1 输入文件

已经计算好的基因数量（多个文件，待统合）

genome list（所有基因组文件名）

the unique gene list of merged genome list （pan genome）

2 python3代码

思路：
读取gene genome list，去换行符，给列表
numpy.zeros(n) 制造n个0填充gene*genome二维表pandas.DataFrame(np.zeros().reshape(()), columns = , index = )构造二维表
遍历各个列表，按照基因名把数量赋给表格

#!/usr/bin/env python
import re,sys,os
import pandas as pd
import numpy as np
# 读取文件，去除换行符给新列表
# 读取需要判断PAV的gene list
with open("gene.list", 'r') as list_genes:
    list_genes = list_genes.readlines()
    list_genes_enter = []
    for each in list_genes:
        list_genes_enter.append(each.strip())

# 读取每个基因组的gene list
with open("genome.list", 'r') as list_genomes:
    list_genomes = list_genomes.readlines()
    list_genomes_enter = []
    for each in list_genomes:
        list_genomes_enter.append(each.strip())

# 构造数据框
num_row = len(list_genes_enter)
num_col = len(list_genomes_enter)
num_total = num_row * num_col
df = pd.DataFrame(np.zeros(num_total).reshape((num_row, num_col)),
                  columns = list_genomes_enter,
                  index = list_genes_enter)

# 遍历所有基因集，遍历所有行名(基因)是否存在于各基因集(CGR2)，重新给表格赋值
route="/hwfssz1/ST_HEALTH/P18Z10200N0423/liuxudong/data/Cazy_results/All_overview/overview23/All_overview_express/All_overview_express_uniq_c_awk"
for each_genome in list_genomes_enter:
    target_file = "{}/{}".format(route, each_genome)
    # 读取基因集
    with open(target_file, 'r') as target:
        target = target.readlines()
        for each_target in target:
        # 遍历基因集，基因，数字
            each_target = each_target.strip()
            each_target_gene = re.split(r'\t', each_target)[0]
            each_target_num = re.split(r'\t', each_target)[1]
            # 判断行名基因是否在基因集，并给表格元素赋值
            # loc: 字符定位表格元素
            # iloc: 数字定位
            df.loc[each_target_gene, each_genome] = each_target_num
    print("\033[32m {} DONE!\033[0m".format(each_genome))

# 表格保存
df.to_csv('table.txt', sep='\t', index = True)