用primer3批量设计引物

primer3有提供批量设计引物的方法，话不多说，直接放脚本！

不过，在这之前要先保证python里有pandas、primer3-py和biopython这3个包

import primer3
import pandas as pd
import sys
from Bio.Seq import Seq

## primer_condition 可以根据实际情况进行条件设置
global_args = {
        'PRIMER_NUM_RETURN': 5,                       # 引物条数
        'PRIMER_OPT_SIZE': 21,                        # 引物最佳长度
        'PRIMER_MIN_SIZE': 18,                        # 引物最小长度
        'PRIMER_MAX_SIZE': 24,                        # 引物最大长度
        'PRIMER_OPT_TM': 60.0,                        # 引物最佳Tm值
        'PRIMER_MIN_TM': 57.0,                        # 引物最小Tm值
        'PRIMER_MAX_TM': 63.0,                        # 引物最大Tm值
        'PRIMER_MIN_GC': 40.0,                        # 引物最小GC含量
        'PRIMER_MAX_GC': 60.0,                        # 引物最大GC含量
        'PRIMER_THERMODYNAMIC_OLIGO_ALIGNMENT': 1,    # 该值设为1，则程序会使用热力学模型来计算oligos形成发夹结构和二聚体的可能性
        'PRIMER_MAX_POLY_X': 5,                       # 所允许的单核苷酸重复的次数
        'PRIMER_INTERNAL_MAX_POLY_X': 5,              # internal所允许的单核苷酸重复的次数
        'PRIMER_SALT_MONOVALENT': 50.0,               # 单价盐离子浓度(mM)
        'PRIMER_DNA_CONC': 50.0,                      # DNA产物浓度(mM)
        'PRIMER_MAX_NS_ACCEPTED': 0,                  # 引物中允许的 N 的数目
        'PRIMER_MAX_SELF_ANY': 8,                     # 引物自身进行反向互补
        'PRIMER_MAX_SELF_END': 3,                     # 引物自身进行 3' 端反向互补形成引物二聚体
        'PRIMER_PAIR_MAX_COMPL_ANY': 8,               # left primer 和 right primer 序列的反向互补
        'PRIMER_PAIR_MAX_COMPL_END': 3,               # left primer 和 right primer 进行 3' 端反向互补形成引物二聚体
        'PRIMER_PRODUCT_SIZE_RANGE': [400,600],       # 指定引物产物的长度范围
        'PRIMER_GC_CLAMP': 1                          #要求 left primer 和 right primer 的 3' 末端序列中有连续指定数目的 Gs 或 Cs 碱基。
}


## function of read fasta
def readfasta(lines):
    seq = []
    index = []
    current_seq = []
    for line in lines:
        line = line.strip()
        if line.startswith(">"):
            if current_seq:
                seq.append("".join(current_seq))
                current_seq = []

            index.append(line[1:])
        else:
            current_seq.append(line)
    if current_seq:
        seq.append("".join(current_seq))
    return index, seq
###读取序列
f = open(sys.argv[1], '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:
                info_tag = key.replace("_" + primer_id, "")
                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)

primer_df.to_csv(sys.argv[2], sep='\t')                # 引物详细文件路径

target_df = primer_df.loc[:,["PRIMER_LEFT_SEQUENCE","PRIMER_RIGHT_SEQUENCE","PRIMER_LEFT","PRIMER_RIGHT"]]
target_df['PRIMER_LEFT'] = target_df['PRIMER_LEFT'].apply(lambda x: x[0])
target_df['PRIMER_RIGHT'] = target_df['PRIMER_RIGHT'].apply(lambda x: x[0])

seq_dict = dict(zip(index, seq))
# 创建空的 DataFrame 来存储截取的序列片段和相关信息
result_df = pd.DataFrame(columns=['F', 'F-6','R', 'R-6', 'seq'])
for i, row in target_df.iterrows():
    seq_index = i.strip().split('_')[0]
    if seq_index in seq_dict:
         # 提取左引物的起始位置和右引物的终止位置
        left_start = row['PRIMER_LEFT']
        right_end = row['PRIMER_RIGHT']

        # 截取序列片段
        sequence = seq_dict[seq_index][left_start:right_end+1]
            # 计算 F, F-6, R-6 位置
        F_minus_6_position = len(row['PRIMER_LEFT_SEQUENCE']) + 6

        R_minus_6_position = len(row['PRIMER_RIGHT_SEQUENCE']) + 6
        # 反向互补序列
        R_minus_6_sequence = Seq(sequence[len(sequence)-R_minus_6_position:]).reverse_complement()
        # 将截取的序列片段和相关信息添加到结果 DataFrame 中
        result_df = result_df._append({'F': row['PRIMER_LEFT_SEQUENCE'],
                                      'F-6': sequence[:F_minus_6_position],
                                      'R':row['PRIMER_RIGHT_SEQUENCE'],
                                      'R-6': R_minus_6_sequence,
                                      'seq': sequence},ignore_index=True)
result_df.set_index(target_df.index, inplace=True)
# 打印结果 DataFrame
result_df.to_csv(sys.argv[3],sep = '\t')

运行命令为：python3 primer.py {详细引物文件} {引物文件}