print('No names file provided!')
print('Type `TaxonNamesResolver.py -h` for help.')
sys.exit()
if not os.path.isfile(args.names):
print('[{0}] could not be found!'.format(args.names))
sys.exit()
print('\n' + description + '\n')
if args.datasource:
datasource = args.datasource
else:
datasource = 'NCBI'
# simple logging, no levels, duplicate to console if verbose
logfile = 'log.txt'
logger = logging.getLogger('')
logger.setLevel(logging.INFO)
loghandler = logging.FileHandler(logfile, 'a')
loghandler.setFormatter(logging.Formatter('%(message)s'))
logger.addHandler(loghandler)
if args.verbose:
console = logging.StreamHandler()
console.setFormatter(logging.Formatter('%(message)s'))
logger.addHandler(console)
# log system info
logSysInfo()
resolver = Resolver(args.names, datasource, args.taxonid)
resolver.main()
resolver.write()
logEndTime()
if not args.verbose:
print('\nComplete\n')
def run(wd=os.getcwd(), logger=logging.getLogger('')):
# PRINT STAGE
logger.info("Stage 1: Names resolution")
# DIRS
outdir = os.path.join(wd, '1_names')
temp_dir = os.path.join(wd, 'tempfiles')
if not os.path.isdir(outdir):
os.mkdir(outdir)
# INPUT
with open(os.path.join(temp_dir, "paradict.p"), "rb") as file:
paradict = pickle.load(file)
with open(os.path.join(temp_dir, "terms.p"), "rb") as file:
terms = pickle.load(file)
# PARAMETERS
outgroupid = paradict["outgroupid"]
ntools.etools.Entrez.email = paradict["email"]
minspecies = int(paradict["minspecies"])
taxonomy = paradict["taxonomic_constraint"]
taxonomy = taxonomy.split('-')
ntools.logger = logger
# PROCESS
logger.info('Searching for taxids ....')
logger.info('------TaxonNamesResolver:Start------')
try:
parentid = paradict["parentid"]
except:
parentid = False
if len(terms) < minspecies:
raise TooFewSpeciesError
resolver = Resolver(terms=terms, datasource="NCBI", taxon_id=parentid,
logger=logger)
resolver.main()
if len(resolver.retrieve('query_name')) < minspecies:
raise TooFewSpeciesError
logger.info('------TaxonNamesResolver:End------')
logger.info("Generating names dictionary ....")
namesdict, allrankids, parentid = ntools.genNamesDict(resolver=resolver,
parentid=parentid,
logger=logger)
logger.info("Finding an outgroup ....")
namesdict = ntools.getOutgroup(namesdict=namesdict, parentid=parentid,
outgroupid=outgroupid, logger=logger)
# add outgroup ids to allrankids
allrankids.extend(namesdict['outgroup']['txids'])
logger.info('Generating taxonomic tree ....')
taxontree = ntools.genTaxTree(resolver=resolver, namesdict=namesdict,
taxonomy=taxonomy, logger=logger)
# OUTPUT
# remove temp TNR folder
shutil.rmtree("resolved_names")
# write out changes to hidden pickled files
with open(os.path.join(temp_dir, "namesdict.p"), "wb") as file:
pickle.dump(namesdict, file)
with open(os.path.join(temp_dir, "allrankids.p"), "wb") as file:
pickle.dump(allrankids, file)
# write namesdict as csv
ntools.writeNamesDict(outdir, namesdict)
# write taxon tree
ntools.Phylo.write(taxontree, os.path.join(outdir, "taxontree.tre"),
"newick")
# FINISH MESSAGE
logger.info('Stage finished. Resolved [{0}] names including outgroup.'.
format(len(namesdict.keys())))
# PACKAGES
from taxon_names_resolver import Resolver
from taxon_names_resolver import TaxDict
from taxon_names_resolver import taxTree
# EXAMPLE NAMES
terms = [
'H**o sapiens', 'Gorilla gorilla', 'Pongo pongo', 'Macca mulatta',
'Mus musculus', 'Ailuropoda melanoleuca', 'Ailurus fulgens',
'Chlorotalpa tytonis', 'Arabidopsis thaliana', 'Bacillus subtilus'
]
# RESOLVE
# pass the terms, the datasource and the logger (optional)
resolver = Resolver(terms=terms, datasource="NCBI", logger=logger)
resolver.main() # resolve!
# CREATE TAXDICT
# extract the unique names for each term ('idents', query_name is best as it is
# guaranteed to be unique)
idents = resolver.retrieve('query_name')
# extract the lists of names for all known parental taxonomic groups for each
# term ('lineages', e.g. H**o, Primate, Mammalia)
lineages = resolver.retrieve('classification_path')
# for Taxonomic IDs instead of names, use:
# lineages = resolver.retrieve('classification_path_ids')
# extract the lists of corresponding rank names for 'lineages' ('ranks', e.g.
# species, genus etc.) for each entity
ranks = resolver.retrieve('classification_path_ranks')
# optional extra data slots are also possible, for example a list of 1s and 0s
