seekdeep_prevalences.smk

'''
takes as input mutations of interest, a metadata sheet, and coverage and
alternate count thresholds, and turns them into prevalence tables

This version is somewhat special purpose because there are many separate runs
'''

configfile: 'seekdeep_prevalences.yaml'

rule all:
	input:
		prevalences='output_files/prevalences.tsv'

rule generate_counts_table:
	'''
	takes multiple sequencing runs as input and outputs the total counts
	associated with each sample for each mutation
	'''
	input:
		input_count_files=expand('{counts_file}', counts_file=config['seekdeep_graphing_runs']),
		interesting_mutations=config['interesting_mutations']
	params:
		replicate_suffix=config['replicate_suffix']
	output:
		counts_yaml='output_files/mutation_counts_table.yaml',
		coverage_csv='output_files/AA_coverage_counts.csv',
		alternate_csv='output_files/AA_alternate_counts.csv'
	script:
		'scripts/generate_counts_table.py'

rule calculate_prevalences:
	'''
	takes mutation counts file and applies thresholds and metadata to generate
	summaries
	'''
	input:
		counts_yaml='output_files/mutation_counts_table.yaml',
		metadata_sheet=config['metadata_sheet']
	params:
		coverage_threshold=config['coverage_threshold'],
		alternate_threshold=config['alternate_threshold'],
		summarize_by=config['summarize_by'],
		sample_column=config['sample_column']
	output:
		prevalence_table='output_files/prevalences.tsv'
	script:
		'scripts/calculate_prevalences.py'