From 1949ee250b9f5ffbe7bfac0d9cb3361ea08aec1c Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Thu, 14 May 2020 08:38:15 -0500 Subject: Working on BLOG --- doc/blog/using-covid-19-pubseq-part1.org | 85 +++++++++++++++++++++++++------- 1 file changed, 67 insertions(+), 18 deletions(-) diff --git a/doc/blog/using-covid-19-pubseq-part1.org b/doc/blog/using-covid-19-pubseq-part1.org index d97660b..617a01d 100644 --- a/doc/blog/using-covid-19-pubseq-part1.org +++ b/doc/blog/using-covid-19-pubseq-part1.org @@ -134,43 +134,85 @@ is http://arvados.org/keep:00fede2c6f52b053a14edca01cfa02b7+126/sequence.fasta * Fetch submitter info and other metadata +To get dataests with submitters we can do the above #+begin_src sql -select ?p ?s +PREFIX pubseq: +select distinct ?dataset ?p ?submitter { - ?p ?s + ?dataset pubseq:submitter ?id . + ?id ?p ?submitter } #+end_src -which will tell you that original FASTA ID is "MT293175.1". It also -says the submitter is nodeID://b31228. +Tells you one submitter is "Roychoudhury,P.;Greninger,A.;Jerome,K." +with a URL [[http://purl.obolibrary.org/obo/NCIT_C42781][predicate]] (http://purl.obolibrary.org/obo/NCIT_C42781) +explaining "The individual who is responsible for the content of a +document." Well formed URIs point to real information about the URI +itself. Welcome to the power of the semantic web. + +Let's focus on one sample with #+begin_src sql -select distinct ?id ?p ?s +PREFIX pubseq: +select distinct ?dataset ?submitter { - ?id . - ?id ?p ?s + ?dataset pubseq:submitter ?id . + ?id ?p ?submitter . + FILTER(CONTAINS(?submitter,"Roychoudhury")) . } #+end_src -Tells you the submitter is "Roychoudhury,P.;Greninger,A.;Jerome,K." -with [[http://purl.obolibrary.org/obo/NCIT_C42781][predicate]] explaining "The individual who is responsible for the -content of a document." Welcome to the power of the semantic web. +That is a lot of samples! We just want to pick one, so let's +see if we can get a sample ID by listing sample predicates -To get more information about the relevant sample +#+begin_src sql +PREFIX pubseq: +select distinct ?p +{ + ?dataset ?p ?o . + ?dataset pubseq:submitter ?id . +} +#+end_src + +which lists a predicate named +http://biohackathon.org/bh20-seq-schema#MainSchema/sample. +Let's zoom in on those of Roychoudhury with + + +#+begin_src sql +PREFIX pubseq: +select distinct ?sid ?sample ?p1 ?dataset ?submitter +{ + ?dataset pubseq:submitter ?id . + ?id ?p ?submitter . + FILTER(CONTAINS(?submitter,"Roychoudhury")) . + ?dataset pubseq:sample ?sid . + ?sid ?p1 ?sample +} +#+end_src + +which shows pretty much [[http://sparql.genenetwork.org/sparql/?default-graph-uri=&query=PREFIX+pubseq%3A+%3Chttp%3A%2F%2Fbiohackathon.org%2Fbh20-seq-schema%23MainSchema%2F%3E%0D%0Aselect+distinct+%3Fsid+%3Fsample+%3Fp1+%3Fdataset+%3Fsubmitter%0D%0A%7B%0D%0A+++%3Fdataset+pubseq%3Asubmitter+%3Fid+.%0D%0A+++%3Fid+%3Fp+%3Fsubmitter+.%0D%0A+++FILTER%28CONTAINS%28%3Fsubmitter%2C%22Roychoudhury%22%29%29+.%0D%0A+++%3Fdataset+pubseq%3Asample+%3Fsid+.%0D%0A+++%3Fsid+%3Fp1+%3Fsample%0D%0A%7D&format=text%2Fhtml&timeout=0&debug=on&run=+Run+Query+][everything known]] about their submissions in +this database. Let's focus on one sample "MT326090.1" with predicate +http://semanticscience.org/resource/SIO_000115. #+begin_src sql -select ?sample ?p ?o +PREFIX pubseq: +PREFIX sio: +select distinct ?sample ?p ?o { - ?sample . - ?sample ?p ?o + ?sample sio:SIO_000115 "MT326090.1" . + ?sample ?p ?o . } #+end_src -we find it originates from Washington state (object -https://www.wikidata.org/wiki/Q1223) , dated "30-Mar-2020". The -sequencing was executed with Illumina and pipeline "custom pipeline -v. 2020-03" which is arguably not that descriptive. +This [[http://sparql.genenetwork.org/sparql/?default-graph-uri=&query=PREFIX+pubseq%3A+%3Chttp%3A%2F%2Fbiohackathon.org%2Fbh20-seq-schema%23MainSchema%2F%3E%0D%0APREFIX+sio%3A+%3Chttp%3A%2F%2Fsemanticscience.org%2Fresource%2F%3E%0D%0Aselect+distinct+%3Fsample+%3Fp+%3Fo%0D%0A%7B%0D%0A+++%3Fsample+sio%3ASIO_000115+%22MT326090.1%22+.%0D%0A+++%3Fsample+%3Fp+%3Fo+.%0D%0A%7D&format=text%2Fhtml&timeout=0&debug=on&run=+Run+Query+][query]] tells us the sample was submitted "2020-03-21" and +originates from http://www.wikidata.org/entity/Q30, i.e., the USA and +is a biospecimen collected from the back of the throat by swabbing. +We can track it back to the original GenBank [[http://identifiers.org/insdc/MT326090.1#sequence][submission]]. + +We have also added country and label data to make it a bit easier +to view/query the database. * Fetch all sequences from Washington state @@ -189,6 +231,13 @@ select ?seq ?sample which lists 300 sequences originating from Washington state! Which is almost half of the set coming out of GenBank. +* Discussion + +The public sequence uploader collects sequences, raw data and +(machine) queriable metadata. Not only that: data gets analyzed in the +pangenome and results are presented immediately. The data can be +referenced in publications and origins are citeable. + * Acknowledgements The overall effort was due to magnificent freely donated input by a -- cgit v1.2.3