全局比对 ：同一物种整体评价
局部比对 ：不同物种局部评价
安装软件
# Installing Bowtie1 (http://bowtie-bio.sourceforge.net/index.shtml)
#wget https://sourceforge.net/projects/bowtie-bio/files/bowtie/1.3.1/bowtie-1.3.1-linux-x86_64.zip -P ~/software
unzip ~/software/bowtie-1.3.1-linux-x86_64.zip -d /opt/biosoft/
echo 'PATH=$PATH:/opt/biosoft/bowtie-1.3.-linux-x86_64/' >> ~/.bashrc
source ~/.bashrc
# Installing bowtie2 (http://bowtie-bio.sourceforge.net/bowtie2/index.shtml)
#wget https://sourceforge.net/projects/bowtie-bio/files/bowtie2/2.5.1/bowtie2-2.5.1-linux-x86_64.zip -P ~/software
unzip ~/software/bowtie2-2.5.1-linux-x86_64.zip -d /opt/biosoft/
echo 'PATH=$PATH:/opt/biosoft/bowtie2-2.5.1-linux-x86_64/' >> ~/.bashrc
source ~/.bashrc
比对
mkdir -p /home/train/06.reads_aligment
cd /home/train/06.reads_aligment
# Bowtie2 practise
mkdir -p /home/train/06.reads_aligment/bowtie2
cd /home/train/06.reads_aligment/bowtie2
ln -s ~/00.incipient_data/data_for_genome_assembling/assemblies_of_Malassezia_sympodialis/Malassezia_sympodialis.genome_V01.fasta genome.fasta
ln -s ~/03.sequencing_data_preprocessing/V?.?.fastq ./
bowtie2-build --threads 8 genome.fasta genome #建立索引
bowtie2 -p 8 -x genome -1 V1.1.fastq -2 V1.2.fastq -S V1.sam --rg-id V1 --rg "PL:Illumina" --rg "SM:V1" 2> V1.bowtie2.log
# real 1m26.553s
# user 11m12.705s
# sys 0m13.891s
bowtie2 -p 8 -x genome -1 V2.1.fastq -2 V2.2.fastq -S V2.sam --rg-id V2 --rg "PL:Illumina" --rg "SM:V2" 2> V2.bowtie2.log
[train@MiWiFi-R3P-srv bowtie2]$ cat V2.bowtie2.log
2240991 reads; of these:
2240991 (100.00%) were paired; of these:
693164 (30.93%) aligned concordantly 0 times
1459657 (65.13%) aligned concordantly exactly 1 time
88170 (3.93%) aligned concordantly >1 times
----
693164 pairs aligned concordantly 0 times; of these:
32957 (4.75%) aligned discordantly 1 time
----
660207 pairs aligned 0 times concordantly or discordantly; of these:
1320414 mates make up the pairs; of these:
1308702 (99.11%) aligned 0 times
7570 (0.57%) aligned exactly 1 time
4142 (0.31%) aligned >1 times
70.80% overall alignment rate # mappling rate较低是由于线粒体基因组的干扰
BWA
软件下载与安装
# Installing BWA (https://sourceforge.net/projects/bio-bwa/files/)
#wget https://sourceforge.net/projects/bio-bwa/files/bwa-0.7.17.tar.bz2 -P ~/software/
tar jxf ~/software/bwa-0.7.17.tar.bz2 -C /opt/biosoft/
cd /opt/biosoft/bwa-0.7.17/
make CC='gcc -fcommon' -j 4
echo 'PATH=$PATH:/opt/biosoft/bwa-0.7.17/' >> ~/.bashrc
source ~/.bashrc
# BWA practise
mkdir -p /home/train/06.reads_aligment/bwa
cd /home/train/06.reads_aligment/bwa
ln -s ~/00.incipient_data/data_for_genome_assembling/assemblies_of_Malassezia_sympodialis/Malassezia_sympodialis.genome_V01.fasta genome.fasta
ln -s ~/03.sequencing_data_preprocessing/V?.?.fastq ./
bwa index genome.fasta -p genome
bwa mem -t 8 -R '@RG\tID:V1\tSM:V1' genome V1.1.fastq V1.2.fastq > V1.mem.sam
# real 0m23.141s
# user 2m31.3.0s
# sys 0m3.354s
bwa bwasw -t 8 genome V1.1.fastq V1.2.fastq > V1.bwasw.sam
# real 2m31.854s
# user 18m43.008s
# sys 0m30.774s
bwa aln -t 8 genome V1.1.fastq > V1.1.sai
# real 0m9.566s
# user 1m2.180s
# sys 0m0.321s
bwa aln -t 8 genome V1.2.fastq > V1.2.sai
bwa sampe genome V1.1.sai V1.2.sai V1.1.fastq V1.2.fastq > V1.backtrack.sam
# real 0m24.595s
# user 0m20.893s
# sys 0m1.737s
网友评论