使用MySQL制作SNP146数据库

SNP数据（txt）文件可以在此下载：http://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/

下载、解压data之后，启动MySQL server，登录进入MySQL

# create database
create database snp146all
use snp146all

# create table:这一步的MySQL script文件可以在上面提到的网站下载
DROP TABLE IF EXISTS `snp146`;
/*!40101 SET @saved_cs_client     = @@character_set_client */;
/*!40101 SET character_set_client = utf8 */;
CREATE TABLE `snp146` (
  `bin` smallint(5) unsigned NOT NULL,
  `chrom` varchar(31) NOT NULL,
  `chromStart` int(10) unsigned NOT NULL,
  `chromEnd` int(10) unsigned NOT NULL,
  `name` varchar(15) NOT NULL,
  `score` smallint(5) unsigned NOT NULL,
  `strand` enum('+','-') NOT NULL,
  `refNCBI` blob NOT NULL,
  `refUCSC` blob NOT NULL,
  `observed` varchar(255) NOT NULL,
  `molType` enum('unknown','genomic','cDNA') NOT NULL,
  `class` enum('unknown','single','in-del','microsatellite','named','mnp','insertion','deletion') NOT NULL,
  `valid` set('unknown','by-cluster','by-frequency','by-submitter','by-2hit-2allele','by-hapmap','by-1000genomes') NOT NULL,
  `avHet` float NOT NULL,
  `avHetSE` float NOT NULL,
  `func` set('unknown','coding-synon','intron','near-gene-3','near-gene-5','ncRNA','nonsense','missense','stop-loss','frameshift','cds-indel','untranslated-3','untranslated-5','splice-3','splice-5') NOT NULL,
  `locType` enum('range','exact','between','rangeInsertion','rangeSubstitution','rangeDeletion','fuzzy') NOT NULL,
  `weight` int(10) unsigned NOT NULL,
  `exceptions` set('RefAlleleMismatch','RefAlleleRevComp','DuplicateObserved','MixedObserved','FlankMismatchGenomeLonger','FlankMismatchGenomeEqual','FlankMismatchGenomeShorter','SingleClassLongerSpan','SingleClassZeroSpan','SingleClassTriAllelic','SingleClassQuadAllelic','ObservedWrongFormat','ObservedTooLong','ObservedContainsIupac','ObservedMismatch','MultipleAlignments','NonIntegerChromCount','AlleleFreqSumNot1','SingleAlleleFreq','InconsistentAlleles') NOT NULL,
  `submitterCount` smallint(5) unsigned NOT NULL,
  `submitters` longblob NOT NULL,
  `alleleFreqCount` smallint(5) unsigned NOT NULL,
  `alleles` longblob NOT NULL,
  `alleleNs` longblob NOT NULL,
  `alleleFreqs` longblob NOT NULL,
  `bitfields` set('clinically-assoc','maf-5-some-pop','maf-5-all-pops','has-omim-omia','microattr-tpa','submitted-by-lsdb','genotype-conflict','rs-cluster-nonoverlapping-alleles','observed-mismatch') NOT NULL,
  KEY `name` (`name`),
  KEY `chrom` (`chrom`,`bin`)
) ENGINE=MyISAM DEFAULT CHARSET=latin1;

# load data
load data infile 'snp146.txt' into table snps fields terminated by '\t' lines terminated by '\n';

这样就制作完成！

然而，另一个问题自然而然地显现：SNP146 database大约占用20+GB的硬盘，所以，需要将其MySQL的存储用的database从default的地方移动到空间更多的地方。这个问题等待下文解决。