def locus2inference_table(biodb):
server, db = manipulate_biosqldb.load_db(biodb)
sql = 'CREATE TABLE locus_tag2uniprot_hit_%s (locus_tag varchar(400),' \
' uniprot_id varchar(400), index locus_tag(locus_tag))' % biodb
server.adaptor.execute(sql, )
locus2seqfeature_id = manipulate_biosqldb.locus_tag2seqfeature_id_dict(
server, biodb)
for locus in locus2seqfeature_id:
sql = 'select value from seqfeature_qualifier_value where seqfeature_id=%s and value like "%%%%UniProtKB%%%%"' % (
locus2seqfeature_id[locus])
try:
data = server.adaptor.execute_and_fetchall(sql, )[0][0]
sql2 = 'insert into locus_tag2uniprot_hit_%s values ("%s", "%s")' % (
biodb, locus, data.split(':')[2])
try:
server.adaptor.execute(sql2, )
server.commit()
except:
print sql2
except:
pass
def locus_list2identity_in_other_genomes(locus_list, biodb):
server, db = manipulate_biosqldb.load_db(biodb)
locus_tag2seqfeature_id = manipulate_biosqldb.locus_tag2seqfeature_id_dict(
server, biodb)
taxon_id2description = manipulate_biosqldb.taxon_id2genome_description(
server, biodb)
import re
for i in taxon_id2description.keys():
taxon_id2description[i] = re.sub(" subsp\. aureus", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub(", complete genome\.", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub(", complete sequence\.", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub("strain ", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub("str\. ", "", taxon_id2description[i])
taxon_id2description[i] = re.sub(" complete genome sequence\.", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub(" complete genome\.", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub(" chromosome", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub("Staphylococcus aureus ", "",
taxon_id2description[i])
header = 'orthogroup\t'
dico = locus_tag2identity_best_hit_all_genomes(biodb, 'wcw_1594',
'group_417')
for i in dico.keys():
header += taxon_id2description[i] + '\t'
final_out = header + '\n'
for locus in locus_list:
#print "locus", i
seqfeature_id = locus_tag2seqfeature_id[locus]
orthogroup = manipulate_biosqldb.seqfeature_id2orthogroup(
server, seqfeature_id, biodb)
#print "ortho", orthogroup
dico = locus_tag2identity_best_hit_all_genomes(biodb, locus,
orthogroup)
#print "dico done..."
out = '%s\t' % orthogroup
for i in dico.keys():
identity = dico[i]
out += '%s\t' % identity
final_out += out + '\n'
return final_out
def locus_list2presence_absence_all_genomes(locus_list, biodb_name):
server, db = manipulate_biosqldb.load_db(biodb_name)
locus_tag2seqfeature_id = manipulate_biosqldb.locus_tag2seqfeature_id_dict(
server, biodb_name)
taxon_id2description = manipulate_biosqldb.taxon_id2genome_description(
server, biodb_name)
import re
for i in taxon_id2description.keys():
taxon_id2description[i] = re.sub(" subsp\. aureus", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub(", complete genome\.", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub(", complete sequence\.", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub("strain ", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub("str\. ", "", taxon_id2description[i])
taxon_id2description[i] = re.sub(" complete genome sequence\.", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub(" complete genome\.", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub(" chromosome", "",
taxon_id2description[i])
taxon_id2description[i] = re.sub("Staphylococcus aureus ", "",
taxon_id2description[i])
header = 'orthogroup\t'
genomes = manipulate_biosqldb.get_genome_taxons_list(server, biodb_name)
for i in genomes:
header += taxon_id2description[i] + '\t'
final_out = header + '\n'
for i in locus_list:
#print "locus", i
seqfeature_id = locus_tag2seqfeature_id[i]
orthogroup = manipulate_biosqldb.seqfeature_id2orthogroup(
server, seqfeature_id, biodb_name)
#print "ortho", orthogroup
dico = heatmap_presence_absence(biodb_name, orthogroup)
#print "dico done..."
#print dico
out = '%s\t' % orthogroup
for i in genomes:
out += '%s\t' % dico[i]
final_out += out + '\n'
return final_out
def create_locus_tag2seqfeature_table(biodb,
locus2seqfeature_id=False,
locus2taxon_id=False):
from chlamdb.biosqldb import manipulate_biosqldb
server, db = manipulate_biosqldb.load_db(biodb)
sql = 'CREATE TABLE IF NOT EXISTS custom_tables.locus2seqfeature_id_%s (locus_tag varchar(400), ' \
' seqfeature_id INT, ' \
' taxon_id INT,' \
' index locus_tag (locus_tag), ' \
' index seqfeature_id(seqfeature_id), ' \
' index taxon_id (taxon_id))' % biodb
server.adaptor.execute(sql)
server.commit()
if not locus2seqfeature_id:
locus2seqfeature_id = manipulate_biosqldb.locus_tag2seqfeature_id_dict(
server, biodb)
if not locus2taxon_id:
locus2taxon_id = manipulate_biosqldb.locus_tag2genome_taxon_id(
server, biodb)
for locus in locus2seqfeature_id:
try:
sql = 'insert into custom_tables.locus2seqfeature_id_%s values ("%s", %s, %s)' % (
biodb, locus, locus2seqfeature_id[locus],
locus2taxon_id[locus])
server.adaptor.execute(sql)
except:
# pseudogenes
sql = 'insert into custom_tables.locus2seqfeature_id_%s values ("%s", %s, %s)' % (
biodb, locus, locus2seqfeature_id[locus], "NULL")
server.adaptor.execute(sql)
server.commit()
if args.create_tables:
create_sql_blastnr_tables(args.mysql_database,
mysql_host,
mysql_user,
mysql_pwd,
mysql_db,
main_blastnr_table=True,
alternate_tables=True)
if args.load_tables:
server, db = manipulate_biosqldb.load_db(biodb)
sys.stdout.write("creating locus_tag2seqfeature_id")
locus_tag2seqfeature_id = manipulate_biosqldb.locus_tag2seqfeature_id_dict(
server, biodb)
sys.stdout.write("creating protein_id2seqfeature_id")
protein_id2seqfeature_id = manipulate_biosqldb.protein_id2seqfeature_id_dict(
server, biodb)
sys.stdout.write("getting seqfeature_id2locus_tag")
seqfeature_id2locus_tag = manipulate_biosqldb.seqfeature_id2locus_tag_dico(
server, biodb)
sys.stdout.write("getting locus_tag2accession")
locus_tag2accession = manipulate_biosqldb.locus_tag2accession(
server, args.mysql_database)
blastnr2biosql(seqfeature_id2locus_tag, locus_tag2seqfeature_id,
protein_id2seqfeature_id, locus_tag2accession, biodb,
parser.add_argument("-d", '--db_name', type=str, help="db name")
args = parser.parse_args()
server, db = manipulate_biosqldb.load_db(args.db_name)
asset_path = "/home/trestan/work/dev/django/chlamydia/assets"
print("parsing orthofinder file")
locus_tag2orthogroup_id, \
orthomcl_groups2locus_tag_list, \
genome_orthomcl_code2proteins, \
protein_id2genome_ortho_mcl_code = parse_orthomcl_output(args.mcl,
True)
print("get locus_tag2seqfeature_id")
locus_tag2seqfeature_id = manipulate_biosqldb.locus_tag2seqfeature_id_dict(
server, args.db_name)
locus_tag2seqfeature_id_CDS = manipulate_biosqldb.locus_tag2seqfeature_id_dict(
server, args.db_name, all=False)
print("number of groups:", len(orthomcl_groups2locus_tag_list))
print("number of locus in locus_tag2orthogroup_id:",
len(locus_tag2orthogroup_id))
print("number of locus in locus_tag2seqfeature_id:",
len(locus_tag2seqfeature_id))
print("number of locus in locus_tag2seqfeature_id_CDS:",
len(locus_tag2seqfeature_id_CDS))
print("adding orthogroup to seqfeature_qualifier_values")
add_orthogroup_to_seq(server, locus_tag2orthogroup_id,
locus_tag2seqfeature_id)
help=
"Path to save core orthogroup fasta. Taxon id as header for concatenation.",
default=None)
parser.add_argument("-o",
'--orthofinder',
action="store_true",
help="orthofinder input file (and not orthomcl)")
args = parser.parse_args()
server, db = manipulate_biosqldb.load_db(args.db_name)
asset_path = "/home/trestan/work/dev/django/chlamydia/assets"
if not args.get_sequences and not args.core_groups_path:
print "creating locus_tag2seqfeature_id"
locus_tag2seqfeature_id = manipulate_biosqldb.locus_tag2seqfeature_id_dict(
server, args.db_name)
print "creating protein_id2seqfeature_id"
protein_id2seqfeature_id = manipulate_biosqldb.protein_id2seqfeature_id_dict(
server, args.db_name)
print "creating locus_tag2taxon_id dictionnary..."
locus_tag2genome_taxon_id = manipulate_biosqldb.locus_tag2genome_taxon_id(
server, args.db_name)
print "creating protein_id2taxon_id dictionnary..."
protein_id2genome_taxon_id = manipulate_biosqldb.protein_id2genome_taxon_id(
server, args.db_name)
print "creating locus_tag2accession dictionnary..."
locus_tag2accession = manipulate_biosqldb.locus_tag2accession(
server, args.db_name)
