python脚本过滤得到non-overlap的utr

使用该脚本对上述的结果"lin_20240321_calculating_rG4score.R"进行过滤

python 复制代码
import csv

def read_file(file_path):
    with open(file_path, 'r') as file:
        reader = csv.DictReader(file, delimiter='\t')
        return list(reader)

def process_sequences(data):
    gene_sequences = {}
    for row in data:
        gene_id = row['Id']
        start = int(row['Start'])
        end = int(row['End'])
        length=int(row['total_length'])
        score = float(row['G4Hscore'])

        if gene_id not in gene_sequences:
            gene_sequences[gene_id] = []

        gene_sequences[gene_id].append({
            'Type': row['Type'],
            'Start': start,
            'End': end,
            'Length': length,
            'Sequence': row['Sequence'],
            'Score': score
        })

    # 对每个基因的序列按分数降序排序
    for gene_id, sequences in gene_sequences.items():
        gene_sequences[gene_id] = sorted(sequences, key=lambda x: x['Score'], reverse=True)

    # 保留分数最高且不重叠的序列
    final_selection = {}
    for gene_id, sequences in gene_sequences.items():
        final_selection[gene_id] = []
        for seq in sequences:
            if not any(seq['Start'] < s['End'] and seq['End'] > s['Start'] for s in final_selection[gene_id]):
                final_selection[gene_id].append(seq)

    return final_selection

def write_results(gene_sequences, output_file):
    with open(output_file, 'w', newline='') as file:
        writer = csv.writer(file, delimiter='\t')
        writer.writerow(['Id', 'Type', 'Start', 'End', 'Total_length','Sequence', 'Score'])
        for gene_id, sequences in gene_sequences.items():
            for seq in sequences:
                writer.writerow([gene_id, seq['Type'], seq['Start'], seq['End'], seq['Length'], seq['Sequence'], seq['Score']])

# 输入和输出文件路径
#usage:python lin_filter_non-overlap_rg4.py -f1 lijinonextended_3utr_allrg4output1.fasta -f2 lijinonextended_3utr_allrg4output2.fasta
import argparse
parser = argparse.ArgumentParser(description="Advanced screening always by hash")
parser.add_argument("-f1","--file1",help="input1")
parser.add_argument("-f2","--file2",help="input2")
args = parser.parse_args()

# 读取文件
data = read_file(args.file1)
# 处理序列,保留得分最高且不重叠的序列
gene_sequences = process_sequences(data)
# 将结果写入新文件
write_results(gene_sequences, args.file2)
相关推荐
love530love35 分钟前
Windows 如何更改 ModelScope 的模型下载缓存位置?
运维·人工智能·windows·python·缓存·modelscope
悦悦子a啊1 小时前
Python之--集合
开发语言·python·编程
胡耀超1 小时前
基于Docker的GPU版本飞桨PaddleOCR部署深度指南(国内镜像)2025年7月底测试好用:从理论到实践的完整技术方案
运维·python·docker·容器·ocr·paddlepaddle·gpu
小关会打代码2 小时前
Python编程进阶知识之第四课处理数据(pandas)
python·机器学习·pandas·数据处理
WJ.Polar2 小时前
Python柱状图
python·信息可视化
一百天成为python专家3 小时前
数据可视化
开发语言·人工智能·python·机器学习·信息可视化·numpy
倒悬于世6 小时前
开源的语音合成大模型-Cosyvoice使用介绍
人工智能·python·语音识别
惜.己7 小时前
pytest中使用skip跳过某个函数
开发语言·python·测试工具·pytest
挽风8218 小时前
Excel file format cannot be determined, you must specify an engine manually.
python
叫我:松哥9 小时前
基于网络爬虫的在线医疗咨询数据爬取与医疗服务分析系统,技术采用django+朴素贝叶斯算法+boostrap+echart可视化
人工智能·爬虫·python·算法·django·数据可视化·朴素贝叶斯