Mercurial > repos > mheinzl > variant_analyzer2
changeset 13:02bf6425fc25 draft
planemo upload for repository https://github.com/Single-Molecule-Genetics/VariantAnalyzerGalaxy/tree/master/tools/variant_analyzer commit ee4a8e6cf290e6c8a4d55f9cd2839d60ab3b11c8
author | mheinzl |
---|---|
date | Mon, 22 Feb 2021 14:18:57 +0000 |
parents | 7a418148319d |
children | bcdb63df70ce |
files | read2mut.py read2mut.xml |
diffstat | 2 files changed, 18 insertions(+), 1 deletions(-) [+] |
line wrap: on
line diff
--- a/read2mut.py Tue Feb 16 07:08:25 2021 +0000 +++ b/read2mut.py Mon Feb 22 14:18:57 2021 +0000 @@ -23,12 +23,14 @@ from __future__ import division import argparse +import csv import json import operator import os import re import sys + import numpy as np import pysam import xlsxwriter @@ -47,6 +49,8 @@ help='JSON file with SSCS counts collected by mut2sscs.py.') parser.add_argument('--outputFile', help='Output xlsx file with summary of mutations.') + parser.add_argument('--outputFile_csv', + help='Output csv file with summary of mutations.') parser.add_argument('--outputFile2', help='Output xlsx file with allele frequencies of mutations.') parser.add_argument('--outputFile3', @@ -59,6 +63,8 @@ help='Integer threshold for assigning mutations at start and end of reads to lower tier. Default 10.') parser.add_argument('--chimera_correction', action="store_true", help='Count chimeric variants and correct the variant frequencies') + + return parser @@ -78,6 +84,7 @@ outfile = args.outputFile outfile2 = args.outputFile2 outfile3 = args.outputFile3 + outputFile_csv = args.outputFile_csv thresh = args.thresh phred_score = args.phred trim = args.trim @@ -227,6 +234,9 @@ else: pure_tags_dict_short = pure_tags_dict + csv_data = open(outputFile_csv, "w") + csv_writer = csv.writer(csv_data) + # output summary with threshold workbook = xlsxwriter.Workbook(outfile) workbook2 = xlsxwriter.Workbook(outfile2) @@ -255,6 +265,7 @@ 'SSCS alt.ab', 'SSCS alt.ba', 'SSCS ref.ab', 'SSCS ref.ba', 'in phase', 'chimeric tag') ws1.write_row(0, 0, header_line) + csv_writer.writerow(header_line) counter_tier11 = 0 counter_tier12 = 0 counter_tier21 = 0 @@ -682,8 +693,10 @@ read_pos3 = read_len_median3 = None line = (var_id, tier, key2[:-5], 'ab1.ba2', read_pos1, read_pos4, read_len_median1, read_len_median4, dcs_median) + details1 + (sscs_mut_ab, sscs_mut_ba, sscs_ref_ab, sscs_ref_ba, add_mut14, chimera) ws1.write_row(row, 0, line) + csv_writer.writerow(line) line = ("", "", key2[:-5], 'ab2.ba1', read_pos2, read_pos3, read_len_median2, read_len_median3, dcs_median) + details2 + (sscs_mut_ab, sscs_mut_ba, sscs_ref_ab, sscs_ref_ba, add_mut23, chimera) ws1.write_row(row + 1, 0, line) + csv_writer.writerow(line) ws1.conditional_format('L{}:M{}'.format(row + 1, row + 2), {'type': 'formula', @@ -904,6 +917,7 @@ workbook.close() workbook2.close() workbook3.close() + csv_data.close() if __name__ == '__main__':
--- a/read2mut.xml Tue Feb 16 07:08:25 2021 +0000 +++ b/read2mut.xml Mon Feb 22 14:18:57 2021 +0000 @@ -1,5 +1,5 @@ <?xml version="1.0" encoding="UTF-8"?> -<tool id="read2mut" name="Call specific mutations in reads:" version="2.0.1" profile="19.01"> +<tool id="read2mut" name="Call specific mutations in reads:" version="2.0.2" profile="17.01"> <description>Looks for reads with mutation at known positions and calculates frequencies and stats.</description> <macros> <import>va_macros.xml</import> @@ -20,6 +20,7 @@ --trim '$trim' $chimera_correction --outputFile '$output_xlsx' + --outputFile_csv '$outputFile_csv' --outputFile2 '$output_xlsx2' --outputFile3 '$output_xlsx3' ]]> @@ -36,6 +37,7 @@ </inputs> <outputs> <data name="output_xlsx" format="xlsx" label="${tool.name} on ${on_string}: XLSX summary"/> + <data name="outputFile_csv" format="csv" label="${tool.name} on ${on_string}: CSV summary"/> <data name="output_xlsx2" format="xlsx" label="${tool.name} on ${on_string}: XLSX allele frequencies"/> <data name="output_xlsx3" format="xlsx" label="${tool.name} on ${on_string}: XLSX tiers"/> </outputs> @@ -50,6 +52,7 @@ <param name="trim" value="10"/> <param name="chimera_correction" value="True"/> <output name="output_xlsx" file="Variant_Analyzer_summary_test.xlsx" decompress="true" lines_diff="10"/> + <output name="outputFile_csv" file="Variant_Analyzer_summary_test.csv" decompress="true" lines_diff="10"/> <output name="output_xlsx2" file="Variant_Analyzer_allele_frequencies_test.xlsx" decompress="true" lines_diff="10"/> <output name="output_xlsx3" file="Variant_Analyzer_tiers_test.xlsx" decompress="true" lines_diff="10"/> </test>