exprmat 0.1.29__tar.gz → 0.1.31__tar.gz

{exprmat-0.1.29 → exprmat-0.1.31}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: exprmat
-Version: 0.1.29
+Version: 0.1.31
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
@@ -56,6 +56,7 @@ Requires-Dist: hdbscan
 Requires-Dist: graphtools
 Requires-Dist: bincsync>=0.3.0
 Requires-Dist: pybigwig
+Requires-Dist: loompy
 Requires-Dist: sphinx ; extra == 'dev'
 Requires-Dist: sphinx-rtd-theme ; extra == 'dev'
 Requires-Dist: twine ; extra == 'dev'

{exprmat-0.1.29 → exprmat-0.1.31}/exprmat/clustering/seriation.py

@@ -31,7 +31,7 @@ def seriation(Z, N, cur_index):
         return (seriation(Z, N, left) + seriation(Z, N, right))
     
 
-def serial_matrix(dist, method = "ward"):
+def serial_matrix(dist, method = "ward", seed = 42):
     '''
     Compute_serial_matrix transforms a distance matrix into a sorted distance matrix 
     according to the order implied by the hierarchical tree (dendrogram).
@@ -51,13 +51,14 @@ def serial_matrix(dist, method = "ward"):
     - res_order: The order implied by the hierarhical tree
     - res_linkage: The hierarhical tree (dendrogram)
     '''
+    np.random.seed(seed)
 
     N = len(dist)
     flat_dist_mat = squareform(dist)
-    res_linkage = linkage(flat_dist_mat, method=method,preserve_input=True)
+    res_linkage = linkage(flat_dist_mat, method = method,preserve_input = True)
     res_order = seriation(res_linkage, N, N + N-2)
     seriated_dist = np.zeros((N,N))
-    a,b = np.triu_indices(N,k=1)
+    a,b = np.triu_indices(N, k = 1)
     seriated_dist[a,b] = dist[ [res_order[i] for i in a], [res_order[j] for j in b]]
     seriated_dist[b,a] = seriated_dist[a,b]
     

{exprmat-0.1.29 → exprmat-0.1.31}/exprmat/dynamics/preprocess.py

@@ -5,7 +5,6 @@ import pandas as pd
 from scipy.sparse import issparse
 from sklearn.utils import sparsefuncs
 
-from scvelo.core import get_initial_size, set_initial_size
 from exprmat.preprocessing import normalize, log1p
 from exprmat.dynamics.generank import get_mean_var
 from exprmat.dynamics.linreg import sum, multiply

exprmat-0.1.31/exprmat/plotting/cnmf.py

@@ -0,0 +1,154 @@
+
+import matplotlib.pyplot as plt
+import pandas as pd
+
+
+def cnmf_silhoutte(adata, nmf_slot = 'cnmf', figsize = (3, 2), dpi = 100):
+
+    fig = plt.figure(figsize = figsize, dpi = dpi)
+    df = adata.uns[f'{nmf_slot}.stats']
+    fig.gca().plot(df.ncomps, df.silhoutte, color = 'k')
+
+    # fig.gca().set_ylim([-0.1, 1.1])
+    # fig.gca().set_yticks([0, 0.25, 0.5, 0.75, 1])
+    fig.gca().set_ylabel('Silhoutte score')
+
+    fig.gca().set_xlabel('NMF components')
+    fig.gca().set_xticks(df.ncomps)
+
+    for pos in ['right', 'top']:
+        fig.gca().spines[pos].set_visible(False)
+
+    return fig
+
+
+def cnmf_density(adata, k, nmf_slot = 'cnmf', figsize = (3, 2), dpi = 100):
+    
+    fig = plt.figure(figsize = figsize, dpi = dpi)
+    df = adata.uns[f'{nmf_slot}.density.{k}']
+    fig.gca().hist(df, bins = 100, color = 'k')
+
+    fig.gca().set_ylabel('Local density')
+    fig.gca().set_xlabel('Distance')
+
+    for pos in ['right', 'top']:
+        fig.gca().spines[pos].set_visible(False)
+
+    return fig
+
+
+def cnmf_distance_comps(adata, k, nmf_slot = 'cnmf', cmap = 'Reds_r', figsize = (3, 3), dpi = 100):
+    
+    fig = plt.figure(figsize = figsize, dpi = dpi)
+    df = adata.uns[f'{nmf_slot}.dist.{k}']
+    fig.gca().imshow(df, cmap = cmap)
+
+    return fig
+
+
+def cnmf_distance_usages(
+    adata, k, nmf_slot = 'cnmf', metrics = 'cosine', downsample = 0.1, method = 'single',
+    annotations = None, show_indices = False, legend_cols = 1,
+    cmap = 'Reds_r', cmap_annotations = 'Set1', figsize = (3, 3), dpi = 100
+):
+    
+    import numpy as np
+
+    df = adata.obsm[f'{nmf_slot}.{k}']
+    nrow = df.shape[0]
+    subset = np.random.choice(range(nrow), int(nrow * downsample), replace = False)
+    from exprmat.clustering.seriation import pdist
+    data = df.iloc[subset, :].copy()
+    pdistc = pdist(data, metric = metrics)
+
+    from exprmat.clustering.seriation import serial_matrix, squareform
+    serial, order, _ = serial_matrix(squareform(pdistc), method = method)
+    indices = adata.obs.iloc[subset, :].iloc[order, :].index.tolist()
+    if annotations: annotations = adata.obs.iloc[subset, :].iloc[order, :][annotations].tolist()
+
+    return matrix_plot(
+        serial, labels = indices, annotations = annotations, cmap_annotations = cmap_annotations, 
+        cmap = cmap, figsize = figsize, dpi = dpi, show_indices = show_indices,
+        legend_cols = legend_cols
+    )
+
+
+def cnmf_distance_modules(
+    adata, k, nmf_slot = 'cnmf', metrics = 'cosine', downsample = 1, method = 'complete',
+    annotations = None, cmap_annotations = 'Set1', show_indices = False,
+    cmap = 'Reds_r', figsize = (3, 3), dpi = 100, legend_cols = 1
+):
+    
+    import numpy as np
+    df = adata.varm[f'{nmf_slot}.{k}']
+    nrow = df.shape[0]
+    subset = np.random.choice(range(nrow), int(nrow * downsample), replace = False)
+    from exprmat.clustering.seriation import pdist
+    data = df[subset, :].copy()
+    pdistc = pdist(data, metric = metrics)
+
+    from exprmat.clustering.seriation import serial_matrix, squareform
+    serial, order, _ = serial_matrix(squareform(pdistc), method = method)
+    indices = adata.var.iloc[subset, :].iloc[order, :].index.tolist()
+    if annotations: annotations = adata.var.iloc[subset, :].iloc[order, :][annotations].tolist()
+
+    return matrix_plot(
+        serial, labels = indices, annotations = annotations, cmap_annotations = cmap_annotations, 
+        cmap = cmap, figsize = figsize, dpi = dpi, show_indices = show_indices, legend_cols = legend_cols
+    )
+
+
+def matrix_plot(
+    mat, labels = None, annotations = None, 
+    cmap = 'Reds_r', cmap_annotations = 'Set1',
+    show_indices = True,
+    figsize = (3, 3), dpi = 100, legend_cols = 1
+):
+    fig = plt.figure(figsize = figsize, dpi = dpi)
+    fig.gca().imshow(mat, cmap = cmap)
+    ax = fig.gca()
+    ax.set_yticks([])
+    ax.set_xticks([])
+    if labels is not None and show_indices:
+        ax.set_yticks([x for x in range(len(labels))])
+        ax.set_yticklabels(labels)
+        ax.set_xticks([])
+
+    if annotations is not None:
+        ax_annot = ax.inset_axes([1.02, 0, 0.05, 1], sharey = ax)
+        annot_u = list(set(annotations))
+        annot_n = [annot_u.index(x) for x in annotations]
+
+        from exprmat.plotting import palettes
+        colors = list(palettes.linear_palette(palettes.all_palettes[cmap_annotations][
+            list(palettes.all_palettes[cmap_annotations].keys())[-1]
+        ], len(annot_u)))
+        colormap = {x: y for x, y in zip(annot_u, colors)}
+
+        ax_annot.set_xlim(-0.5, 0.5)
+        ax_annot.set_ylim(len(annot_n) - 0.5, -0.5)
+        for idx, x in enumerate(annot_n):
+            ax_annot.fill_between([-0.5, 0.5], [idx - 0.5, idx - 0.5], [idx + 0.5, idx + 0.5], color = colormap[annot_u[x]])
+
+        # ax_annot.set_yticks([])
+        ax_annot.set_xticks([0])
+        ax_annot.set_xticklabels([''])
+        ax_annot.tick_params(axis = "y", labelleft = False, length = 0)
+        
+        from matplotlib.lines import Line2D as line2d
+
+        legend_elements = [
+            line2d([0], [0], marker = 's', color = 'w', label = alab,
+                markerfacecolor = acol, markersize = 8)
+            for alab, acol in zip(annot_u, colors)
+        ]
+
+        ax_annot.legend(
+            handles = legend_elements, 
+            bbox_to_anchor = (1.0, 1), 
+            loc = 'upper left', 
+            borderaxespad = 0, frameon = False,
+            ncol = legend_cols
+        )
+    
+    return fig

{exprmat-0.1.29 → exprmat-0.1.31}/exprmat/plotting/de.py

@@ -280,8 +280,8 @@ def marker_plot(
             adata,
             var_names,
             groupby,
-            show=show,
-            save=save,
+            show = False,
+            save = save,
             gene_symbols = gene_symbols,
             **kwds,
         )
@@ -293,8 +293,8 @@ def marker_plot(
             adata,
             var_names,
             groupby,
-            show=show,
-            save=save,
+            show = False,
+            save = save,
             gene_symbols = gene_symbols,
             **kwds,
         )

{exprmat-0.1.29 → exprmat-0.1.31}/exprmat/plotting/expression.py

@@ -58,7 +58,7 @@ def barplot(
         grid_color = 'lightgray'
     )
             
-    axes.legend().remove()
+    axes.legend(bbox_to_anchor = (1.2, 1), loc = 'upper left', borderaxespad = 0, frameon = False)
     axes.set_xlabel('')
     axes.set_ylabel(gene)
     # axes.set_xticks(selected_groups)
@@ -80,7 +80,7 @@ def barplot(
                 xtl += [ct + '\n{:.3f}'.format(w.pvalue)]
             else: xtl += [ct]
         
-        axes.set_xticks(selected_groups)
+        # axes.set_xticks(selected_groups)
         axes.set_xticklabels(xtl, rotation = 45)
     
     else:
@@ -123,6 +123,7 @@ def compare_scatter(
 
     plt.xlabel(f'Average expression in {group_x}')
     plt.ylabel(f'Average expression in {group_y}')
+    plt.plot([0, mean_x.max()], [0, mean_x.max()], linewidth = 1, linestyle = '--', color = 'red')
 
     for x, y, name in zip(mean_x, mean_y, varn):
         if name in markers:

{exprmat-0.1.29 → exprmat-0.1.31}/exprmat/preprocessing/integrate.py

@@ -1,6 +1,7 @@
 
 import anndata as ad
 import numpy as np
+from exprmat.utils import choose_layer
 from exprmat.ansi import error, warning
 
 
@@ -148,6 +149,8 @@ def harmony(
     *,
     basis: str = "pca",
     adjusted_basis: str = "harmony",
+    transform_data = False,
+    data_slot = 'X',
     **kwargs,
 ):
     """
@@ -220,16 +223,20 @@ def harmony(
     default_params.update(kwargs)
     harmony_out = harmonypy.run_harmony(X, adata.obs, key, **default_params)
     adata.obsm[adjusted_basis] = harmony_out.Z_corr.T
-    _, x_corr, _, _ = moe_correct_ridge(
-        X.T, None, None, 
-        harmony_out.R, None, 
-        harmony_out.K, None, 
-        harmony_out.Phi_moe, harmony_out.lamb
-    )
+
+    if transform_data:
+        data = choose_layer(adata, layer = data_slot)
+        _, x_corr, _, _ = moe_correct_ridge(
+            data, None, None, 
+            harmony_out.R, None, 
+            harmony_out.K, None, 
+            harmony_out.Phi_moe, harmony_out.lamb
+        )
     
-    x_corr = np.array(x_corr.T)
-    x_corr[x_corr < 0] = 0
-    adata.layers[adjusted_basis] = x_corr
+        x_corr = np.array(x_corr.T)
+        x_corr[x_corr < 0] = 0
+        adata.layers[adjusted_basis] = x_corr
+        
     return adata
 
 

{exprmat-0.1.29 → exprmat-0.1.31}/exprmat/reader/experiment.py

@@ -1103,6 +1103,9 @@ class experiment:
     def plot_rna_embedding(self, run_on_samples = False, **kwargs):
         return self.plot_for_rna(run_on_samples, st.rna_plot_embedding, **kwargs)
     
+    def plot_rna_embedding_mask(self, run_on_samples = False, **kwargs):
+        return self.plot_for_rna(run_on_samples, st.rna_plot_embedding_mask, **kwargs)
+    
     def plot_rna_embedding_atlas(self, run_on_samples = False, **kwargs):
         return self.plot_for_rna(run_on_samples, st.rna_plot_embedding_atlas, **kwargs)
 

{exprmat-0.1.29 → exprmat-0.1.31}/exprmat/reader/metadata.py

@@ -12,12 +12,22 @@ class metadata:
     ----------
 
     locations : list[str]
-        File system paths indicating directories where the 10x-like matrix files locate. The 
-        file reading scheme is default to 10x matrix files including ``matrix.mtx``, 
-        ``barcodes.tsv`` and ``features.tsv``. Appropriate compression levels and column 
-        information is guessed from file extensions and content columns of ``features.tsv`` 
-        (or ``genes.tsv``).
+        File system paths indicating directories where the data files locate.
+        The protocols and procedures on how to load the dump files in the directory is 
+        determined by `modality` and what this `location` points to. For example, 
+        when `modality` is `rna`, the program will search for 10X-compatible mtx and 
+        tsv files if a folder is provided, or h5ad/h5 files if files are specified directly.
     
+    modality : list[str]
+        What modality is in the location. Supported values are:
+        - `rna` (Single cell RNA-seq),
+        - `rna.splicing` (Supplementary spliced/unspliced counts in loom or mtx)
+        - `rna.tcr` (10X 5' TCR annotations),
+        - `atac` (Single cell ATAC-seq)
+
+    default_taxa : list[str]
+        The reference taxa of the sample.
+
     names : list[str] | None
         Sample names in the loaded experiment. If left to None, names of the folder will be 
         used. Since the folder names may duplicate, this is not forced to be unique. This might 
@@ -28,6 +38,7 @@ class metadata:
     
     groups : list[str] | None
         Experimental groupings, if not set, this column is set to uniform value '.'.
+
     
     Notes
     -----------
@@ -37,6 +48,8 @@ class metadata:
     modality, ``taxa`` for default taxa where no prefix in features is specified. other metadata 
     information is not necessary, and can be appended as specified by user, but do not set duplicate
     column names as these six.
+
+    You may load a TSV table as metadata using :py:func:`load_metadata`.
     """
 
     def __init__(
@@ -173,7 +186,7 @@ class metadata:
 
     def set_if_ends(self, key = 'sample', dest = 'group', ends = '.', value = '.'):
         '''
-        Alter the content of a column if starting with a string in the key column.
+        Alter the content of a column if ending with a string in the key column.
 
         Parameters
         ----------
@@ -200,7 +213,7 @@ class metadata:
 
     def set_if_contains(self, key = 'sample', dest = 'group', contains = '.', value = '.'):
         '''
-        Alter the content of a column if starting with a string in the key column.
+        Alter the content of a column if containing a string in the key column.
 
         Parameters
         ----------
@@ -212,7 +225,7 @@ class metadata:
             The column you may want to alter value according to the patterns in column ``key``, 
             according to the conditions given.
         
-        ends : str
+        contains : str
             Test if values is contained in the ``key``. This requires that both variables be string.
         
         value : str

{exprmat-0.1.29 → exprmat-0.1.31}/exprmat/reader/static.py

@@ -612,9 +612,13 @@ def rna_consensus_nmf(
         return_k = None, # for the first round, return statistics
         **kwargs
     )
+    
+    combs = {}
+    for ky in comb.keys():
+        combs[str(ky)] = comb[ky]
 
     stats = pd.DataFrame(stats, index = ['ncomps', 'threshold', 'silhoutte', 'error']).T
-    adata.uns[key_added] = comb
+    adata.uns[key_added] = combs
     adata.uns[f'{key_added}.stats'] = stats
     adata.uns[f'{key_added}.args'] = kwargs
 
@@ -632,7 +636,10 @@ def rna_consensus_nmf_extract_k(
     from exprmat.preprocessing import normalize
 
     kwargs.update(adata.uns[f'{nmf_slot}.args'])
-    comb = adata.uns[nmf_slot]
+    
+    comb = {}
+    for ky in adata.uns[nmf_slot].keys():
+        comb[int(ky)] = adata.uns[nmf_slot][ky]
 
     _, res = cnmf(
         adata, comb = comb,
@@ -641,6 +648,7 @@ def rna_consensus_nmf_extract_k(
     )
 
     local_density, dist, _, rf_usages, spectra_tpm, usage_coef, _ = res
+    rf_usages.columns = ['C' + str(x) for x in rf_usages.columns]
     adata.obsm[usage_added.format(k)] = rf_usages
     destindex = adata.var_names.tolist()
 
@@ -757,6 +765,16 @@ def rna_plot_embedding(adata, sample_name, **kwargs):
     return embedding(adata, sample_name = sample_name, **kwargs)
 
 
+def rna_plot_embedding_mask(adata, sample_name, color, values, **kwargs):
+    from exprmat.reduction.plot import embedding
+    if color in adata.obs.keys():
+        adata.obs['.mask'] = [x in values for x in adata.obs[color]]
+    else: error('`color` must be within adata.obs')
+    fig = embedding(adata, sample_name = sample_name, color = '.mask', **kwargs)
+    if color in adata.obs.keys(): del adata.obs['.mask']
+    return fig
+
+
 def rna_plot_embedding_atlas(adata, sample_name, **kwargs):
     from exprmat.reduction.plot import embedding_atlas
     return embedding_atlas(adata, sample_name = sample_name, **kwargs)
@@ -774,11 +792,25 @@ def rna_plot_gene_gene_regress(adata, sample_name, **kwargs):
 def rna_plot_markers(adata, sample_name, figsize, dpi, **kwargs):
     from exprmat.plotting.de import marker_plot
     pl = marker_plot(adata, sample_name = sample_name, **kwargs)
-    pl.width = figsize[0]
-    pl.height = figsize[1]
-    pl.show()
-    pl.fig.set_dpi(dpi)
-    return pl.fig
+
+    from scanpy.plotting import DotPlot, StackedViolin, MatrixPlot
+    if isinstance(pl, DotPlot) or isinstance(pl, StackedViolin) or isinstance(pl, MatrixPlot):
+        pl.width = figsize[0]
+        pl.height = figsize[1]
+        pl.show()
+        pl.fig.set_dpi(dpi)
+        return pl.fig
+    
+    else:
+        fig = pl['heatmap_ax'].figure if 'heatmap_ax' in pl.keys() else None
+        fig = pl['track_axes'][0].figure if 'track_axes' in pl.keys() else fig
+
+        if fig:
+            fig.set_dpi(dpi)
+            fig.set_figwidth(figsize[0])
+            fig.set_figheight(figsize[1])
+            return fig
+    
 
 
 def rna_plot_expression_bar(
@@ -1321,6 +1353,11 @@ def rna_plot_cnmf_distance_usages(adata, sample_name, **kwargs):
     return cnmf_distance_usages(adata, **kwargs)
 
 
+def rna_plot_cnmf_distance_modules(adata, sample_name, **kwargs):
+    from exprmat.plotting.cnmf import cnmf_distance_modules
+    return cnmf_distance_modules(adata, **kwargs)
+
+
 def atac_plot_qc(adata, sample_name, **kwargs):
     from exprmat.plotting.atac import atac_qc_metrics
     return atac_qc_metrics(adata, sample_name, **kwargs)

{exprmat-0.1.29 → exprmat-0.1.31}/pyproject.toml

@@ -18,7 +18,7 @@ description = "exprmat: Routines for expression matrices"
 readme = "readme.md"
 license = {file = "license"}
 requires-python = ">=3.9, <3.13"
-version = "0.1.29"
+version = "0.1.31"
 authors = [
     {name = "Zheng Yang", email = "xornent@outlook.com"}
 ]
@@ -81,7 +81,8 @@ dependencies = [
     'hdbscan',
     'graphtools',
     'bincsync >= 0.3.0',
-    'pyBigWig'
+    'pyBigWig',
+    'loompy'
 ]
 
 [project.optional-dependencies]

exprmat-0.1.29/exprmat/plotting/cnmf.py

@@ -1,66 +0,0 @@
-
-import matplotlib.pyplot as plt
-import pandas as pd
-
-
-def cnmf_silhoutte(adata, nmf_slot = 'cnmf', figsize = (3, 2), dpi = 100):
-
-    fig = plt.figure(figsize = figsize, dpi = dpi)
-    df = adata.uns[f'{nmf_slot}.stats']
-    fig.gca().plot(df.ncomps, df.silhoutte, color = 'k')
-
-    # fig.gca().set_ylim([-0.1, 1.1])
-    # fig.gca().set_yticks([0, 0.25, 0.5, 0.75, 1])
-    fig.gca().set_ylabel('Silhoutte score')
-
-    fig.gca().set_xlabel('NMF components')
-    fig.gca().set_xticks(df.ncomps)
-
-    for pos in ['right', 'top']:
-        fig.gca().spines[pos].set_visible(False)
-
-    return fig
-
-
-def cnmf_density(adata, k, nmf_slot = 'cnmf', figsize = (3, 2), dpi = 100):
-    
-    fig = plt.figure(figsize = figsize, dpi = dpi)
-    df = adata.uns[f'{nmf_slot}.density.{k}']
-    fig.gca().hist(df, bins = 100, color = 'k')
-
-    fig.gca().set_ylabel('Local density')
-    fig.gca().set_xlabel('Distance')
-
-    for pos in ['right', 'top']:
-        fig.gca().spines[pos].set_visible(False)
-
-    return fig
-
-
-def cnmf_distance_comps(adata, k, nmf_slot = 'cnmf', cmap = 'Reds_r', figsize = (3, 3), dpi = 100):
-    
-    fig = plt.figure(figsize = figsize, dpi = dpi)
-    df = adata.uns[f'{nmf_slot}.dist.{k}']
-    fig.gca().imshow(df, cmap = cmap)
-
-    return fig
-
-
-def cnmf_distance_usages(
-    adata, k, nmf_slot = 'cnmf', metrics = 'cosine', downsample = 0.1,
-    cmap = 'Reds_r', figsize = (3, 3), dpi = 100
-):
-    
-    import numpy as np
-    fig = plt.figure(figsize = figsize, dpi = dpi)
-    df = adata.obsm[f'{nmf_slot}.{k}']
-    nrow = df.shape[0]
-    subset = np.random.choice(range(nrow), int(nrow * downsample), replace = False)
-    from exprmat.clustering.seriation import pdist
-    pdistc = pdist(df.iloc[subset, :], metric = 'cosine')
-
-    from exprmat.clustering.seriation import serial_matrix, squareform
-    serial, _, _ = serial_matrix(squareform(pdistc), method = 'single')
-    fig.gca().imshow(serial, cmap = cmap)
-
-    return fig