import datetime
import re
from glob import glob
from collections import namedtuple
from agalma import config
from agalma import database
import biolite.database
from biolite import diagnostics
from biolite import report
from biolite import utils
from biolite import wrappers
from biolite import workflows
from biolite.pipeline import Pipeline
from biolite.pipeline import BasePipeline
pipe = Pipeline('orthofinder', "Pipeline for executing orthofinder")
pipe.add_arg('load_ids', nargs='+', metavar='LOAD_ID', help="""
Specifies which datasets to analyze; A space delimited list of run_id's
corresponding to the load runs that populated the database""")
pipe.add_arg('--seq_type', '-t', metavar='TYPE', default='protein', help="""
Choose whether comparisons are based on 'nucleotide', 'protein', or
'masked_protein' sequences.""")
pipe.add_arg(
'--genome_type', '-g', nargs="+", metavar='TYPE',
default=['nuclear'], help="""
Select sequences with genome type: nuclear, mitochondrial, and/or
plastid.""")
import os
import numpy
import networkx as nx
from collections import namedtuple
from glob import glob
from agalma import config
from agalma import database
import biolite.database
from biolite import diagnostics
from biolite import report
from biolite import utils
from biolite import wrappers
from biolite import workflows
from biolite.pipeline import Pipeline
pipe = Pipeline("homologize", __doc__)
### ARGUMENTS ###
pipe.add_arg(
"load_ids",
nargs="+",
metavar="LOAD_ID",
help="""
Specifies which datasets to analyze; A space delimited list of run_id's
corresponding to the load runs that populated the database""",
)
pipe.add_arg(
"--seq_type",
"-t",