi
assemble_cpus: Default # cpus for assembly
assemble_memory: default memory (GB) for assembly
assembler: Assembler, choice of "GetOrgnalle" (default) or "MitoFinder"
seeds_db: Path to the gotOrganelle seeds database, can be a URL, cannot have same file name as labels_db. Default is a fish database built from RefSeq. https://raw.githubusercontent.com/smithsonian/MitoPilot/main/ref_dbs/getOrganelle/seeds/fish_mito_seeds.fasta
labels_db: Path to the gotOrganelle labels database, can be a URL, cannot have same file name as seeds_db. Default is a fish database built from RefSeq. https://raw.githubusercontent.com/smithsonian/MitoPilot/main/ref_dbs/getOrganelle/seeds/fish_mito_labels.fasta
getOrganelle: Default getOrganelle command line options
mitofinder_db: Path to MitoFinder reference db, must be GenBank format (.gb), can be a URL. Default is the Danio rerio mitogenome (https://raw.githubusercontent.com/Smithsonian/MitoPilot/refs/heads/main/ref_dbs/MitoFinder/NC_002333_Danio_rerio.gb)
mitofinder: Default MitoFinder command line options
max_paths: Maximum number of assembly paths allowed for a sample to continue past the Assemble step (default = 10). Samples exceeding this are flagged as failed and skipped by downstream steps in WF1.
max_scaffolds: Maximum number of scaffolds (within a single path) allowed for a sample to continue past the Assemble step (default = 10). Samples exceeding this are flagged as failed and skipped by downstream steps in WF1.
min_assembly_length: Minimum contig length (bp) to retain for coverage calculations, BLAST, and annotation. Scaffolds shorter than this threshold are stored but flagged as ignored (default = 500).
annotate_cpus: Default # cpus for annotation
annotate_memory: Default memory (GB) for annotation
annotate_ref_db: Default Mitos2 reference database
annotate_ref_dir: Default Mitos2 reference database directory
mitos_opts: Default MITOS2 command line options
trnaScan_opts: Default tRNAscan-SE command line options
arwen_opts: Default ARWEN command line options
aragorn_opts: Default ARAGORN command line options
curate_cpus: Default # cpus for curation
curate_memory: Default memory (GB) for curation
curate_target: Default target database for curation
curate_ref_db: Default curation reference database (default = "Metazoa_RefSeq235", the only bundled DB with rRNA BLAST references)
max_blast_hits: Maximum number of top BLAST hits to retain (default = 10)
linear_complete: Treat linear assemblies as complete genomes for the export "completeness" field? By default only circular assemblies are labeled "complete genome" and linear assemblies "partial genome". Set TRUE for taxa whose complete mitogenome is genuinely linear (default = FALSE). Editable later in the curation-options modal.
curate_params: Default curation parameters
orf_cpus: CPUs for the optional ORF-finder step (default = 4)
orf_memory: Memory (GB) for the optional ORF-finder step (default = 8)
orffinder_opts: Default NCBI ORFfinder options (default = "-s 1")
orf_min_len: Minimal ORF length in nucleotides (default = 300)
orf_max_overlap: Maximum overlap with existing annotations, as a fraction of the ORF length, before an ORF is discarded (default = 0.1)