def get_replicates(gemini_db):
"""
Returns a dataframe of sample information with the following columns:
samples, plate_num, tissue, replicate
"""
samples_df = pd.DataFrame([[sample] + list(split_id(sample)) for sample in gem_ops.get_samples(gemini_db)], \
columns=["full_name", "sample", "plate", "tissue", "replicate"])
return samples_df
min_allele_freq = args.min_allele_freq
min_depth = args.min_depth
min_alt_depth = args.min_alt_depth
max_num_het = args.max_num_het
max_aaf_all = args.max_aaf_all
tissue = args.tissue.split(",")
sample_pattern = args.sample_pattern
annotations = args.annotations.split(",")
results_file = args.results_file
add_joint = args.add_joint
if operation == "find_all":
# Get all variants in a set of samples.
# Get samples to process.
samples = [sample for sample in gem_ops.get_samples(gemini_db) if re.search(sample_pattern, sample) > 0]
# Get sample variants.
all_vars_df = get_variants_in_samples(gemini_db, samples, annotations, min_allele_freq, min_alt_depth, min_depth, max_aaf_all, somatic=False)
# Write results to file.
if sample_pattern == ".*":
sample_pattern = "all"
out_filename = "find_vars_results_%s_minaf%.2f_ad%i_d%i.txt" % (sample_pattern, min_allele_freq, min_alt_depth, min_depth)
out_file = open(out_filename, "w")
out_file.write( all_vars_df.to_csv(sep="\t", index=False, float_format='%.3f') )
out_file.close()
print "Wrote results to file %s" % out_filename
elif operation == "augment_vars":
