def cli(ctx, bam, reference, variants, bed4_file, min_freq, mutation_db, reporting_threshold, output): rs = parse_references_from_fasta(reference) mapped_read_collection_arr = [] for r in rs: # Create a MappedReadCollection object mapped_read_collection_arr.append(parse_mapped_reads_from_bam(r, bam)) variants_obj = parse_nt_variants_from_vcf(variants, rs) # Mask the unconfident differences for mrc in mapped_read_collection_arr: mrc.mask_unconfident_differences(variants_obj) # Parse the genes from the gene file genes = parse_BED4_file(bed4_file, rs[0].name) # Determine which frames our genes are in frames = set() for gene in genes: frames.add(genes[gene]['frame']) # Create an AACensus object aa_census = AACensus(reference, mapped_read_collection_arr, genes, frames) # Create AAVar collection and print the aavf file aa_vars = AAVariantCollection.from_aacensus(aa_census) # Filter for mutant frequency aa_vars.filter('mf' + str(min_freq), 'freq<' + str(min_freq), True) # Build the mutation database mutation_db = MutationDB(mutation_db, genes) # Generate the mutation report if output: output.write( aa_vars.report_dr_mutations(mutation_db, reporting_threshold)) output.close() else: click.echo( aa_vars.report_dr_mutations(mutation_db, reporting_threshold))
def aavar(bam, reference, variants, genes_file, min_freq, mutation_db, output): rs = parse_references_from_fasta(reference) mapped_read_collection_arr = [] for r in rs: # Create a MappedReadCollection object mapped_read_collection_arr.append(parse_mapped_reads_from_bam(r, bam)) variants_obj = parse_nt_variants_from_vcf(variants, rs) # Mask the unconfident differences for mrc in mapped_read_collection_arr: mrc.mask_unconfident_differences(variants_obj) # Parse the genes from the gene file genes = parse_genes_file(genes_file, rs[0].name) # Determine which frames our genes are in frames = set() for gene in genes: frames.add(genes[gene]['frame']) # Create an AACensus object aa_census = AACensus(reference, mapped_read_collection_arr, genes, frames) # Create AAVar collection and print the hmcf file aa_vars = AAVariantCollection.from_aacensus(aa_census) # Filter for mutant frequency aa_vars.filter('mf0.01', 'freq<0.01', True) # Build the mutation database and update collection if mutation_db is not None: mutation_db = MutationDB(mutation_db, genes) aa_vars.apply_mutation_db(mutation_db) if output: output.write(aa_vars.to_hmcf_file(CONFIDENT)) else: click.echo(aa_vars.to_hmcf_file(CONFIDENT))
def codonvar(bam, reference, offset, bed4_file, variants, error_rate, output): rs = parse_references_from_fasta(reference) mapped_read_collection_arr = [] # Create a MappedReadCollection object for r in rs: mapped_read_collection_arr.append(parse_mapped_reads_from_bam(r, bam)) if variants: variants_obj = parse_nt_variants_from_vcf(variants, rs) else: variants = NTVariantCollection.from_mapped_read_collections( error_rate, rs, *mapped_read_collection_arr) variants.filter('q30', 'QUAL<30', True) variants.filter('ac5', 'AC<5', True) variants.filter('dp100', 'DP<100', True) variants_obj = variants # Mask the unconfident differences for mrc in mapped_read_collection_arr: mrc.mask_unconfident_differences(variants_obj) # Parse the genes from the gene file genes = parse_BED4_file(bed4_file, rs[0].name) # Determine which frames our genes are in frames = set() for gene in genes: frames.add(genes[gene]['frame']) aa_census = AACensus(reference, mapped_read_collection_arr, genes, frames) codon_variants = CodonVariantCollection.from_aacensus(aa_census) if output: output.write(codon_variants.to_csv_file(offset)) output.close() else: click.echo(codon_variants.to_csv_file(offset))
def setup(self): reference = TEST_PATH + "/data/hxb2_pol.fas" bam = TEST_PATH + "/data/align.bam" genes_file = TEST_PATH + "/data/hxb2_pol.bed" mutation_db = TEST_PATH + "/data/mutation_db.tsv" min_freq = 0.01 rs = parse_references_from_fasta(reference) mapped_read_collection_arr = [] for r in rs: # Create a MappedReadCollection object mapped_read_collection_arr.append( parse_mapped_reads_from_bam(r, bam)) variants_obj = parse_nt_variants_from_vcf(VARIANTS_FILE, rs) # Mask the unconfident differences for mrc in mapped_read_collection_arr: mrc.mask_unconfident_differences(variants_obj) # Parse the genes from the gene file genes = parse_genes_file(genes_file, rs[0].name) # Determine which frames our genes are in frames = set() for gene in genes: frames.add(genes[gene]['frame']) # Create an AACensus object aa_census = AACensus(reference, mapped_read_collection_arr, genes, frames) # Find the AA mutations self.aa_collection = AAVariantCollection.from_aacensus(aa_census) # Build the mutation database self.mutation_db = MutationDB(mutation_db, genes)
def aavar(bam, reference, bed4_file, variants, mutation_db, min_freq, error_rate, output): rs = parse_references_from_fasta(reference) mapped_read_collection_arr = [] for r in rs: # Create a MappedReadCollection object mapped_read_collection_arr.append(parse_mapped_reads_from_bam(r, bam)) if variants: variants_obj = parse_nt_variants_from_vcf(variants, rs) else: variants = NTVariantCollection.from_mapped_read_collections( error_rate, rs, *mapped_read_collection_arr) variants.filter('q30', 'QUAL<30', True) variants.filter('ac5', 'AC<5', True) variants.filter('dp100', 'DP<100', True) variants_obj = variants # Mask the unconfident differences for mrc in mapped_read_collection_arr: mrc.mask_unconfident_differences(variants_obj) # Parse the genes from the gene file genes = parse_BED4_file(bed4_file, rs[0].name) # Determine which frames our genes are in frames = set() for gene in genes: frames.add(genes[gene]['frame']) # Create an AACensus object aa_census = AACensus(reference, mapped_read_collection_arr, genes, frames) # Create AAVar collection and print the aavf file aa_vars = AAVariantCollection.from_aacensus(aa_census) # Filter for mutant frequency aa_vars.filter('mf0.01', 'freq<0.01', True) # Build the mutation database and update collection if mutation_db is not None: mutation_db = MutationDB(mutation_db, genes) aa_vars.apply_mutation_db(mutation_db) aavf_obj = aa_vars.to_aavf_obj("aavar", os.path.basename(reference), CONFIDENT) records = list(aavf_obj) if output: writer = parser.Writer(output, aavf_obj) else: writer = parser.Writer(sys.stdout, aavf_obj) for record in records: writer.write_record(record) if output: output.close writer.close()
def test_valid_vcf_file(self): """Tests to ensure that valid vcf files are parsed properly.""" reference = TEST_PATH + \ "/data/hxb2_pol.fas" bam = TEST_PATH + "/data/align.bam" rs = parse_references_from_fasta(reference) mapped_read_collection_arr = [] for r in rs: # Create a MappedReadCollection object mapped_read_collection_arr.append( parse_mapped_reads_from_bam(r, bam)) variants_obj = NTVariantCollection(rs) for i in range(0, 20): variant = NTVariant(chrom="hxb2_pol", pos=i, id=".", ref='a', alt='t', qual="50", filter="PASS", info={ "DP": "300", "AC": "1", "AF": "0.0025" }) variants_obj.variants["hxb2_pol"][i]['t'] = variant #Create a valid vcf file valid_vcf_file = TEST_PATH + "/data/valid_vcf_file.vcf" with open(valid_vcf_file, "w+") as f: f.write( "##fileformat=VCFv4.2\n" "##fileDate=20171005\n" "##source=quasitools\n" "##INFO=<ID=DP,Number=1,Type=Integer,Description=\"Total Depth\">\n" "##INFO=<ID=AC,Number=A,Type=Integer,Description=\"Allele Count\">\n" "##INFO=<ID=AF,Number=A,Type=Float,Description=\"Allele Frequency\">\n" "##FILTER=<ID=q30,Description=\"Quality below 30\">\n" "##FILTER=<ID=dp100,Description=\"Read depth below 100\">\n" "##FILTER=<ID=ac5,Description=\"Allele count below 5\">\n" "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO") for rid in variants_obj.variants: for pos in variants_obj.variants[rid]: for alt in variants_obj.variants[rid][pos]: variant = variants_obj.variants[rid][pos][alt] f.write("\n%s\t%i\t%s\t%s\t%s\t%s\t%s" % (variant.chrom, int( variant.pos), variant.id, variant.ref, variant.alt, variant.qual, variant.filter)) f.write( "\tDP=%i;AC=%i;AF=%0.4f" % (int(variant.info["DP"]), int(variant.info["AC"]), float(variant.info["AF"]))) parsed_nt_var = parse_nt_variants_from_vcf(valid_vcf_file, rs) # Check equality of parsed NTVariantCollection vs. the valid NTVariantCollection for rid in parsed_nt_var.variants: for pos in parsed_nt_var.variants[rid]: for alt in parsed_nt_var.variants[rid][pos]: parsed_variant = parsed_nt_var.variants[rid][pos][alt] variant = variants_obj.variants[rid][pos][alt] assert parsed_variant.chrom == variant.chrom assert parsed_variant.pos == variant.pos assert parsed_variant.id == variant.id assert parsed_variant.ref == variant.ref assert parsed_variant.alt == variant.alt assert parsed_variant.qual == variant.qual assert parsed_variant.filter == variant.filter assert parsed_variant.info["DP"] == variant.info["DP"] assert parsed_variant.info["AC"] == variant.info["AC"] assert parsed_variant.info["AF"] == variant.info["AF"] os.remove(valid_vcf_file)