100天生信-Day11

最近一直在做湿实验，需要大量设计引物，发现primer3有python版本，可以批量设计，简直神器。

import primer3
import pandas as pd

## primer_condition
global_args = {
        'PRIMER_NUM_RETURN': 10,
        'PRIMER_OPT_SIZE': 23,
        'PRIMER_MIN_SIZE': 20,
        'PRIMER_MAX_SIZE': 25,
        'PRIMER_OPT_TM': 59.0,
        'PRIMER_MIN_TM': 57.0,
        'PRIMER_MAX_TM': 61.0,
        'PRIMER_MIN_GC': 40.0,
        'PRIMER_MAX_GC': 60.0,
        'PRIMER_THERMODYNAMIC_OLIGO_ALIGNMENT': 1,
        'PRIMER_MAX_POLY_X': 100,
        'PRIMER_INTERNAL_MAX_POLY_X': 100,
        'PRIMER_SALT_MONOVALENT': 50.0,
        'PRIMER_DNA_CONC': 50.0,
        'PRIMER_MAX_NS_ACCEPTED': 0,
        'PRIMER_MAX_SELF_ANY': 12,
        'PRIMER_MAX_SELF_END': 8,
        'PRIMER_PAIR_MAX_COMPL_ANY': 12,
        'PRIMER_PAIR_MAX_COMPL_END': 8,
        'PRIMER_PRODUCT_SIZE_RANGE': [140,160],
        'PRIMER_GC_CLAMP': 1
}

## function of read fasta
def readfasta(lines):
    seq = []
    index = []
    seqplast = ""
    numlines = 0
    for i in lines:
        if ">" in i:
            index.append(i.replace("\n", "").replace(">", ""))
            seq.append(seqplast.replace("\n", ""))                       
            seqplast = ""
            numlines += 1
        else:
            seqplast = seqplast + i.replace("\n", "")
            numlines += 1
        if numlines == len(lines):                                      
            seq.append(seqplast.replace("\n", ""))
    seq = seq[1:]                                                                  
    return index, seq

## function of split table in txt
def str_split(lines):
    list2 = lines.split()
    return list2

## read fasta
f = open('/Users/lichuanshun/Desktop/Ta_NaCl_cds_name.txt', 'r')
lines = f.readlines()
(index, seq) = readfasta(lines)
f.close()

## build table
primer_df = pd.DataFrame()

## primer finder, dic -> datafrme
for i in range(len(index)):
    seq_args = {
        'SEQUENCE_ID': str(index[i]),
        'SEQUENCE_TEMPLATE': str(seq[i]),
        'SEQUENCE_INCLUDED_REGION': [0,len(seq[i])-1],
        }
    GeneID = str(index[i])
    
    primer3_result = primer3.bindings.designPrimers(seq_args, global_args)

    ## change dic
    primer3_result_table_dict = {} 
    for j in range(primer3_result["PRIMER_PAIR_NUM_RETURNED"]):
        primer_id = str(j) 
        for key in primer3_result: 
            if primer_id in key:
                # 要将每个信息中的数字和下划线去掉
                info_tag = key.replace("_" + primer_id, "")
                # 就是把不同的引物对结果归到一起
                try:
                    primer3_result_table_dict[info_tag] 
                except:
                    primer3_result_table_dict[info_tag] = [] 
                finally:
                    primer3_result_table_dict[info_tag].append(primer3_result[key])

    df_index = []      
    
    ## append dataframe    
    for m in range(primer3_result["PRIMER_PAIR_NUM_RETURNED"]):
        df_index.append(GeneID + "_" + str(m + 1))
    primer3_result_df = pd.DataFrame(primer3_result_table_dict, index=df_index)
    primer_df = primer_df.append(primer3_result_df)

## writing csv & txt
primer_df.to_csv("/Users/lichuanshun/Desktop/primer3_result.csv")
primer_df.to_csv("/Users/lichuanshun/Desktop/primer3_result.txt", sep='\t')

## read txt
f_gtf = open('/Users/lichuanshun/Desktop/primer3_result.txt', 'r')
lines_gtf = f_gtf.readlines()
f_gtf.close()

## writing fasta of primer
fo = open('/Users/lichuanshun/Desktop/qpcr_primer.txt', 'w')
for i in range(1,len(lines_gtf)):
    fo.write('>' + str_split(lines_gtf[i])[0] + '_F' + '\n'
              + str_split(lines_gtf[i])[4] + '\n' 
              + '>' + str_split(lines_gtf[i])[0] + '_R' + '\n' 
              + str_split(lines_gtf[i])[5] + '\n' )

fo.close()

参考教程：
https://mp.weixin.qq.com/s/MA7Tw7KOwB1phZmUoEy02g
http://www.chenlianfu.com/?tag=primer