def get_ham_treemap_from_row(row, tree, level=None):
fam, orthoxml = row
orthoxml = switch_name_ncbi_id(orthoxml)
try:
if level is None:
ham_obj = pyham.Ham(tree,
orthoxml,
type_hog_file="orthoxml",
use_internal_name=True,
orthoXML_as_string=True)
tp = ham_obj.create_tree_profile(
hog=ham_obj.get_list_top_level_hogs()[0])
return tp.treemap
else:
ham_obj = pyham.Ham(tree,
orthoxml,
type_hog_file="orthoxml",
use_internal_name=True,
orthoXML_as_string=True)
#return subHOGs at level
slice = ham_obj.get_ancestral_genome_by_name(level)
treeprofiles = [
ham_obj.create_tree_profile(hog=h) for h in
ham_obj.get_list_top_level_hogs()[0].get_at_level(slice)
]
except TypeError as err:
print('Type error:', err)
return None
except AttributeError as err:
print('Attribute error:', err)
return None
def _load_ogs(self):
"""
Using the orthoxml file select only the OGs of interest that have more species than the min_species threshold
:return: Dictionary with og name as key and list of SeqRecords
"""
if '.fa' in self.args.dna_reference or '.fasta' in self.args.dna_reference:
print('--- Load ogs and find their corresponding DNA seq from {} ---'.format(self.args.dna_reference))
print(
'Loading {} into memory. This might take a while . . . '.format(self.args.dna_reference.split("/")[-1]))
self._db = SeqIO.index(self.args.dna_reference, "fasta")
self._db_source = 'fa'
elif '.h5' in self.args.dna_reference:
print('--- Load ogs and find their corresponding DNA seq from {} ---'.format(self.args.dna_reference))
self._db = db.Database(self.args.dna_reference)
self._db_id_map = db.OmaIdMapper(self._db)
self._db_source = 'h5'
else:
print('--- Load ogs and find their corresponding DNA seq using the REST api ---')
self._db_source = 'REST_api'
if self.oma.mode is 'standalone':
self._og_orthoxml = os.path.join(self.oma_output_path, 'OrthologousGroups.orthoxml')
self._tree_str = os.path.join(self.oma_output_path, 'EstimatedSpeciesTree.nwk')
self._ham_analysis = pyham.Ham(self._tree_str, self._og_orthoxml, use_internal_name=False)
ogs = {}
orthologous_groups_aa = os.path.join(self.args.output_path, "01_ref_ogs_aa")
if not os.path.exists(orthologous_groups_aa):
os.makedirs(orthologous_groups_aa)
orthologous_groups_dna = os.path.join(self.args.output_path, "01_ref_ogs_dna")
if not os.path.exists(orthologous_groups_dna):
os.makedirs(orthologous_groups_dna)
names_og = self.ogs
for name, records in tqdm(names_og.items(), desc='Loading OGs', unit=' OGs'):
# name = file.split("/")[-1].split(".")[0]
ogs[name] = OG()
ogs[name].aa = self._get_aa_records(name, records)
output_file_aa = os.path.join(orthologous_groups_aa, name + ".fa")
output_file_dna = os.path.join(orthologous_groups_dna, name + ".fa")
if self._db_source:
ogs[name].dna = self._get_dna_records(ogs[name].aa, name)
else:
print("DNA reference was not provided. Only amino acid sequences gathered!")
self._write(output_file_dna, ogs[name].dna)
self._write(output_file_aa, ogs[name].aa)
return ogs
def orthoxml_parsing(orthoxml, nwk, species_list, gene_hog_dict):
ham_analysis = pyham.Ham(nwk, orthoxml)
for species in species_list:
sp_extant_genome = ham_analysis.get_extant_genome_by_name(species)
for gene in sp_extant_genome.genes:
xref = gene.get_dict_xref()['protId'].split(" ")[0]
hog = gene.get_top_level_hog()
if hog.is_singleton():
gene_hog_dict[xref] = "singleton"
else:
gene_hog_dict[xref] = gene.get_top_level_hog().hog_id
# This is the HAM package
import pyham
# OPTIONAL: only if you want to have the logger information printed
import logging
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s %(name)-12s %(levelname)-8s %(message)s")
# Initialise pyHam with a gene oma id
query = 'HUMAN12'
pyham_analysis = pyham.Ham(query_database=query, use_data_from='oma')
hog = pyham_analysis.get_hog_by_id('HOG:0359282')
# create the iHam for it and store it into an html file
output_name = "iHam{}.html".format(hog.hog_id)
pyham_analysis.create_iHam(hog=hog, outfile=output_name)
# create the iHam for it and store it into an html file
output_name = "TreeProfile{}.html".format(hog.hog_id)
pyham_analysis.create_tree_profile(hog=hog, outfile=output_name)
# This is the HAM package
import pyham
# OPTIONAL: only if you want to have the logger information printed
import logging
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s %(name)-12s %(levelname)-8s %(message)s")
# Initialise pyHam with a phyloxml tree and orthoXML HOGs
phyloxml_path = "simpleEx.phyloxml"
orthoxml_path3 = "simpleEx.orthoxml"
pyham_analysis = pyham.Ham(phyloxml_path,
orthoxml_path3,
use_internal_name=True,
tree_format='phyloxml')
hog = pyham_analysis.get_hog_by_id('HOG:0355161')
# create the iHam for it and store it into an html file
output_name = "iHam{}.html".format(hog.hog_id)
pyham_analysis.create_iHam(hog=hog, outfile=output_name)
second=second_ancestor,
results_tag=results_tag), 'a') as output_txt:
for xref in results_xref:
output_txt.write("{xref}\n".format(xref=xref))
if __name__ == "__main__":
# All genes in ancestor genomes according to pyHAM:
digenea_ancestor_all, platy_ancestor_all, = [], []
# Filtered sets of genes from ancestor genomes:
digenea_ancestor_filtered, platy_ancestor_filtered = [], []
# For vertical comparison:
retained_gene_ids, duplicated_gene_ids, gained_gene_ids = [], [], []
# pyHAM analysis:
ham_analysis = pyham.Ham(nwk_file, orthoxml_file, use_internal_name=True)
# Ancestor genome reconstruction:
digenea_ancestor_genome = ham_analysis.get_ancestral_genome_by_name(
"Digenea")
platy_ancestor_genome = ham_analysis.get_ancestral_genome_by_name(
"Platyhelminthes")
digenea_ancestor_all.extend(digenea_ancestor_genome.genes)
print(
"According to pyHAM, Digenea ancestor genome model includes {num} genes"
.format(num=len(digenea_ancestor_all)))
platy_ancestor_all.extend(platy_ancestor_genome.genes)
print(
"According to pyHAM, Platyhelminthes ancestor genome model includes {num} genes"
.format(num=len(platy_ancestor_all)))