omega分析实战

把xlsx表1中每个基因都和xlsx表2的里面的每个基因进行一对一的跑一下

原table

读取WK.xlsx里的第一个表，将第一列添加>作为fasta的序列名，第二列作为fasta文件的序列

import pandas as pd

def excel_to_fasta(excel_file, fasta_file):
    try:
        # 读取 Excel 文件的第一个表
        df = pd.read_excel(excel_file, sheet_name=0)

        # 打开 FASTA 文件以写入
        with open(fasta_file, 'w') as f:
            for index, row in df.iterrows():
                # 添加序列名
                f.write(f">{row[0]}\n")
                # 添加序列
                f.write(f"{row[1]}\n")

        print(f"成功将 {excel_file} 转换为 {fasta_file}")
    except FileNotFoundError:
        print(f"错误: 文件 {excel_file} 未找到!")
    except Exception as e:
        print(f"错误: 发生了一个未知错误: {e}")

if __name__ == "__main__":
    excel_file = 'WRKY_VQ.xlsx'
    fasta_file = 'output.fasta'
    excel_to_fasta(excel_file, fasta_file)

omega

omegafold VQ.fasta VQ
omegafold WRKY.fasta WRKY

多个一起运行

cat wrkyid |while read id1
do
    cat vqid|while read id2
    do
    echo "hdock WRKY/$id1.pdb VQ/$id2.pdb -out ${id1}vs${id2}.out" >>work1.sh
    done
done

nohup  parallel -j 100 <work1.sh &

结构提取：

import os
import csv


def extract_value(file_path):
    try:
        with open(file_path, 'r') as file:
            lines = file.readlines()
            if len(lines) >= 6:
                sixth_line = lines[5].split()
                if len(sixth_line) >= 7:
                    return sixth_line[6]
    except Exception as e:
        print(f"处理文件 {file_path} 时出错: {e}")
    return None


def main():
    csv_data = []
    current_dir = os.getcwd()
    for filename in os.listdir(current_dir):
        if filename.endswith('.out'):
            file_path = os.path.join(current_dir, filename)
            value = extract_value(file_path)
            if value is not None:
                csv_data.append([filename, value])

    with open('output.csv', 'w', newline='') as csvfile:
        writer = csv.writer(csvfile)
        writer.writerow(['文件名', '提取的数值'])
        writer.writerows(csv_data)


if __name__ == "__main__":
    main()
    ```