Mercurial > repos > earlhaminst > replace_chromosome_names
changeset 1:6c0373cc070f draft default tip
planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/replace_chromosome_names/ commit c8418d1d7657dacae7f81fe4aa0aba051873d4ad
author | earlhaminst |
---|---|
date | Tue, 13 Jun 2017 14:43:07 -0400 |
parents | 97c11d04cd4c |
children | |
files | replace_chromosome_names.py replace_chromosome_names.xml test-data/gemini_load_input.vcf |
diffstat | 3 files changed, 12 insertions(+), 3 deletions(-) [+] |
line wrap: on
line diff
--- a/replace_chromosome_names.py Thu May 18 14:17:48 2017 -0400 +++ b/replace_chromosome_names.py Tue Jun 13 14:43:07 2017 -0400 @@ -32,9 +32,14 @@ line_cols = line.split('\t') for col_to_map in cols_to_map: old_value = line_cols[col_to_map] - line_cols[col_to_map] = map_dict.get(old_value, old_value) - mapped_line = '\t'.join(line_cols) - print(mapped_line, file=args.output) + new_value = map_dict.get(old_value, '') + if not new_value: + print('%s has no valid mapping, skipping line: %s' % (old_value, line), file=sys.stderr) + break + line_cols[col_to_map] = new_value + else: + mapped_line = '\t'.join(line_cols) + print(mapped_line, file=args.output) if __name__ == "__main__":
--- a/replace_chromosome_names.xml Thu May 18 14:17:48 2017 -0400 +++ b/replace_chromosome_names.xml Tue Jun 13 14:43:07 2017 -0400 @@ -28,6 +28,9 @@ <param name="mapping" ftype="tabular" value="GRCh37_ensembl2UCSC.txt" /> <param name="comment_char" value="#" /> <output name="output" ftype="vcf" file="replace_chromosome_names_output.vcf" /> + <assert_stderr> + <has_text text="HG1007_PATCH" /> + </assert_stderr> </test> </tests> <help><![CDATA[
--- a/test-data/gemini_load_input.vcf Thu May 18 14:17:48 2017 -0400 +++ b/test-data/gemini_load_input.vcf Tue Jun 13 14:43:07 2017 -0400 @@ -68,3 +68,4 @@ 1 55816 rs187434873 G A 100.0 PASS AN=2184;THETA=0.0119;VT=SNP;AC=10;RSQ=0.4578;AA=A;SNPSOURCE=LOWCOV;AVGPOST=0.9844;LDAF=0.0108;ERATE=0.0007;AF=0.0046;AMR_AF=0.01;EUR_AF=0.01;EFF=INTERGENIC(MODIFIER|||||||||) 1 55850 rs191890754 C G 100.0 PASS AVGPOST=0.9921;AA=G;AN=2184;VT=SNP;RSQ=0.4083;THETA=0.0045;LDAF=0.0056;AC=5;SNPSOURCE=LOWCOV;ERATE=0.0006;AF=0.0023;EUR_AF=0.01;EFF=INTERGENIC(MODIFIER|||||||||) 1 55852 rs184233019 G C 100.0 PASS THETA=0.0137;AA=G;AN=2184;RSQ=0.5433;ERATE=0.0009;LDAF=0.0046;VT=SNP;AVGPOST=0.9953;AC=5;SNPSOURCE=LOWCOV;AF=0.0023;AMR_AF=0.01;EUR_AF=0.0013;EFF=INTERGENIC(MODIFIER|||||||||) +HG1007_PATCH 55852 rs184233019 G C 100.0 PASS THETA=0.0137;AA=G;AN=2184;RSQ=0.5433;ERATE=0.0009;LDAF=0.0046;VT=SNP;AVGPOST=0.9953;AC=5;SNPSOURCE=LOWCOV;AF=0.0023;AMR_AF=0.01;EUR_AF=0.0013;EFF=INTERGENIC(MODIFIER|||||||||)