def main():
no_threads = 8
outdir = "raw_tables"
os.makedirs(outdir, exist_ok=True)
db = connect_to_mysql(Config.mysql_conf_file)
cursor = db.cursor()
[all_species, ensembl_db_name] = get_species(cursor)
# unprocessed_species = check_species_done(cursor, all_species, ensembl_db_name, outdir)
# print("unprocessed_species:", len(unprocessed_species))
# print("\n".join(unprocessed_species))
# exit()
# all_species = unprocessed_species
# all_species = ['monodelphis_domestica']
# all_species = sample(all_species, 1)
cursor.close()
db.close()
parallelize(no_threads, store_exon_seqs_species, all_species,
[ensembl_db_name, outdir])
def main():
special = 'test'
no_threads = 10
method = 'usearch'
if len(sys.argv) > 1 and len(sys.argv)<4:
print "usage: %s <set name> <number of threads> <method>" % sys.argv[0]
exit(1) # exit if bad number of cmdline params
elif len(sys.argv)==4:
special = sys.argv[1]
special = special.lower()
if special == 'none': special = None
no_threads = int(sys.argv[2])
method = sys.argv[3]
if not (method =='usearch' or method=='sw_sharp'):
print "unrecognized method: ", method
exit(1) # exit if unrecognized search method
# sw_sharps chokes if there is only one graphics card
if method=='sw_sharp': no_threads = 1
db = connect_to_mysql()
cfg = ConfigurationReader()
cursor = db.cursor()
[all_species, ensembl_db_name] = get_species (cursor)
print '======================================='
print sys.argv[0]
if special:
print "using", special, "set"
if special == 'complement':
gene_list = get_complement_ids(cursor, ensembl_db_name, cfg)
else:
gene_list = get_theme_ids (cursor, ensembl_db_name, cfg, special )
else:
print "using all protein coding genes"
switch_to_db (cursor, ensembl_db_name['homo_sapiens'])
gene_list = get_gene_ids (cursor, biotype='protein_coding', is_known=1)
cursor.close()
db.close()
parallelize (no_threads, find_missing_exons, gene_list, [local_db, ensembl_db_name, method])
return True
def main():
no_threads = 10
db = connect_to_mysql()
cursor = db.cursor()
[all_species, ensembl_db_name] = get_species (cursor)
cursor.close()
db.close()
parallelize (no_threads, collect_paralogues, all_species, [local_db, ensembl_db_name])
return True
def main():
no_threads = 1
db = connect_to_mysql()
cursor = db.cursor()
[all_species, ensembl_db_name] = get_species (cursor)
cursor.close()
db .close()
parallelize (no_threads, make_alignments, all_species, [local_db, ensembl_db_name])
return True
def main():
no_threads = 12
special = None
if len(sys.argv) > 1 and len(sys.argv)<3:
print "usage: %s <set name> <no of processes>" % sys.argv[0]
exit(1) # after usage statement
elif len(sys.argv)>=3:
special = sys.argv[1]
special = special.lower()
if special == 'none': special = None
no_processes = int(sys.argv[2])
db = connect_to_mysql()
cfg = ConfigurationReader()
cursor = db.cursor()
[all_species, ensembl_db_name] = get_species (cursor)
print "running ", sys.argv[0]
if special:
print "using", special, "set"
if special == 'complement':
gene_list = get_complement_ids(cursor, ensembl_db_name, cfg)
else:
gene_list = get_theme_ids (cursor, ensembl_db_name, cfg, special )
else:
print "using all protein coding genes"
switch_to_db (cursor, ensembl_db_name['homo_sapiens'])
gene_list = get_gene_ids (cursor, biotype='protein_coding', is_known=1)
cursor.close()
db.close()
parallelize (no_processes, multiple_exon_alnmt, gene_list, [local_db, ensembl_db_name])
return True
def main():
no_threads = 1
special = ''
db = connect_to_mysql()
cfg = ConfigurationReader()
cursor = db.cursor()
[all_species, ensembl_db_name] = get_species (cursor)
species = ''
if len(sys.argv) > 1 and len(sys.argv)<3 or len(sys.argv) >= 2 and sys.argv[1]=="-h":
print "usage: %s <set name/species> <number of processes>" % sys.argv[0]
exit(1) # after usage statement
elif len(sys.argv)==3:
special = sys.argv[1].lower()
if special == 'none':
special = None
elif special in all_species:
species = special
no_threads = int(sys.argv[2])
print '======================================='
print sys.argv[0]
if species:
print species, "only"
switch_to_db (cursor, ensembl_db_name[species])
if (species=='homo_sapiens'):
gene_ids = get_gene_ids (cursor, biotype='protein_coding', is_known=1, ref_only=True)
else:
gene_ids = get_gene_ids (cursor, biotype='protein_coding')
parallelize_args = [no_threads, one_species_all_genes_loop, gene_ids, [local_db, ensembl_db_name, species]]
elif special:
print "using", special, "set"
gene_list = get_theme_ids (cursor, ensembl_db_name, cfg, special )
parallelize_args = [no_threads, ortologues_for_given_genes_loop, gene_list, [local_db, ensembl_db_name]]
else:
parallelize_args = [no_threads, all_species_all_genes_loop, all_species, [local_db, ensembl_db_name]]
cursor.close()
db .close()
parallelize (*parallelize_args)
def main():
no_threads = 1
special = 'test'
if len(sys.argv) > 1 and len(sys.argv) < 3:
print "usage: %s <set name> <number of threads>" % sys.argv[0]
exit(1)
elif len(sys.argv) == 3:
special = sys.argv[1]
special = special.lower()
if special == 'none': special = None
no_threads = int(sys.argv[2])
db = connect_to_mysql()
cfg = ConfigurationReader()
cursor = db.cursor()
[all_species, ensembl_db_name] = get_species(cursor)
print '======================================='
print sys.argv[0]
if special:
print "using", special, "set"
if special == 'complement':
gene_list = get_complement_ids(cursor, ensembl_db_name, cfg)
else:
gene_list = get_theme_ids(cursor, ensembl_db_name, cfg, special)
else:
print "using all protein coding genes"
switch_to_db(cursor, ensembl_db_name['homo_sapiens'])
gene_list = get_gene_ids(cursor, biotype='protein_coding', is_known=1)
cursor.close()
db.close()
parallelize(no_threads, exon_cleanup, gene_list,
[local_db, ensembl_db_name])
return True
def main():
no_threads = 1
special = 'one'
if len(sys.argv) > 1 and len(sys.argv)<3:
print "usage: %s <set name> <number of threads> <method>"
exit(1)
elif len(sys.argv)==3:
special = sys.argv[1]
special = special.lower()
if special == 'none': special = None
no_threads = int(sys.argv[2])
db = connect_to_mysql()
cfg = ConfigurationReader()
cursor = db.cursor()
[all_species, ensembl_db_name] = get_species (cursor)
print '======================================='
print sys.argv[0]
if special:
print "using", special, "set"
if special == 'complement':
gene_list = get_complement_ids(cursor, ensembl_db_name, cfg)
else:
gene_list = get_theme_ids (cursor, ensembl_db_name, cfg, special )
else:
print "using all protein coding genes that have an sw# or usearch patch"
switch_to_db (cursor, ensembl_db_name['homo_sapiens'])
gene_list = human_genes_w_novel_exon_orthologues (cursor, ensembl_db_name)
cursor.close()
db.close()
parallelize (no_threads, maps_for_gene_list, gene_list[0:15000], [local_db, ensembl_db_name])
return True
def main():
no_threads = 10
special = None
if len(sys.argv) > 1 and len(sys.argv)<3:
print "usage: %s <set name> <number of threads> " % sys.argv[0]
exit(1)
elif len(sys.argv)==3:
special = sys.argv[1]
special = special.lower()
if special == 'none': special = None
no_threads = int(sys.argv[2])
db = connect_to_mysql()
cfg = ConfigurationReader()
cursor = db.cursor()
[all_species, ensembl_db_name] = get_species (cursor)
print '======================================='
print sys.argv[0]
if special:
print "using", special, "set"
gene_list = get_theme_ids (cursor, ensembl_db_name, cfg, special )
else:
print "using all protein coding genes"
switch_to_db (cursor, ensembl_db_name['homo_sapiens'])
gene_list = get_gene_ids (cursor, biotype='protein_coding', is_known=1)
cursor.close()
db.close()
parallelize (no_threads, maps_for_gene_list, gene_list, [local_db, ensembl_db_name])
return True
def main():
# TODO: cplit codons
no_processes = 1
rep_species = 'monodelphis_domestica'
db = connect_to_mysql(Config.mysql_conf_file)
cursor = db.cursor()
[all_species, ensembl_db_name] = get_species(cursor)
# switch_to_db(cursor, ensembl_db_name[rep_species])
# qry = "select distinct(g.gene_id) from exon_map e left join gene2exon g on e.exon_id = g.exon_id"
# genes_with_maps = [ret[0] for ret in hard_landing_search(cursor, qry)]
# print(f"genes with maps: {len(genes_with_maps)}")
# gene_list = sample(genes_with_maps, 10)
gene_list = [8979] # NARS; only three exons out of 14, and not the same species as the ones for which I have the full seqeuence
cursor.close()
db.close()
parallelize(no_processes, multiple_alignment_genes, gene_list, [rep_species, ensembl_db_name])
return True
def main():
"""
Main entry point, but in reality does nothing except taking care of the parallelization.
The parallelization here is per-species.
"""
no_threads = 1
special = ''
if len(sys.argv) > 1 and len(sys.argv)<3 or len(sys.argv) >= 2 and sys.argv[1]=="-h":
print "usage: %s <set name> <number of threads>" % sys.argv[0]
exit(1) # after usage statment
elif len(sys.argv)==3:
special = sys.argv[1].lower()
if special == 'none': special = None
no_threads = int(sys.argv[2])
db = connect_to_mysql()
cfg = ConfigurationReader()
cursor = db.cursor()
[all_species, ensembl_db_name] = get_species (cursor)
print '======================================='
print sys.argv[0]
if special:
print "using", special, "set"
gene_list = get_theme_ids (cursor, ensembl_db_name, cfg, special )
cursor.close()
db .close()
# two version of the main loop:
# 1) over all species, and all genes in each speceis
if not special:
parallelize (no_threads, store_exon_seqs, all_species, [local_db, ensembl_db_name])
else:
parallelize (no_threads, store_exon_seqs_special, gene_list, [local_db, ensembl_db_name])
