P52基因序列统计分析

P52基因序列统计分析

下载P52基因序列，采用Phython, 设置扫描窗口，窗口长度size分别设为1，2，3，每次窗口移动的步长step=1, 统计输出单个字符，紧邻两个字符，紧邻三个字符，各自的数目和所占百分比。
如：A 的个数和百分比，AA 的个数和百分比，AAA 的个数和百分比，保存在本地文件。

from Bio import SeqIO
import pandas as pd

fa_seq = SeqIO.read("p53_datasets/ncbi_dataset/data/gene.fna", "fasta").seq


def find_seq(num):
    L = 0
    R = num
    dict_count = {}
    seq_list = []
    while R < len(fa_seq):
        L += 1
        R += 1
        if fa_seq[L:R] not in dict_count:
            dict_count[fa_seq[L:R]] = 1
        else:
            dict_count[fa_seq[L:R]] += 1
    for seq_key, seq_value in dict_count.items():
        dict_seq = {}
        dict_seq['seq'] = seq_key
        dict_seq['count'] = seq_value
        dict_seq['ratio'] = round(seq_value / (len(fa_seq) - num + 1), 3)  # 保留3位小数
        seq_list.append(dict_seq)
    return seq_list


for i in range(1, 4):
    ret = find_seq(i)
    print(ret)
    pf = pd.DataFrame(ret)
    pf.to_csv('test2.csv', mode="a", index=False, header=True, encoding="utf-8")