R获取芯片平台与注释【检索】

刘小泽写于18.9.12
处理芯片数据离不开注释包，并且不同的芯片数据使用不同的注释。知道GSE号后就能知道GPL平台号，但是怎么把平台和注释信息联系起来是个问题。今天花个十几分钟学习了怎么导出相对应的注释
自己获取丰衣足食

### ---------------
### Creator: Liu Xiaoze
### Date: 2019-11-06
### Email: [email protected]
### R获取芯片平台与注释
### ---------------

## 配置几个包
options(BioC_mirror="http://mirrors.ustc.edu.cn/bioc/")
BiocManager::install("GEOmetadb")
install.packages("RSQLite")
devtools::install_github("ggrothendieck/sqldf")
library(GEOmetadb)
library(RSQLite)
library(sqldf)

## 使用SQLite
getSQLiteFile() 
# 这个函数也是直接下载到当前目录下
# trying URL 'http://starbuck1.s3.amazonaws.com/sradb/GEOmetadb.sqlite.gz'
# Content type 'binary/octet-stream' length 528141472 bytes (503.7 MB)
# 网速可以的话，先自己下载到本地

################################
## 如果你的下载出现了问题，直接跳过上面的操作
################################
# 我也把这个文件放在微云：链接：https://share.weiyun.com/5njbq8z 
# 密码：3b8pkg
# 然后解压缩GEOmetadb.sqlite.gz，解压缩后是8G
con <- dbConnect(RSQLite::SQLite(),'GEOmetadb.sqlite')
gplToBioc <- dbGetQuery(con,'select gpl,bioc_package,title from gpl where bioc_package is not null')

	gpl	bioc_package	title
1	GPL32	mgu74a	[MG_U74A] Affymetrix Murine Genome U74A Array
2	GPL33	mgu74b	[MG_U74B] Affymetrix Murine Genome U74B Array
3	GPL34	mgu74c	[MG_U74C] Affymetrix Murine Genome U74C Array
4	GPL71	ag	[AG] Affymetrix Arabidopsis Genome Array
5	GPL72	drosgenome1	[DrosGenome1] Affymetrix Drosophila Genome Array
6	GPL74	hcg110	[HC_G110] Affymetrix Human Cancer Array
7	GPL75	mu11ksuba	[Mu11KsubA] Affymetrix Murine 11K SubA Array
8	GPL76	mu11ksubb	[Mu11KsubB] Affymetrix Murine 11K SubB Array
9	GPL77	mu19ksuba	[Mu19KsubA] Affymetrix Murine 19K SubA Array
10	GPL78	mu19ksubb	[Mu19KsubB] Affymetrix Murine 19K SubB Array
11	GPL79	mu19ksubc	[Mu19KsubC] Affymetrix Murine 19K SubC Array
12	GPL80	hu6800	[Hu6800] Affymetrix Human Full Length HuGeneFL Array
13	GPL81	mgu74av2	[MG_U74Av2] Affymetrix Murine Genome U74A Version 2 Array
14	GPL82	mgu74bv2	[MG_U74Bv2] Affymetrix Murine Genome U74B Version 2 Array
15	GPL83	mgu74cv2	[MG_U74Cv2] Affymetrix Murine Genome U74 Version 2 Array
16	GPL85	rgu34a	[RG_U34A] Affymetrix Rat Genome U34 Array
17	GPL86	rgu34b	[RG_U34B] Affymetrix Rat Genome U34 Array
18	GPL87	rgu34c	[RG_U34C] Affymetrix Rat Genome U34 Array
19	GPL88	rnu34	[RN_U34] Affymetrix Rat Neurobiology U34 Array
20	GPL89	rtu34	[RT_U34] Affymetrix Rat Toxicology U34 Array
21	GPL90	ygs98	[YG_S98] Affymetrix Yeast Genome S98 Array
22	GPL91	hgu95av2	[HG_U95A] Affymetrix Human Genome U95A Array
23	GPL92	hgu95b	[HG_U95B] Affymetrix Human Genome U95B Array
24	GPL93	hgu95c	[HG_U95C] Affymetrix Human Genome U95C Array
25	GPL94	hgu95d	[HG_U95D] Affymetrix Human Genome U95D Array
26	GPL95	hgu95e	[HG_U95E] Affymetrix Human Genome U95E Array
27	GPL96	hgu133a	[HG-U133A] Affymetrix Human Genome U133A Array
28	GPL97	hgu133b	[HG-U133B] Affymetrix Human Genome U133B Array
29	GPL98	hu35ksuba	[Hu35KsubA] Affymetrix Human 35K SubA Array
30	GPL99	hu35ksubb	[Hu35KsubB] Affymetrix Human 35K SubB Array
31	GPL100	hu35ksubc	[Hu35KsubC] Affymetrix Human 35K SubC Array
32	GPL101	hu35ksubd	[Hu35KsubD] Affymetrix Human 35K SubD Array
33	GPL198	ath1121501	[ATH1-121501] Affymetrix Arabidopsis ATH1 Genome Array
34	GPL199	ecoli2	[Ecoli_ASv2] Affymetrix E. coli Antisense Genome Array
35	GPL200	celegans	[Celegans] Affymetrix C. elegans Genome Array
36	GPL201	hgfocus	[HG-Focus] Affymetrix Human HG-Focus Target Array
37	GPL339	moe430a	[MOE430A] Affymetrix Mouse Expression 430A Array
38	GPL340	mouse4302	[MOE430B] Affymetrix Mouse Expression 430B Array
39	GPL341	rae230a	[RAE230A] Affymetrix Rat Expression 230A Array
40	GPL342	rae230b	[RAE230B] Affymetrix Rat Expression 230B Array
41	GPL570	hgu133plus2	[HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array
42	GPL571	hgu133a2	[HG-U133A_2] Affymetrix Human Genome U133A 2.0 Array
43	GPL886	hgug4111a	Agilent-011871 Human 1B Microarray G4111A (Feature Number version)
44	GPL887	hgug4110b	Agilent-012097 Human 1A Microarray (V2) G4110B (Feature Number version)
45	GPL1261	mouse430a2	[Mouse430_2] Affymetrix Mouse Genome 430 2.0 Array
46	GPL1318	xenopuslaevis	[Xenopus_laevis] Affymetrix Xenopus laevis Genome Array
47	GPL1319	zebrafish	[Zebrafish] Affymetrix Zebrafish Genome Array
48	GPL1322	drosophila2	[Drosophila_2] Affymetrix Drosophila Genome 2.0 Array
49	GPL1352	u133x3p	[U133_X3P] Affymetrix Human X3P Array
50	GPL1355	rat2302	[Rat230_2] Affymetrix Rat Genome 230 2.0 Array
51	GPL1708	hgug4112a	Agilent-012391 Whole Human Genome Oligo Microarray G4112A (Feature Number version)
52	GPL2112	bovine	[Bovine] Affymetrix Bovine Genome Array
53	GPL2529	yeast2	[Yeast_2] Affymetrix Yeast Genome 2.0 Array
54	GPL2891	h20kcod	GE Healthcare/Amersham Biosciences CodeLinkダｽ UniSet Human 20K I Bioarray
55	GPL2898	adme16cod	GE Healthcare/Amersham Biosciences CodeLinkダｽ ADME Rat 16-Assay Bioarray
56	GPL3154	ecoli2	[E_coli_2] Affymetrix E. coli Genome 2.0 Array
57	GPL3213	chicken	[Chicken] Affymetrix Chicken Genome Array
58	GPL3533	porcine	[Porcine] Affymetrix Porcine Genome Array
59	GPL3738	canine2	[Canine_2] Affymetrix Canine Genome 2.0 Array
60	GPL3921	hthgu133a	[HT_HG-U133A] Affymetrix HT Human Genome U133A Array
61	GPL3979	canine	[Canine] Affymetrix Canine Genome 1.0 Array
62	GPL4032		[Maize] Affymetrix Maize Genome Array
63	GPL4191	h10kcod	CodeLink UniSet Human I Bioarray
64	GPL5188	huex10sttranscriptcluster	[HuEx-1_0-st] Affymetrix Human Exon 1.0 ST Array [probe set (exon) version]
65	GPL5689	hgug4100a	Agilent Human 1 cDNA Microarray (G4100A) [layout C]
66	GPL6097	illuminaHumanv1	Illumina human-6 v1.0 expression beadchip
67	GPL6102	illuminaHumanv2	Illumina human-6 v2.0 expression beadchip
68	GPL6244	hugene10sttranscriptcluster	[HuGene-1_0-st] Affymetrix Human Gene 1.0 ST Array [transcript (gene) version]
69	GPL6246	mogene10sttranscriptcluster	[MoGene-1_0-st] Affymetrix Mouse Gene 1.0 ST Array [transcript (gene) version]
70	GPL6885	illuminaMousev2	Illumina MouseRef-8 v2.0 expression beadchip
71	GPL6947	illuminaHumanv3	Illumina HumanHT-12 V3.0 expression beadchip
72	GPL8300	hgu95av2	[HG_U95Av2] Affymetrix Human Genome U95 Version 2 Array
73	GPL8321	mouse430a2	[Mouse430A_2] Affymetrix Mouse Genome 430A 2.0 Array
74	GPL8490	IlluminaHumanMethylation27k	Illumina HumanMethylation27 BeadChip (HumanMethylation27_270596_v.1.2)
75	GPL10558	illuminaHumanv4	Illumina HumanHT-12 V4.0 expression beadchip
76	GPL11532	hugene11sttranscriptcluster	[HuGene-1_1-st] Affymetrix Human Gene 1.1 ST Array [transcript (gene) version]
77	GPL13497	HsAgilentDesign026652	Agilent-026652 Whole Human Genome Microarray 4x44K v2 (Probe Name version)
78	GPL13534	IlluminaHumanMethylation450k	Illumina HumanMethylation450 BeadChip (HumanMethylation450_15017482)
79	GPL13667	hgu219	[HG-U219] Affymetrix Human Genome U219 Array
80	GPL14877	hgu133plus2	Affymetrix Human Genome U133 Plus 2.0 Array [Brainarray Version 13, HGU133Plus2_Hs_ENTREZG]
81	GPL15380	GGHumanMethCancerPanelv1	Illumina Sentrix Array Matrix (SAM) - GoldenGate Methylation Cancer Panel I
82	GPL15396	hthgu133b	[HT_HG-U133B] Affymetrix HT Human Genome U133B Array [custom CDF: ENTREZ brainarray v. 14]
83	GPL17556	hugene10sttranscriptcluster	[HuGene-1_0-st] Affymetrix Human Gene 1.0 ST Array [HuGene10stv1_Hs_ENTREZG_17.0.0]
84	GPL17897	hthgu133a	[HT_HG-U133A] Affymetrix Human Genome U133A Array (custom CDF: HTHGU133A_Hs_ENTREZG.cdf version 17.0.0)
85	GPL18190	hugene11sttranscriptcluster	[HuGene-1_1-st] Affymetrix Human Gene 1.1 ST Array [CDF: Brainarray HuGene11stv1_Hs_ENTREZG_15.1.0]