基因测序：对wgs数据进行处理

import pandas as pd import os # ## 1.生成属-count # import os # import pandas as pd # import math # # inputpath_mngs=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-new20230629\宏基因组' # inputpath_mngs_base=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-new20230629\宏基因组\base.xls' # # inputpath_capture=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-new20230629\捕获' # inputpath_capture_base=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-new20230629\捕获\base.xls' # # # outputpath1=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-greengene\species_input' # outputpath2=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-new20230629\genus_input_count' # # df_mngs_base=pd.read_csv(inputpath_mngs_base,sep='\t') # dict_mngs_base=dict(zip(df_mngs_base['name'],df_mngs_base['base'])) # dict_mngs_base={ item: dict_mngs_base[item]/1000000000 for item in dict_mngs_base} # # print(dict_mngs_base) # df_capture_base=pd.read_csv(inputpath_capture_base,sep='\t') # dict_capture_base=dict(zip(df_capture_base['name'],df_capture_base['base'])) # dict_capture_base={ item: dict_capture_base[item]/1000000000 for item in dict_capture_base} # # ## 第一步找到共有的物种 # ## mngs数据 # list_mngs=[item for item in os.listdir(inputpath_mngs) if item.endswith('.classify.last.xls')] # list_mngs_sample=list(set([item.split('.',1)[0] for item in list_mngs])) # print(list_mngs_sample) # # list_mngs_need_species=[] # for i in list_mngs_sample: # for j in list_mngs: # if j.startswith(i): # df1=pd.read_csv(inputpath_mngs+'/'+j,sep='\t') # df1=df1[df1['G/S']=='genus'].copy() # df1.sort_values(by=['count'],ascending=False,inplace=True) # # if len(df1) <= 30 : # list_mngs_need_species+=df1['Ename'].tolist() # else: # df1=df1.iloc[0:30,:] # list_mngs_need_species += df1['Ename'].tolist() # # # # ## capture数据 # list_capture=[item for item in os.listdir(inputpath_capture) if item.endswith('.classify.last.xls')] # list_capture_sample=list(set([item.split('.',1)[0] for item in list_capture])) # print(list_capture_sample) # # list_capture_need_species=[] # for i in list_capture_sample: # for j in list_capture: # if j.startswith(i): # df1=pd.read_csv(inputpath_capture+'/'+j,sep='\t') # df1=df1[df1['G/S']=='genus'].copy() # df1.sort_values(by=['count'],ascending=False,inplace=True) # # if len(df1) <= 30 : # list_capture_need_species +=df1['Ename'].tolist() # else: # df1=df1.iloc[0:30,:] # list_capture_need_species += df1['Ename'].tolist() # # list_need_species=list(set(list_capture_need_species+list_mngs_need_species)) # # print(len(list_need_species)) # # ## 第二步生成表格 # # ## mngs数据 # list_mngs=[item for item in os.listdir(inputpath_mngs) if item.endswith('.classify.last.xls')] # list_mngs_sample=list(set([item.split('.',1)[0] for item in list_mngs])) # print(list_mngs_sample) # # # with open(outputpath1,'a') as f1: # for i in list_mngs_sample: # with open(outputpath2+'/'+i+'.mngs.input.xls','w') as f1: # f1.write('%s\t%s\t%s\t%s\n' %('x','y','value','group')) # for j in list_mngs: # if j.startswith(i): # df1=pd.read_csv(inputpath_mngs+'/'+j,sep='\t') # df1=df1[df1['Ename'].isin(list_need_species)].copy() # # df1.sort_values(by=['count'],ascending=False,inplace=True) # dict_name_to_count = dict(zip(df1['Ename'], df1['count'])) # # for item in dict_name_to_count: # # print(type(item),type(dict_name_to_count[item])) # # print(j.split('.')[1]+'\t'+item+'\t'+str(dict_name_to_count[item]/int(dict_mngs_base[item])) # f1.write('{}\t{}\t{}\t{}\n'.format(j.split('.')[1],item,str(dict_name_to_count[item]),'mNGS')) # # print(j) # # ## capture数据 # list_capture=[item for item in os.listdir(inputpath_capture) if item.endswith('.classify.last.xls')] # list_capture_sample=list(set([item.split('.',1)[0] for item in list_capture])) # print(list_capture_sample) # # # with open(outputpath1,'a') as f1 # for i in list_capture_sample: # with open(outputpath2+'/'+i+'.capture.input.xls','w') as f1: # f1.write('%s\t%s\t%s\t%s\n' %('x','y','value','group')) # for j in list_capture: # if j.startswith(i): # df1=pd.read_csv(inputpath_capture+'/'+j,sep='\t') # df1=df1[df1['Ename'].isin(list_need_species)].copy() # df1.sort_values(by=['count'],ascending=False,inplace=True) # # dict_name_to_count = dict(zip(df1['Ename'], df1['count'])) # # for item in dict_name_to_count: # f1.write('{}\t{}\t{}\t{}\n'.format(j.split('.')[1],item,str(dict_name_to_count[item]),'16S')) # # # list_merge=[item for item in os.listdir(outputpath2) if item.endswith('.xls')] # list_merge_sample=list(set([item.split('.',1)[0] for item in list_mngs])) # # list_kmer=[2,5,8,10,15,20,25,30,40] # # # for i in list_merge: # df_add = pd.DataFrame(columns=['x']) # df2=pd.read_csv(outputpath2+'/'+i,sep='\t') # for j in list_kmer: # df_part=df2[df2['x']==j].copy() # df_add=df_add.append(df_part) # df_add.to_csv(outputpath2 + '/' + i , sep='\t', index=None) # # # # for i in list_merge_sample: # df_add=pd.DataFrame(columns=['x']) # for j in list_merge: # if j.startswith(i): # df2=pd.read_csv(outputpath2+'/'+j,sep='\t') # df_add=df_add.append(df2) # df_add['value']=df_add['value'].apply(lambda x:int(x)) # # # df_add.columns=['kmer','genus','value','group'] # # df_add.sort_values(by=['kmer'],ascending=True,inplace=True) # df_add.to_csv(outputpath2+'/'+i+'.input.txt',sep='\t',index=None) # ## 2.生成属-标准化 # import os # import pandas as pd # import math # # inputpath_mngs=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-new20230629\宏基因组' # inputpath_mngs_base=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-new20230629\宏基因组\base.xls' # # inputpath_capture=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-new20230629\捕获' # inputpath_capture_base=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-new20230629\捕获\base.xls' # # # outputpath1=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图2\species_input' # outputpath2=r'C:\Users\Administrator\Desktop\自己测试捕获\20230619\第三张图-new20230629\genus_input' # # df_mngs_base=pd.read_csv(inputpath_mngs_base,sep='\t') # dict_mngs_base=dict(zip(df_mngs_base['name'],df_mngs_base['base'])) # dict_mngs_base={ item: dict_mngs_base[item]/1000000000 for item in dict_mngs_base} # # print(dict_mngs_base) # df_capture_base=pd.read_csv(inputpath_capture_base,sep='\t') # dict_capture_base=dict(zip(df_capture_base['name'],df_capture_base['base'])) # dict_capture_base={ item: dict_capture_base[item]/1000000000 for item in dict_capture_base} # # ## 第一步找到共有的物种 # ## mngs数据 # list_mngs=[item for item in os.listdir(inputpath_mngs) if item.endswith('.classify.last.xls')] # list_mngs_sample=list(set([item.split('.',1)[0] for item in list_mngs])) # print(list_mngs_sample) # # list_mngs_need_species=[] # for i in list_mngs_sample: # for j in list_mngs: # if j.startswith(i): # df1=pd.read_csv(inputpath_mngs+'/'+j,sep='\t') #