export PATH=/work/bin/maker/bin:/work/bin/RepeatMasker:/work/bin/maker/exe/snap:$PATH export ZOE=/work/bin/maker/exe/snap/Zoe cd ~/$USER/maker_tutorial/example_02_abinitio maker -CTL
(3) 修正控制文件
maker_opts.ctl
将修改后的文件放在相同的目录“example_02_abinitio” 中。
1 2 3 4 5 6 7 8 9 10 11 12 13 14
# 在 maker_opts.ctl修改以下变量，分为两部分：
## 运行RepeatMasker的配置 model_org=simple # tells RepeatMasker to mask the low complexity sequence (e.g.“AAAAAAAAAAAAA”) rmlib= # tells RepeatMasker not to mask repeat sequences like transposon elements. If you have a repeat fasta file (e.g. output fromRepeatModeler) that you need to mask, put the fasta file name next to “rmlib=” softmask=1 # tells RepeatMasker to do soft-masking which converts repeats to lower case, instead of hard-masking which converts repeats to “N”. "Soft-masking" is important so that short repeat sequences within genes can still be annotated as part of gene.
## 匹配文件pyu_est.fasta中转录序列与文件sp_protein.fasta中蛋白质序列到基因组以及推断证据支持基因模型中 genome=pyu_contig.fasta est=pyu_est.fasta protein=sp_protein.fasta # specify the fasta file names of the EST and protein sequences. In general, the EST sequence file contains the assembled transcriptome from RNA-seq data. The protein sequence file include proteins from closely related species or swiss-prot. If you have multiple protein or EST files, separate file names with ",". est2genome=1 protein2genome=1 # tell MAKER to align the transcript sequences from the pyu_est.fasta file and protein sequences from the sp_protein.fasta file to the genome. These two files are used to define evidence supported gene model. TMP=~/$USER/tmp #important for big genome, as the default /tmp is too small
mkdir snap1 cd snap1 gff3_merge -d ../pyu_rnd1.maker.output/pyu_rnd1_master_datastore_index.log maker2zff -l 50 -x 0.5 pyu_rnd1.all.gff # specify that only gene models with AED score>0.5 and protein length>50 are used for building models.
maker_gff= pyu_rnd1.all.gff est_pass=1 # use est alignment from round 1 protein_pass=1 #use protein alignment from round 1 rm_pass=1 # use repeats in the gff file snaphmm=pyu1.hmm est= # remove est file, do not run EST blast again protein= # remove protein file, do not run blast again model_org= #remove repeat mask model, so not running RM again rmlib= # not running repeat masking again repeat_protein= #not running repeat masking again est2genome=0 # do not do EST evidence based gene model protein2genome=0 # do not do protein based gene model. pred_stats=1 #report AED stats alt_splice=0 # 0: keep one isoform per gene; 1: identify splicing variants of the same gene keep_preds=1 # keep genes even without evidence support, set to 0 if no
