生物信息學(xué)常見的數(shù)據(jù)下載，包括基因組凛捏，gtf担忧，bed，注釋

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

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

?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請(qǐng)聯(lián)系作者

人面猴
序言：七十年代末坯癣，一起剝皮案震驚了整個(gè)濱河市瓶盛，隨后出現(xiàn)的幾起案子，更是在濱河造成了極大的恐慌，老刑警劉巖惩猫，帶你破解...
沈念sama閱讀 216,372評(píng)論 6贊 498
死咒
序言：濱河連續(xù)發(fā)生了三起死亡事件芝硬，死亡現(xiàn)場離奇詭異，居然都是意外死亡轧房，警方通過查閱死者的電腦和手機(jī)拌阴，發(fā)現(xiàn)死者居然都...
沈念sama閱讀 92,368評(píng)論 3贊 392
救了他兩次的神仙讓他今天三更去死
文/潘曉璐我一進(jìn)店門，熙熙樓的掌柜王于貴愁眉苦臉地迎上來奶镶，“玉大人迟赃，你說我怎么就攤上這事〕д颍” “怎么了纤壁？”我有些...
開封第一講書人閱讀 162,415評(píng)論 0贊 353
道士緝兇錄：失蹤的賣姜人
文/不壞的土叔我叫張陵，是天一觀的道長捺信。經(jīng)常有香客問我酌媒，道長，這世上最難降的妖魔是什么迄靠？我笑而不...
開封第一講書人閱讀 58,157評(píng)論 1贊 292
?港島之戀（遺憾婚禮）
正文為了忘掉前任秒咨，我火速辦了婚禮，結(jié)果婚禮上梨水，老公的妹妹穿的比我還像新娘拭荤。我一直安慰自己，他們只是感情好疫诽，可當(dāng)我...
茶點(diǎn)故事閱讀 67,171評(píng)論 6贊 388
惡毒庶女頂嫁案：這布局不是一般人想出來的
文/花漫我一把揭開白布舅世。她就那樣靜靜地躺著，像睡著了一般奇徒。火紅的嫁衣襯著肌膚如雪雏亚。梳的紋絲不亂的頭發(fā)上，一...
開封第一講書人閱讀 51,125評(píng)論 1贊 297
城市分裂傳說
那天摩钙，我揣著相機(jī)與錄音罢低，去河邊找鬼。笑死胖笛，一個(gè)胖子當(dāng)著我的面吹牛网持，可吹牛的內(nèi)容都是我干的。我是一名探鬼主播长踊，決...
沈念sama閱讀 40,028評(píng)論 3贊 417
雙鴛鴦連環(huán)套：你想象不到人心有多黑
文/蒼蘭香墨我猛地睜開眼功舀，長吁一口氣：“原來是場噩夢啊……” “哼！你這毒婦竟也來了身弊？” 一聲冷哼從身側(cè)響起辟汰，我...
開封第一講書人閱讀 38,887評(píng)論 0贊 274
萬榮殺人案實(shí)錄
序言：老撾萬榮一對(duì)情侶失蹤列敲，失蹤者是張志新（化名）和其女友劉穎，沒想到半個(gè)月后帖汞，有當(dāng)?shù)厝嗽跇淞掷锇l(fā)現(xiàn)了一具尸體戴而，經(jīng)...
沈念sama閱讀 45,310評(píng)論 1贊 310
?護(hù)林員之死
正文獨(dú)居荒郊野嶺守林人離奇死亡，尸身上長有42處帶血的膿包…… 初始之章·張勛以下內(nèi)容為張勛視角年9月15日...
茶點(diǎn)故事閱讀 37,533評(píng)論 2贊 332
?白月光啟示錄
正文我和宋清朗相戀三年翩蘸，在試婚紗的時(shí)候發(fā)現(xiàn)自己被綠了所意。大學(xué)時(shí)的朋友給我發(fā)了我未婚夫和他白月光在一起吃飯的照片。...
茶點(diǎn)故事閱讀 39,690評(píng)論 1贊 348
活死人
序言：一個(gè)原本活蹦亂跳的男人離奇死亡鹿鳖，死狀恐怖扁眯，靈堂內(nèi)的尸體忽然破棺而出，到底是詐尸還是另有隱情翅帜，我是刑警寧澤姻檀，帶...
沈念sama閱讀 35,411評(píng)論 5贊 343
?日本核電站爆炸內(nèi)幕
正文年R本政府宣布，位于F島的核電站涝滴，受9級(jí)特大地震影響绣版，放射性物質(zhì)發(fā)生泄漏。R本人自食惡果不足惜歼疮，卻給世界環(huán)境...
茶點(diǎn)故事閱讀 41,004評(píng)論 3贊 325
男人毒藥：我在死后第九天來索命
文/蒙蒙一杂抽、第九天我趴在偏房一處隱蔽的房頂上張望。院中可真熱鬧韩脏，春花似錦缩麸、人聲如沸。這莊子的主人今日做“春日...
開封第一講書人閱讀 31,659評(píng)論 0贊 22
一樁弒父案杭朱，背后竟有這般陰謀
文/蒼蘭香墨我抬頭看了看天上的太陽。三九已至吹散，卻和暖如春弧械，著一層夾襖步出監(jiān)牢的瞬間，已是汗流浹背空民。一陣腳步聲響...
開封第一講書人閱讀 32,812評(píng)論 1贊 268
情欲美人皮
我被黑心中介騙來泰國打工刃唐，沒想到剛下飛機(jī)就差點(diǎn)兒被人妖公主榨干…… 1. 我叫王不留，地道東北人界轩。一個(gè)月前我還...
沈念sama閱讀 47,693評(píng)論 2贊 368
代替公主和親
正文我出身青樓画饥，卻偏偏與公主長得像，于是被迫代替她去往敵國和親浊猾。傳聞我的和親對(duì)象是個(gè)殘疾皇子荒澡，可洞房花燭夜當(dāng)晚...
茶點(diǎn)故事閱讀 44,577評(píng)論 2贊 353

生物信息學(xué)常見的數(shù)據(jù)下載俯抖，包括基因組倾剿，gtf，bed蚌成，注釋

生物信息學(xué)常見的數(shù)據(jù)下載，包括基因組凛捏，gtf担忧，bed，注釋

推薦閱讀更多精彩內(nèi)容