一眨眼CellphoneDB都更新到v5啦：2025年3月25号发表在Nature Protocols(IF=13.1)

conda create -y -n cpdb python=3.9
conda activate cpdb
pip install cellphonedb
pip install -U ipykernel

import pandas as pd
import glob
import os

from IPython.display import HTML, display
from cellphonedb.utils import db_releases_utils

display(HTML(db_releases_utils.get_remote_database_versions_html()['db_releases_html_table']))

# -- Version of the databse
cpdb_version = 'v5.0.0'

# -- Path where the input files to generate the database are located
cpdb_target_dir = os.path.join('./cellphonedb_v500_NatProtocol/', cpdb_version)
cpdb_target_dir
# './cellphonedb_v500_NatProtocol/v5.0.0'
# 保证当前目录中有这个目录，如果没有就手动创建一个

active_TFs.tsv
DEGs_inv_trophoblast.tsv
metadata.tsv
microenvironment.tsv
normalised_log_counts.h5ad

# 导入模块
import pandas as pd
import sys
import os
pd.set_option('display.max_columns', 100)
print(sys.version)
# 3.9.22 | packaged by conda-forge | (main, Apr 14 2025, 23:35:59) 
# [GCC 13.3.0]

cpdb_file_path = 'cellphonedb_v500_NatProtocol/v5.0.0/cellphonedb.zip'
meta_file_path = 'data/metadata.tsv'
counts_file_path = 'data/normalised_log_counts.h5ad'
microenvs_file_path = 'data/microenvironment.tsv'
degs_file_path = 'data/DEGs_inv_trophoblast.tsv'
active_tf_path = 'data/active_TFs.tsv'
out_path = 'results_method3_withScore'

# 1.读取细胞注释信息，第一列为细胞barcode，第二列为所属的细胞类型
# read meta
metadata = pd.read_csv(meta_file_path, sep = '\t')
metadata.head(3)

# barcode_sample cell_type
# 0 AGCGATTAGTCTAACC-1_Pla_HDBR10917733 B_cells
# 1 ATCCGTGAGGCTAGAA-1_Pla_Camb10714918 B_cells
# 2 AGTAACCCATTAAAGG-1_Pla_HDBR10917733 B_cells

# 用type()获取对象的数据类型
type(metadata)
# 每种细胞类型里的细胞数量
metadata.cell_type.value_counts()

# 2.读取细胞表达矩阵，h5ad格式。共3312个细胞：
import anndata
adata = anndata.read_h5ad(counts_file_path)
adata

# 检查metadata的barcode与表达矩阵中的细胞id是否一致
list(adata.obs.index).sort() == list(metadata['barcode_sample']).sort()

# 3.读取亚群差异基因
deg = pd.read_csv(degs_file_path, sep = '\t')
deg.head(3)

# 4.微环境
microenv = pd.read_csv(microenvs_file_path, sep = '\t')
microenv.head(3)
microenv.groupby('microenvironment', group_keys = False)['cell_type'].apply(lambda x : list(x.value_counts().index))

# 5.活性转录因子
tf = pd.read_csv(active_tf_path, sep = '\t')
tf.head(3)

from cellphonedb.src.core.methods import cpdb_degs_analysis_method

cpdb_results = cpdb_degs_analysis_method.call(
    cpdb_file_path = cpdb_file_path,            # 必须文件: CellphoneDB 数据库压缩zip文件.
    meta_file_path = meta_file_path,            # 必须文件: tsv结尾，细胞注释文件.
    counts_file_path = counts_file_path,        # 必须文件: 标准化后的count矩阵-可以是路径,或读取进来后的anndata对象.
    degs_file_path = degs_file_path,            # 必修文件: tsv结尾，细胞亚群上调差异基因.
    counts_data = 'hgnc_symbol',                # count矩阵中的基因类型.
    active_tfs_file_path = active_tf_path,      # 可选: 细胞类型与active TFs.
    microenvs_file_path = microenvs_file_path,  # 可选(默认: None): 定义细胞微环境.
    score_interactions = True,                  # 可选: 对互作是否进行打分. 
    threshold = 0.1,                            # 过滤低表达基因：至少在多少细胞中表达%.
    result_precision = 3,                       # Sets the rounding for the mean values in significan_means.
    separator = '|',                            # 对结果中"cellA|CellB"的分隔符.
    debug = False,                              # 是否保存所有中间结果.
    output_path = out_path,                     # 输出结果路径
    output_suffix = None,                       # 输出结果文件前缀 (default: None)
    threads = 50                                # 使用线程数
    )

# 用type()获取对象的数据类型
type(cpdb_results)

# 具体的关键词
print(cpdb_results.keys())
# ['deconvoluted', 'deconvoluted_percents', 'means', 'relevant_interactions', 'significant_means', 'CellSign_active_interactions', 'CellSign_active_interactions_deconvoluted', 'interaction_scores']

# 每一个具体的结果
cpdb_results['relevant_interactions'].head(2)
cpdb_results['significant_means'].head(2)
cpdb_results['means'].head(2)
cpdb_results['deconvoluted'].head(2)
cpdb_results['interaction_scores'].head(2)
cpdb_results['CellSign_active_interactions'].head(2)

degs_analysis_CellSign_active_interactions_05_06_2025_212857.txt
degs_analysis_CellSign_active_interactions_deconvoluted_05_06_2025_212857.txt
degs_analysis_deconvoluted_05_06_2025_212857.txt
degs_analysis_deconvoluted_percents_05_06_2025_212857.txt
degs_analysis_interaction_scores_05_06_2025_212857.txt
degs_analysis_means_05_06_2025_212857.txt
degs_analysis_relevant_interactions_05_06_2025_212857.txt
degs_analysis_significant_means_05_06_2025_212857.txt