def __post_init__(self):
os.makedirs(self.download_directory, exist_ok=True)
file_name = os.path.basename(self.input_path)
file_prefix = StrConverter.extract_file_name(file_name)
self.kegg_result_path = os.path.join(
self.output_directory, '%s_kegg_result.txt' % file_prefix)
self.kegg_error_path = os.path.join(self.output_directory,
'%s_kegg_error.txt' % file_prefix)
self.logger = LoggerFactory()
def __init__(self, file_path, ignore_gene=False, enable_debug_info=False):
self.ignore_gene = ignore_gene
self.gene_segments = []
self.dna_code = []
self.gene_name_segment_map = {}
self.source = None
self.enable_debug_info = enable_debug_info
self.file_path = file_path
self.logger = LoggerFactory(1)
def __post_init__(self):
self.logger = LoggerFactory(1)
file_prefix = StrConverter.extract_file_name(self.rna_tag)
self.cluster_result_path = os.path.join(
self.output_directory, '%s_cluster_result.txt' % file_prefix)
self.sample_result_path = os.path.join(
self.output_directory, '%s_sample_result.txt' % file_prefix)
self.all_result_path = os.path.join(self.output_directory,
'%s_all_result.txt' % file_prefix)
self.only_result_path = os.path.join(
self.output_directory, '%s_only_result.txt' % file_prefix)
def __post_init__(self):
self.inter_path = self.input_path if self.mode == 'inter' else None
self.rna_path = self.input_path if self.mode == 'rna' else None
file_name = os.path.basename(self.input_path)
file_prefix = StrConverter.extract_file_name(file_name)
suffix = 'stream_%d' % self.limit if self.mode == 'rna' else 'gene'
self.result_path = os.path.join(
self.output_directory, '%s_%s_result.txt' % (file_prefix, suffix))
self.gene_reader = GeneFileReader(self.data_path)
self.logger = LoggerFactory()
self.headers = {}
self.inv_headers = []
def __post_init__(self):
self.data_name = os.path.basename(self.data_path)
file_name = os.path.basename(self.gene_path)
file_prefix = StrConverter.extract_file_name(file_name)
self.result_path = os.path.join(self.output_directory,
'%s_match_result.txt' % (file_prefix))
self.gene_reader = GeneFileReader(self.data_path)
self.dna_code = None
self.rev_dna_code = None
self.logger = LoggerFactory()
self.lock = threading.Lock()
self.solved = 0
self.total = 0
self.weighted_sum = sum(self.weighted)
assert self.weighted_sum > 0 and len(self.weighted) == 5
def find_neighbor_batch(self, datas, iteration_time):
fw = open(self.neighbor_result_path, 'a')
solve_cnt, success_cnt, total_cnt = 0, 0, len(datas)
logger = LoggerFactory(1)
logger.info_with_expire_time(
'[Iteration %d]completed %d/%d=%.2f%%' %
(iteration_time, solve_cnt, total_cnt,
solve_cnt * 100.0 / total_cnt), solve_cnt, total_cnt)
fe = open(
self.error_result_path_prefix + ".iter-%d.txt" % iteration_time,
'w')
fail_datas = []
for key, inter, additional in datas:
solve_cnt += 1
file_path = os.path.join(self.download_directory, key + '.txt')
flag, data = self.download_and_analysis(key, inter, file_path)
if flag:
success_cnt += 1
direction = '+' if (inter[0] < inter[1]) else '-'
fw.write('>%s/%s-%s(%s)\n' %
(key, inter[0], inter[1], direction))
if additional != '':
for kv in additional.split(','):
k, v = kv.split('=')
fw.write('%s\t%s\n' % (k, v))
fw.write('SOURCE\t%s\n' % (data.get('source', 'UNKNOWN')))
for elem in data['data']:
fw.write('%s\n' % elem)
fw.write('sequence\t%s\n' % (data.get('sequence', '')))
fw.write('\n')
fw.flush()
else:
if os.path.exists(file_path):
os.remove(file_path)
fe.write('>%s/%s-%s\n' % (key, inter[0], inter[1]))
fe.flush()
fail_datas.append([key, inter])
self.logger.info_with_expire_time(
'[Iteration %d]completed %d/%d=%.2f%%, success %d/%d=%.2f%%' %
(iteration_time, solve_cnt, total_cnt,
solve_cnt * 100.0 / total_cnt, success_cnt, solve_cnt,
success_cnt * 100.0 / solve_cnt), solve_cnt, total_cnt)
time.sleep(random.random())
self.logger.info('[Iteration %d]done .' % iteration_time)
fw.close()
return fail_datas
def __post_init__(self):
self.logger = LoggerFactory(3)
file_name = os.path.basename(self.input_path)
file_prefix = StrConverter.extract_file_name(file_name)
self.neighbor_result_path = os.path.join(
self.output_directory, '%s_neighbor_result.txt' % file_prefix)
self.next_gene_result_path = os.path.join(
self.output_directory, '%s_next_neighbor_result.txt' % file_prefix)
self.source_count_path = os.path.join(
self.output_directory, '%s_source_count_result.txt' % file_prefix)
self.gene_count_path = os.path.join(
self.output_directory, '%s_gene_count_result.txt' % file_prefix)
error_directory = os.path.join(self.output_directory, 'error')
if not os.path.exists(error_directory):
os.makedirs(error_directory)
self.error_result_path_prefix = os.path.join(
error_directory, '%s_error_result' % file_prefix)
def __post_init__(self):
self.from_gene_names = self.ecocyc_params['from_gene_names']
self.output_best_promoter = self.ecocyc_params['output_best_promoter']
self.output_detail_information = self.ecocyc_params[
'output_detail_information']
self.analysis_promoter = self.ecocyc_params['analysis_promoter']
self.if_get_summary = self.ecocyc_params['if_get_summary']
self.if_get_go_table = self.ecocyc_params['if_get_go_table']
self.sequence_start_idx = None
self.sequence_end_idx = None
self.headers = {}
self.inv_headers = []
file_name = os.path.basename(self.input_path)
file_prefix = StrConverter.extract_file_name(file_name)
self.ecocyc_result_path = os.path.join(
self.output_directory, '%s_ecocyc_result.txt' % file_prefix)
self.ecocyc_error_path = os.path.join(
self.output_directory, '%s_ecocyc_error.txt' % file_prefix)
self.logger = LoggerFactory()