comparison decoupler_pseudobulk.py @ 1:046d8ff974ff draft

planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit 45145f380b27c3092e1fa2249adc36d7d6fdf5fe

0:59a7f3f83aec

    # replace any index starting with digits to start with C instead.
    obs_for_deseq.rename(index=prepend_c_to_index, inplace=True)
    # avoid dash that is read as point on R colnames.
    obs_for_deseq.index = obs_for_deseq.index.str.replace("-", "_")
    obs_for_deseq.index = obs_for_deseq.index.str.replace(" ", "_")
    col_metadata_file = f"{output_dir}col_metadata.csv"
    # write obs to a col_metadata file
    if factor_fields:
        # only output the index plus the columns in factor_fields in that order
        obs_for_deseq[factor_fields].to_csv(col_metadata_file, sep=",", index=True)
    else:
        obs_for_deseq.to_csv(col_metadata_file, sep=",", index=True)
    # write var to a gene_metadata file
    pdata.var.to_csv(f"{output_dir}gene_metadata.csv", sep=",", index=True)
    # write the counts matrix of a specified layer to file
    if layer is None:
        # write the X numpy matrix transposed to file
        df = pd.DataFrame(pdata.X.T, index=pdata.var.index, columns=obs_for_deseq.index)
    else:
        df = pd.DataFrame(
            pdata.layers[layer].T, index=pdata.var.index, columns=obs_for_deseq.index
        )
    df.to_csv(f"{output_dir}counts_matrix.csv", sep=",", index_label="")


def plot_pseudobulk_samples(
    pseudobulk_data,
    groupby,

1:046d8ff974ff

    # replace any index starting with digits to start with C instead.
    obs_for_deseq.rename(index=prepend_c_to_index, inplace=True)
    # avoid dash that is read as point on R colnames.
    obs_for_deseq.index = obs_for_deseq.index.str.replace("-", "_")
    obs_for_deseq.index = obs_for_deseq.index.str.replace(" ", "_")
    col_metadata_file = f"{output_dir}col_metadata.tsv"
    # write obs to a col_metadata file
    if factor_fields:
        # only output the index plus the columns in factor_fields in that order
        obs_for_deseq[factor_fields].to_csv(col_metadata_file, sep="\t", index=True)
    else:
        obs_for_deseq.to_csv(col_metadata_file, sep="\t", index=True)
    # write var to a gene_metadata file
    pdata.var.to_csv(f"{output_dir}gene_metadata.tsv", sep="\t", index=True)
    # write the counts matrix of a specified layer to file
    if layer is None:
        # write the X numpy matrix transposed to file
        df = pd.DataFrame(pdata.X.T, index=pdata.var.index, columns=obs_for_deseq.index)
    else:
        df = pd.DataFrame(
            pdata.layers[layer].T, index=pdata.var.index, columns=obs_for_deseq.index
        )
    df.to_csv(f"{output_dir}counts_matrix.tsv", sep="\t", index_label="")


def plot_pseudobulk_samples(
    pseudobulk_data,
    groupby,