单细胞数据质控-双细胞预测-scrublet使用教程

pip install scrublet

wget http://cf.10xgenomics.com/samples/cell-exp/2.1.0/pbmc8k/pbmc8k_filtered_gene_bc_matrices.tar.gz
tar xfz pbmc8k_filtered_gene_bc_matrices.tar.gz

import sys
print(sys.path)

def _normalize_shape(ndarray, shape, cast_to_int=True):
    """
    Private function which does some checks and normalizes the possibly
    much simpler representations of ‘pad_width‘, ‘stat_length‘,
    ‘constant_values‘, ‘end_values‘.

    Parameters
    ----------
    narray : ndarray
        Input ndarray
    shape : {sequence, array_like, float, int}, optional
        The width of padding (pad_width), the number of elements on the
        edge of the narray used for statistics (stat_length), the constant
        value(s) to use when filling padded regions (constant_values), or the
        endpoint target(s) for linear ramps (end_values).
        ((before_1, after_1), ... (before_N, after_N)) unique number of
        elements for each axis where `N` is rank of `narray`.
        ((before, after),) yields same before and after constants for each
        axis.
        (constant,) or val is a shortcut for before = after = constant for
        all axes.
    cast_to_int : bool, optional
        Controls if values in ``shape`` will be rounded and cast to int
        before being returned.

    Returns
    -------
    normalized_shape : tuple of tuples
        val                               => ((val, val), (val, val), ...)
        [[val1, val2], [val3, val4], ...] => ((val1, val2), (val3, val4), ...)
        ((val1, val2), (val3, val4), ...) => no change
        [[val1, val2], ]                  => ((val1, val2), (val1, val2), ...)
        ((val1, val2), )                  => ((val1, val2), (val1, val2), ...)
        [[val ,     ], ]                  => ((val, val), (val, val), ...)
        ((val ,     ), )                  => ((val, val), (val, val), ...)

    """
    ndims = ndarray.ndim

    # Shortcut shape=None
    if shape is None:
        return ((None, None), ) * ndims

    # Convert any input `info` to a NumPy array
    shape_arr = np.asarray(shape)

    try:
        shape_arr = np.broadcast_to(shape_arr, (ndims, 2))
    except ValueError:
        fmt = "Unable to create correctly shaped tuple from %s"
        raise ValueError(fmt % (shape,))

    # Cast if necessary
    if cast_to_int is True:
        shape_arr = np.round(shape_arr).astype(int)

    # Convert list of lists to tuple of tuples
    return tuple(tuple(axis) for axis in shape_arr.tolist())


def _validate_lengths(narray, number_elements):
    """
    Private function which does some checks and reformats pad_width and
    stat_length using _normalize_shape.

    Parameters
    ----------
    narray : ndarray
        Input ndarray
    number_elements : {sequence, int}, optional
        The width of padding (pad_width) or the number of elements on the edge
        of the narray used for statistics (stat_length).
        ((before_1, after_1), ... (before_N, after_N)) unique number of
        elements for each axis.
        ((before, after),) yields same before and after constants for each
        axis.
        (constant,) or int is a shortcut for before = after = constant for all
        axes.

    Returns
    -------
    _validate_lengths : tuple of tuples
        int                               => ((int, int), (int, int), ...)
        [[int1, int2], [int3, int4], ...] => ((int1, int2), (int3, int4), ...)
        ((int1, int2), (int3, int4), ...) => no change
        [[int1, int2], ]                  => ((int1, int2), (int1, int2), ...)
        ((int1, int2), )                  => ((int1, int2), (int1, int2), ...)
        [[int ,     ], ]                  => ((int, int), (int, int), ...)
        ((int ,     ), )                  => ((int, int), (int, int), ...)

    """
    normshp = _normalize_shape(narray, number_elements)
    for i in normshp:
        chk = [1 if x is None else x for x in i]
        chk = [1 if x >= 0 else -1 for x in chk]
        if (chk[0] < 0) or (chk[1] < 0):
            fmt = "%s cannot contain negative values."
            raise ValueError(fmt % (number_elements,))
    return normshp

%matplotlib inline
import scrublet as scr
import scipy.io
import matplotlib.pyplot as plt
import numpy as np
import os
import pandas as pd

plt.rcParams['font.family'] = 'sans-serif'
plt.rcParams['font.sans-serif'] = 'Arial'
plt.rc('font', size=14)
plt.rcParams['pdf.fonttype'] = 42

input_dir = '/Users/yuanzan/Desktop/doublets/filtered_gene_bc_matrices/GRCh38/'
counts_matrix = scipy.io.mmread(input_dir   '/matrix.mtx').T.tocsc()
genes = np.array(scr.load_genes(input_dir   '/genes.tsv', delimiter='t', column=1))
out_df = pd.read_csv(input_dir   '/barcodes.tsv', header = None, index_col=None, names=['barcode'])


print('Counts matrix shape: {} rows, {} columns'.format(counts_matrix.shape[0], counts_matrix.shape[1]))
print('Number of genes in gene list: {}'.format(len(genes)))

scrub = scr.Scrublet(counts_matrix, expected_doublet_rate=0.06)

doublet_scores, predicted_doublets = scrub.scrub_doublets(min_counts=2, min_cells=3, min_gene_variability_pctl=85, n_prin_comps=30)

scrub.call_doublets(threshold=0.25)

# 画doublet score直方图
scrub.plot_histogram()

print('Running UMAP...')
scrub.set_embedding('UMAP', scr.get_umap(scrub.manifold_obs_, 10, min_dist=0.3))
print('Done.')

scrub.plot_embedding('UMAP', order_points=True)

# doublets占比
print (scrub.detected_doublet_rate_)
# 0.043789523923159525

out_df['doublet_scores'] = doublet_scores
out_df['predicted_doublets'] = predicted_doublets
out_df.to_csv(input_dir   '/doublet.txt', index=False,header=True)
out_df.head()