参考基因组下载和建立索引

下载的小鼠基因组
cd ~/bioreference
mkdir -p  genome/mm10  && cd genome/mm10
nohup wget http://hgdownload.cse.ucsc.edu/goldenPath/mm10/bigZips/chromFa.tar.gz  &
tar zvfx chromFa.tar.gz
cat *.fa > mm10.fa
rm chr*.fa下载hg19：
cd ~/bioreference
mkdir -p genome/hg19  && cd genome/hg19
nohup wget http://hgdownload.cse.ucsc.edu/goldenPath/hg19/bigZips/chromFa.tar.gz &
tar zvfx chromFa.tar.gz
cat *.fa > hg19.fa
rm chr*.fa下载hg38
cd ~/bioreference
mkdir -p genome/hg38  && cd genome/hg38
nohup wget http://hgdownload.cse.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz  &bowtie软件建立索引文件
cd ~/bioreference
mkdir -p index/bowtie && cd index/bowtie
nohup time ~/biosoft/bowtie/bowtie2-2.2.9/bowtie2-build  ~/reference/genome/hg19/hg19.fa  ~/reference/index/bowtie/hg19 1>hg19.bowtie_index.log 2>&1 &
nohup time ~/biosoft/bowtie/bowtie2-2.2.9/bowtie2-build  ~/reference/genome/hg38/hg38.fa  ~/reference/index/bowtie/hg38 1>hg38.bowtie_index.log 2>&1 &
nohup time ~/biosoft/bowtie/bowtie2-2.2.9/bowtie2-build  ~/reference/genome/mm10/mm10.fa  ~/reference/index/bowtie/mm10 1>mm10.bowtie_index.log 2>&1 &bwa软件建立索引文件cd ~/bioreference
mkdir -p index/bwa && cd index/bwa
nohup time bwa index   -a bwtsw   -p ~/bioreference/index/bwa/hg19  ~/bioreference/genome/hg19/hg19.fa 1>hg19.bwa_index.log 2>&1   &
nohup time bwa index   -a bwtsw   -p ~/bioreference/index/bwa/hg38  ~/bioreference/genome/hg38/hg38.fa 1>hg38.bwa_index.log 2>&1   &
nohup time bwa index   -a bwtsw   -p ~/bioreference/index/bwa/mm10  ~/bioreference/genome/mm10/mm10.fa 1>mm10.bwa_index.log 2>&1   &hisat软件建立索引文件
cd ~/reference
mkdir -p index/hisat && cd index/hisat
nohup wget ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2/data/hg19.tar.gz  &
nohup wget ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2/data/hg38.tar.gz  &
nohup wget ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2/data/grcm38.tar.gz &
tar zxvf hg19.tar.gz
tar zxvf grcm38.tar.gz
tar zxvf hg38.tar.gz

常用注释文件

# human genome reference
# md5sum hg19.fa 806c02398f5ac5da8ffd6da2d1d5d1a9
cd /media/yuansh/14THHD/reference
mkdir -p genome/hg19  && cd genome/hg19
nohup wget -c http://hgdownload.cse.ucsc.edu/goldenPath/hg19/bigZips/hg19.fa.gz &# md5sum hg38.fa 1c9dcaddfa41027f17cd8f7a82c7293b
cd /media/yuansh/14THHD/reference
mkdir -p genome/hg38  && cd genome/hg38
nohup wget http://hgdownload.cse.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz  &# bowtie
cd /media/yuansh/14THHD/reference
mkdir -p index/bowtie && cd index/bowtie
nohup time /media/yuansh/14THHD/biosoft/bowtie/bowtie2-2.2.9/bowtie2-build  /media/yuansh/14THHD/reference/genome/hg19/hg19.fa  /media/yuansh/14THHD/reference/index/bowtie/hg19 1>hg19.bowtie_index.log 2>&1 &
nohup time /media/yuansh/14THHD/biosoft/bowtie/bowtie2-2.2.9/bowtie2-build  /media/yuansh/14THHD/reference/genome/hg38/hg38.fa  /media/yuansh/14THHD/reference/index/bowtie/hg38 1>hg38.bowtie_index.log 2>&1 &
nohup time /media/yuansh/14THHD/biosoft/bowtie/bowtie2-2.2.9/bowtie2-build  /media/yuansh/14THHD/reference/genome/mm10/mm10.fa  /media/yuansh/14THHD/reference/index/bowtie/mm10 1>mm10.bowtie_index.log 2>&1 &# bwa
cd /media/yuansh/14THHD/reference
mkdir -p index/bwa && cd index/bwa
nohup time /media/yuansh/14THHD/biosoft/bwa/bwa-0.7.15/bwa index   -a bwtsw   -p /media/yuansh/14THHD/reference/index/bwa/hg19  /media/yuansh/14THHD/reference/genome/hg19/hg19.fa 1>hg19.bwa_index.log 2>&1   &
nohup time /media/yuansh/14THHD/biosoft/bwa/bwa-0.7.15/bwa index   -a bwtsw   -p /media/yuansh/14THHD/reference/index/bwa/hg38  /media/yuansh/14THHD/reference/genome/hg38/hg38.fa 1>hg38.bwa_index.log 2>&1   &
nohup time /media/yuansh/14THHD/biosoft/bwa/bwa-0.7.15/bwa index   -a bwtsw   -p /media/yuansh/14THHD/reference/index/bwa/mm10  /media/yuansh/14THHD/reference/genome/mm10/mm10.fa 1>mm10.bwa_index.log 2>&1   &# hista
cd /media/yuansh/14THHD/reference
mkdir -p index/hisat && cd index/hisat
nohup wget ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2/data/hg19.tar.gz  &
nohup wget ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2/data/hg38.tar.gz  &
tar zxvf hg19.tar.gz
tar zxvf hg38.tar.gzmkdir -p /media/yuansh/14THHD/annotation/variation/human/ExAC
cd /media/yuansh/14THHD/reference/annotation/variation/human/ExAC
## http://exac.broadinstitute.org/
## ftp://ftp.broadinstitute.org/pub/ExAC_release/current
wget ftp://ftp.broadinstitute.org/pub/ExAC_release/release1/ExAC.r1.sites.vep.vcf.gz.tbi
nohup wget ftp://ftp.broadinstitute.org/pub/ExAC_release/release1/ExAC.r1.sites.vep.vcf.gz &
wget ftp://ftp.broadinstitute.org/pub/ExAC_release/current/cnv/exac-final-cnv.gene.scores071316
wget ftp://ftp.broadinstitute.org/pub/ExAC_release/current/cnv/exac-final.autosome-1pct-sq60-qc-prot-coding.cnv.bed## https://www.ncbi.nlm.nih.gov/projects/SNP/
## ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b147_GRCh38p2/
## ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b147_GRCh37p13/mkdir -p /media/yuansh/14THHD/annotation/variation/human/dbSNP/hg19_GRCH37
cd /media/yuansh/14THHD/annotation/variation/human/dbSNP/hg19_GRCH37# md5sum vcf.gz  4f696650bbc5b34270a8a9727120a0e3
nohup wget -c ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh37p13/VCF/All_20180423.vcf.gz &
nohup wget -c ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh37p13/VCF/All_20180423.vcf.gz.md5
nohup wget -c ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh37p13/VCF/All_20180423.vcf.gz.tbi &mkdir -p /media/yuansh/14THHD/annotation/variation/human/dbSNP/hg38_GRCH38
cd /media/yuansh/14THHD/annotation/variation/human/dbSNP/hg38_GRCH38
nohup wget -c ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh38p7/VCF/All_20180418.vcf.gz &
nohup wget -c ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh38p7/VCF/All_20180418.vcf.gz.md5 &
nohup wget -c ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh38p7/VCF/All_20180418.vcf.gz.tbi &mkdir -p /media/yuansh/14THHD/annotation/variation/human/1000genomes
cd /media/yuansh/14THHD/annotation/variation/human/1000genomes
## ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/release/20130502/
nohup wget  -c -r -nd -np -k -L -p  ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/release/20130502 &
smkdir -p ~/annotation/variation/human/ESP6500
cd ~/annotation/variation/human/ESP6500
# http://evs.gs.washington.edu/EVS/
nohup wget http://evs.gs.washington.edu/evs_bulk_data/ESP6500SI-V2-SSA137.GRCh38-liftover.snps_indels.vcf.tar.gz & mkdir -p ~/annotation/variation/human/UK10K
cd ~/annotation/variation/human/UK10K
# http://www.uk10k.org/
nohup wget ftp://ngs.sanger.ac.uk/production/uk10k/UK10K_COHORT/REL-2012-06-02/UK10K_COHORT.20160215.sites.vcf.gz & mkdir -p ~/annotation/variation/human/gonl
cd ~/annotation/variation/human/gonl
## http://www.nlgenome.nl/search/
## https://molgenis26.target.rug.nl/downloads/gonl_public/variants/release5/
nohup wget  -c -r -nd -np -k -L -p  https://molgenis26.target.rug.nl/downloads/gonl_public/variants/release5  &mkdir -p ~/annotation/variation/human/omin
cd ~/annotation/variation/human/ominmkdir -p ~/annotation/variation/human/GWAS
cd ~/annotation/variation/human/GWASmkdir -p ~/annotation/variation/human/hapmap
cd ~/annotation/variation/human/hapmap
# ftp://ftp.ncbi.nlm.nih.gov/hapmap/
wget ftp://ftp.ncbi.nlm.nih.gov/hapmap/phase_3/relationships_w_pops_051208.txt
nohup wget -c -r -np -k -L -p  -nd -A.gz ftp://ftp.ncbi.nlm.nih.gov/hapmap/phase_3/hapmap3_reformatted &
# ftp://ftp.hgsc.bcm.tmc.edu/pub/data/HapMap3-ENCODE/ENCODE3/ENCODE3v1/
wget ftp://ftp.hgsc.bcm.tmc.edu/pub/data/HapMap3-ENCODE/ENCODE3/ENCODE3v1/bcm-encode3-QC.txt
wget ftp://ftp.hgsc.bcm.tmc.edu/pub/data/HapMap3-ENCODE/ENCODE3/ENCODE3v1/bcm-encode3-submission.txt.gz## 1 million single nucleotide polymorphisms (SNPs) for DNA samples from each of the three ethnic groups in Singapore – Chinese, Malays and Indians.
## The Affymetrix Genome-Wide Human SNP Array 6.0   && The Illumina Human1M single BeadChip
## http://www.statgen.nus.edu.sg/~SGVP/
## http://www.statgen.nus.edu.sg/~SGVP/singhap/files-website/samples-information.txt
# http://www.statgen.nus.edu.sg/~SGVP/singhap/files-website/genotypes/2009-01-30/QC/## Singapore Sequencing Malay Project (SSMP)
mkdir -p ~/annotation/variation/human/SSMP
cd ~/annotation/variation/human/SSMP
## http://www.statgen.nus.edu.sg/~SSMP/
## http://www.statgen.nus.edu.sg/~SSMP/download/vcf/2012_05 ## Singapore Sequencing Indian Project (SSIP)
mkdir -p ~/annotation/variation/human/SSIP
cd ~/annotation/variation/human/SSIP
# http://www.statgen.nus.edu.sg/~SSIP/
## http://www.statgen.nus.edu.sg/~SSIP/download/vcf/dataFreeze_Feb2013wget ftp://ftp.ensembl.org/pub/release-75/gtf/homo_sapiens/Homo_sapiens.GRCh37.75.gtf.gz
wget ftp://ftp.ensembl.org/pub/release-86/gtf/homo_sapiens/Homo_sapiens.GRCh38.86.chr.gtf.gz mkdir -p ~/reference/gtf/gencode
cd  ~/reference/gtf/gencode
## https://www.gencodegenes.org/releases/current.html
wget ftp://ftp.sanger.ac.uk/pub/gencode/Gencode_human/release_25/gencode.v25.2wayconspseudos.gtf.gz
wget ftp://ftp.sanger.ac.uk/pub/gencode/Gencode_human/release_25/gencode.v25.long_noncoding_RNAs.gtf.gz
wget ftp://ftp.sanger.ac.uk/pub/gencode/Gencode_human/release_25/gencode.v25.polyAs.gtf.gz
wget ftp://ftp.sanger.ac.uk/pub/gencode/Gencode_human/release_25/gencode.v25.annotation.gtf.gz
## https://www.gencodegenes.org/releases/25lift37.html
wget ftp://ftp.sanger.ac.uk/pub/gencode/Gencode_human/release_25/GRCh37_mapping/gencode.v25lift37.annotation.gtf.gz
wget ftp://ftp.sanger.ac.uk/pub/gencode/Gencode_human/release_25/GRCh37_mapping/gencode.v25lift37.metadata.HGNC.gz
wget ftp://ftp.sanger.ac.uk/pub/gencode/Gencode_human/release_25/GRCh37_mapping/gencode.v25lift37.metadata.EntrezGene.gz
wget ftp://ftp.sanger.ac.uk/pub/gencode/Gencode_human/release_25/GRCh37_mapping/gencode.v25lift37.metadata.RefSeq.gz mkdir -p ~/reference/gtf/ensembl/homo_sapiens_86
cd  ~/reference/gtf/ensembl/homo_sapiens_86
## http://asia.ensembl.org/info/data/ftp/index.htmlcd ~/reference
mkdir -p  genome/GRCh38_reference_genome  && cd genome/GRCh38_reference_genome
# http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/ nohup wget http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/GRCh38_reference_genome/GRCh38_full_analysis_set_plus_decoy_hla.fawget http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/GRCh38_reference_genome/GRCh38_full_analysis_set_plus_decoy_hla.fa.fai
wget http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/GRCh38_reference_genome/GRCh38_full_analysis_set_plus_decoy_hla.dict## ftp://ftp.broadinstitute.org/bundle/b37/
mkdir -p ~/annotation/GATK
cd ~/annotation/variation/GATK
wget ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/1000G_phase1.snps.high_confidence.b37.vcf.gz
wget ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/dbsnp_138.b37.vcf.gz
wget ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/human_g1k_v37.fasta.gz
wget ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/NA12878.HiSeq.WGS.bwa.cleaned.raw.subset.b37.sites.vcf.gz
wget ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/Mills_and_1000G_gold_standard.indels.b37.vcf.gz
wget ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/hapmap_3.3.b37.vcf.gz
wget ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/1000G_phase1.indels.b37.vcf.gz
wget ftp://gsapubftp-anonymous@ftp.broadinstitute.org/bundle/b37/1000G_phase1.indels.b37.vcf.idx.gz
gunzip 1000G_phase1.indels.b37.vcf.idx.gz
gunzip 1000G_phase1.indels.b37.vcf.gzmkdir -p  ~/institute/ENSEMBL/gtf
cd  ~/institute/ENSEMBL/gtf
wget ftp://ftp.ensembl.org/pub/release-87/gtf/homo_sapiens/Homo_sapiens.GRCh38.87.chr.gtf.gz
wget ftp://ftp.ensembl.org/pub/release-87/gtf/mus_musculus/Mus_musculus.GRCm38.87.chr.gtf.gz
wget ftp://ftp.ensembl.org/pub/release-87/gtf/danio_rerio/Danio_rerio.GRCz10.87.chr.gtf.gzcd ~/institute/TCGA/firehose
## https://gdac.broadinstitute.org/
wget http://gdac.broadinstitute.org/runs/stddata__2016_01_28/data/ACC/20160128/gdac.broadinstitute.org_ACC.Merge_snp__genome_wide_snp_6__broad_mit_edu__Level_3__segmented_scna_minus_germline_cnv_hg19__seg.Level_3.2016012800.0.0.tar.gz  -O ACC.gistic.seg.tar.gz
wget http://gdac.broadinstitute.org/runs/stddata__2016_01_28/data/ACC/20160128/gdac.broadinstitute.org_ACC.Merge_snp__genome_wide_snp_6__broad_mit_edu__Level_3__segmented_scna_hg19__seg.Level_3.2016012800.0.0.tar.gz  -O ACC.raw.seg.tar.gz
wget http://gdac.broadinstitute.org/runs/stddata__2016_01_28/data/ACC/20160128/gdac.broadinstitute.org_ACC.Mutation_Packager_Calls.Level_3.2016012800.0.0.tar.gz -O ACC.maf.tar.gz
wget http://gdac.broadinstitute.org/runs/stddata__2016_01_28/data/ACC/20160128/gdac.broadinstitute.org_ACC.Mutation_Packager_Oncotated_Calls.Level_3.2016012800.0.0.tar.gz -O ACC.maf.anno.tar.gz

SSH 传输文件

在linux下一般用scp这个命令来通过ssh传输文件。

#1、从服务器上下载文件
scp username@servername:/path/filename /var/www/local_dir（本地目录）#例如scp root@192.168.0.101:/var/www/test.txt 把192.168.0.101上的/var/www/test.txt 的文件下载到/var/www/local_dir（本地目录）#2、上传本地文件到服务器
scp /path/filename username@servername:/path  #例如scp /Users/yuansh/Desktop/1.pdf yuansh@192.168.1.153:/mnt/c/Users/yuansh/Desktop#3、从服务器下载整个目录
scp -r username@servername:/var/www/remote_dir/（远程目录） /var/www/local_dir（本地目录）#例如:scp -r yaunsh@192.168.0.153:/mnt/c/Users/yuansh/Desktop/data/U /Users/yuansh/Desktop  #4、上传目录到服务器
scp -r local_dir username@servername:remote_dir
#例如：scp -r test  root@192.168.0.101:/var/www/  把当前目录下的test目录上传到服务器的/var/www/ 目录

GATK软件安装

搜索github，自行下载最新版本

Releases · broadinstitute/gatk (github.com)

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-K4AAXwTD-1635737746121)(…/image/image-20201211204436619.png)]

右键点击复制链接然后下载

cd biosoft
proxy_on # 开启终端代理
wget -c https://github.com/broadinstitute/gatk/releases/download/4.1.9.0/gatk-4.1.9.0.zip
# 因为我安装了zsh，如果是bash的话，请使用unzip
# 如果没有unzip，则先下载
# sudo apt install unzip
x gatk-4.1.9.0.zip
mv gatk-4.1.9.0 gatk #改一下名字#添加环境变量
vim ~/.zshrc
export PATH=/home/yuansh/biosoft/gatk:$PATH
# 运行显示下面的东西则安装完毕
gatk

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-xN7mUJTM-1635737746126)(…/image/image-20201211210243279.png)]

参考基因组下载和建立索引相关推荐

菜鸟自学02：下载参考基因组及构建bowtie2索引
菜鸟自学02:下载参考基因组及构建bowtie2索引 1.下载参考基因组根据文章里的"Data deposition: The sequence reported in this pape ...
常用或特别的人类fasta参考基因组下载链接
Fasta格式是一种基于文本用于表示核酸序列或多肽序列的格式,一般情况下可在大型的国际基因组网站的ftp链接下载到,文件后缀名多为".fasta".".fa". ...
如何下载人类的参考基因组和注释文件
参考基因组概况参考基因组下载的网站主要有3个NCBI,Ensembl,UCSC,一般参考基因组的.gz压缩文件文件大小为900M以上不超过950M,解压后大于等于3G. 基因组的主要版本对应关系参 ...
[爬虫实战]利用python快速爬取NCBI中参考基因组assembly的相关信息
1.问题导向最近在做某个课题的时候,按老师的要求需要从NCBI中批量下载不同物种的参考基因组,同时收集相应参考基因组的一些组装信息,基因组非常多,导致工作量巨大,一个一个手动收集的话,既费时又费力, ...
参考基因组和注释文件下载
首先下载猪的参考基因组和注释文件我是在ensembl上下载的,链接地址ftp://ftp.ensembl.org/pub/ 选择最先版本参考基因组下载:wget ftp://ftp.ensembl.o ...
Ensembl数据库下载参考基因组（植物拟南芥）
Ensembl数据库下载参考基因组下面以植物拟南芥为例: 1.进入网站:http://plants.ensembl.org/index.html 一些常用的物种列在首页拟南芥,水稻,玉米等如果想 ...
lucene(全文搜索)_建立索引_根据关键字全文搜索_源码下载
项目结构: 效果图: 需要建立索引的文件(我们需要从中查找出关键字的文档) 建立好的所有文件搜索关键字"lucene"信息大家是不是也想亲自动手尝试一下呢... ======= ...
NGS数据分析实践：02. 参考基因组及注释库的下载
NGS数据分析实践:02. 参考基因组及注释库的下载 1. 参考基因组数据 2. 已知的SNP和Indel变异数据 3. annovar注释所需数据库的下载 4. 其他数据库系列文章: 二代测序方法 ...
RNA-seq(2):下载参考基因组及基因注释，及测序数据-学习笔记
今天学习了如题的一些操作.但是并不算成功.本来打算做到quality control,结果大部分时间卡在了下载测序数据上. 参考网站: 下载参考基因组及基因注释) 1.安装ASPERA 1)wget ...

参考基因组下载和建立索引

参考基因组下载和建立索引

常用注释文件

SSH 传输文件

GATK软件安装

参考基因组下载和建立索引相关推荐

最新文章

热门文章