统计文件test.genome.fa，中每一条contig序列的长度、GC含量（GC占所有非N序列的比例）、重复序列含量（小写字母占所有非N序列的比例）

对scaffold和contig的说明：

123456.png

以上这条序列即为scaffold序列。其包括两条以N为分割的contig序列。

python代码如下：

seq={}
contig_dic={}
#读入fasta文件
with open(r"test.genome_fa.txt") as f:
    for line in f:
        if line.startswith('>'):
            name=line.replace('>','').split()[0]
            seq[name]=''
        else:
            seq[name]+=line.replace('\n','').strip()
seq_list=list(seq.keys())
total_contig_list=[]
for i in seq_list:
    scaffold=seq[i]
    contig_list=[]
    out_Str = ''
    for i in range(0,len(scaffold)):
        if scaffold[i] !='N':
            out_Str+=scaffold[i]
        else:
            if scaffold[i+1]!='N':
                contig_list.append(out_Str)
                out_Str=''
    total_contig_list.append(contig_list)
#对同一scaffold中的contig进行命名，并将contig存放到contig_dic内
for i in range(0,len(seq_list)):
    contig_list=total_contig_list[i]
    num=1
    contig_num=len(contig_list)
    if(num<=contig_num):
        contig_dic[seq_list[i]+'_contig1']=contig_list[0]
        num=2
        if(num<=contig_num):
            contig_dic[seq_list[i]+'_contig2']=contig_list[1]
            num=3
            if (num <= contig_num):
                contig_dic[seq_list[i] + '_contig3'] = contig_list[2]
contig_list=list(contig_dic.keys())
contig_len={}
contig_CG={}
contig_repe={}
for i in contig_list:
    contig=contig_dic[i]
    contig_len[i]=len(contig)
    basic_len=len(contig)
    basic_CG_len=0
    basic_repe_len=0
    for basic in contig:
        if basic == 'C' or basic == 'G':
            basic_CG_len=basic_CG_len+1
        if basic.islower()==1:
            basic_repe_len=basic_repe_len+1
    contig_CG[i]=basic_CG_len/basic_len
    contig_repe[i]=basic_repe_len/basic_len
#根据contig长度进行排序
list_sort=sorted(contig_len.items(),key = lambda k : k[1])
index=[]
for i in list_sort:
    index.append(i[0])
index.reverse()
#输出每一条contig的长度、CG含量、重复序列含量
with open(r'contig.statisitics.txt','w') as f:
    print("contig id\tcontig length\tCG\trepetition",file=f)
    for i in index:
        print("%s\t%d\t%f\t%f" % (i,contig_len[i],contig_CG[i],contig_repe[i]),file=f)