Python anndata.AnnData方法代码示例

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def fit_transform(self, X, **kwargs):
        """Computes the diffusion operator and the position of the cells in the
        embedding space

        Parameters
        ----------
        X : array, shape=[n_samples, n_features]
            input data with `n_samples` samples and `n_dimensions`
            dimensions. Accepted data types: `numpy.ndarray`,
            `scipy.sparse.spmatrix`, `pd.DataFrame`, `anndata.AnnData` If
            `knn_dist` is 'precomputed', `data` should be a n_samples x
            n_samples distance or affinity matrix

        kwargs : further arguments for `PHATE.transform()`
            Keyword arguments as specified in :func:`~phate.PHATE.transform`

        Returns
        -------
        embedding : array, shape=[n_samples, n_dimensions]
            The cells embedded in a lower dimensional space using PHATE
        """
        with _logger.task("PHATE"):
            self.fit(X)
            embedding = self.transform(**kwargs)
        return embedding 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def test_log1p(tmp_path):
    A = np.random.rand(200, 10)
    A_l = np.log1p(A)
    ad = AnnData(A)
    ad2 = AnnData(A)
    ad3 = AnnData(A)
    ad3.filename = tmp_path / 'test.h5ad'
    sc.pp.log1p(ad)
    assert np.allclose(ad.X, A_l)
    sc.pp.log1p(ad2, chunked=True)
    assert np.allclose(ad2.X, ad.X)
    sc.pp.log1p(ad3, chunked=True)
    assert np.allclose(ad3.X, ad.X)

    # Test base
    ad4 = AnnData(A)
    sc.pp.log1p(ad4, base=2)
    assert np.allclose(ad4.X, A_l/np.log(2)) 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def test_normalize_per_cell():
    adata = AnnData(
        np.array([[1, 0], [3, 0], [5, 6]]))
    sc.pp.normalize_per_cell(adata, counts_per_cell_after=1,
                             key_n_counts='n_counts2')
    assert adata.X.sum(axis=1).tolist() == [1., 1., 1.]
    # now with copy option
    adata = AnnData(
        np.array([[1, 0], [3, 0], [5, 6]]))
    # note that sc.pp.normalize_per_cell is also used in
    # pl.highest_expr_genes with parameter counts_per_cell_after=100
    adata_copy = sc.pp.normalize_per_cell(
        adata, counts_per_cell_after=1, copy=True)
    assert adata_copy.X.sum(axis=1).tolist() == [1., 1., 1.]
    # now sparse
    adata = AnnData(
        np.array([[1, 0], [3, 0], [5, 6]]))
    adata_sparse = AnnData(
        sp.csr_matrix([[1, 0], [3, 0], [5, 6]]))
    sc.pp.normalize_per_cell(adata)
    sc.pp.normalize_per_cell(adata_sparse)
    assert adata.X.sum(axis=1).tolist() == adata_sparse.X.sum(
        axis=1).A1.tolist() 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def test_regress_out_ordinal():
    from scipy.sparse import random
    adata = AnnData(random(1000, 100, density=0.6, format='csr'))
    adata.obs['percent_mito'] = np.random.rand(adata.X.shape[0])
    adata.obs['n_counts'] = adata.X.sum(axis=1)

    # results using only one processor
    single = sc.pp.regress_out(
        adata, keys=['n_counts', 'percent_mito'], n_jobs=1, copy=True)
    assert adata.X.shape == single.X.shape

    # results using 8 processors
    multi = sc.pp.regress_out(
        adata, keys=['n_counts', 'percent_mito'], n_jobs=8, copy=True)

    np.testing.assert_array_equal(single.X, multi.X) 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def test_scvi():
    n_samples = 4
    n_genes = 7
    batch1 = np.random.randint(1, 5, size=(n_samples, n_genes))
    batch2 = np.random.randint(1, 5, size=(n_samples, n_genes))
    ad1 = AnnData(batch1)
    ad2 = AnnData(batch2)
    adata = ad1.concatenate(ad2, batch_categories=['test1', 'test2'])
    n_latent = 30
    sce.pp.scvi(
        adata,
        use_cuda=False,
        n_epochs=1,
        n_latent=n_latent,
        return_posterior=True,
        batch_key='batch',
        model_kwargs={'reconstruction_loss': 'nb'},
    )
    assert adata.obsm['X_scvi'].shape == (n_samples * 2, n_latent)
    assert adata.obsm['X_scvi_denoised'].shape == adata.shape
    assert adata.obsm['X_scvi_sample_rate'].shape == adata.shape 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def _check_array_function_arguments(**kwargs):
    """Checks for invalid arguments when an array is passed.

    Helper for functions that work on either AnnData objects or array-likes.
    """
    # TODO: Figure out a better solution for documenting dispatched functions
    invalid_args = [k for k, v in kwargs.items() if v is not None]
    if len(invalid_args) > 0:
        raise TypeError(
            f"Arguments {invalid_args} are only valid if an AnnData object is passed."
        )


# --------------------------------------------------------------------------------
# Graph stuff
# -------------------------------------------------------------------------------- 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def paga_degrees(adata: AnnData) -> List[int]:
    """Compute the degree of each node in the abstracted graph.

    Parameters
    ----------
    adata
        Annotated data matrix.

    Returns
    -------
    List of degrees for each node.
    """
    import networkx as nx
    g = nx.Graph(adata.uns['paga']['connectivities'])
    degrees = [d for _, d in g.degree(weight='weight')]
    return degrees 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def paga_expression_entropies(adata) -> List[float]:
    """Compute the median expression entropy for each node-group.

    Parameters
    ----------
    adata : AnnData
        Annotated data matrix.

    Returns
    -------
    Entropies of median expressions for each node.
    """
    from scipy.stats import entropy
    groups_order, groups_masks = _utils.select_groups(
        adata, key=adata.uns['paga']['groups']
    )
    entropies = []
    for mask in groups_masks:
        X_mask = adata.X[mask].todense()
        x_median = np.nanmedian(X_mask, axis=1,overwrite_input=True)
        x_probs = (x_median - np.nanmin(x_median)) / (np.nanmax(x_median) - np.nanmin(x_median))
        entropies.append(entropy(x_probs))
    return entropies 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def burczynski06() -> AnnData:
    """\
    Bulk data with conditions ulcerative colitis (UC) and Crohn's disease (CD).

    The study assesses transcriptional profiles in peripheral blood mononuclear
    cells from 42 healthy individuals, 59 CD patients, and 26 UC patients by
    hybridization to microarrays interrogating more than 22,000 sequences.

    Reference
    ---------
    Burczynski et al., "Molecular classification of Crohn's disease and
    ulcerative colitis patients using transcriptional profiles in peripheral
    blood mononuclear cells"
    J Mol Diagn 8, 51 (2006). PMID:16436634.
    """
    filename = settings.datasetdir / 'burczynski06/GDS1615_full.soft.gz'
    url = 'ftp://ftp.ncbi.nlm.nih.gov/geo/datasets/GDS1nnn/GDS1615/soft/GDS1615_full.soft.gz'
    adata = read(filename, backup_url=url)
    return adata 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def toggleswitch() -> AnnData:
    """\
    Simulated toggleswitch.

    Data obtained simulating a simple toggleswitch [Gardner00]_

    Simulate via :func:`~scanpy.tl.sim`.

    Returns
    -------
    Annotated data matrix.
    """
    filename = HERE / 'toggleswitch.txt'
    adata = read(filename, first_column_names=True)
    adata.uns['iroot'] = 0
    return adata 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def pbmc68k_reduced() -> AnnData:
    """\
    Subsampled and processed 68k PBMCs.

    10x PBMC 68k dataset from
    https://support.10xgenomics.com/single-cell-gene-expression/datasets

    The original PBMC 68k dataset was preprocessed using scanpy and was saved
    keeping only 724 cells and 221 highly variable genes.

    The saved file contains the annotation of cell types (key: `'bulk_labels'`),
    UMAP coordinates, louvain clustering and gene rankings based on the
    `bulk_labels`.

    Returns
    -------
    Annotated data matrix.
    """

    filename = HERE / '10x_pbmc68k_reduced.h5ad'
    with warnings.catch_warnings():
        warnings.filterwarnings("ignore", category=FutureWarning, module="anndata")
        return read(filename) 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def _get_plot_data(data, ndim=None):
    """Get plot data out of an input object

    Parameters
    ----------
    data : array-like, `phate.PHATE` or `scanpy.AnnData`
    ndim : int, optional (default: None)
        Minimum number of dimensions
    """
    out = data
    if isinstance(data, PHATE):
        out = data.transform()
    else:
        try:
            if isinstance(data, anndata.AnnData):
                try:
                    out = data.obsm["X_phate"]
                except KeyError:
                    raise RuntimeError(
                        "data.obsm['X_phate'] not found. "
                        "Please run `sc.tl.phate(adata)` before plotting."
                    )
        except NameError:
            # anndata not installed
            pass
    if ndim is not None and out[0].shape[0] < ndim:
        if isinstance(data, PHATE):
            data.set_params(n_components=ndim)
            out = data.transform()
        else:
            raise ValueError(
                "Expected at least {}-dimensional data, got {}".format(
                    ndim, out[0].shape[0]
                )
            )
    return out 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def test_simple():
    tree_data, tree_clusters = phate.tree.gen_dla(n_branch=3)
    phate_operator = phate.PHATE(knn=15, t=100, verbose=False)
    tree_phate = phate_operator.fit_transform(tree_data)
    assert tree_phate.shape == (tree_data.shape[0], 2)
    clusters = phate.cluster.kmeans(phate_operator, n_clusters='auto')
    assert np.issubdtype(clusters.dtype, np.signedinteger)
    assert len(np.unique(clusters)) >= 2
    assert len(clusters.shape) == 1
    assert len(clusters) == tree_data.shape[0]
    clusters = phate.cluster.kmeans(phate_operator, n_clusters=3)
    assert np.issubdtype(clusters.dtype, np.signedinteger)
    assert len(np.unique(clusters)) == 3
    assert len(clusters.shape) == 1
    assert len(clusters) == tree_data.shape[0]
    phate_operator.fit(phate_operator.graph)
    G = graphtools.Graph(
        phate_operator.graph.kernel,
        precomputed="affinity",
        use_pygsp=True,
        verbose=False,
    )
    phate_operator.fit(G)
    G = pygsp.graphs.Graph(G.W)
    phate_operator.fit(G)
    phate_operator.fit(anndata.AnnData(tree_data))
    with assert_raises_message(TypeError, "Expected phate_op to be of type PHATE. Got 1"):
        phate.cluster.kmeans(1) 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def integrate_scanpy(adatas, **kwargs):
    """Integrate a list of `scanpy.api.AnnData`.

    Parameters
    ----------
    adatas : `list` of `scanpy.api.AnnData`
        Data sets to integrate.
    kwargs : `dict`
        See documentation for the `integrate()` method for a full list of
        parameters to use for batch correction.

    Returns
    -------
    integrated
        Returns a list of `np.ndarray` with integrated low-dimensional
        embeddings.
    """
    datasets_dimred, genes = integrate(
        [adata.X for adata in adatas],
        [adata.var_names.values for adata in adatas],
        **kwargs
    )

    return datasets_dimred

# Visualize a scatter plot with cluster labels in the
# `cluster' variable. 

# 需要导入模块: import anndata [as 别名]
# 或者: from anndata import AnnData [as 别名]
def test_init(self):
        data = np.random.randint(1, 5, size=(3, 7))
        ad = anndata.AnnData(data)
        dataset = AnnDatasetFromAnnData(ad)
        self.assertEqual(3, dataset.nb_cells)
        self.assertEqual(7, dataset.nb_genes)