def __init__(self, src_file, title='ENSEMBL', version='', tx_mode=TranscriptProvider.TX_MODE_CANONICAL, protocol="file", is_thread_safe=False, tx_filter="dummy", custom_canonical_txs=None):
super(EnsemblTranscriptDatasource, self).__init__(src_file=src_file, title=title, version=version)
ensembl_index_fname = src_file + ".transcript.idx"
ensembl_gene_to_transcript_index_fname = src_file + ".transcript_by_gene.idx"
ensembl_genomic_position_bins_to_transcript_index_fname = src_file + ".transcript_by_gp_bin.idx"
# Seconds before a cache entry should be cleared out
timeout = 1000
max_entries = 25000
cache_protocol = "memory"
if not is_thread_safe:
logging.getLogger(__name__).info("%s %s is being set up in faster, NOT thread-safe mode (for annotation). " % (title, version))
cache_protocol = "simple"
# Contains a key of transcript id and value of a Transcript class, with sequence data where possible.
# By specifying "memory" for the cache, this is thread safe. Otherwise, use "simple"
self.transcript_db = shove.Shove(protocol + '://%s' % ensembl_index_fname, cache_protocol + "://", timeout=timeout, max_entries=max_entries)
self.gene_db = shove.Shove(protocol + '://%s' % ensembl_gene_to_transcript_index_fname, cache_protocol + "://", timeout=timeout, max_entries=max_entries)
self.gp_bin_db = shove.Shove(protocol + '://%s' % ensembl_genomic_position_bins_to_transcript_index_fname, cache_protocol + "://", timeout=timeout, max_entries=max_entries)
tmp = self.gp_bin_db.keys()
logging.getLogger(__name__).info("%s %s is being set up with default tx-mode: %s. " % (title, version, tx_mode))
self.set_tx_mode(tx_mode)
logging.getLogger(__name__).info("%s %s is being set up with %s filtering. " % (title, version, tx_filter))
self._tx_filter = TranscriptFilterFactory.create_instance(tx_filter)
self._hgvs_xformer = HgvsChangeTransformer()
# Store a list of the custom canonical transcripts
self._custom_canonical_txs = custom_canonical_txs or []
def __init__(self, src_file, title='ENSEMBL', version='', tx_mode=TranscriptProvider.TX_MODE_CANONICAL, protocol="file", is_thread_safe=False, tx_filter="dummy"):
super(EnsemblTranscriptDatasource, self).__init__(src_file=src_file, title=title, version=version)
ensembl_index_fname = src_file + ".transcript.idx"
ensembl_gene_to_transcript_index_fname = src_file + ".transcript_by_gene.idx"
ensembl_genomic_position_bins_to_transcript_index_fname = src_file + ".transcript_by_gp_bin.idx"
# Seconds before a cache entry should be cleared out
timeout = 1000
max_entries = 25000
cache_protocol = "memory"
if not is_thread_safe:
logging.getLogger(__name__).info("%s %s is being set up in faster, NOT thread-safe mode (for annotation). " % (title, version))
cache_protocol = "simple"
# Contains a key of transcript id and value of a Transcript class, with sequence data where possible.
# By specifying "memory" for the cache, this is thread safe. Otherwise, use "simple"
self.transcript_db = shove.Shove(protocol + '://%s' % ensembl_index_fname, cache_protocol + "://", timeout=timeout, max_entries=max_entries)
self.gene_db = shove.Shove(protocol + '://%s' % ensembl_gene_to_transcript_index_fname, cache_protocol + "://", timeout=timeout, max_entries=max_entries)
self.gp_bin_db = shove.Shove(protocol + '://%s' % ensembl_genomic_position_bins_to_transcript_index_fname, cache_protocol + "://", timeout=timeout, max_entries=max_entries)
tmp = self.gp_bin_db.keys()
logging.getLogger(__name__).info("%s %s is being set up with default tx-mode: %s. " % (title, version, tx_mode))
self.set_tx_mode(tx_mode)
logging.getLogger(__name__).info("%s %s is being set up with %s filtering. " % (title, version, tx_filter))
self._tx_filter = TranscriptFilterFactory.create_instance(tx_filter)
self._hgvs_xformer = HgvsChangeTransformer()
def test_basic_tag_filtering(self):
"""Test several cases for the BasicTagTranscriptFilter"""
tx_filter = TranscriptFilterFactory.create_instance("basic")
ensembl_ds = TestUtils._create_test_gencode_v19_ds("out/basic_tag_filter_ensembl_ds")
tx_dict = ensembl_ds.getTranscriptDict()
tx = tx_dict["ENST00000215832.6"]
self.assertTrue(len(tx_filter.filter([tx])) == 1)
attrib_dict = tx.get_other_attributes()
attrib_dict.pop('tag', None)
self.assertTrue(len(tx_filter.filter([tx])) == 0)
def test_basic_tag_filtering(self):
"""Test several cases for the BasicTagTranscriptFilter"""
tx_filter = TranscriptFilterFactory.create_instance("basic")
ensembl_ds = TestUtils._create_test_gencode_v19_ds(
"out/basic_tag_filter_ensembl_ds")
tx_dict = ensembl_ds.getTranscriptDict()
tx = tx_dict["ENST00000215832.6"]
self.assertTrue(len(tx_filter.filter([tx])) == 1)
attrib_dict = tx.get_other_attributes()
attrib_dict.pop('tag', None)
self.assertTrue(len(tx_filter.filter([tx])) == 0)
