def main():
parameter = {}
# in case I ever have to handle multiple versions of ensembl
# (but for now I don't have enough space)
# note though that there are functions in el_utils/mysql.py that assume
# that whatever ensembl stuff is available to the mysql server corresponds to the same release
release_number = '76'
parameter['ensembl_release_number'] = release_number
parameter['blastp_e_value'] = "1.e-10" # it will be used as a string when fmting the blastp cmd
parameter['min_accptbl_exon_sim'] = 0.33333 #minimum acceptable exon similarity
dir_path = {}
dir_path['ensembl_fasta'] = '/mnt/ensembl-mirror/release-'+release_number+'/fasta'
# local juggling of data from one database base to the other
dir_path['afs_dumps'] = '/afs/bii.a-star.edu.sg/dept/biomodel_design/Group/ivana/'
dir_path['afs_dumps'] += 'ExoLocator/results/dumpster'
dir_path['resources'] = '/afs/bii.a-star.edu.sg/dept/biomodel_design/Group/ivana/'
dir_path['resources'] += 'pypeworks/exolocator/resources'
dir_path['scratch'] = '/tmp'
dir_path['maxentscan'] = '/afs/bii.a-star.edu.sg/dept/biomodel_design/Group/ivana/'
dir_path['maxentscan'] += 'pypeworks/exolocator/pl_utils/maxentscan'
util_path = {}
util_path['mafft'] = '/usr/bin/mafft'
util_path['blastall'] = '/usr/bin/blastall'
util_path['fastacmd'] = '/usr/bin/fastacmd'
util_path['sw#'] = '/usr/bin/swsharp'
util_path['usearch'] = '/usr/bin/usearch'
util_path['score3'] = dir_path['maxentscan'] + '/score3.pl'
util_path['score5'] = dir_path['maxentscan'] + '/score5.pl'
if 1:
# check if the paths are functioning (at this point at least)
for util in util_path.values():
if (not os.path.exists(util)):
print util, " not found "
sys.exit (1)
for dir in dir_path.values():
if (not os.path.exists(dir)):
print dir, " not found "
sys.exit (1)
if (not os.path.isdir (dir)):
print dir, " is not a directory "
sys.exit (1)
db = connect_to_mysql()
cursor = db.cursor()
#######################################################
# check if the config db exists -- if not, make it
db_name = "exolocator_config"
qry = "show databases like'%s'" % db_name
rows = search_db (cursor, qry)
if (not rows):
print db_name, "database not found"
qry = "create database %s " % db_name
rows = search_db (cursor, qry)
if (rows):
print "some problem creating the database ..."
rows = search_db (cursor, qry, verbose = True)
else:
print db_name, "database found"
qry = "use %s " % db_name
search_db (cursor, qry)
# make tables
for table in ['util_path', 'dir_path', 'parameter']:
if ( check_table_exists (cursor, db_name, table)):
print table, " found in ", db_name
else:
print table, " not found in ", db_name
make_table (cursor, table)
# fill util, dir and path tables
fixed_fields = {}
update_fields = {}
for [name, path] in util_path.iteritems():
fixed_fields['name'] = name
update_fields['path'] = path
store_or_update (cursor, 'util_path', fixed_fields, update_fields)
fixed_fields = {}
update_fields = {}
for [name, path] in dir_path.iteritems():
fixed_fields['name'] = name
update_fields['path'] = path
store_or_update (cursor, 'dir_path', fixed_fields, update_fields)
fixed_fields = {}
update_fields = {}
for [name, value] in parameter.iteritems():
fixed_fields['name'] = name
update_fields['value'] = value
store_or_update (cursor, 'parameter', fixed_fields, update_fields)
#######################################################
# add trivial names to ncbi_taxonomy.names
[all_species, ensembl_db_name] = get_species (cursor)
feed_trivial_names (cursor, all_species)
#######################################################
# add species shorthands (used in ENS* names formation)
# though we will not needed unit the paralogue alignment reconstruction point)
feed_name_shorthands (cursor, all_species)
cursor.close()
db.close()
def feed_name_shorthands (cursor, all_species):
short = {}
short['ailuropoda_melanoleuca'] = 'AME'
short['anas_platyrhynchos'] = 'APL'
short['anolis_carolinensis'] = 'ACA'
short['astyanax_mexicanus'] = 'AMX'
short['bos_taurus'] = 'BTA'
short['callithrix_jacchus'] = 'CJA'
short['canis_familiaris'] = 'CAF'
short['cavia_porcellus'] = 'CPO'
short['choloepus_hoffmanni'] = 'CHO'
short['danio_rerio'] = 'DAR'
short['dasypus_novemcinctus'] = 'DNO'
short['dipodomys_ordii'] = 'DOR'
short['echinops_telfairi'] = 'ETE'
short['equus_caballus'] = 'ECA'
short['erinaceus_europaeus'] = 'EEU'
short['felis_catus'] = 'FCA'
short['ficedula_albicollis'] = 'FAL'
short['gadus_morhua'] = 'GMO'
short['gallus_gallus'] = 'GAL'
short['gasterosteus_aculeatus'] = 'GAC'
short['gorilla_gorilla'] = 'GGO'
short['homo_sapiens'] = ''
short['ictidomys_tridecemlineatus'] = 'STO'
short['latimeria_chalumnae'] = 'LAC'
short['lepisosteus_oculatus'] = 'LOC'
short['loxodonta_africana'] = 'LAF'
short['macaca_mulatta'] = 'MMU'
short['macropus_eugenii'] = 'MEU'
short['meleagris_gallopavo'] = 'MGA'
short['microcebus_murinus'] = 'MIC'
short['monodelphis_domestica'] = 'MOD'
short['mus_musculus'] = 'MUS'
short['mustela_putorius_furo'] = 'MPU'
short['myotis_lucifugus'] = 'MLU'
short['nomascus_leucogenys'] = 'NLE'
short['ochotona_princeps'] = 'OPR'
short['oreochromis_niloticus'] = 'ONI'
short['ornithorhynchus_anatinus'] = 'OAN'
short['oryctolagus_cuniculus'] = 'OCU'
short['oryzias_latipes'] = 'ORL'
short['ovis_aries'] = 'OAR'
short['otolemur_garnettii'] = 'OGA'
short['pan_troglodytes'] = 'PTR'
short['papio_anubis'] = 'PAN'
short['poecilia_formosa'] = 'PFO'
short['pelodiscus_sinensis'] = 'PSI'
short['petromyzon_marinus'] = 'PMA'
short['pongo_abelii'] = 'PPY'
short['procavia_capensis'] = 'PCA'
short['pteropus_vampyrus'] = 'PVA'
short['rattus_norvegicus'] = 'RNO'
short['sarcophilus_harrisii'] = 'SHA'
short['sorex_araneus'] = 'SAR'
short['sus_scrofa'] = 'SSC'
short['taeniopygia_guttata'] = 'TGU'
short['takifugu_rubripes'] = 'TRU'
short['tarsius_syrichta'] = 'TSY'
short['tetraodon_nigroviridis'] = 'TNI'
short['tupaia_belangeri'] = 'TBE'
short['tursiops_truncatus'] = 'TTR'
short['vicugna_pacos'] = 'VPA'
short['xenopus_tropicalis'] = 'XET'
short['xiphophorus_maculatus'] = 'XMA'
db_name = get_compara_name (cursor)
qry = "use %s " % db_name
search_db (cursor, qry)
table = 'species_name_shorthands'
# if the table does not exist, make it
if not check_table_exists (cursor, db_name, table):
qry = "CREATE TABLE " + table + " (id INT(10) PRIMARY KEY AUTO_INCREMENT)"
rows = search_db (cursor, qry)
if (rows): return False
qry = "ALTER TABLE %s ADD %s VARCHAR(100)" % (table, 'species')
rows = search_db (cursor, qry)
if (rows): return False
qry = "ALTER TABLE %s ADD %s VARCHAR(10)" % (table, 'shorthand')
rows = search_db (cursor, qry)
if (rows): return False
for species in all_species:
if short.has_key(species):
fixed_fields = {}
update_fields = {}
fixed_fields ['species'] = species
update_fields ['shorthand'] = short[species]
store_or_update (cursor, table, fixed_fields, update_fields)
else:
print "short for ", species, " not found "
short[species] = ""
