BH16.12/FALDO
提供：TogoWiki
目次 |
JBrowse/Trackに組込むサンプルSPARQL
CyanoBase
#DEFINE sql:select-option "order"
prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>
prefix xsd: <http://www.w3.org/2001/XMLSchema#>
prefix obo: <http://purl.obolibrary.org/obo/>
prefix faldo: <http://biohackathon.org/resource/faldo#>
prefix idorg: <http://rdf.identifiers.org/database/>
PREFIX insdc: <http://ddbj.nig.ac.jp/ontologies/nucleotide/>
SELECT
IF(?fstart < ?fend , ?fstart, ?fend) as ?start,IF(?fstart < ?fend , ?fend, ?fstart) as ?end
,IF( ?faldo_type = faldo:ForwardStrandPosition,1, IF( ?faldo_type = faldo:ReverseStrandPosition,-1,0)) as ?strand
,str(?obj_type) as ?type,
str(?label) as ?name,
str(?obj_name) as ?description
, str(?obj) as ?uniqueID
FROM <http://genome.microbedb.jp/resources/cyanobase/genbank>
WHERE {
#values ?entry { <http://identifiers.org/insdc/CACA01000081.1>}
#values ?seq_base { "{ref}" }
#values ?seq_base { "CACA01000081" }
values ?faldo_type { faldo:ForwardStrandPosition faldo:ReverseStrandPosition faldo:BothStrandsPosition }
?entry insdc:sequence_version ?seq_version.
BIND(STRBEFORE(?seq_version,".") as ?seq_acc).
filter(?seq_acc = "CACA01000081")
#filter(?seq_acc = "{ref}")
?entry insdc:sequence ?seq.
?obj obo:so_part_of+ ?seq .
?obj rdf:type ?obj_type .
?obj faldo:location ?faldo .
?faldo faldo:begin/rdf:type ?faldo_type .
?faldo faldo:begin/faldo:position ?fstart .
?faldo faldo:end/faldo:position ?fend .
?obj obo:so_part_of ?parent . filter( ?obj_type = obo:SO_0000704 || ?parent != ?seq )
optional {?obj insdc:locus_tag ?label .}
optional {?obj insdc:product ?obj_name .}
#filter ( !(?start > {end} || ?end < {start}) )
}
MBGD
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX mbgdr: <http://mbgd.genome.ad.jp/rdf/resource/>
PREFIX org: <http://mbgd.genome.ad.jp/rdf/resource/organism/>
PREFIX orth: <http://purl.jp/bio/11/orth#>
PREFIX dct: <http://purl.org/dc/terms/>
PREFIX faldo: <http://biohackathon.org/resource/faldo#>
SELECT
IF(?fstart < ?fend , ?fstart, ?fend) as ?start,IF(?fstart < ?fend , ?fend, ?fstart) as ?end
,IF( ?faldo_type = faldo:ForwardStrandPosition,1, IF( ?faldo_type = faldo:ReverseStrandPosition,-1,0)) as ?strand
,?gene_id as ?uniqueID, ?cluster_id, ?label as ?name, ?description, ?url, ?reference
,?p, ?o
WHERE {
values ?faldo_type { faldo:ForwardStrandPosition faldo:ReverseStrandPosition faldo:BothStrandsPosition }
?group a orth:OrthologGroup ;
orth:inDataset mbgdr:default ;
dct:identifier ?cluster_id ;
orth:member/orth:gene ?gene .
#?group ?p ?o.
?group rdfs:label ?label.
?group <http://purl.org/dc/terms/description> ?description.
?group <http://xmlns.com/foaf/0.1/page> ?url.
?gene orth:organism org:syn ;
dct:identifier ?gene_id .
?gene faldo:location ?region.
filter(?gene_id = "syn:NDHK2")
?region faldo:begin ?begin.
?region faldo:end ?end.
?begin faldo:position ?fstart.
?begin a ?faldo_type.
?begin faldo:reference ?reference.
?end faldo:position ?fend.
?reference ?p ?o.
}
ORDER BY ?gene_id
limit 100
DDBJ-PDBj/chain
BH16.12/LinkDB > PDB chain IDから塩基配列の座標を取得する
課題
- Sequence IDに相当する faldo:referenceのObjectおよびrdfs:labelはそれぞれ異なるので、RDFでつなぐ必要がある
- exon-intronなどのsubfeatureをもつ真核遺伝子のグリフ表現をSPARQL ep.経由で表示可能かの確認
- 配列のリビジョン、アノテーションのリフトオーバーを行なうためのFALDO2FALDO
