C/C++/Python讀取fasta/fastq文件

C/C++使用kseq.h，鏈接時加-lz

#include <string.h>
#include <zlib.h>
#include "kseq.h"

KSEQ_INIT(gzFile, gzread)

//readfile
int main(int argc, char *argv[])
{

    gzFile fp;
    kseq_t *ks;

    fp = gzopen(argv[1],"r");
    if(NULL == fp){
        fprintf(stderr,"Fail to open file: %s\n", argv[1]);
        return 0;
    }

    ks = kseq_init(fp);

    while( kseq_read(ks) >= 0 ){

        fprintf(stderr,"seq: %s\n", ks->seq.s);

    }

    kseq_destroy(ks);
    gzclose(fp);

    return EXIT_SUCCESS;

}

python使用SeqIO

#pip install biopython
from Bio import SeqIO

with open("./clean_total_genomic.fna",'r') as fq:
    for record in SeqIO.parse(fq,'fasta'):
        print(record.seq)

自己寫文件處理

使用fileopen，fasta尋找">"，fastq按行處理