def __init__(self, af_sp, max_genomes, ani_cache_file, cpus, output_dir):
"""Initialization."""
check_dependencies(['fastANI', 'mash'])
self.cpus = cpus
self.output_dir = output_dir
self.logger = logging.getLogger('timestamp')
self.af_sp = af_sp
self.fastani = FastANI(ani_cache_file, cpus)
# maximum number of randomly selected genomes to
self.max_genomes_for_stats = max_genomes
# consider when calculating pairwise statistics
self.RepStats = namedtuple(
'RepStats', 'min_ani mean_ani std_ani median_ani')
self.PairwiseStats = namedtuple('PairwiseStats', ('min_ani',
'mean_ani',
'std_ani',
'median_ani',
'ani_to_medoid',
'mean_ani_to_medoid',
'mean_ani_to_rep',
'ani_below_95'))
def __init__(self, ani_ncbi_erroneous, ani_cache_file, cpus, output_dir):
"""Initialization."""
self.output_dir = output_dir
self.logger = logging.getLogger('timestamp')
self.ani_ncbi_erroneous = ani_ncbi_erroneous
self.fastani = FastANI(ani_cache_file, cpus)
def __init__(self, ani_cache_file, cpus, output_dir):
"""Initialization."""
check_dependencies(['fastANI'])
self.cpus = cpus
self.output_dir = output_dir
self.logger = logging.getLogger('timestamp')
self.fastani = FastANI(ani_cache_file, cpus)
def __init__(self, ani_sp, af_sp, ani_cache_file, cpus, output_dir):
"""Initialization."""
check_dependencies(['fastANI', 'mash'])
self.cpus = cpus
self.output_dir = output_dir
self.logger = logging.getLogger('timestamp')
self.true_str = ['t', 'T', 'true', 'True']
self.ani_sp = ani_sp
self.af_sp = af_sp
self.min_mash_ani = 90.0
self.fastani = FastANI(ani_cache_file, cpus)
def __init__(self, ani_sp, af_sp, ani_cache_file, cpus, output_dir):
"""Initialization."""
check_dependencies(['fastANI', 'mash'])
self.cpus = cpus
self.output_dir = output_dir
self.logger = logging.getLogger('timestamp')
self.ani_sp = ani_sp
self.af_sp = af_sp
self.max_ani_neighbour = 97.0
self.min_mash_ani = 90.0
self.ClusteredGenome = namedtuple('ClusteredGenome', 'ani af gid')
self.fastani = FastANI(ani_cache_file, cpus)
def __init__(self, derep_ani, derep_af, max_genomes_per_sp, ani_cache_file,
cpus, output_dir):
"""Initialization."""
check_dependencies(['fastANI', 'mash'])
self.cpus = cpus
self.output_dir = output_dir
self.logger = logging.getLogger('timestamp')
self.max_genomes_per_sp = max_genomes_per_sp
self.derep_ani = derep_ani
self.derep_af = derep_af
# minimum MASH ANI value for dereplicating within a species
self.min_mash_intra_sp_ani = derep_ani - 1.0
self.mash = Mash(self.cpus)
self.fastani = FastANI(ani_cache_file, cpus)
def __init__(self, ani_cache_file, cpus, output_dir):
"""Initialization."""
self.ltp_dir = 'rna_ltp_132'
self.ltp_results_file = 'ssu.taxonomy.tsv'
self.LTP_METADATA = namedtuple('LTP_METADATA', 'taxonomy taxa species ssu_len evalue bitscore aln_len perc_iden perc_aln')
self.ltp_pi_threshold = 99.0
self.ltp_pa_threshold = 90.0
self.ltp_ssu_len_threshold = 900
self.ltp_evalue_threshold = 1e-10
self.output_dir = output_dir
self.logger = logging.getLogger('timestamp')
self.cpus = cpus
self.fastani = FastANI(ani_cache_file, cpus)
self.ani_pickle_dir = os.path.join(self.output_dir, 'ani_pickles')
if not os.path.exists(self.ani_pickle_dir):
os.makedirs(self.ani_pickle_dir)
def __init__(self, ani_cache_file, cpus, output_dir):
"""Initialization."""
self.output_dir = output_dir
self.logger = logging.getLogger('timestamp')
self.fastani = FastANI(ani_cache_file, cpus)
# action parameters
self.genomic_update_ani = 99.0
self.genomic_update_af = 0.80
self.new_rep_ani = 99.0
self.new_rep_af = 0.80
self.new_rep_qs_threshold = 10 # increase in ANI score require to select
# new representative
self.action_log = open(os.path.join(self.output_dir, 'action_log.tsv'),
'w')
self.action_log.write(
'Genome ID\tPrevious GTDB species\tAction\tParameters\n')
self.new_reps = {}
