예제 #1
0
def run_cluster(*data):
    """
    Run seqcluster cluster to detect smallRNA clusters
    """
    sample = data[0][0]
    tools = dd.get_expression_caller(data[0][0])
    work_dir = dd.get_work_dir(sample)
    out_dir = op.join(work_dir, "seqcluster", "cluster")
    out_dir = op.abspath(safe_makedir(out_dir))
    prepare_dir = op.join(work_dir, "seqcluster", "prepare")
    bam_file = data[0][0]["work_bam"]
    if "seqcluster" in tools:
        sample["seqcluster"] = _cluster(bam_file, data[0][0]["seqcluster_prepare_ma"], out_dir, dd.get_ref_file(sample), dd.get_srna_gtf_file(sample))
        sample["report"] = _report(sample, dd.get_ref_file(sample))

    out_mirna = _make_isomir_counts(data, out_dir=op.join(work_dir, "mirbase"))
    if out_mirna:
        sample = dd.set_mirna_counts(sample, out_mirna[0])
        sample = dd.set_isomir_counts(sample, out_mirna[1])

    out_novel = _make_isomir_counts(data, "seqbuster_novel", op.join(work_dir, "mirdeep2"), "_novel")
    if out_novel:
        sample = dd.set_novel_mirna_counts(sample, out_novel[0])
        sample = dd.set_novel_isomir_counts(sample, out_novel[1])
    data[0][0] = sample
    return data
예제 #2
0
def run_cluster(*data):
    """
    Run seqcluster cluster to detect smallRNA clusters
    """
    sample = data[0][0]
    work_dir = dd.get_work_dir(sample)
    out_dir = op.join(work_dir, "seqcluster", "cluster")
    out_dir = op.abspath(safe_makedir(out_dir))
    prepare_dir = op.join(work_dir, "seqcluster", "prepare")
    bam_file = op.join(work_dir, "align", "seqs.bam")
    cluster_dir = _cluster(bam_file, prepare_dir, out_dir, dd.get_ref_file(sample), dd.get_srna_gtf_file(sample))
    sample["report"] = _report(sample, dd.get_ref_file(sample))
    sample["seqcluster"] = out_dir

    out_mirna = _make_isomir_counts(data, out_dir=op.join(work_dir, "mirbase"))
    if out_mirna:
        sample = dd.set_mirna_counts(sample, out_mirna[0])
        sample = dd.set_isomir_counts(sample, out_mirna[1])

    out_novel = _make_isomir_counts(data, "seqbuster_novel", op.join(work_dir, "mirdeep2"), "_novel")
    novel_db = mirdeep.run(data)
    if out_novel:
        sample = dd.set_novel_mirna_counts(sample, out_novel[0])
        sample = dd.set_novel_isomir_counts(sample, out_novel[1])
    data[0][0] = sample
    return data
예제 #3
0
def run_cluster(*data):
    """
    Run seqcluster cluster to detect smallRNA clusters
    """
    sample = data[0][0]
    tools = dd.get_expression_caller(data[0][0])
    work_dir = dd.get_work_dir(sample)
    out_dir = op.join(work_dir, "seqcluster", "cluster")
    out_dir = op.abspath(safe_makedir(out_dir))
    prepare_dir = op.join(work_dir, "seqcluster", "prepare")
    bam_file = data[0][0]["cluster_bam"]
    if "seqcluster" in tools:
        gtf_file = dd.get_transcriptome_gtf(sample) if dd.get_transcriptome_gtf(sample) else dd.get_srna_gtf_file(sample)
        sample["seqcluster"] = _cluster(bam_file, data[0][0]["seqcluster_prepare_ma"],
                                        out_dir, dd.get_ref_file(sample),
                                        gtf_file)
        sample["report"] = _report(sample, dd.get_ref_file(sample))

    if "mirge" in tools:
        sample["mirge"] = mirge.run(data)

    out_mirna = _make_isomir_counts(data, out_dir=op.join(work_dir, "mirbase"))
    if out_mirna:
        sample = dd.set_mirna_counts(sample, out_mirna[0])
        sample = dd.set_isomir_counts(sample, out_mirna[1])

    out_novel = _make_isomir_counts(data, "seqbuster_novel", op.join(work_dir, "mirdeep2"), "_novel")
    if out_novel:
        sample = dd.set_novel_mirna_counts(sample, out_novel[0])
        sample = dd.set_novel_isomir_counts(sample, out_novel[1])
    data[0][0] = sample
    data = spikein.combine_spikein(data)
    return data