From 2d201e156d530e5e912252c4300245da382b846e Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Sat, 16 May 2020 10:14:13 -0500 Subject: Counting number of sequences --- doc/blog/using-covid-19-pubseq-part1.org | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-) (limited to 'doc') diff --git a/doc/blog/using-covid-19-pubseq-part1.org b/doc/blog/using-covid-19-pubseq-part1.org index 617a01d..4b7ddc6 100644 --- a/doc/blog/using-covid-19-pubseq-part1.org +++ b/doc/blog/using-covid-19-pubseq-part1.org @@ -75,8 +75,10 @@ these identifiers throughout. * Predicates -Lets look at all the predicates in the dataset by pasting -the following in a SPARQL end point http://sparql.genenetwork.org/sparql/ +To explore an RDF dataset, the first query we can do is open and gets +us a list. Lets look at all the predicates in the dataset by pasting +the following in a SPARQL end point +http://sparql.genenetwork.org/sparql/ #+begin_src sql select distinct ?p @@ -86,9 +88,19 @@ select distinct ?p #+end_src you can ignore the openlink and w3 ones. To reduce results to a named -graph set the default graph to +graph set the default graph. +To get a [[http://sparql.genenetwork.org/sparql/?default-graph-uri=&query=select+distinct+%3Fg%0D%0A%7B%0D%0A++++GRAPH+%3Fg+%7B%3Fs+%3Fp+%3Fo%7D%0D%0A%7D&format=text%2Fhtml&timeout=0&debug=on&run=+Run+Query+][list of graphs]] in the dataset, first do + +#+begin_src sql +select distinct ?g +{ + GRAPH ?g {?s ?p ?o} +} +#+end_src + +Limiting search to metadata add http://covid-19.genenetwork.org/graph/metadata.ttl in the top input -box. There you can find a predicate for submitter that looks like +box. Now you can find a [[http://sparql.genenetwork.org/sparql/?default-graph-uri=http%3A%2F%2Fcovid-19.genenetwork.org%2Fgraph%2Fmetadata.ttl&query=select+distinct+%3Fp%0D%0A%7B%0D%0A+++%3Fo+%3Fp+%3Fs%0D%0A%7D&format=text%2Fhtml&timeout=0&debug=on&run=+Run+Query+][predicate]] for submitter that looks like http://biohackathon.org/bh20-seq-schema#MainSchema/submitter. To list all submitters, try @@ -131,6 +143,17 @@ by University of Washington is is http://arvados.org/keep:00fede2c6f52b053a14edca01cfa02b7+126/sequence.fasta (note the ID may have changed so pick one with above query). +Now we got this far, lets [[http://sparql.genenetwork.org/sparql/?default-graph-uri=http%3A%2F%2Fcovid-19.genenetwork.org%2Fgraph%2Fmetadata.ttl&query=PREFIX+pubseq%3A+%3Chttp%3A%2F%2Fbiohackathon.org%2Fbh20-seq-schema%23MainSchema%2F%3E%0D%0Aselect+%28COUNT%28distinct+%3Fdataset%29+as+%3Fnum%29%0D%0A%7B%0D%0A+++%3Fdataset+pubseq%3Asubmitter+%3Fid+.%0D%0A+++%3Fid+%3Fp+%3Fsubmitter%0D%0A%7D+&format=text%2Fhtml&timeout=0&debug=on&run=+Run+Query+][count the datasets]] submitted with + +#+begin_src sql +PREFIX pubseq: +select (COUNT(distinct ?dataset) as ?num) +{ + ?dataset pubseq:submitter ?id . + ?id ?p ?submitter +} +#+end_src + * Fetch submitter info and other metadata -- cgit v1.2.3