User:Lindenb/Notebook/UMR915/20100927
From OpenWetWare
Moving SQL to mongo
VCFs
mysql -N -u anonymous \
-e 'select * from vcf_input' -D umr915 |\
awk -F ' ' '{printf("v={sqlid:%d,fileformat:\"%s\",filename:\"%s\",description:\"%s\",creation:\"%s\",projects:[\"XXX\"],individuals:[],headers:[]};db.vcfinputs.save(v);\n",$1,$2,$3,$4,$6);}' \
> jeter.js
indexes
db.vcfinputs.ensureIndex({projects:1})
db.vcfinputs.ensureIndex({individuals:1})
add headers:
mysql -u anonymous -N -e 'select distinct input_id,propValue from vcf_input_meta' -D umr915 |\
awk -F ' ' "{printf(\"v= db.vcfinputs.findOne({sqlid:%s}); if(v!=null) {v.headers.push(\'%s\');db.vcfinputs.save(v);}\n\",\$1,\$2);}"
> v=db.vcfinputs.findOne({sqlid:6})
{
"_id" : ObjectId("4ca07bb0302820c9d33ff054"),
"sqlid" : 6,
"fileformat" : "PILEUP",
"filename" : "XXXXX",
"description" : "XXXXXX",
"creation" : "2010-06-23 10:40:08",
"projects" : [
"XX"
],
"individuals" : [ ],
"headers" : [
"##fileformat=VCFv3.3",
"##filedate=2010-05-26 18:01:43",
"##reference=NCBI36",
"##dbSNP=dbSNP129",
"##phasing=none",
"##annotation=ensembl.54",
"##INFO=DP,1,Integer,\"Total Depth\"",
"##INFO=AC,1,String,\"Allele count\"",
"##INFO=AN,1,Integer,\"Total number of alleles\"",
"##INFO=MQ,1,Integer,\"MQ RMS mapping quality\"",
"##INFO=CQ,1,String,Highest ensembl protein coding gene consequence\"",
"##INFO=GN,1,String,\"Gene name\"",
"##INFO=DB,1,Integer,\"dbSNP entry\"",
"##INFO=HM3,0,Flag,\"Hapmap3 membership\"",
"##INFO=PA,1,String,\"Population data\"",
"##INFO=PS,1,String,\"Population source\"",
"##INFO=NC,1,String,\"Nucleotide conservation (GERP)\"",
"##INFO=CNV,0,Flag,\"In known CNV\"",
"##INFO=MZ,1,Integer,\"Number of mapping quality zero reads\""
]
}
Families
adding the 10 families in mongodb
stopping mongodb
stop mongodb
mongo > use admin switched to db admin > db.shutdownServer()
