コード例 #1
0
def _get_annotation(c, loci):
    """get annotation of transcriptional units"""
    data_ann_temp = {}
    data_ann = []
    counts = Counter()
    for lid in c.loci2seq:
        # original Py 2.7 code
        #for dbi in loci[lid].db_ann.keys():
        #    data_ann_temp[dbi] = {dbi: map(lambda (x): loci[lid].db_ann[dbi].ann[x].name, loci[lid].db_ann[dbi].ann.keys())}
        # suggestion by 2to3
        for dbi in list(loci[lid].db_ann.keys()):
            data_ann_temp[dbi] = {
                dbi: [
                    loci[lid].db_ann[dbi].ann[x].name
                    for x in list(loci[lid].db_ann[dbi].ann.keys())
                ]
            }
            logger.debug("_json_: data_ann_temp %s %s" %
                         (dbi, data_ann_temp[dbi]))
            counts[dbi] += 1
        # original Py 2.7 code
        #data_ann = data_ann + map(lambda (x): data_ann_temp[x], data_ann_temp.keys())
        # suggestion by 2to3
        data_ann = data_ann + [
            data_ann_temp[x] for x in list(data_ann_temp.keys())
        ]
        logger.debug("_json_: data_ann %s" % data_ann)
    counts = {k: v for k, v in iter(counts.items())}
    total_loci = sum([counts[db] for db in counts])
    valid_ann = [
        k for k, v in iter(counts.items()) if up_threshold(v, total_loci, 0.7)
    ]
    return data_ann, valid_ann
コード例 #2
0
ファイル: metacluster.py プロジェクト: lpantano/seqcluster
def _common(s1, s2, i1, i2):
    """calculate the common % percentage of sequences"""
    c = len(set(s1).intersection(s2))
    t = min(len(s1), len(s2))
    pct = 1.0 * c / t * t
    is_gt = up_threshold(pct, t * 1.0, parameters.similar)
    logger.debug("_common: pct %s of clusters:%s %s = %s" % (1.0 * c / t, i1, i2, is_gt))
    if pct < parameters.similar and is_gt and pct > 0:
        pct = parameters.similar
    return pct / t
コード例 #3
0
ファイル: metacluster.py プロジェクト: smoe/seqcluster
def _common(s1, s2, i1, i2):
    """calculate the common % percentage of sequences"""
    c = len(set(s1).intersection(s2))
    t = min(len(s1), len(s2))
    pct = 1.0 * c / t * t
    is_gt = up_threshold(pct, t * 1.0, parameters.similar)
    logger.debug("_common: pct %s of clusters:%s %s = %s" %
                 (1.0 * c / t, i1, i2, is_gt))
    if pct < parameters.similar and is_gt and pct > 0:
        pct = parameters.similar
    return pct / t
コード例 #4
0
ファイル: make_clusters.py プロジェクト: lpantano/seqcluster
def _get_annotation(c, loci):
    """get annotation of transcriptional units"""
    data_ann_temp = {}
    data_ann = []
    counts = Counter()
    for lid in c.loci2seq:
        # original Py 2.7 code
        #for dbi in loci[lid].db_ann.keys():
        #    data_ann_temp[dbi] = {dbi: map(lambda (x): loci[lid].db_ann[dbi].ann[x].name, loci[lid].db_ann[dbi].ann.keys())}
        # suggestion by 2to3
        for dbi in list(loci[lid].db_ann.keys()):
            data_ann_temp[dbi] = {dbi: [loci[lid].db_ann[dbi].ann[x].name for x in list(loci[lid].db_ann[dbi].ann.keys())]}
            logger.debug("_json_: data_ann_temp %s %s" % (dbi, data_ann_temp[dbi]))
            counts[dbi] += 1
        # original Py 2.7 code
        #data_ann = data_ann + map(lambda (x): data_ann_temp[x], data_ann_temp.keys())
        # suggestion by 2to3
        data_ann = data_ann + [data_ann_temp[x] for x in list(data_ann_temp.keys())]
        logger.debug("_json_: data_ann %s" % data_ann)
    counts = {k: v for k, v in iter(counts.items())}
    total_loci = sum([counts[db] for db in counts])
    valid_ann = [k for k, v in iter(counts.items()) if up_threshold(v, total_loci, 0.7)]
    return data_ann, valid_ann