multigenome.py 文件源码

def _classify_gems(counts0, counts1):
        """ Infer number of distinct transcriptomes present in each GEM (1 or 2) and
            report cr_constants.GEM_CLASS_GENOME0 for a single cell w/ transcriptome 0,
            report cr_constants.GEM_CLASS_GENOME1 for a single cell w/ transcriptome 1,
            report cr_constants.GEM_CLASS_MULTIPLET for multiple transcriptomes """
        # Assumes that most of the GEMs are single-cell; model counts independently
        thresh0, thresh1 = [cr_constants.DEFAULT_MULTIPLET_THRESHOLD] * 2
        if sum(counts0 > counts1) >= 1 and sum(counts1 > counts0) >= 1:
            thresh0 = np.percentile(counts0[counts0 > counts1], cr_constants.MULTIPLET_PROB_THRESHOLD)
            thresh1 = np.percentile(counts1[counts1 > counts0], cr_constants.MULTIPLET_PROB_THRESHOLD)

        doublet = np.logical_and(counts0 >= thresh0, counts1 >= thresh1)
        dtype = np.dtype('|S%d' % max(len(cls) for cls in cr_constants.GEM_CLASSES))
        result = np.where(doublet, cr_constants.GEM_CLASS_MULTIPLET, cr_constants.GEM_CLASS_GENOME0).astype(dtype)
        result[np.logical_and(np.logical_not(result == cr_constants.GEM_CLASS_MULTIPLET), counts1 > counts0)] = cr_constants.GEM_CLASS_GENOME1

        return result