生物信息学常见的数据下载，包括基因组，gtf，bed，注释

cd ~/reference

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



cd ~/reference

mkdir -p genome/hg38  && cd genome/hg38 

nohup wget http://hgdownload.cse.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz  &


cd ~/reference

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



cd ~/biosoft/RNA-SeQC

wget http://www.broadinstitute.org/cancer/cga/sites/default/files/data/tools/rnaseqc/ThousandReads.bam

wget http://www.broadinstitute.org/cancer/cga/sites/default/files/data/tools/rnaseqc/gencode.v7.annotation_goodContig.gtf.gz

wget http://www.broadinstitute.org/cancer/cga/sites/default/files/data/tools/rnaseqc/Homo_sapiens_assembly19.fasta.gz

wget http://www.broadinstitute.org/cancer/cga/sites/default/files/data/tools/rnaseqc/Homo_sapiens_assembly19.other.tar.gz

wget http://www.broadinstitute.org/cancer/cga/sites/default/files/data/tools/rnaseqc/gencode.v7.gc.txt

wget http://www.broadinstitute.org/cancer/cga/sites/default/files/data/tools/rnaseqc/rRNA.tar.gz


cd ~/reference

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 &


cd ~/reference

mkdir -p index/bwa && cd index/bwa 

nohup time ~/biosoft/bwa/bwa-0.7.15/bwa index   -a bwtsw   -p ~/reference/index/bwa/hg19  ~/reference/genome/hg19/hg19.fa 1>hg19.bwa_index.log 2>&1   &

nohup time ~/biosoft/bwa/bwa-0.7.15/bwa index   -a bwtsw   -p ~/reference/index/bwa/hg38  ~/reference/genome/hg38/hg38.fa 1>hg38.bwa_index.log 2>&1   &

nohup time ~/biosoft/bwa/bwa-0.7.15/bwa index   -a bwtsw   -p ~/reference/index/bwa/mm10  ~/reference/genome/mm10/mm10.fa 1>mm10.bwa_index.log 2>&1   &


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 &

nohup wget ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2/data/mm10.tar.gz  &

tar zxvf hg19.tar.gz

tar zxvf grcm38.tar.gz

tar zxvf hg38.tar.gz

tar zxvf mm10.tar.gz



mkdir -p ~/annotation/variation/human/ExAC

cd ~/annotation/variation/human/ExAC

## http://exac.broadinstitute.org/

## ftp://ftp.broadinstitute.org/pub/ExAC_release/current

wget ftp://ftp.broadinstitute.org/pub/ExAC_release/current/ExAC.r0.3.1.sites.vep.vcf.gz.tbi

nohup wget ftp://ftp.broadinstitute.org/pub/ExAC_release/current/ExAC.r0.3.1.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



mkdir -p ~/annotation/variation/human/dbSNP

cd ~/annotation/variation/human/dbSNP

## 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/

nohup wget ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b147_GRCh37p13/VCF/All_20160601.vcf.gz &

wget ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b147_GRCh37p13/VCF/All_20160601.vcf.gz.tbi



mkdir -p ~/annotation/variation/human/1000genomes

cd ~/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 &


mkdir -p ~/annotation/variation/human/cosmic

cd ~/annotation/variation/human/cosmic

## we need to register before we can download this file.


mkdir -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/omin


mkdir -p ~/annotation/variation/human/GWAS

cd ~/annotation/variation/human/GWAS


mkdir -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_Feb2013




wget 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.html




cd ~/reference

mkdir -p  genome/human_g1k_v37  && cd genome/human_g1k_v37

# http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/

nohup wget http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/human_g1k_v37.fasta.gz  &

gunzip human_g1k_v37.fasta.gz

wget http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/human_g1k_v37.fasta.fai

wget http://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/README.human_g1k_v37.fasta.txt

java -jar ~/biosoft/picardtools/picard-tools-1.119/CreateSequenceDictionary.jar R=human_g1k_v37.fasta O=human_g1k_v37.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.gz



mkdir -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.gz






cd ~/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

参考帖子：http://www.biotrainee.com/forum.php?mod=viewthread&tid=857&page=1&authorid=16

©著作权归作者所有,转载或内容合作请联系作者
  • 人面猴
    序言：七十年代末，一起剥皮案震惊了整个滨河市，随后出现的几起案子，更是在滨河造成了极大的恐慌，老刑警刘岩，带你破解...
    沈念sama阅读 206,839评论 6赞 482
  • 死咒
    序言：滨河连续发生了三起死亡事件，死亡现场离奇诡异，居然都是意外死亡，警方通过查阅死者的电脑和手机，发现死者居然都...
    沈念sama阅读 88,543评论 2赞 382
  • 救了他两次的神仙让他今天三更去死
    文/潘晓璐 我一进店门，熙熙楼的掌柜王于贵愁眉苦脸地迎上来，“玉大人，你说我怎么就摊上这事。” “怎么了？”我有些...
    开封第一讲书人阅读 153,116评论 0赞 344
  • 道士缉凶录：失踪的卖姜人
    文/不坏的土叔 我叫张陵，是天一观的道长。 经常有香客问我，道长，这世上最难降的妖魔是什么？ 我笑而不...
    开封第一讲书人阅读 55,371评论 1赞 279
  • 港岛之恋（遗憾婚礼）
    正文 为了忘掉前任，我火速办了婚礼，结果婚礼上，老公的妹妹穿的比我还像新娘。我一直安慰自己，他们只是感情好，可当我...
    茶点故事阅读 64,384评论 5赞 374
  • 恶毒庶女顶嫁案：这布局不是一般人想出来的
    文/花漫 我一把揭开白布。 她就那样静静地躺着，像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上，一...
    开封第一讲书人阅读 49,111评论 1赞 285
  • 城市分裂传说
    那天，我揣着相机与录音，去河边找鬼。 笑死，一个胖子当着我的面吹牛，可吹牛的内容都是我干的。 我是一名探鬼主播，决...
    沈念sama阅读 38,416评论 3赞 400
  • 双鸳鸯连环套：你想象不到人心有多黑
    文/苍兰香墨 我猛地睁开眼，长吁一口气：“原来是场噩梦啊……” “哼！你这毒妇竟也来了？” 一声冷哼从身侧响起，我...
    开封第一讲书人阅读 37,053评论 0赞 259
  • 万荣杀人案实录
    序言：老挝万荣一对情侣失踪，失踪者是张志新（化名）和其女友刘颖，没想到半个月后，有当地人在树林里发现了一具尸体，经...
    沈念sama阅读 43,558评论 1赞 300
  • 护林员之死
    正文 独居荒郊野岭守林人离奇死亡，尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 36,007评论 2赞 325
  • 白月光启示录
    正文 我和宋清朗相恋三年，在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 38,117评论 1赞 334
  • 活死人
    序言：一个原本活蹦乱跳的男人离奇死亡，死状恐怖，灵堂内的尸体忽然破棺而出，到底是诈尸还是另有隐情，我是刑警宁泽，带...
    沈念sama阅读 33,756评论 4赞 324
  • 日本核电站爆炸内幕
    正文 年R本政府宣布，位于F岛的核电站，受9级特大地震影响，放射性物质发生泄漏。R本人自食恶果不足惜，却给世界环境...
    茶点故事阅读 39,324评论 3赞 307
  • 男人毒药：我在死后第九天来索命
    文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹，春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 30,315评论 0赞 19
  • 一桩弑父案，背后竟有这般阴谋
    文/苍兰香墨 我抬头看了看天上的太阳。三九已至，却和暖如春，着一层夹袄步出监牢的瞬间，已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 31,539评论 1赞 262
  • 情欲美人皮
    我被黑心中介骗来泰国打工， 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留，地道东北人。 一个月前我还...
    沈念sama阅读 45,578评论 2赞 355
  • 代替公主和亲
    正文 我出身青楼，却偏偏与公主长得像，于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子，可洞房花烛夜当晚...
    茶点故事阅读 42,877评论 2赞 345

推荐阅读更多精彩内容