def compatible(self, options):
"""Compatible command"""
check_file_exists(options.reference_file)
check_file_exists(options.scaffold_stats_file)
make_sure_path_exists(options.output_dir)
# read scaffold statistics and calculate genome stats
self.logger.info('Reading scaffold statistics.')
scaffold_stats = ScaffoldStats()
scaffold_stats.read(options.scaffold_stats_file)
genome_stats = GenomeStats()
genome_stats = genome_stats.run(scaffold_stats)
# identify putative homologs to reference genomes
reference = Reference(1, None)
putative_homologs = reference.homology_check(options.reference_file,
options.min_genes,
float(options.perc_genes))
# identify scaffolds compatible with bins
outliers = Outliers()
output_file = os.path.join(options.output_dir, 'compatible.tsv')
outliers.compatible(putative_homologs, scaffold_stats, genome_stats,
options.gc_perc, options.td_perc, options.cov_corr,
options.cov_perc, options.report_type, output_file)
self.logger.info('Results written to: ' + output_file)
def reference(self, options):
"""Reference command"""
self.logger.info('')
self.logger.info('*******************************************************************************')
self.logger.info('[RefineM - reference] Identifying scaffolds similar to specific genome(s).')
self.logger.info('*******************************************************************************')
check_file_exists(options.scaffold_prot_file)
check_file_exists(options.scaffold_stats_file)
make_sure_path_exists(options.output_dir)
ref_gene_files = self._genome_files(options.ref_genome_prot_dir, options.protein_ext)
if not self._check_protein_seqs(ref_gene_files):
self.logger.warning('[Warning] All files must contain amino acid sequences.')
sys.exit()
reference = Reference(options.cpus, options.output_dir)
reference_out = reference.run(options.scaffold_prot_file,
options.scaffold_stats_file,
ref_gene_files,
options.db_file,
options.evalue,
options.per_identity)
self.logger.info('')
self.logger.info(' Results written to: ' + reference_out)
self.time_keeper.print_time_stamp()
def reference(self, options):
"""Reference command"""
check_file_exists(options.scaffold_prot_file)
check_file_exists(options.scaffold_stats_file)
make_sure_path_exists(options.output_dir)
ref_gene_files = self._genome_files(options.ref_genome_prot_dir,
options.protein_ext)
if not self._check_protein_seqs(ref_gene_files):
self.logger.warning('All files must contain amino acid sequences.')
sys.exit()
reference = Reference(options.cpus, options.output_dir)
reference_out = reference.run(options.scaffold_prot_file,
options.scaffold_stats_file,
ref_gene_files, options.db_file,
options.evalue, options.per_identity,
options.per_aln_len)
self.logger.info('Results written to: ' + reference_out)
def compatible(self, options):
"""Compatible command"""
self.logger.info('')
self.logger.info('*******************************************************************************')
self.logger.info('[RefineM - compatible] Identify scaffolds with compatible genomic statistics.')
self.logger.info('*******************************************************************************')
check_file_exists(options.reference_file)
check_file_exists(options.scaffold_stats_file)
make_sure_path_exists(options.output_dir)
# read scaffold statistics and calculate genome stats
self.logger.info('')
self.logger.info(' Reading scaffold statistics.')
scaffold_stats = ScaffoldStats()
scaffold_stats.read(options.scaffold_stats_file)
genome_stats = GenomeStats()
genome_stats = genome_stats.run(scaffold_stats)
# identify putative homologs to reference genomes
reference = Reference(1, None)
putative_homologs = reference.homology_check(options.reference_file,
options.min_genes,
float(options.perc_genes))
# identify scaffolds compatible with bins
outliers = Outliers()
output_file = os.path.join(options.output_dir, 'compatible.tsv')
outliers.compatible(putative_homologs, scaffold_stats, genome_stats,
options.gc_perc, options.td_perc,
options.cov_corr, options.cov_perc,
options.report_type, output_file)
self.logger.info('')
self.logger.info(' Results written to: ' + output_file)
self.time_keeper.print_time_stamp()