def generate_ATT_from_phylesystem(aln,
workdir,
study_id,
tree_id,
phylesystem_loc='api'):
"""gathers together tree, alignment, and study info - forces names to otu_ids.
Outputs AlignTreeTax object.
an alignemnt, a
Input can be either a study ID and tree ID from OpenTree
Alignemnt need to be a Dendropy DNA character matrix!"""
#TODO CHECK ARGS
assert(isinstance(aln, datamodel.charmatrixmodel.DnaCharacterMatrix))
for tax in aln.taxon_namespace:
tax.label = tax.label.replace(" ", "_") #Forcing all spaces to underscore UGH
nexson = get_nexson(study_id, phylesystem_loc)
ott_ids = get_subtree_otus(nexson,
tree_id=tree_id,
subtree_id="ingroup",
return_format="ottid")
ott_mrca = get_mrca_ott(ott_ids)
newick = extract_tree(nexson,
tree_id,
PhyloSchema('newick',
output_nexml2json='1.2.1',
content="tree",
tip_label="ot:originalLabel"))
newick = newick.replace(" ", "_") #UGH Very heavy handed, need to make sure happens on alignement side as well.
tre = Tree.get(data=newick,
schema="newick",
preserve_underscores=True,
taxon_namespace=aln.taxon_namespace)
otus = get_subtree_otus(nexson, tree_id=tree_id)
otu_dict = {}
orig_lab_to_otu = {}
treed_taxa = {}
for otu_id in otus:
otu_dict[otu_id] = extract_otu_nexson(nexson, otu_id)[otu_id]
otu_dict[otu_id]['^physcraper:status'] = "original"
otu_dict[otu_id]['^physcraper:last_blasted'] = "1900/01/01"
orig = otu_dict[otu_id].get(u'^ot:originalLabel').replace(" ", "_")
orig_lab_to_otu[orig] = otu_id
treed_taxa[orig] = otu_dict[otu_id].get(u'^ot:ottId')
for tax in aln.taxon_namespace:
try:
tax.label = orig_lab_to_otu[tax.label].encode('ascii')
except KeyError:
sys.stderr.write("{} doesn't have an otu id. It is being removed from the alignement. This may indicate a mismatch between tree and alignement\n".format(tax.label))
#need to prune tree to seqs and seqs to tree...
otu_newick = tre.as_string(schema="newick")
return AlignTreeTax(otu_newick, otu_dict, aln, ingroup_mrca=ott_mrca, workdir=workdir) #newick should be bare, but alignement should be DNACharacterMatrix
def _get_mrca(self):
if not _study_get:
_get_study()
ott_ids = get_subtree_otus(self.nexson, tree_id=self.tree_id) #TODO are these ottids or OTUs?
self.mrca_node = tree_of_life.mrca(ott_ids=ottids, wrap_response=True)
sys.stdout.write("mrca_node found, {}\n".format(mrca_node.nearest_taxon.ott_id))
self._found_mrca = 1
def generate_ATT_from_phylesystem(aln,
workdir,
config_obj,
study_id,
tree_id,
phylesystem_loc='api',
ingroup_mrca=None):
"""gathers together tree, alignment, and study info - forces names to otu_ids.
Study and tree ID's can be obtained by using python ./scripts/find_trees.py LINEAGE_NAME
Spaces vs underscores kept being an issue, so all spaces are coerced to underscores when data are read in.
:param aln: dendropy :class:`DnaCharacterMatrix <dendropy.datamodel.charmatrixmodel.DnaCharacterMatrix>` alignment object
:param workdir: path to working directory
:param config_obj: config class containing the settings
:param study_id: OToL study id of the corresponding phylogeny which shall be updated
:param tree_id: OToL corresponding tree ID as some studies have several phylogenies
:param phylesystem_loc: access the github version of the OpenTree data store, or a local clone
:param ingroup_mrca: optional. OToL identifier of the mrca of the clade that shall be updated (can be subset of the phylogeny)
:return: object of class ATT
"""
assert isinstance(aln, datamodel.charmatrixmodel.DnaCharacterMatrix), \
"your alignment `%s` ist not of type DnaCharacterMatrix" % aln
for tax in aln.taxon_namespace:
tax.label = tax.label.replace(" ",
"_") # Forcing all spaces to underscore
nexson = get_nexson(study_id, phylesystem_loc)
newick = extract_tree(
nexson, tree_id,
PhyloSchema('newick',
output_nexml2json='1.2.1',
content="tree",
tip_label="ot:originalLabel"))
newick = newick.replace(
" ", "_"
) # UGH Very heavy handed, need to make sure happens on alignment side as well.
tre = Tree.get(data=newick,
schema="newick",
preserve_underscores=True,
taxon_namespace=aln.taxon_namespace)
# this gets the taxa that are in the subtree with all of their info - ott_id, original name,
otus = get_subtree_otus(nexson, tree_id=tree_id)
otu_dict = {}
orig_lab_to_otu = {}
treed_taxa = {}
for otu_id in otus:
otu_dict[otu_id] = extract_otu_nexson(nexson, otu_id)[otu_id]
otu_dict[otu_id]["^physcraper:status"] = "original"
otu_dict[otu_id]["^physcraper:last_blasted"] = None
orig = otu_dict[otu_id].get(u"^ot:originalLabel").replace(" ", "_")
orig_lab_to_otu[orig] = otu_id
treed_taxa[orig] = otu_dict[otu_id].get(u"^ot:ottId")
for tax in aln.taxon_namespace:
if tax.label in otu_dict:
sys.stdout.write("{} aligned\n".format(tax.label))
else:
try:
tax.label = orig_lab_to_otu[tax.label].encode("ascii")
except KeyError:
sys.stderr.write(
"{} doesn't have an otu id. It is being removed from the alignment. "
"This may indicate a mismatch between tree and alignment\n"
.format(tax.label))
# need to prune tree to seqs and seqs to tree...
otu_newick = tre.as_string(schema="newick")
ott_ids = get_subtree_otus(nexson,
tree_id=tree_id,
subtree_id="ingroup",
return_format="ottid")
if ingroup_mrca:
if type(ingroup_mrca) == list:
ott_ids = set(ingroup_mrca)
ott_mrca = get_mrca_ott(ott_ids)
else:
ott_mrca = int(ingroup_mrca)
elif ott_ids: # if no ingroup is specified, ott_ids will be none
ott_mrca = get_mrca_ott(ott_ids)
else: # just get the mrca for teh whole tree
ott_mrca = get_mrca_ott(
[otu_dict[otu_id].get(u"^ot:ottId") for otu_id in otu_dict])
workdir = os.path.abspath(workdir)
return physcraper.aligntreetax.AlignTreeTax(otu_newick,
otu_dict,
aln,
ingroup_mrca=ott_mrca,
workdir=workdir,
config_obj=config_obj)
