Beispiel #1
0
def mRNA_RPKM_length_bias():
    gtf_fn = '/home/jah/projects/arlen/data/organisms/saccharomyces_cerevisiae/EF4/transcriptome/genes.gtf'
    genome_dir = '/home/jah/projects/arlen/data/organisms/saccharomyces_cerevisiae/EF4/genome'
    coding_sequence_fetcher = gtf.make_coding_sequence_fetcher(gtf_fn, genome_dir)
    lengths = np.asarray([len(coding_sequence_fetcher(name)) for name in gene_names])

    explore_UTRs.scatter_with_hists_colors(lengths,
                                           #np.log2(arrays['weinberg']['Dynabeads']) - np.log2(arrays['weinberg']['Unselected']),
                                           np.log2(arrays['weinberg']['RPF']) - np.log2(arrays['ingolia']['RPF']),
                                           'coding sequence length',
                                           'log2(Ingolia mRNA RPKM / Weinberg mRNA RPKM)',
                                           '',
                                          )

    plt.ylim(-7, 7)
    plt.gcf().set_size_inches(12, 8)