一. 准备文件
首先,下载基因组注释文件abc.gff3和蛋白序列文件abc.aa;然后,进行格式转换和重命名,得到abc.gff,abc.lens,abc.pep;接着做blast,得到abc_abc.blast 文件
python 01.getgff.py abc.gff3 old.gff
python 02.gff_lens.py old.gff Ela abc.gff abc.lens
python 03.seq_newname.py abc.gff abc.aa abc.pep
diamond makedb --in abc.pep -d abc
diamond blastp -d abc -q abc.pep -o abc_abc.blast -e 1e-5 -k 5
二. 找原始染色体
根据点阵图Dotplot,找出原始染色体,整理成ancestor.txt格式,然后利用-ak命令生成染色体gff,lens,pep文件,参照基于WGDI的祖先核型成分推断
22 | 1 | 1248 | RoyalBlue | 1 |
---|---|---|---|---|
17 | 1 | 1257 | red | 1 |
... | ... | ... | ... | ... |
wgdi -d total.conf
wgdi -ak total.conf
三. 绘制核型图
依次执行以下命令:
1. wgdi -icl total.conf
2. wgdi -bi total.conf
3. wgdi -c total.conf
4. wgdi -km total.conf
5. wgdi -k total.conf
附total.conf文件实例:
[collinearity]
gff1 = abc.gff
gff2 = AEK.gff
lens1 = abc.lens
lens2 = AEK.lens
blast = abc_AEK.blast
blast_reverse = false
multiple = 1
process = 8
evalue = 1e-5
score = 100
grading = 50,40,25
mg = 25,25
pvalue = 1
repeat_number = 10
positon = order
savefile = abc_AEK.collinearity
#wgdi -icl total.conf
[blockinfo]
blast = abc_AEK.blast
gff1 = abc.gff
gff2 = AEK.gff
lens1 = abc.lens
lens2 = AEK.lens
collinearity = abc_AEK.collinearity
score = 100
evalue = 1e-5
repeat_number = 20
position = order
ks = none
ks_col = ks_NG86
savefile = abc_AEK.blockinfo.csv
#wgdi -bi total.conf
[correspondence]
blockinfo = abc_AEK.blockinfo.csv
lens1 = abc.lens
lens2 = AEK.lens
tandem = true
tandem_length = 200
pvalue = 0.2
block_length = 50
tandem_ratio = 0.5
multiple = 1
homo = -1,1
savefile = abc_AEK.blockinfo.new.csv
#wgdi -c total.conf
[karyotype_mapping]
blast = abc_AEK.blast
blast_reverse = false
gff1 = abc.gff
gff2 = AEK.gff
score = 100
evalue = 1e-5
repeat_number = 5
#ancestor_left = ancestor location file (Only one of ('left', 'top') can be reserved)
ancestor_top = AEK.ancestor.txt
the_other_lens = abc.lens
blockinfo = abc_AEK.blockinfo.new.csv
blockinfo_reverse = false
limit_length = 5
the_other_ancestor_file = abc.ancestor.txt
#wgdi -km total.conf
[karyotype]
ancestor = abc.ancestor.txt
width = 0.5
figsize = 10,6.18
savefig = abc.ancestor.pdf
#wgdi -k total.conf
[blockks]
lens1 = abc.lens
lens2 = AEK.lens
genome1_name = abc
genome2_name = AEK
blockinfo = abc_AEK.blockinfo.csv
pvalue = 0.05
tandem = true
tandem_length = 200
markersize = 1
area = -1,2
block_length = 5
figsize = 8,8
savefig = abc_bk_ks.dotplot.pdf
#wgdi -bk total.conf
[dotplot]
blast = abc_AEK.blast
gff1 = abc.gff
gff2 = AEK.gff
lens1 = abc.lens
lens2 = AEK.lens
genome1_name = abc
genome2_name = AEK
multiple = 1
score = 100
evalue = 1e-5
repeat_number = 10
position = order
blast_reverse = false
ancestor_left = abc.ancestor.txt
ancestor_top = AEK.ancestor.txt
markersize = 0.5
figsize = 10,10
savefig = abc_AEK.dotplot.pdf
#wgdi -d total.conf
[ancestral_karyotype]
gff = abc.gff
pep_file = abc.pep
ancestor = abc_AEK.ancestor.txt1
mark = Jaeuk
ancestor_gff = AEK.gff
ancestor_lens = AEK.lens
ancestor_pep = AEK.pep
ancestor_file = AEK.ancestor.txt
#wgdi -ak total.conf