def preprocessing(project_directory, var_matrix_path, full_matrix_path,
flag_file_path, **kwargs):
"""
Groups variant sites into amplicon windows and filters
out any amplicons that do not have well conserved
upstream and downstream primer regions
"""
logger = logging.getLogger(__name__)
logger.info("BEGIN Preprocessing")
args = _set_parameters(**kwargs)
start_time = time.time()
history = History(project_directory.make_new_file("history",
"preprocessing_history"),
"Preprocessing",
project_directory.timestamp,
param_dict=args)
# Get strains and sites from matrix
strains = _get_strains_from_file(var_matrix_path, args["sep"])
sites = _get_sites_from_file(var_matrix_path, args["sep"])
# Remove excluded strains
if args["exclude_strains"] is not None:
strains = _remove_strains(args["exclude_strains"], strains)
var_matrix = _parse_var_matrix(var_matrix_path, strains, args["sep"])
if args["strict"]:
n_sites_before = len(sites)
var_matrix, sites = _remove_ambiguous_sites(var_matrix, sites)
logger.info("Strict Mode: {} sites with ambiguous "
"or missing data were removed".format(n_sites_before -
len(sites)))
history.add_path("VARIANT SITE MATRIX FILE", var_matrix_path)
history.add_parameter("Number of Sites", len(sites))
history.add_parameter("Number of Strains", len(strains))
_check_inputs(args["pz_size"], args["pz_filter_length"],
args["strain_cutoff"], len(strains))
if full_matrix_path is not None:
flag_df = get_flags_from_matrix(full_matrix_path, strains, history,
project_directory, **args)
if flag_file_path is not None:
flag_df = get_flags_from_file(flag_file_path, history)
flag_dic = _get_flags_from_counts(flag_df, args["strain_cutoff"])
amplicon_filter = AmpliconFilter(sites, var_matrix, flag_dic,
args['window'], args['pz_size'],
args['pz_filter_length'],
args['pz_filter_percent'], args['strict'])
patterns = amplicon_filter.filter_amplicons_get_patterns()
# Write patterns to a json file
pattern_json_file = project_directory.make_new_file(
"patterns", "patterns", "json")
patterns.to_json(pattern_json_file, list(strains))
history.add_path("PATTERN JSON", pattern_json_file)
# Write history
logger.info("FINISHED Preprocessing")
run_time = time.time() - start_time
history.add_other("Run Time", run_time)
history.write()
