comparison draw_amr_matrix.py @ 3:7d7884f2d921 draft

Uploaded

2:9fcc1ffd7526

            # TODO: So far, no samples have produced mutations, so we haven't been able
            # to produce a populated VarScan VCF file of mutations - https://github.com/appliedbinf/pima_md/blob/main/pima.py#L2923.
            # The call_amr_mutations Galaxy tool will currently produce this VarScan VCF file, but we need a sample that
            # will produce a populated file.  After we find one, we'll need to figure out how to implement this loop
            # https://github.com/appliedbinf/pima_md/blob/main/pima.py#L2925 in a Galaxy tool so that the VarScan VCF
            # file will be converted to the TSV amr_mutations_file that thsi tool expects. 
            # Roll up potentially resistance conferring mutations.
            for mutation_region, mutation_hits in amr_mutations.iteritems():
                for mutation_idx, mutation_hit in mutation_hits.iterrows():
                    mutation_name = mutation_region + ' ' + mutation_hit['REF'] + '->' + mutation_hit['ALT']
                    amr_to_draw = amr_to_draw.append(pandas.Series([mutation_name, mutation_hit['DRUG']], name=amr_to_draw.shape[0], index=amr_to_draw.columns))

        if amr_deletions_file is not None:
            # TODO: So far, no samples have produced deletions, but we do have all the pices in place
            # within the workflow to receive the amr_deletions_file here, although it is currently
            # always empty...
            # Roll up deletions that might confer resistance.
            amr_deletions = pandas.read_csv(filepath_or_buffer=amr_deletions_file, sep='\t', header=None)
            if amr_deletions.shape[0] > 0:
                amr_deletions.columns = ['contig', 'start', 'stop', 'name', 'type', 'drug', 'note']
                amr_deletions = amr_deletions.loc[amr_deletions['type'].isin(['large-deletion', 'any']), :]
                for deletion_idx, deleted_gene in amr_deletions.iterrows():
                    amr_to_draw = amr_to_draw.append(pandas.Series(['\u0394' + deleted_gene[3], deleted_gene[5]], name=amr_to_draw.shape[0], index=amr_to_draw.columns))

3:7d7884f2d921

            # TODO: So far, no samples have produced mutations, so we haven't been able
            # to produce a populated VarScan VCF file of mutations - https://github.com/appliedbinf/pima_md/blob/main/pima.py#L2923.
            # The call_amr_mutations Galaxy tool will currently produce this VarScan VCF file, but we need a sample that
            # will produce a populated file.  After we find one, we'll need to figure out how to implement this loop
            # https://github.com/appliedbinf/pima_md/blob/main/pima.py#L2925 in a Galaxy tool so that the VarScan VCF
            # file will be converted to the TSV amr_mutations_file that thsi tool expects.
            amr_mutations = pandas.DataFrame()
            # Roll up potentially resistance conferring mutations.
            for mutation_region, mutation_hits in amr_mutations.iteritems():
                for mutation_idx, mutation_hit in mutation_hits.iterrows():
                    mutation_name = mutation_region + ' ' + mutation_hit['REF'] + '->' + mutation_hit['ALT']
                    amr_to_draw = amr_to_draw.append(pandas.Series([mutation_name, mutation_hit['DRUG']], name=amr_to_draw.shape[0], index=amr_to_draw.columns))

        if amr_deletions_file is not None:
            # TODO: So far, no samples have produced deletions, but we do have all the pices in place
            # within the workflow to receive the amr_deletions_file here, although it is currently
            # always empty...
            # Roll up deletions that might confer resistance.
            try:
                amr_deletions = pandas.read_csv(filepath_or_buffer=amr_deletions_file, sep='\t', header=None)
            except Exception:
                amr_deletions = pandas.DataFrame()
            if amr_deletions.shape[0] > 0:
                amr_deletions.columns = ['contig', 'start', 'stop', 'name', 'type', 'drug', 'note']
                amr_deletions = amr_deletions.loc[amr_deletions['type'].isin(['large-deletion', 'any']), :]
                for deletion_idx, deleted_gene in amr_deletions.iterrows():
                    amr_to_draw = amr_to_draw.append(pandas.Series(['\u0394' + deleted_gene[3], deleted_gene[5]], name=amr_to_draw.shape[0], index=amr_to_draw.columns))