Mercurial > repos > greg > vsnp_add_zero_coverage
changeset 2:01312f8a6ca9 draft
Uploaded
| author | greg |
|---|---|
| date | Sun, 03 Jan 2021 16:29:00 +0000 |
| parents | eaf4c304fd22 |
| children | 4ebdeb4df6ca |
| files | macros.xml tool_data_table_conf.xml.test vsnp_add_zero_coverage.py vsnp_add_zero_coverage.xml |
| diffstat | 4 files changed, 170 insertions(+), 285 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Sun Jan 03 16:29:00 2021 +0000 @@ -0,0 +1,24 @@ +<?xml version='1.0' encoding='UTF-8'?> +<macros> + <token name="@WRAPPER_VERSION@">1.0</token> + <token name="@PROFILE@">19.09</token> + <xml name="param_reference_source"> + <param name="reference_source" type="select" label="Choose the source for the reference genome"> + <option value="cached" selected="true">locally cached</option> + <option value="history">from history</option> + </param> + </xml> + <xml name="citations"> + <citations> + <citation type="bibtex"> + @misc{None, + journal = {None}, + author = {1. Stuber T}, + title = {Manuscript in preparation}, + year = {None}, + url = {https://github.com/USDA-VS/vSNP},} + </citation> + </citations> + </xml> +</macros> +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.test Sun Jan 03 16:29:00 2021 +0000 @@ -0,0 +1,6 @@ +<tables> + <table name="fasta_indexes" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="${__HERE__}/test-data/fasta_indexes.loc" /> + </table> +</tables>
--- a/vsnp_add_zero_coverage.py Tue Apr 21 09:51:00 2020 -0400 +++ b/vsnp_add_zero_coverage.py Sun Jan 03 16:29:00 2021 +0000 @@ -1,191 +1,132 @@ #!/usr/bin/env python import argparse -import multiprocessing import os -import pandas -import pysam -import queue import re import shutil -from numpy import mean + +import pandas +import pysam from Bio import SeqIO -INPUT_BAM_DIR = 'input_bam_dir' -INPUT_VCF_DIR = 'input_vcf_dir' -OUTPUT_VCF_DIR = 'output_vcf_dir' -OUTPUT_METRICS_DIR = 'output_metrics_dir' - -def get_base_file_name(file_path): +def get_sample_name(file_path): base_file_name = os.path.basename(file_path) if base_file_name.find(".") > 0: # Eliminate the extension. return os.path.splitext(base_file_name)[0] - elif base_file_name.find("_") > 0: - # The dot extension was likely changed to - # the " character. - items = base_file_name.split("_") - return "_".join(items[0:-1]) - else: - return base_file_name + return base_file_name + + +def get_coverage_df(bam_file): + # Create a coverage dictionary. + coverage_dict = {} + coverage_list = pysam.depth(bam_file, split_lines=True) + for line in coverage_list: + chrom, position, depth = line.split('\t') + coverage_dict["%s-%s" % (chrom, position)] = depth + # Convert it to a data frame. + coverage_df = pandas.DataFrame.from_dict(coverage_dict, orient='index', columns=["depth"]) + return coverage_df + + +def get_zero_df(reference): + # Create a zero coverage dictionary. + zero_dict = {} + for record in SeqIO.parse(reference, "fasta"): + chrom = record.id + total_len = len(record.seq) + for pos in list(range(1, total_len + 1)): + zero_dict["%s-%s" % (str(chrom), str(pos))] = 0 + # Convert it to a data frame with depth_x + # and depth_y columns - index is NaN. + zero_df = pandas.DataFrame.from_dict(zero_dict, orient='index', columns=["depth"]) + return zero_df -def get_coverage_and_snp_count(task_queue, reference, output_metrics, output_vcf, timeout): - while True: - try: - tup = task_queue.get(block=True, timeout=timeout) - except queue.Empty: - break - bam_file, vcf_file = tup - # Create a coverage dictionary. - coverage_dict = {} - coverage_list = pysam.depth(bam_file, split_lines=True) - for line in coverage_list: - chrom, position, depth = line.split('\t') - coverage_dict["%s-%s" % (chrom, position)] = depth - # Convert it to a data frame. - coverage_df = pandas.DataFrame.from_dict(coverage_dict, orient='index', columns=["depth"]) - # Create a zero coverage dictionary. - zero_dict = {} - for record in SeqIO.parse(reference, "fasta"): - chrom = record.id - total_len = len(record.seq) - for pos in list(range(1, total_len + 1)): - zero_dict["%s-%s" % (str(chrom), str(pos))] = 0 - # Convert it to a data frame with depth_x - # and depth_y columns - index is NaN. - zero_df = pandas.DataFrame.from_dict(zero_dict, orient='index', columns=["depth"]) - coverage_df = zero_df.merge(coverage_df, left_index=True, right_index=True, how='outer') - # depth_x "0" column no longer needed. - coverage_df = coverage_df.drop(columns=['depth_x']) - coverage_df = coverage_df.rename(columns={'depth_y': 'depth'}) - # Covert the NaN to 0 coverage and get some metrics. - coverage_df = coverage_df.fillna(0) - coverage_df['depth'] = coverage_df['depth'].apply(int) - total_length = len(coverage_df) - average_coverage = coverage_df['depth'].mean() - zero_df = coverage_df[coverage_df['depth'] == 0] - total_zero_coverage = len(zero_df) - total_coverage = total_length - total_zero_coverage - genome_coverage = "{:.2%}".format(total_coverage / total_length) - # Process the associated VCF input. - column_names = ["CHROM", "POS", "ID", "REF", "ALT", "QUAL", "FILTER", "INFO", "FORMAT", "Sample"] - vcf_df = pandas.read_csv(vcf_file, sep='\t', header=None, names=column_names, comment='#') - good_snp_count = len(vcf_df[(vcf_df['ALT'].str.len() == 1) & (vcf_df['REF'].str.len() == 1) & (vcf_df['QUAL'] > 150)]) - base_file_name = get_base_file_name(vcf_file) - if total_zero_coverage > 0: - header_file = "%s_header.csv" % base_file_name - with open(header_file, 'w') as outfile: - with open(vcf_file) as infile: +def output_zc_vcf_file(base_file_name, vcf_file, zero_df, total_zero_coverage, output_vcf): + column_names = ["CHROM", "POS", "ID", "REF", "ALT", "QUAL", "FILTER", "INFO", "FORMAT", "Sample"] + vcf_df = pandas.read_csv(vcf_file, sep='\t', header=None, names=column_names, comment='#') + good_snp_count = len(vcf_df[(vcf_df['ALT'].str.len() == 1) & (vcf_df['REF'].str.len() == 1) & (vcf_df['QUAL'] > 150)]) + if total_zero_coverage > 0: + header_file = "%s_header.csv" % base_file_name + with open(header_file, 'w') as outfile: + with open(vcf_file) as infile: + for line in infile: + if re.search('^#', line): + outfile.write("%s" % line) + vcf_df_snp = vcf_df[vcf_df['REF'].str.len() == 1] + vcf_df_snp = vcf_df_snp[vcf_df_snp['ALT'].str.len() == 1] + vcf_df_snp['ABS_VALUE'] = vcf_df_snp['CHROM'].map(str) + "-" + vcf_df_snp['POS'].map(str) + vcf_df_snp = vcf_df_snp.set_index('ABS_VALUE') + cat_df = pandas.concat([vcf_df_snp, zero_df], axis=1, sort=False) + cat_df = cat_df.drop(columns=['CHROM', 'POS', 'depth']) + cat_df[['ID', 'ALT', 'QUAL', 'FILTER', 'INFO']] = cat_df[['ID', 'ALT', 'QUAL', 'FILTER', 'INFO']].fillna('.') + cat_df['REF'] = cat_df['REF'].fillna('N') + cat_df['FORMAT'] = cat_df['FORMAT'].fillna('GT') + cat_df['Sample'] = cat_df['Sample'].fillna('./.') + cat_df['temp'] = cat_df.index.str.rsplit('-', n=1) + cat_df[['CHROM', 'POS']] = pandas.DataFrame(cat_df.temp.values.tolist(), index=cat_df.index) + cat_df = cat_df[['CHROM', 'POS', 'ID', 'REF', 'ALT', 'QUAL', 'FILTER', 'INFO', 'FORMAT', 'Sample']] + cat_df['POS'] = cat_df['POS'].astype(int) + cat_df = cat_df.sort_values(['CHROM', 'POS']) + body_file = "%s_body.csv" % base_file_name + cat_df.to_csv(body_file, sep='\t', header=False, index=False) + with open(output_vcf, "w") as outfile: + for cf in [header_file, body_file]: + with open(cf, "r") as infile: for line in infile: - if re.search('^#', line): - outfile.write("%s" % line) - vcf_df_snp = vcf_df[vcf_df['REF'].str.len() == 1] - vcf_df_snp = vcf_df_snp[vcf_df_snp['ALT'].str.len() == 1] - vcf_df_snp['ABS_VALUE'] = vcf_df_snp['CHROM'].map(str) + "-" + vcf_df_snp['POS'].map(str) - vcf_df_snp = vcf_df_snp.set_index('ABS_VALUE') - cat_df = pandas.concat([vcf_df_snp, zero_df], axis=1, sort=False) - cat_df = cat_df.drop(columns=['CHROM', 'POS', 'depth']) - cat_df[['ID', 'ALT', 'QUAL', 'FILTER', 'INFO']] = cat_df[['ID', 'ALT', 'QUAL', 'FILTER', 'INFO']].fillna('.') - cat_df['REF'] = cat_df['REF'].fillna('N') - cat_df['FORMAT'] = cat_df['FORMAT'].fillna('GT') - cat_df['Sample'] = cat_df['Sample'].fillna('./.') - cat_df['temp'] = cat_df.index.str.rsplit('-', n=1) - cat_df[['CHROM', 'POS']] = pandas.DataFrame(cat_df.temp.values.tolist(), index=cat_df.index) - cat_df = cat_df[['CHROM', 'POS', 'ID', 'REF', 'ALT', 'QUAL', 'FILTER', 'INFO', 'FORMAT', 'Sample']] - cat_df['POS'] = cat_df['POS'].astype(int) - cat_df = cat_df.sort_values(['CHROM', 'POS']) - body_file = "%s_body.csv" % base_file_name - cat_df.to_csv(body_file, sep='\t', header=False, index=False) - if output_vcf is None: - output_vcf_file = os.path.join(OUTPUT_VCF_DIR, "%s.vcf" % base_file_name) - else: - output_vcf_file = output_vcf - with open(output_vcf_file, "w") as outfile: - for cf in [header_file, body_file]: - with open(cf, "r") as infile: - for line in infile: - outfile.write("%s" % line) - else: - if output_vcf is None: - output_vcf_file = os.path.join(OUTPUT_VCF_DIR, "%s.vcf" % base_file_name) - else: - output_vcf_file = output_vcf - shutil.copyfile(vcf_file, output_vcf_file) - bam_metrics = [base_file_name, "", "%4f" % average_coverage, genome_coverage] - vcf_metrics = [base_file_name, str(good_snp_count), "", ""] - if output_metrics is None: - output_metrics_file = os.path.join(OUTPUT_METRICS_DIR, "%s.tabular" % base_file_name) - else: - output_metrics_file = output_metrics - metrics_columns = ["File", "Number of Good SNPs", "Average Coverage", "Genome Coverage"] - with open(output_metrics_file, "w") as fh: - fh.write("# %s\n" % "\t".join(metrics_columns)) - fh.write("%s\n" % "\t".join(bam_metrics)) - fh.write("%s\n" % "\t".join(vcf_metrics)) - task_queue.task_done() + outfile.write("%s" % line) + else: + shutil.move(vcf_file, output_vcf) + return good_snp_count -def set_num_cpus(num_files, processes): - num_cpus = int(multiprocessing.cpu_count()) - if num_files < num_cpus and num_files < processes: - return num_files - if num_cpus < processes: - half_cpus = int(num_cpus / 2) - if num_files < half_cpus: - return num_files - return half_cpus - return processes +def output_metrics_file(base_file_name, average_coverage, genome_coverage, good_snp_count, output_metrics): + bam_metrics = [base_file_name, "", "%4f" % average_coverage, genome_coverage] + vcf_metrics = [base_file_name, str(good_snp_count), "", ""] + metrics_columns = ["File", "Number of Good SNPs", "Average Coverage", "Genome Coverage"] + with open(output_metrics, "w") as fh: + fh.write("# %s\n" % "\t".join(metrics_columns)) + fh.write("%s\n" % "\t".join(bam_metrics)) + fh.write("%s\n" % "\t".join(vcf_metrics)) + + +def output_files(vcf_file, total_zero_coverage, zero_df, output_vcf, average_coverage, genome_coverage, output_metrics): + base_file_name = get_sample_name(vcf_file) + good_snp_count = output_zc_vcf_file(base_file_name, vcf_file, zero_df, total_zero_coverage, output_vcf) + output_metrics_file(base_file_name, average_coverage, genome_coverage, good_snp_count, output_metrics) + + +def get_coverage_and_snp_count(bam_file, vcf_file, reference, output_metrics, output_vcf): + coverage_df = get_coverage_df(bam_file) + zero_df = get_zero_df(reference) + coverage_df = zero_df.merge(coverage_df, left_index=True, right_index=True, how='outer') + # depth_x "0" column no longer needed. + coverage_df = coverage_df.drop(columns=['depth_x']) + coverage_df = coverage_df.rename(columns={'depth_y': 'depth'}) + # Covert the NaN to 0 coverage and get some metrics. + coverage_df = coverage_df.fillna(0) + coverage_df['depth'] = coverage_df['depth'].apply(int) + total_length = len(coverage_df) + average_coverage = coverage_df['depth'].mean() + zero_df = coverage_df[coverage_df['depth'] == 0] + total_zero_coverage = len(zero_df) + total_coverage = total_length - total_zero_coverage + genome_coverage = "{:.2%}".format(total_coverage / total_length) + # Output a zero-coverage vcf fil and the metrics file. + output_files(vcf_file, total_zero_coverage, zero_df, output_vcf, average_coverage, genome_coverage, output_metrics) if __name__ == '__main__': parser = argparse.ArgumentParser() + parser.add_argument('--bam_input', action='store', dest='bam_input', help='bam input file') parser.add_argument('--output_metrics', action='store', dest='output_metrics', required=False, default=None, help='Output metrics text file') parser.add_argument('--output_vcf', action='store', dest='output_vcf', required=False, default=None, help='Output VCF file') parser.add_argument('--reference', action='store', dest='reference', help='Reference dataset') - parser.add_argument('--processes', action='store', dest='processes', type=int, help='User-selected number of processes to use for job splitting') + parser.add_argument('--vcf_input', action='store', dest='vcf_input', help='vcf input file') args = parser.parse_args() - # The assumption here is that the list of files - # in both INPUT_BAM_DIR and INPUT_VCF_DIR are - # equal in number and named such that they are - # properly matched if the directories contain - # more than 1 file (i.e., hopefully the bam file - # names and vcf file names will be something like - # Mbovis-01D6_* so they can be # sorted and properly - # associated with each other). - bam_files = [] - for file_name in sorted(os.listdir(INPUT_BAM_DIR)): - file_path = os.path.abspath(os.path.join(INPUT_BAM_DIR, file_name)) - bam_files.append(file_path) - vcf_files = [] - for file_name in sorted(os.listdir(INPUT_VCF_DIR)): - file_path = os.path.abspath(os.path.join(INPUT_VCF_DIR, file_name)) - vcf_files.append(file_path) - - multiprocessing.set_start_method('spawn') - queue1 = multiprocessing.JoinableQueue() - num_files = len(bam_files) - cpus = set_num_cpus(num_files, args.processes) - # Set a timeout for get()s in the queue. - timeout = 0.05 - - # Add each associated bam and vcf file pair to the queue. - for i, bam_file in enumerate(bam_files): - vcf_file = vcf_files[i] - queue1.put((bam_file, vcf_file)) - - # Complete the get_coverage_and_snp_count task. - processes = [multiprocessing.Process(target=get_coverage_and_snp_count, args=(queue1, args.reference, args.output_metrics, args.output_vcf, timeout, )) for _ in range(cpus)] - for p in processes: - p.start() - for p in processes: - p.join() - queue1.join() - - if queue1.empty(): - queue1.close() - queue1.join_thread() + get_coverage_and_snp_count(args.bam_input, args.vcf_input, args.reference, args.output_metrics, args.output_vcf)
--- a/vsnp_add_zero_coverage.xml Tue Apr 21 09:51:00 2020 -0400 +++ b/vsnp_add_zero_coverage.xml Sun Jan 03 16:29:00 2021 +0000 @@ -1,147 +1,72 @@ -<tool id="vsnp_add_zero_coverage" name="vSNP: add zero coverage" version="1.0.0"> +<tool id="vsnp_add_zero_coverage" name="vSNP: add zero coverage" version="@WRAPPER_VERSION@.2" profile="@PROFILE@"> <description></description> + <macros> + <import>macros.xml</import> + </macros> <requirements> <requirement type="package" version="1.76">biopython</requirement> - <requirement type="package" version="1.16.5">numpy</requirement> <requirement type="package" version="0.25.3">pandas</requirement> <requirement type="package" version="0.15.4">pysam</requirement> </requirements> <command detect_errors="exit_code"><![CDATA[ -#import os #import re -#set input_type = $input_type_cond.input_type -#set input_bam_dir = 'input_bam_dir' -#set input_vcf_dir = 'input_vcf_dir' -#set output_vcf_dir = 'output_vcf_dir' -#set output_metrics_dir = 'output_metrics_dir' -mkdir -p $input_bam_dir && -mkdir -p $input_vcf_dir && -mkdir -p $output_vcf_dir && -mkdir -p $output_metrics_dir && -#if str($input_type) == "single": - #set bam_input = $input_type_cond.bam_input - #set file_name = $bam_input.file_name - #set file_name_base = $os.path.basename($file_name) - ln -s $file_name $input_bam_dir/$file_name_base && - #set vcf_input = $input_type_cond.vcf_input - #set file_name = $vcf_input.file_name - #set file_name_base = $os.path.basename($file_name) - ln -s $file_name $input_vcf_dir/$file_name_base && -#else: - #for $i in $input_type_cond.bam_input_collection: - #set filename = $i.file_name - #set identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) - ln -s $filename $input_bam_dir/$identifier && - #end for - #for $i in $input_type_cond.vcf_input_collection: - #set filename = $i.file_name - #set identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) - ln -s $filename $input_vcf_dir/$identifier && - #end for -#end if + +## The identifer for both of the following files is likely the same +## string, so we append a file extension to allow for both links. +#set bam_identifier = re.sub('[^\s\w\-]', '_', str($bam_input.element_identifier)) + '.bam' +ln -s '${bam_input}' '${bam_identifier}' && +#set vcf_identifier = re.sub('[^\s\w\-]', '_', str($vcf_input.element_identifier)) + '.vcf' +ln -s '${vcf_input}' '${vcf_identifier}' && + python '$__tool_directory__/vsnp_add_zero_coverage.py' ---processes $processes -#if str($reference_cond.reference_source) == "cached" +--bam_input '$bam_identifier' +--vcf_input '$vcf_identifier' +#if str($reference_cond.reference_source) == 'cached' --reference '$reference_cond.reference.fields.path' #else: --reference '$reference_cond.reference' #end if -#if str($input_type) == "single": - --output_metrics '$output_metrics' - --output_vcf '$output_vcf' -#end if +--output_metrics '$output_metrics' +--output_vcf '$output_vcf' ]]></command> <inputs> - <conditional name="input_type_cond"> - <param name="input_type" type="select" label="Choose the category of the files to be analyzed"> - <option value="single" selected="true">Single files</option> - <option value="collection">Collections of files</option> - </param> - <when value="single"> - <param name="bam_input" type="data" format="bam" label="BAM file"> - <validator type="unspecified_build"/> - </param> - <param name="vcf_input" type="data" format="vcf" label="VCF file"> - <validator type="unspecified_build"/> - </param> - </when> - <when value="collection"> - <param name="bam_input_collection" type="data_collection" format="bam" collection_type="list" label="Collection of BAM files"> - <validator type="unspecified_build"/> - </param> - <param name="vcf_input_collection" type="data_collection" format="vcf" collection_type="list" label="Collection of VCF files"> - <validator type="unspecified_build"/> - </param> - </when> - </conditional> + <param name="bam_input" type="data" format="bam" label="BAM file"/> + <param name="vcf_input" type="data" format="vcf" label="VCF file"/> <conditional name="reference_cond"> - <param name="reference_source" type="select" label="Choose the source for the reference genome"> - <option value="cached" selected="true">locally cached</option> - <option value="history">from history</option> - </param> + <expand macro="param_reference_source"/> <when value="cached"> <param name="reference" type="select" label="Using reference genome"> - <options from_data_table="fasta_indexes"/> - <!-- No <filter> tag here! --> - <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected BAM file"/> + <options from_data_table="fasta_indexes"> + <filter type="data_meta" column="1" key="dbkey" ref="bam_input"/> + <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected BAM file"/> + </options> </param> </when> <when value="history"> - <param name="reference" type="data" format="fasta" label="Using reference genome"> + <param name="reference" type="data" format="fasta,fasta.gz" label="Using reference genome"> <validator type="no_options" message="The current history does not include a fasta dataset"/> </param> </when> </conditional> - <param name="processes" type="integer" min="1" max="20" value="8" label="Number of processes for job splitting"/> </inputs> <outputs> - <data name="output_vcf" format="vcf" label="${tool.name} (filtered VCF) on ${on_string}"> - <filter>input_type_cond['input_type'] == 'single'</filter> - </data> - <collection name="output_vcf_collection" type="list" label="${tool.name} (filtered VCFs) on ${on_string}"> - <discover_datasets pattern="__name__" directory="output_vcf_dir" format="vcf" /> - <filter>input_type_cond['input_type'] == 'collection'</filter> - </collection> - <data name="output_metrics" format="tabular" label="${tool.name} (metrics) on ${on_string}"> - <filter>input_type_cond['input_type'] == 'single'</filter> - </data> - <collection name="output_metrics_collection" type="list" label="${tool.name} (metrics) on ${on_string}"> - <discover_datasets pattern="__name__" directory="output_metrics_dir" format="tabular" /> - <filter>input_type_cond['input_type'] == 'collection'</filter> - </collection> + <data name="output_vcf" format="vcf" label="${tool.name} on ${on_string} (filtered VCF)"/> + <data name="output_metrics" format="tabular" label="${tool.name} on ${on_string} (metrics)"/> </outputs> <tests> - <test> - <param name="input_type" value="collection"/> - <param name="bam_input_collection"> - <collection type="list"> - <element name="bam_input.bam" value="bam_input.bam" dbkey="89"/> - <element name="bam_input2.bam" value="bam_input2.bam" dbkey="89"/> - </collection> - </param> - <param name="vcf_input_collection"> - <collection type="list"> - <element name="vcf_input.vcf" value="vcf_input.vcf" dbkey="89"/> - <element name="vcf_input2.vcf" value="vcf_input2.vcf" dbkey="89"/> - </collection> - </param> - <param name="reference_source" value="history"/> - <param name="reference" value="NC_002945v4.fasta" ftype="fasta"/> - <output_collection name="output_vcf_collection" type="list"> - <element name="vcf_input.vcf" file="output_vcf.vcf" ftype="vcf" compare="contains"/> - <element name="vcf_input2.vcf" file="output_vcf.vcf" ftype="vcf" compare="contains"/> - </output_collection> - <output_collection name="output_metrics_collection" type="list"> - <element name="vcf_input.tabular" file="output_metrics.tabular" ftype="tabular" compare="contains"/> - <element name="vcf_input2.tabular" file="output_metrics.tabular" ftype="tabular" compare="contains"/> - </output_collection> - </test> - <test> + <test expect_num_outputs="2"> <param name="bam_input" value="bam_input.bam" ftype="bam" dbkey="89"/> <param name="vcf_input" value="vcf_input.vcf" ftype="vcf" dbkey="89"/> <param name="reference_source" value="history"/> <param name="reference" value="NC_002945v4.fasta" ftype="fasta"/> - <param name="output_vcf" value="output_vcf.vcf" ftype="vcf" compare="contains"/> + <output name="output_vcf" value="output_vcf.vcf" ftype="vcf" compare="contains"/> + <output name="output_metrics" file="output_metrics.tabular" ftype="tabular"/> + </test> + <test expect_num_outputs="2"> + <param name="bam_input" value="bam_input.bam" ftype="bam" dbkey="89"/> + <param name="vcf_input" value="vcf_input.vcf" ftype="vcf" dbkey="89"/> + <param name="reference_source" value="cached"/> + <output name="output_vcf" value="output_vcf.vcf" ftype="vcf" compare="contains"/> <output name="output_metrics" file="output_metrics.tabular" ftype="tabular" compare="contains"/> </test> </tests> @@ -157,19 +82,8 @@ **Required Options** - * **Choose the category of the files to be analyzed** - select "Single files" or "Collections of files", then select the appropriate history items (single BAM and VCF files or collections of BAM and VCF files) based on the selected option. * **Choose the source for the reference genome** - select "locally cached" if the reference associated with the BAM and VCF files is available within the Galaxy environment or "from history" to select the reference from the current history. - * **Number of processes for job splitting** - Select the number of processes for splitting the job to shorten execution time. </help> - <citations> - <citation type="bibtex"> - @misc{None, - journal = {None}, - author = {1. Stuber T}, - title = {Manuscript in preparation}, - year = {None}, - url = {https://github.com/USDA-VS/vSNP},} - </citation> - </citations> + <expand macro="citations" /> </tool>