def print_stats(self):
pretty_names = [
('total_seqs', 'Total num seqs', None),
('total_passed', 'Total passed as tRNA seq', 'green'),
('total_full_length', 'Total full length tRNA seqs', 'green'),
('total_rejected', 'Total rejected', 'red'),
('anticodon_unknown', 'Total with an unknown anticodon', None)
]
## ('short_rejected', 'Rejected due to short length', None),
## ('long_rejected', 'Rejected due to long length', None),
## ('acceptor_seq_rejected', 'Rejected due to acceptor seq', None),
## ('t_loop_seq_rejected', 'Rejected due to t-loop seq', None),
## ('both_rejected', 'Rejected due to both', None),
## ('no_divergence', 'No divergence', None),
## ('t_loop_divergence', 'Divergence at t-loop', None),
#### ('div_at_0', 't-loop divergence at pos 0', None),
#### ('div_at_1', 't-loop divergence at pos 1', None),
#### ('div_at_2', 't-loop divergence at pos 2', None),
#### ('div_at_3', 't-loop divergence at pos 3', None),
#### ('div_at_8', 't-loop divergence at pos 8', None),
## ('acceptor_divergence', 'Divergence at acceptor', None)]
## ('div_at_neg_1', 'Acceptor divergence at pos -1', None),
## ('div_at_neg_2', 'Acceptor divergence at pos -2', None),
## ('div_at_neg_3', 'Acceptor divergence at pos -3', None)]
for elem in filters.IsTRNA("").getFilters():
pretty_names.append((str(elem), "Failed at " + str(elem), None))
for key, label, color in pretty_names:
try:
if color:
self.run.info(label, self.stats[key], mc=color)
else:
self.run.info(label, self.stats[key])
except KeyError:
self.run.info(label, 0)
def __init__(self):
"""Initializes variables for the extractor"""
self.extractor_stats_file = ""
self.loop_guidelines = filters.IsTRNA("").getAnticodonGuidelines()
self.extractor_stats = ExtractorStats(
[self.loop_guidelines[2], self.loop_guidelines[3]])
self.allowed_pairings = {
"G": ["C", "T"],
"T": ["A", "G"],
"C": ["G"],
"A": ["T"]
}
def process(self):
"""Run the sorter."""
self.sanity_check()
# creating an empty profile databsae
profile_db = dbops.tRNADatabase(self.output_db_path)
profile_db.create(meta_values={'sample_name': self.sample_name})
# a list buffer to keep results
results_buffer = []
# an arbitrary max size to store and reset the buffer
memory_max = 2000000
# the filteredSequences directory
slash_index = self.output_db_path.rfind("/")
if slash_index == -1:
slash_index = self.output_db_path.rfind(".")
folder_output_path = self.output_db_path[:slash_index] + "/filteredSequences/"
if not os.path.exists(folder_output_path):
os.makedirs(folder_output_path)
is_trna = filters.IsTRNA(folder_output_path)
t_loop_guidelines = is_trna.get_t_loop_and_acceptor_guidelines()
run_filters = is_trna.getFilters()
for i in range(2):
for elem in run_filters[i]:
temp = open(folder_output_path + elem, "w")
temp.write("")
sub_size = 24
input_fasta = u.SequenceSource(self.input_fasta_path)
self.run.info('Hi', terminal.get_date(), mc='green')
self.run.info('Sample name', self.sample_name)
self.run.info('Input FASTA', self.input_fasta_path)
table_for_tRNA_seqs = dbops.TableFortRNASequences(self.output_db_path)
self.progress.new('Profiling tRNAs')
self.progress.update('...')
while next(input_fasta):
self.stats_dict['total_seqs'] += 1
seq = input_fasta.seq.upper()
length = len(seq)
cur_seq_specs = SeqSpecs()
cur_seq_specs.length = length
problem = is_trna.istRNA(seq, input_fasta.id)
if problem != "":
self.stats_dict[problem] += 1
self.stats_dict['total_rejected'] += 1
else:
#trying to determine length of trailer
for i in range(length - sub_size + 1):
sub_str = seq[-(i + sub_size):(length - i)]
missed = []
for position_tuple in t_loop_guidelines[0]:
if sub_str[position_tuple[0]] != position_tuple[1]:
missed.append(position_tuple)
if len(missed) < t_loop_guidelines[1] + 1:
for elem in missed:
self.stats_dict[str(elem)] += 1
if len(missed) == 0:
self.stats_dict['no_divergence']
cur_seq_specs.seq = seq
cur_seq_specs.seq_sub = sub_str
cur_seq_specs.t_loop_seq = sub_str[0:9]
cur_seq_specs.acceptor_seq = sub_str[-3:]
cur_seq_specs = self.handle_pass_seq(cur_seq_specs, i)
results_buffer.append(
('%s_%d' % (self.sample_name, input_fasta.pos),
cur_seq_specs))
break
if sys.getsizeof(results_buffer) > memory_max:
self.progress.update(
'Writing %d items in the buffer to the DB ...' %
len(results_buffer))
table_for_tRNA_seqs.append_sequences(results_buffer)
results_buffer = []
if self.stats_dict['total_seqs'] % 1000 == 0:
t, p = self.stats_dict['total_seqs'], self.stats_dict[
'total_passed']
self.progress.update('%s :: %s (num tRNAs :: num raw reads so far): %.2f%% ...' %\
(pp(p), pp(t), p * 100 / t))
self.progress.update('Writing %d items in the buffer to the DB ...' %
len(results_buffer))
table_for_tRNA_seqs.append_sequences(results_buffer)
results_buffer = []
# essentially we are done here. let's populate the stats table:
profile_db = dbops.tRNADatabase(self.output_db_path)
self.progress.update('Writing stats ...')
for key in self.stats_dict:
profile_db.db.set_stat_value(key, self.stats_dict[key])
profile_db.disconnect()
self.progress.end()
self.run.info('Total raw seqs processed',
self.stats_dict['total_seqs'])
self.run.info('Total tRNA seqs recovered',
self.stats_dict['total_passed'])
self.run.info('Total full length tRNA seqs',
self.stats_dict['total_full_length'])
self.run.info('Output DB path', self.output_db_path)
self.run.info('Bye', terminal.get_date(), mc='green')
self.run.quit()