def format_protein_db(self, input_file_path, output_file_path):
progress.new('Formatting raw files')
progress.update('Decompressing protein sequences')
# poor man's uncompress
temp_fasta_path = filesnpaths.get_temp_file_path()
with open(temp_fasta_path,
'wb') as f_out, gzip.open(input_file_path, 'rb') as f_in:
f_out.write(f_in.read())
progress.end()
if utils.is_program_exists('diamond', dont_raise=True):
output_dir = J(self.COG_data_dir, 'DB_DIAMOND')
if os.path.exists(output_dir):
shutil.rmtree(output_dir)
os.mkdir(output_dir)
output_db_path = J(output_dir, 'COG')
log_file_path = J(output_dir, 'log.txt')
self.run.info('Diamond log', log_file_path)
diamond = Diamond(temp_fasta_path)
diamond.num_threads = self.num_threads
diamond.run.log_file_path = log_file_path
diamond.makedb(output_db_path)
else:
self.run.warning(
"Diamond does not seem to be installed on this system, so anvi'o is not going to\
generate a search database for it. Remember this when/if things go South."
)
if utils.is_program_exists(
'makeblastdb', dont_raise=True) and utils.is_program_exists(
'blastp', dont_raise=True):
output_dir = J(self.COG_data_dir, 'DB_BLAST')
if os.path.exists(output_dir):
shutil.rmtree(output_dir)
os.mkdir(output_dir)
output_db_path = J(output_dir, 'COG')
log_file_path = J(output_dir, 'log.txt')
self.run.info('BLAST log', log_file_path)
blast = BLAST(temp_fasta_path)
blast.run.log_file_path = log_file_path
blast.num_threads = self.num_threads
blast.makedb(os.path.join(output_db_path, 'COG.fa'))
else:
self.run.warning(
"BLAST tools do not seem to be installed on this system, so anvi'o is not going to\
generate a search database for them to be used. Keep this in mind for later."
)
os.remove(temp_fasta_path)
def format_protein_db(self, input_file_path, output_file_path):
progress.new('Formatting raw files')
progress.update('Decompressing protein sequences')
# poor man's uncompress
temp_fasta_path = filesnpaths.get_temp_file_path()
try:
with open(temp_fasta_path, 'wb') as f_out, gzip.open(input_file_path, 'rb') as f_in:
f_out.write(f_in.read())
except Exception as e:
progress.end()
raise ConfigError(f"Something went wrong while decompressing the downloaded file :/ It is likely that "
f"the download failed and only part of the file was downloaded. If you would like to "
f"try again, please run the setup command with the flag `--reset`. Here is what the "
f"downstream library said: '{e}'.")
progress.end()
if utils.is_program_exists('diamond', dont_raise=True):
output_dir = J(self.COG_data_dir, 'DB_DIAMOND')
if os.path.exists(output_dir):
shutil.rmtree(output_dir)
os.mkdir(output_dir)
output_db_path = J(output_dir, 'COG')
log_file_path = J(output_dir, 'log.txt')
self.run.info('Diamond log', log_file_path)
diamond = Diamond(temp_fasta_path)
diamond.num_threads = self.num_threads
diamond.run.log_file_path = log_file_path
diamond.makedb(output_db_path)
else:
self.run.warning("DIAMOND does not seem to be installed on this system, so anvi'o is not going to "
"generate a search database for it. Remember this when/if things go South.")
if utils.is_program_exists('makeblastdb', dont_raise=True) and utils.is_program_exists('blastp', dont_raise=True):
output_dir = J(self.COG_data_dir, 'DB_BLAST')
if os.path.exists(output_dir):
shutil.rmtree(output_dir)
os.mkdir(output_dir)
output_db_path = J(output_dir, 'COG')
log_file_path = J(output_dir, 'log.txt')
self.run.info('BLAST log', log_file_path)
blast = BLAST(temp_fasta_path)
blast.run.log_file_path = log_file_path
blast.num_threads = self.num_threads
blast.makedb(os.path.join(output_db_path, 'COG.fa'))
else:
self.run.warning("BLAST tools do not seem to be installed on this system, so anvi'o is not going to "
"generate a search database for them to be used. Keep this in mind for later.")
os.remove(temp_fasta_path)
def format_protein_db(self, input_file_path, output_file_path):
progress.new('Formatting raw files')
progress.update('Decompressing protein sequences')
# poor man's uncompress
temp_fasta_path = filesnpaths.get_temp_file_path()
with open(temp_fasta_path, 'wb') as f_out, gzip.open(input_file_path, 'rb') as f_in:
f_out.write(f_in.read())
progress.end()
if utils.is_program_exists('diamond', dont_raise=True):
output_dir = J(self.COG_data_dir, 'DB_DIAMOND')
if os.path.exists(output_dir):
shutil.rmtree(output_dir)
os.mkdir(output_dir)
output_db_path = J(output_dir, 'COG')
log_file_path = J(output_dir, 'log.txt')
self.run.info('Diamond log', log_file_path)
diamond = Diamond(temp_fasta_path)
diamond.num_threads = self.num_threads
diamond.run.log_file_path = log_file_path
diamond.makedb(output_db_path)
else:
self.run.warning("Diamond does not seem to be installed on this system, so anvi'o is not going to\
generate a search database for it. Remember this when/if things go South.")
if utils.is_program_exists('makeblastdb', dont_raise=True) and utils.is_program_exists('blastp', dont_raise=True):
output_dir = J(self.COG_data_dir, 'DB_BLAST')
if os.path.exists(output_dir):
shutil.rmtree(output_dir)
os.mkdir(output_dir)
output_db_path = J(output_dir, 'COG')
log_file_path = J(output_dir, 'log.txt')
self.run.info('BLAST log', log_file_path)
blast = BLAST(temp_fasta_path)
blast.run.log_file_path = log_file_path
blast.num_threads = self.num_threads
blast.makedb(os.path.join(output_db_path, 'COG.fa'))
else:
self.run.warning("BLAST tools do not seem to be installed on this system, so anvi'o is not going to\
generate a search database for them to be used. Keep this in mind for later.")
os.remove(temp_fasta_path)
def search_with_diamond(self, aa_sequences_file_path):
diamond = Diamond(aa_sequences_file_path, run=self.run, progress=self.progress, num_threads=self.num_threads)
diamond.target_fasta = self.available_db_search_program_targets['diamond']
self.run.log_file_path = self.log_file_path or J(self.temp_dir_path, 'log.txt')
diamond.search_output_path = J(self.temp_dir_path, 'diamond-search-results')
diamond.tabular_output_path = J(self.temp_dir_path, 'diamond-search-results.txt')
diamond.sensitive = self.sensitive
diamond.max_target_seqs = 1
diamond.blastp()
diamond.view()
return diamond.tabular_output_path
def run_diamond(self, unique_proteins_fasta_path, unique_proteins_names_dict):
diamond = Diamond(unique_proteins_fasta_path, run=self.run, progress=self.progress,
num_threads=self.num_threads, overwrite_output_destinations=self.overwrite_output_destinations)
diamond.names_dict = unique_proteins_names_dict
diamond.target_db_path = self.get_output_file_path(filesnpaths.get_name_from_file_path(unique_proteins_fasta_path))
diamond.search_output_path = self.get_output_file_path('diamond-search-results')
diamond.tabular_output_path = self.get_output_file_path('diamond-search-results.txt')
diamond.sensitive = self.sensitive
return diamond.get_blastall_results()
def run_diamond(self, unique_proteins_fasta_path, unique_proteins_names_dict):
diamond = Diamond(unique_proteins_fasta_path, run=self.run, progress=self.progress,
num_threads=self.num_threads, overwrite_output_destinations=self.overwrite_output_destinations)
diamond.names_dict = unique_proteins_names_dict
diamond.target_db_path = self.get_output_file_path(filesnpaths.get_name_from_file_path(unique_proteins_fasta_path))
diamond.search_output_path = self.get_output_file_path('diamond-search-results')
diamond.tabular_output_path = self.get_output_file_path('diamond-search-results.txt')
diamond.sensitive = self.sensitive
return diamond.get_blastall_results()
def search_with_diamond(self, aa_sequences_file_path):
diamond = Diamond(aa_sequences_file_path, run=self.run, progress=self.progress, num_threads=self.num_threads)
diamond.target_db_path = self.available_db_search_program_targets['diamond']
self.run.log_file_path = self.log_file_path or J(self.temp_dir_path, 'log.txt')
diamond.search_output_path = J(self.temp_dir_path, 'diamond-search-results')
diamond.tabular_output_path = J(self.temp_dir_path, 'diamond-search-results.txt')
diamond.sensitive = self.sensitive
diamond.max_target_seqs = 1
diamond.blastp()
diamond.view()
return diamond.tabular_output_path