test10 针对蛋白质鉴定列表 进行PCA分析

一、准备文件：

1、下机文件

蛋白质鉴定列表.xlsx

三种格式：DIA、labelFree、TMT

• TMT 文件格式

image.png

• labelFree 文件格式

  
  image.png

• DIA 文件格式

  
  image.png

2、sample.txt

sample  label   sib group
CHOL_1  CHOL_1  1   CHOL
CHOL_2  CHOL_2  2   CHOL
CHOL_3  CHOL_3  3   CHOL
Ctrl_1  Ctrl_1  1   Ctrl
Ctrl_2  Ctrl_2  2   Ctrl
Ctrl_3  Ctrl_3  3   Ctrl

二、脚本

#! /usr/bin/env python
# _*_ coding: utf-8 _*_
#script for DIA/labelFree/TMT PCA
# eg:  python3 pca_main.py 蛋白质鉴定列表.xlsx sample.txt

import pandas as pd
import re
import sys
import os

if __name__ == "__main__":
    if len(sys.argv) != 3:
        print("usage: python pca_main.py 蛋白质鉴定列表.xlsx sample.txt ")
        sys.exit()

    # file = "E:/Script/python/test10_pca/蛋白质鉴定列表DIA.xlsx"
    file = sys.argv[1]
    out = "pca.txt"

    df = pd.read_excel(file, sheet_name=0)
    columns = df.columns.values.tolist()
    # print(columns)

    cluster_col = ["Accession"]
    for i in columns:
        if "raw.PG.Quantity" in i:
            col_Acc = [str(i).split(";")[0] for i in df["PG.ProteinAccessions"]]
            df["Accession"] = col_Acc
            cluster_col.append(i)
            df1 = df.loc[:, cluster_col]
            df1.columns = df1.columns.str.replace(".raw.PG.Quantity", "")
            df1.columns = [re.sub("\[\d+\]", "", v) for v in df1.columns]
            df1.columns = [re.sub("\s+$", "", v) for v in df1.columns]
            df1.columns = [re.sub("^\s+", "", v) for v in df1.columns]   #替换空格

        elif "LFQ intensity" in i:
            df["Accession"] = df["Protein IDs"]
            cluster_col.append(i)
            df1 = df.loc[:, cluster_col]
            df1.columns = df1.columns.str.replace("LFQ intensity ", "")
        elif "Abundances" in i:
            cluster_col.append(i)
            df1 = df.loc[:, cluster_col]
            df1.columns = df1.columns.str.replace("Abundances ", "")

    df1.set_index("Accession", inplace=True)
    df1 = df1.dropna(how='all')
    nsmallest = df1.stack().min()
    df1 = df1.fillna(value=float(nsmallest))
    df1.reset_index(level=0, inplace=True)
    print(type(df1))
    df1.to_csv(out, sep="\t", index=False)


    command1 = "Rscript /xtt/PCA/bin/PCA.R -m {0} -i pca.txt -o pna.png".format(sys.argv[2])
    command2 = "Rscript /xtt/PCA/bin/PCA.R -m {0} -i pca.txt -o Principal_Component_Analysis.pdf".format(sys.argv[2])
    os.system(command1)
    os.system(command2)

三、结果文件

├── pca.txt
├── pna.png
├── Principal_Component_Analysis.pdf