问删除重复的列值，并根据pandas中的条件选择保留行

EN

import pandas as pd

#NOTE: i've only created a dataframe with 6 columns, but the code still applies to your dataframe of 13 columns
#data
d = {'COL1': ['APE.1:8-9(+):Canis_lups', 'APE.1:8-9(+):Canis_lups', 'APE.1:8-9(+):Canis_lups', 'APZ.1:1-1(-):Felis_catus', 'OKI:3946-7231(-):Ratus', 'OKI:3946-7231(-):Ratus'],
 'COL2': ['SEQ1', 'YP_SEQ1', 'SEQ1', 'SEQ1', 'SEQ3', 'XP_SEQ3'],
 'COL3': [0.171, 0.171, 0.20, 0.184, 0.185, 0.185],
 'COL4': [243, 243, 248, 184, 203, 203],
 'COL5': [0, 0, 1, 0, 0, 0],
 'COL6': [436, 436, 436, 61, 388, 388]}

#create data frame
df = pd.DataFrame(data = d)

#list of substrings
prefix_list =['AC_','NC_',"YP_"]
#list of columns to group
groupingColumns = [c for c in df if c is not 'COL2']
#create check column
df['prefix_check'] = 0
#flag the check column with 1 if substrings in the list appear in column 2
for item in prefix_list:
    df['prefix_check'] = df['COL2'].apply(lambda x: 1 if (df['prefix_check'] > 0).any() else (1 if item in x else 0))
#sort dataframe (asc=False)
df = df.sort_values(by=df.columns.tolist(), ascending=False)
#drop duplicates based on other columns and keep first value (this will keep the one where the flag check is 1)
output = df.drop_duplicates(subset=groupingColumns, keep='first').reset_index(drop = True)
#remove check column
output = output.drop(['prefix_check'], axis=1)

print(output)

                       COL1     COL2   COL3  COL4  COL5  COL6 ..........
0    OKI:3946-7231(-):Ratus  XP_SEQ3  0.185   203     0   388 ..........
1  APZ.1:1-1(-):Felis_catus     SEQ1  0.184   184     0    61 ..........
2   APE.1:8-9(+):Canis_lups  YP_SEQ1  0.171   243     0   436 ..........
3   APE.1:8-9(+):Canis_lups     SEQ1  0.200   248     1   436 ..........

#List
prefix_list =['AC_','NC_',"YP_"]
#collapse list into string
s="|".join(prefix_list)
#create a dtaframe with those meeting list criteria
df2=df[df.COL2.str.contains(s)]
#drop duplicates in the original datframe but excluding COL2
df.drop_duplicates(subset=df.columns.difference(['COL2']), inplace=True)
#cOMBINE THE TWO LISTS. Here I combine on two fields that should not have duplicates
df4 = (df2.set_index(['COL1','COL3']).combine_first(df.set_index(['COL1','COL3'])).reset_index())
#df4=pd.merge([df,df2], left_on='COL1',right_on='COL1', how='outer')