def __init__(self, name, **kwargs):
# If using CLI then "cli" is included in kwargs
self._cli = False
if kwargs.get("cli"):
self._cli = True
# this is False and only updated during .run()
self.quiet = False
# No special characters in assembly name
check_name(name)
self.name = name
if (not kwargs.get("quiet")) and (not self._cli):
self._print("New Assembly: {}".format(self.name))
# Default ipcluster launch info
self.ipcluster = {
"cluster_id": "",
"profile": "default",
"engines": "Local",
"quiet": 0,
"timeout": 120,
"cores": 0, # detect_cpus(),
"threads": 2,
"pids": {},
}
# ipcluster settings can be set during init using kwargs
for key, val in kwargs.items():
if key in self.ipcluster:
self.ipcluster[key] = val
# statsfiles is a dict with file locations
# stats_dfs is a dict with pandas dataframes
self.stats_files = ObjDict({})
self.stats_dfs = ObjDict({})
# samples linked {sample-name: sample-object}
self.samples = {}
# populations {popname: poplist}
self.populations = {}
# multiplex files linked
self.barcodes = {}
# outfiles locations
self.outfiles = ObjDict()
self.outfiles.loci = ""
# storing supercatg file
self.clust_database = ""
self.database = ""
## the default params dict
self.params = Params(self)
self.hackersonly = Hackers()
## Store data directories for this Assembly. Init with default project
self.dirs = ObjDict({
"project":
os.path.realpath(self.params.project_dir),
"fastqs":
"",
"edits":
"",
"clusts":
"",
"consens":
"",
"across":
"",
"outfiles":
"",
})
def __init__(self, name=""):
self.name = name
self.barcode = ""
# link to files
self.files = ObjDict({
"fastqs": [],
"edits": [],
"mapped_reads": [],
"unmapped_reads": [],
"clusters": [],
"consens": [],
"database": []
})
## summary stats dictionary
self.stats = pd.Series(index=[
"state",
"reads_raw",
"reads_passed_filter",
"reads_merged",
"refseq_mapped_reads",
"refseq_unmapped_reads",
"clusters_total",
"clusters_hidepth",
"hetero_est",
"error_est",
"reads_consens",
],
dtype=object)
## stats for each step
self.stats_dfs = ObjDict({
"s1":
pd.Series(index=[
"reads_raw",
], dtype=object),
"s2":
pd.Series(index=[
"reads_raw",
"trim_adapter_bp_read1",
"trim_adapter_bp_read2",
"trim_quality_bp_read1",
"trim_quality_bp_read2",
"reads_filtered_by_Ns",
"reads_filtered_by_minlen",
"reads_passed_filter",
],
dtype=object),
#"filtered_by_qscore",
#"filtered_by_adapter",
"s3":
pd.Series(index=[
"merged_pairs",
"clusters_total",
"hidepth_min",
"clusters_hidepth",
"avg_depth_total",
"avg_depth_mj",
"avg_depth_stat",
"sd_depth_total",
"sd_depth_mj",
"sd_depth_stat",
"filtered_bad_align",
],
dtype=object),
"s4":
pd.Series(index=[
"hetero_est",
"error_est",
], dtype=object),
"s5":
pd.Series(index=[
"clusters_total",
"filtered_by_depth",
"filtered_by_maxH",
"filtered_by_maxAlleles",
"filtered_by_maxN",
"reads_consens",
"nsites",
"nhetero",
"heterozygosity",
],
dtype=object),
})
## store cluster depth information (biggest memory cost),
self.depths = {}