def get_flanking_positions(obj_tt, genomic_range, flank_type):
"""
Find the position flanking the genomic alteration
-if mutation, then complete_rf = True for codons flanking codon affected
-if insertion, then complete_rf = False, need to retrieve codons immediately before & after genomic alteration
-if deletion, then complete_rf = False, need to retrieve codons immediately before & after genomic alteration
Args:
-obj_tt
-genomic_range = string that is genomic range of genomic alteration ()
-alt_type = integer that is the "flank_type", either to stay on the position in 'genomic_range' or to get the position before & after the genomic alteration (-1 & +1 for before & after genomic alteration, respectively)
-0 = stay on genomic position of genomic alteration
-should do this for SNVs and events where genomic alteration does not alter the reading frame.
-1 = retrieve the position before (-1) & after (+1)
-should do this for frameshifting events as the reading frame has been altered
Returns:
returns a string
"""
hash_pos = Isoform.split_genome_pos(genomic_range)
if flank_type == 0:
return hash_pos
else:
return {
'chrom': hash_pos['chrom'],
'start': hash_pos['start'] - 1,
'end': hash_pos['end'] + 1
}
def create_obj_tt(isoform_id, genome_pos):
"""
Creates an instance of TranslateTranscript
Args:
-isoform_id = string that is the isoform, usually in the form of an Ensembl ID (e.g. ENST000..)
-row = from pandas Dataframe, a row from the file contain mutation position
"""
##TEST:: print "MAIN: start of cott: isoform_id = ", isoform_id
db_type = 2 #this means the database is Ensembl
hash_gp = Isoform.split_genome_pos(genome_pos) #hash_gp = hash genome pos
hash_pos = {
'chrom': 'chr' + str(hash_gp['chrom']),
'pos_oi': hash_gp['start']
}
iso_sj = IsoformSJ(db_type, isoform_id, [], -10, hash_pos, False, 0, True)
canon_transcript = iso_sj.create_canon_transcript(False, False)
obj_tt = TranslateTranscript(canon_transcript, iso_sj, DIR_GENOME, {})
return obj_tt
# print i2, " - aa_orig = ", aa_orig
# print i2, " - aa_alt = ", aa_alt
# for i2 in range( 0, len( obj_iso.list_mRNA ) ):
# mrna_orig = obj_iso.list_mRNA[i2]
# mrna_alt = obj_iso.list_mRNA_alt[i2]
# #retrieve nucleotide
# # [subseq_orig, subseq_alt] = obj_iso.retrieve_mRNA_neoep_subseq( mrna_orig, mrna_alt )
# # print "subseq_orig = ", subseq_orig
# # print "subseq_alt = ", subseq_alt
# #retrieve amino acid sequence
# [aa_orig, aa_alt] = SimpleNeoepitopeIsoformV2.retrieve_comparative_neoeps( mrna_orig, mrna_alt, 9 )
# print i2, " - aa_orig = ", aa_orig
# print i2, " - aa_alt = ", aa_alt
print "mRNA: ********", i, "********\n"
#retrieve the isoform IDs (from Ensembl OR RefSeq OR UCSC) and display them
hash_gp = Isoform.split_genome_pos( genomic_range )
hash_gp_chrom = "chr" + hash_gp['chrom'] if not "chr" in hash_gp['chrom'] else hash_gp['chrom']
print "hash_gp = ", hash_gp
db_type = 1 #1 = uses RefSeq, 2 = uses Ensembl, 3 = uses UCSC
all_isoforms = Isoform.get_isoforms_by_pos_db_all( hash_gp_chrom, hash_gp['start'], hash_gp['end'], db_type )
all_iso_id = [x.name for x in all_isoforms]
print "all_iso_id = ", all_iso_id
print "------------ TDD Completed: 171108_SimpleNeoepV2_NMD.py ------------"