OmicVerse

作者，Evil Genius

今天我们分享一个分析框架，文章在

框架内容很多，基于python的全流程。

文章的第一作者也发布了一篇文章作为介绍，在我们这篇Nature Communication背后的故事（ 第一作者解读）。

OmicVerse 是一个集成的 Python 框架，旨在简化和增强bulk RNA 测序（Bulk RNA-seq）、单细胞 RNA 测序（scRNA-seq）和Spatial的分析。它通过整合多种分析工具，为用户提供一致且用户友好的界面，使得在一个编程环境中即可进行全面的转录组分析。

当然我们主要关注单细胞和空间的部分

空间部分应该是更新了的。

当然，空间主要是一些基础的分析部分。

我们重点要看一下NMF的运用(示例)。

代码语言：javascript代码运行次数：0运行复制

import scanpy as sc
import omicverse as ov
ov.plot_set()

import scvelo as scv
adata=scv.datasets.dentategyrus()

adata=ov.pp.preprocess(adata,mode='shiftlog|pearson',n_HVGs=2000,)

ov.pp.scale(adata)
ov.pp.pca(adata)

import matplotlib.pyplot as plt
from matplotlib import patheffects
fig, ax = plt.subplots(figsize=(4,4))
ov.pl.embedding(
    adata,
    basis="X_umap",
    color=['clusters'],
    frameon='small',
    title="Celltypes",
    #legend_loc='on data',
    legend_fontsize=14,
    legend_fontoutline=2,
    #size=10,
    ax=ax,
    #legend_loc=True, 
    add_outline=False, 
    #add_outline=True,
    outline_color='black',
    outline_width=1,
    ）

代码语言：javascript代码运行次数：0运行复制

import numpy as np
## Initialize the cnmf object that will be used to run analyses
cnmf_obj = ov.single.cNMF(adata,components=np.arange(5,11), n_iter=20, seed=14, num_highvar_genes=2000,
                          output_dir='example_dg/cNMF', name='dg_cNMF')
## Specify that the jobs are being distributed over a single worker (total_workers=1) and then launch that worker
cnmf_obj.factorize(worker_i=0, total_workers=2)

cnmf_objbine(skip_missing_files=True)

cnmf_obj.k_selection_plot(close_fig=False)

选择最佳的k值。

代码语言：javascript代码运行次数：0运行复制

selected_K = 7
density_threshold = 2.00

cnmf_obj.consensus(k=selected_K, 
                   density_threshold=density_threshold, 
                   show_clustering=True, 
                   close_clustergram_fig=False)

代码语言：javascript代码运行次数：0运行复制

density_threshold = 0.10

cnmf_obj.consensus(k=selected_K, 
                   density_threshold=density_threshold, 
                   show_clustering=True, 
                   close_clustergram_fig=False)

代码语言：javascript代码运行次数：0运行复制

import seaborn as sns
import matplotlib.pyplot as plt
from matplotlib import patheffects

from matplotlib import gridspec
import matplotlib.pyplot as plt

width_ratios = [0.2, 4, 0.5, 10, 1]
height_ratios = [0.2, 4]
fig = plt.figure(figsize=(sum(width_ratios), sum(height_ratios)))
gs = gridspec.GridSpec(len(height_ratios), len(width_ratios), fig,
                        0.01, 0.01, 0.98, 0.98,
                       height_ratios=height_ratios,
                       width_ratios=width_ratios,
                       wspace=0, hspace=0)
            
D = cnmf_obj.topic_dist[cnmf_obj.spectra_order, :][:, cnmf_obj.spectra_order]
dist_ax = fig.add_subplot(gs[1,1], xscale='linear', yscale='linear',
                                      xticks=[], yticks=[],xlabel='', ylabel='',
                                      frameon=True)
dist_im = dist_ax.imshow(D, interpolation='none', cmap='viridis',
                         aspect='auto', rasterized=True)

left_ax = fig.add_subplot(gs[1,0], xscale='linear', yscale='linear', xticks=[], yticks=[],
                xlabel='', ylabel='', frameon=True)
left_ax.imshow(cnmf_obj.kmeans_cluster_labels.values[cnmf_obj.spectra_order].reshape(-1, 1),
                            interpolation='none', cmap='Spectral', aspect='auto',
                            rasterized=True)

top_ax = fig.add_subplot(gs[0,1], xscale='linear', yscale='linear', xticks=[], yticks=[],
                xlabel='', ylabel='', frameon=True)
top_ax.imshow(cnmf_obj.kmeans_cluster_labels.values[cnmf_obj.spectra_order].reshape(1, -1),
                  interpolation='none', cmap='Spectral', aspect='auto',
                    rasterized=True)

cbar_gs = gridspec.GridSpecFromSubplotSpec(3, 3, subplot_spec=gs[1, 2],
                                   wspace=0, hspace=0)
cbar_ax = fig.add_subplot(cbar_gs[1,2], xscale='linear', yscale='linear',
    xlabel='', ylabel='', frameon=True, title='Euclidean\nDistance')
cbar_ax.set_title('Euclidean\nDistance',fontsize=12)
vmin = D.min().min()
vmax = D.max().max()
fig.colorbar(dist_im, cax=cbar_ax,
        ticks=np.linspace(vmin, vmax, 3),
        )
cbar_ax.set_yticklabels(cbar_ax.get_yticklabels(),fontsize=12)

代码语言：javascript代码运行次数：0运行复制

density_filter = cnmf_obj.local_density.iloc[:, 0] < density_threshold
fig, hist_ax = plt.subplots(figsize=(4,4))

#hist_ax = fig.add_subplot(hist_gs[0,0], xscale='linear', yscale='linear',
 #   xlabel='', ylabel='', frameon=True, title='Local density histogram')
hist_ax.hist(cnmf_obj.local_density.values, bins=np.linspace(0, 1, 50))
hist_ax.yaxis.tick_right()

xlim = hist_ax.get_xlim()
ylim = hist_ax.get_ylim()
if density_threshold < xlim[1]:
    hist_ax.axvline(density_threshold, linestyle='--', color='k')
    hist_ax.text(density_threshold  + 0.02, ylim[1] * 0.95, 'filtering\nthreshold\n\n', va='top')
hist_ax.set_xlim(xlim)
hist_ax.set_xlabel('Mean distance to k nearest neighbors\n\n%d/%d (%.0f%%) spectra above threshold\nwere removed prior to clustering'%(sum(~density_filter), len(density_filter), 100*(~density_filter).mean()))
hist_ax.set_title('Local density histogram')

代码语言：javascript代码运行次数：0运行复制

result_dict = cnmf_obj.load_results(K=selected_K, density_threshold=density_threshold)

cnmf_obj.get_results(adata,result_dict)

ov.pl.embedding(adata, basis='X_umap',color=result_dict['usage_norm'].columns,
           use_raw=False, ncols=3, vmin=0, vmax=1,frameon='small')

代码语言：javascript代码运行次数：0运行复制

ov.pl.embedding(
    adata,
    basis="X_umap",
    color=['cNMF_cluster'],
    frameon='small',
    #title="Celltypes",
    #legend_loc='on data',
    legend_fontsize=14,
    legend_fontoutline=2,
    #size=10,
    #legend_loc=True, 
    add_outline=False, 
    #add_outline=True,
    outline_color='black',
    outline_width=1,
    show=False,
)

代码语言：javascript代码运行次数：0运行复制

cnmf_obj.get_results_rfc(adata,result_dict,
                         use_rep='scaled|original|X_pca',
                        cNMF_threshold=0.5)
ov.pl.embedding(
    adata,
    basis="X_umap",
    color=['cNMF_cluster_rfc','cNMF_cluster_clf'],
    frameon='small',
    #title="Celltypes",
    #legend_loc='on data',
    legend_fontsize=14,
    legend_fontoutline=2,
    #size=10,
    #legend_loc=True, 
    add_outline=False, 
    #add_outline=True,
    outline_color='black',
    outline_width=1,
    show=False,
)

代码语言：javascript代码运行次数：0运行复制

plot_genes=[]
for i in result_dict['top_genes'].columns:
    plot_genes+=result_dict['top_genes'][i][:3].values.reshape(-1).tolist()

sc.pl.dotplot(adata,plot_genes,
              "cNMF_cluster", dendrogram=False,standard_scale='var',)

生活很好，有你更好