基因组注释流程

news2025/2/24 2:21:56

一边学习，一边总结，一边分享！

详细教程请访问：
组学分析流程

本期分析流程

Hisat2-Samtools
Trinity_GG_denovo
PASA

…

本期教程文章

题目：Genomic insights into local adaptation and future climate-induced vulnerability of a keystone forest tree in East Asia

Hisat2-samtools分析流程

#!/bin/bash

genome=$1
index=${genome%.*}
rna_1_fq=`cat $2|grep 1P|sed ":a;N;s/\n/,/g;ta"` #1.fq path list
rna_2_fq=`cat $2|grep 2P|sed ":a;N;s/\n/,/g;ta"` #2.fq path list

#echo $index
hisat2-build -p 20 $genome $index

hisat2 -x $index \
           -1 $rna_1_fq\
           -2 $rna_2_fq\
           --threads 20 \
           --min-intronlen 20 \
           --max-intronlen 20000 \
           --dta \
           --score-min L,0.0,-0.4 \
           -S ${index}.sam


samtools sort -@ 20 \
                  -o ${index}.sorted.bam \
                      -O BAM \
                ${index}.sam

PSSA_align

#!/bin/bash

export PATH="$PATH:/usr_storage/jcf/.conda/envs/PASA"
source  /pub_storage2/new_PASA/.bashrc

#cat $Trinity_GG $Trinity_denovo >transcripts.fasta #
transcripts_fasta="$1" # transcripts.fasta generated from merging fasta file of Trinity denovo and Trinity genome guided mode

#perl -e 'while(<>) { print "$1\n" if />(\S+)/ }' Trinity.fasta >tdn.accs #
denovo_transcript_id="$2" 
alignAssembly_config="$3"
genome="$4" #reference fasta file



seqclean $transcripts_fasta \
	     -v /pub_storage2/PASA/UniVec
		 

Launch_PASA_pipeline.pl -c $alignAssembly_config \
					    -C -R -T \
						-g $genome \ 
						-t $transcripts_fasta.clean \
						-u ${transcripts_fasta} \
						--ALIGNERS gmap,blat \
						--CPU 8 \ 
						--TDN $denovo_transcript_id

Trinity GG denovo

#!/bin/bash

#conda activate trinity

export PATH="$PATH:/usr_storage/jcf/.conda/envs/trinity"

rna_1_fq="cat $1|sed ":a;N;s/\n/,/g;ta"" #1.fq path list 
rna_2_fq="cat $2|sed ":a;N;s/\n/,/g;ta"" #2.fq path list
bam="$3"  #sorted.bam from hisat
out=${bam%.*}


Trinity --left $rna_1_fq \
	    --right $rna_2_fq \
		--seqType fq  \
		--max_memory 100G \
		--no_normalize_reads \
		--CPU 20 \
		--bflyCalculateCPU  \
		--output trinity_denovo_$out
		
Trinity --genome_guided_bam $bam  \
		--genome_guided_max_intron 10000 \
		--max_memory 100G \
		--no_normalize_reads \
		--CPU 20 \
		--bflyCalculateCPU\
		--output trinity_GG_$out

ab homo

#!/bin/bash

export PATH="$PATH:/usr_storage/jcf/.conda/envs/BUSCO"
source /usr_storage/jcf/geta-user204/.bashrc


rna_1_fq="cat $1|sed ":a;N;s/\n/,/g;ta"" #1.fq path list 
rna_2_fq="cat $2|sed ":a;N;s/\n/,/g;ta"" #2.fq path list
genome="$3" #genome fasta file 
conf="$4" #small genome conf.txt of geta pipepline setting as default parameters
out=${genome%.*}
homo_pro="$5"

geta.pl \
	--RM_species Embryophyta\
	--out_prefix `pwd`/$out \
	--config $conf \
	--cpu 20 \
	--protein $homo_pro\
	-genome $genome \
	-1 $rna_1_fq \
	-2 $rna_2_fq \
	--augustus_species $out

Evm

#!/bin/bash

export PATH="/usr_storage/xyf/jcf/genewise/EVM/EVidenceModeler-1.1.1/EvmUtils/:$PATH"

genome="$1" #genome fasta file 
augustus_gff3="$2" #gff3 generated from augutus 
genewise_gff3="$3" #gff3 generated from tblastn and genewise
pasa_align_gff3="$4" #gff3 generated from PASA 
repeat_gff3="$5" #repeat gff3 generated from repeatemasker
partition="$6" #partition path for evm



partition_EVM_inputs.pl \
		--genome $genome\
		--gene_predictions $augustus_gff3 \
		--protein_alignments $genewise_gff3 \
		--transcript_alignments $pasa_align_gff3 \
		--repeats $repeat_gff3 \
		--segmentSize 5000000 \
		--overlapSize 10000 \
		--partition_listing $partition
		
write_EVM_commands.pl \
		--genome $genome \
		--gene_predictions $augustus_gff3 \
		--protein_alignments $genewise_gff3 \
		--transcript_alignments $pasa_align_gff3 \
		--repeats $repeat_gff3 \
		--output_file_name evm.out \
		--weights $weight >command.list
		
ParaFly -c command.list -CPU 32 

recombine_EVM_partial_outputs.pl \
		--partitions $partition \
		--output_file_name evm.out 
		
convert_EVM_outputs_to_GFF3.pl \
		--partitions $partition \
		--output_file_name evm.out \
		--genome  $genome 

cat */evm.out.gff3 >evm.out.gff3

PASA update

#!/bin/bash


export PATH="$PATH:/usr_storage/jcf/.conda/envs/PASA "
source  /pub_storage2/new_PASA/.bashrc

genome="$1" #genome fasta file
annotation_conf="$2" #pasa annotation compare conf 
transcripts_fasta="$3" #transcripts_fasta file for PASA seqclean step
gff3="$4" #gff3 for PASA updata


Launch_PASA_pipeline.pl \
		-c $annotation_conf\
		-A -T -L \
		-g $genome\
		-t ${transcripts_fasta}.clean \
		-u $transcripts_fasta \
		--annots $gff3

这里只是提供了各个分析流程的脚本，对于初学者来说是比较有好的。我们在转录组上游分析教程[零基础]中提供了详细转录组上游分析的参数，对于初学者来说是比较友好的。