Blitvak Week 15
From LMU BioDB 2015
Revision as of 23:30, 8 December 2015 by Blitvak (Talk | contribs) (added info regarding the duplicate counts)
12/8
7121 - orf
6993 - uniprot
128 - diff
205 - query for duplicates
77 - number of records
128 + 77 = 205
select genetype_name_hjid, count(value) from genenametype where type = 'ORF' and value ~ 'p?BCA[LMS]?[0-9][0-9][0-9][Aa]?[0-9]?[A-Z,a-z]?' group by genetype_name_hjid;
select genetype_name_hjid, count(value) from genenametype where type = 'ORF' and value ~ 'p?BCA[LMS]?[0-9][0-9][0-9][Aa]?[0-9]?[A-Z,a-z]?' group by genetype_name_hjid having count(value) > 1;
select sum(dupe_count) from (select genetype_name_hjid, count(value) as dupe_count
from genenametype where type = 'ORF' and value ~ 'p?BCA[LMS]?[0-9][0-9][0-9][Aa]?[0-9]?[A-Z,a-z]?' group by genetype_name_hjid having count(value) > 1 order by count(value) desc) as dupe_tally;
select genetype_name_hjid, count(value) as dupe_count
from genenametype where type = 'ORF' and value ~ 'p?BCA[LMS]?[0-9][0-9][0-9][Aa]?[0-9]?[A-Z,a-z]?' group by genetype_name_hjid having count(value) > 1 order by count(value) desc;
select *
from genenametype where genetype_name_hjid = 66138;
select genetype_name_hjid, count(value) from genenametype where type = 'ORF' and value ~ 'p?BCA[LMS]?[0-9][0-9][0-9][Aa]?[0-9]?[A-Z,a-z]?' group by genetype_name_hjid having count(value) > 1 order by count(value) desc;
