diffexp.py 文件源码

def run_differential_expression(matrix, clusters, sseq_params=None):
    """ Compute differential expression for each cluster vs all other cells
        Args: matrix      - GeneBCMatrix  :  gene expression data
              clusters    - np.array(int) :  1-based cluster labels
              sseq_params - dict          :  params from compute_sseq_params """

    n_clusters = np.max(clusters)

    if sseq_params is None:
        print "Computing params..."
        sys.stdout.flush()
        sseq_params = compute_sseq_params(matrix.m)

    # Create a numpy array with 3*K columns;
    # each group of 3 columns is mean, log2, pvalue for cluster i
    all_de_results = np.zeros((matrix.genes_dim, 3*n_clusters))

    for cluster in xrange(1, 1+n_clusters):
        in_cluster = clusters == cluster
        group_a = np.flatnonzero(in_cluster)
        group_b = np.flatnonzero(np.logical_not(in_cluster))
        print 'Computing DE for cluster %d...' % cluster
        sys.stdout.flush()

        de_result = sseq_differential_expression(
            matrix.m, group_a, group_b, sseq_params)
        all_de_results[:, 0+3*(cluster-1)] = de_result['norm_mean_a']
        all_de_results[:, 1+3*(cluster-1)] = de_result['log2_fold_change']
        all_de_results[:, 2+3*(cluster-1)] = de_result['adjusted_p_value']

    return DIFFERENTIAL_EXPRESSION(all_de_results)