def genome(aphidicola):
handler = TestHandler()
genome = ("GCA_000521565.1_Buchnera_aphidicola_G002_"
"Myzus_persicae_Complete_Genome.fasta")
genome = os.path.join(aphidicola.path, genome)
with handler:
genome = Genome(genome, assembly_summary)
genome.sketch()
genome.get_contigs()
genome.get_assembly_size()
genome.get_unknowns()
yield genome, handler
def genome(ctx, path, metadata):
"""
Get information about a single genome.
"""
genome = Genome(path, ctx.assembly_summary)
if metadata:
click.echo(genome.metadata)
def __init__(self,
path,
max_unknowns=200,
contigs=3.0,
assembly_size=3.0,
mash=3.0,
assembly_summary=None,
processes=1):
"""Represents a collection of genomes in `path`
:param path: Path to the directory of related genomes you wish to analyze.
:param max_unknowns: Number of allowable unknown bases, i.e. not [ATCG]
:param contigs: Acceptable deviations from median number of contigs
:param assembly_size: Acceptable deviations from median assembly size
:param mash: Acceptable deviations from median MASH distances
:param assembly_summary: a pandas DataFrame with assembly summary information
"""
self.max_unknowns = max_unknowns
self.contigs = contigs
self.assembly_size = assembly_size
self.mash = mash
self.assembly_summary = assembly_summary
self.deviation_values = [max_unknowns, contigs, assembly_size, mash]
self.ncpus = processes
self.path = os.path.abspath(path)
self.name = os.path.basename(os.path.normpath(path))
self.log = logbook.Logger(self.name)
self.qc_dir = os.path.join(self.path, "qc")
self.label = '-'.join(map(str, self.deviation_values))
self.qc_results_dir = os.path.join(self.qc_dir, self.label)
self.passed_dir = os.path.join(self.qc_results_dir, "passed")
self.stats_path = os.path.join(self.qc_dir, 'stats.csv')
self.nw_path = os.path.join(self.qc_dir, 'tree.nw')
self.dmx_path = os.path.join(self.qc_dir, 'dmx.csv')
self.failed_path = os.path.join(self.qc_results_dir, "failed.csv")
self.tree_img = os.path.join(self.qc_results_dir, "tree.svg")
self.summary_path = os.path.join(self.qc_results_dir, "summary.txt")
self.allowed_path = os.path.join(self.qc_results_dir, "allowed.p")
self.paste_file = os.path.join(self.qc_dir, 'all.msh')
# Figure out if defining these as None is necessary
self.tree = None
self.stats = None
self.dmx = None
if os.path.isfile(self.stats_path):
self.stats = pd.read_csv(self.stats_path, index_col=0)
if os.path.isfile(self.nw_path):
self.tree = Tree(self.nw_path, 1)
if os.path.isfile(self.failed_path):
self.failed_report = pd.read_csv(self.failed_path, index_col=0)
if os.path.isfile(self.dmx_path):
try:
self.dmx = pd.read_csv(self.dmx_path, index_col=0, sep="\t")
self.log.info("Distance matrix read succesfully")
except pd.errors.EmptyDataError:
self.log.exception()
self.metadata_path = os.path.join(self.qc_dir,
"{}_metadata.csv".format(self.name))
try:
self.metadata_df = pd.read_csv(self.metadata_path,
index_col="accession")
except FileNotFoundError:
self.metadata_df = pd.DataFrame(columns=["accession"])
self.criteria = ["unknowns", "contigs", "assembly_size", "distance"]
self.tolerance = {
"unknowns": max_unknowns,
"contigs": contigs,
"assembly_size": assembly_size,
"distance": mash
}
self.passed = self.stats
self.failed = {}
self.med_abs_devs = {}
self.dev_refs = {}
self.allowed = {"unknowns": max_unknowns}
self.colors = {
"unknowns": "red",
"contigs": "green",
"distance": "purple",
"assembly_size": "orange"
}
self.genomes = [
Genome.Genome(genome, self.assembly_summary)
for genome in self.genome_paths
]
self.assess_tree()
def genome(path, metadata):
""" Get information about a single genome."""
genome = Genome(path)
if metadata:
click.echo(genome.metadata)
def ecoli_genome(genbank):
genome = "GCA_002012025.1_Escherichia_coli_Ecol_542_Complete_Genome.fasta"
genome = os.path.join(genbank.root, "Escherichia_coli", genome)
genome = Genome(genome, assembly_summary)
yield genome