def create_SQ_header(database_v,species):
'''
:param database_v: database version
:return: list of chromosomes with their size (from ENSEMBL)
'''
SQ=[]
# create connection to ensembm database
# create connection to ensembl database
if species=="arabidopsis_thaliana":
Genome_species=Species.getCommonName(species.replace('_',' '))
account=host.HostAccount(host="mysql-eg-publicsql.ebi.ac.uk",user="******",passwd="",port=4157)
ensembl=Genome(Species=Genome_species,account=account,Release=30)
else:
Genome_species=Species.getCommonName(species.replace('_',' '))
ensembl=Genome(Species=Genome_species,Release=database_v,account=None)
# convert IDs
coord_table=ensembl.CoreDb.getTable('coord_system')
seq_region_table=ensembl.CoreDb.getTable('seq_region')
select_obj=[seq_region_table.c.name,
seq_region_table.c.length,
coord_table.c.version,
]
from_obj=seq_region_table.join(coord_table,coord_table.c.coord_system_id==seq_region_table.c.coord_system_id)
query = sql.select(select_obj,from_obj=[from_obj],
whereclause = coord_table.c.rank==1)
for row in query.execute():
if '_' not in row[0]:
SQ_string= "@SQ\tSN:chr"+str(row[0])+"\tLN:"+str(row[1])+"\tAS:"+str(row[2])+"\tSP:"+str(species)
SQ.append(SQ_string)
return SQ
def prepareAnnotationENSEMBL(psm_protein_id,mode,database_v,species,three_frame_translation):
'''
:param psm_protein_id: list of protein IDs (untagged)
:param mode: transcript or protein mode
:param database_v: database version
:param species: species name
:return: dictionairy mapping proteins into ENSEMBL
'''
print('Commencing ENSEMBL data retrieval')
# create connection to ensembl database
if species=="arabidopsis_thaliana":
Genome_species=Species.getCommonName(species.replace('_',' '))
account=host.HostAccount(host="mysql-eg-publicsql.ebi.ac.uk",user="******",passwd="",port=4157)
ensembl=Genome(Species=Genome_species,account=account,Release=30)
else:
Genome_species=Species.getCommonName(species.replace('_',' '))
ensembl=Genome(Species=Genome_species,Release=database_v,account=None)
# convert IDs
translation_table=ensembl.CoreDb.getTable('translation')
transcript_table=ensembl.CoreDb.getTable('transcript')
select_obj=[transcript_table.c.stable_id,
translation_table.c.stable_id,
transcript_table.c.transcript_id,
translation_table.c.seq_start,
translation_table.c.start_exon_id,
]
from_obj=translation_table.join(transcript_table,transcript_table.c.transcript_id==translation_table.c.transcript_id)
if mode=='protein':
id=1
query = sql.select(select_obj,from_obj=[from_obj],
whereclause = translation_table.c.stable_id.in_(psm_protein_id))
elif mode=='transcript':
id=0
query = sql.select(select_obj,from_obj=[from_obj],
whereclause = transcript_table.c.stable_id.in_(psm_protein_id))
psm_protein_id={}
transcript_ids=[]
for row in query.execute():
#print row
transcript_ids.append(row[2])
psm_protein_id[row[id]]={'transcript_id':row[0],'translation_id':row[1],
'transcript_seq':'','protein_seq':'',
'chr':'','strand':'','5UTR_offset':row[3],'start_exon_rank':row[4]}
return ensembl_construct_sequences(psm_protein_id,ensembl,transcript_ids,database_v,species,
three_frame_translation,mode)