下载mature.fa文件

1.打开miRbase网站：miRBase - Downloads
2.查看mature.fa文件，发现里面包含很多物种的miRNA序列，人的miRNA序列是以hsa开头，按照这个特征提取人的miRNA序列

使用R语言从mature.fa提取人的miRNA序列

library(tidyverse)
library(dplyr)
library(Biostrings)

data = read.delim("mature.fa", header = F)
View(data)

data$V1[seq(2,length(data$V1),by = 2)]

df = data.frame("miRNA" = data$V1[seq(1,length(data$V1),by = 2)],
                "sequence" = data$V1[seq(2,length(data$V1),by = 2)])
df = subset(df, miRNA %in% grep("^>hsa-", df$miRNA, value = T))
head(df)
fasta_content = paste(df$miRNA,"\n",df$sequence,"\n")
writeLines(fasta_content, "human_miRNA.fasta")

使用targetscan软件预测miRNA的靶基因

进行这一步操作时，需要获取到miRNA的2-9个核酸序列，可以通过任何方式获取这段序列，闲来无事用C语言写了一个脚本来获取这段序列。
输出的文件为：human_miRNA_seed.fasta

#include <stdio.h>
#include <string.h>

struct targetscan
{
    char miRNA[1024];
    char sequence[1024];
    int ID;
} data;

int main(void)
{
    FILE *res_file;
    FILE *new_file;
    char line[1024];
    int line_number = 0;

    // 修改文件打开方式为 "rt"（读取文本文件）
    if ((res_file = fopen("human_miRNA.fasta", "rt")) == NULL)
    {
        printf("The file is not exist.\n");
        return 1;
    }

    // 修改文件打开方式为 "wt"（写入文本文件）
    if ((new_file = fopen("human_miRNA_seed.fasta", "wt")) == NULL)
    {
        printf("The file is not exist.\n");
        // 如果打开失败，关闭已经打开的文件
        fclose(res_file);
        return 1;
    }
    fprintf(new_file, "miRNA\tsequence\tID\n");
    while (fgets(line, sizeof(line), res_file))
    {
        if (line_number % 2 == 0)
        {
            sscanf(line, "%s", data.miRNA);
        }
        else
        {
            // 复制第二个到第九个字符到 data.sequence
            strncpy(data.sequence, line + 1, 8);
            data.sequence[8] = '\0';  // 手动添加字符串结束符
            data.ID = 9606;

            // 输出到新文件
            fprintf(new_file, "%s\t%s\t%d\n", data.miRNA, data.sequence,data.ID);
        }

        line_number++;
    }

    // 关闭文件
    fclose(res_file);
    fclose(new_file);

    return 0;
}