diff --git a/Model/lib/xml/tuningManager/apiTuningManager.xml b/Model/lib/xml/tuningManager/apiTuningManager.xml
index 3622661be1..a497d051dd 100644
--- a/Model/lib/xml/tuningManager/apiTuningManager.xml
+++ b/Model/lib/xml/tuningManager/apiTuningManager.xml
@@ -3,7 +3,7 @@
-
+
Locations and Sequence of Transmembrane Domains (TMHMM)
@@ -14,22 +14,22 @@
@@ -51,7 +51,7 @@
-
+
Locations and Sequence of Signal Peptide Domains (SignalP)
@@ -65,12 +65,11 @@
@@ -170,7 +169,7 @@
-
+
Attributes for Metabolic Pathways
@@ -581,7 +580,7 @@
-
+
the max and min depth of each ontology term in OntologyRelationship. Used by the GoTermSummary tuning table
@@ -635,7 +634,7 @@
-
+
GeneGoTerms: each row represents one GO term assignment to one gene, right from what was loaded.
@@ -643,17 +642,18 @@
+
@@ -1022,7 +1023,7 @@
WITH profiles AS (
SELECT p.source_id,
ga.project_id,
- ga.sequence_id,
+ ga.na_sequence_source_id,
d.name,
row_number() over(partition by d.name
order by ga.chromosome_order_num, p.profile_as_string desc) as rn
@@ -1048,7 +1049,7 @@
-
+
Each record maps a gene to a PDB structure. Used by the model to find
genes that have a PDB structure and to find the PDB structures for a
given gene.
@@ -1444,14 +1445,15 @@
+
-
@@ -1498,7 +1500,7 @@ tablespace indx
-
+
GeneId maps any valid ID for a gene onto its official ID. These two quantities
are stored in the "id" and "gene" columns, respectively. The "unique_mapping"
column is set to 1 for IDs which map to only one gene.
@@ -1509,7 +1511,6 @@ tablespace indx
understand which part (or parts) of the SQL is responsible for each ID-to-gene
mapping.
-
@@ -1528,7 +1529,8 @@ tablespace indx
@@ -1726,7 +1727,7 @@ tablespace indx
regexp_replace(id, '\.\d\d?$', '') as id,
gene, unique_mapping, union_member, database_name
FROM &prefixGeneId&1
- WHERE regexp_like(id, '(.*)\.\d\d?$'))
+ WHERE id SIMILAR TO '%.\d\d?')
SELECT id, gene, 0 as unique_mapping, 'base ID' as union_member, database_name
FROM munge
WHERE id NOT IN (SELECT id FROM &prefixGeneId&1)
@@ -1835,7 +1836,7 @@ tablespace indx
-
+
This table maps IDs for a sequence onto the official ID of the sequence.
It is analogous to GeneId, which does the same thing for genes. Used by
genomic-sequence record queries, by the sequence retrieval tool, and by
@@ -1851,12 +1852,23 @@ tablespace indx
-
+
Used by GeneTables.Epitopes to map a gene to its epitopes.
@@ -1901,15 +1913,16 @@ tablespace indx
-
+
@@ -1942,7 +1954,7 @@ tablespace indx
-
+
Stores (transcript, sequence, distance from centromere) 3-tuples for transcripts
that lie on a sequence for which we have a centomere location.
@@ -1952,7 +1964,7 @@ tablespace indx
@@ -1975,12 +1987,10 @@ tablespace indx
-
+
The BFMV for proteins. Each protein gets a single record, which
stores all its attributes. Used mainly to create TranscriptAttributes
-
-
@@ -1995,99 +2005,17 @@ tablespace indx
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
The BFMV for the gene record. Each gene gets a single record, which
stores all its attributes. Used widely, in the model and elsewhere, for
queries involving genes, as well as in the creation of more than a
@@ -2213,9 +2123,7 @@ tablespace indx
-
-
@@ -2223,25 +2131,18 @@ tablespace indx
-
-
-
-
-
-
-
@@ -2585,7 +2450,7 @@ tablespace indx
@@ -2593,94 +2458,34 @@ tablespace indx
-
-
-
-
-
-
-
-
-
-
-
10 )
+ SET exon_count = (SELECT count(*) + 1 FROM apidb.IntronLocation il
+ WHERE '&ORG_ABBREV_' || il.parent_id = ta.internal_feature_id
+ AND il.end_max - il.start_min + 1 > 10 )
WHERE ta.project_id = 'TriTrypDB'
]]>
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
@@ -2723,7 +2511,7 @@ tablespace indx
@@ -2741,62 +2529,63 @@ tablespace indx
= 20
- GROUP BY atr.gene_source_id, atr.source_id, atr.taxon_id, atr.organism, ltr.transcript_novelty, ltr.transcript_length
+ GROUP BY atr.gene_source_id, atr.source_id, atr.ncbi_tax_id, atr.organism, ltr.transcript_novelty, ltr.transcript_length
) t
WHERE total_reads >= 5
UNION
- SELECT atr.gene_source_id, atr.source_id, atr.taxon_id,
+ SELECT atr.gene_source_id, atr.source_id, atr.ncbi_tax_id,
'intron_junction' as ontology_term_name, it.string_value string_value,
null as number_value
FROM
@@ -2816,7 +2605,7 @@ tablespace indx
, TranscriptAttributes atr
WHERE it.gene_source_id = atr.gene_source_id
UNION
- SELECT atr.gene_source_id, atr.source_id, atr.taxon_id,
+ SELECT atr.gene_source_id, atr.source_id, atr.ncbi_tax_id,
'Unique_reads' as ontology_term_name, null as string_value , gj.total_unique number_value
FROM
GeneIntronJunction gj
@@ -2828,7 +2617,7 @@ tablespace indx
@@ -2936,7 +2725,7 @@ tablespace indx
-
+
Stores, for each transcript, a string containing the gene-relative coordinates
of all its introns and UTRs.
@@ -2946,7 +2735,8 @@ tablespace indx
-
-
-
-
+
A single product string per gene
@@ -3007,14 +2790,14 @@ tablespace indx
from (select distinct gf.source_id, gfp.product
from dots.GeneFeature gf, apidb.GeneFeatureProduct gfp
where gfp.na_feature_id = gf.na_feature_id
- and gfp.is_preferred = 1)
+ and gfp.is_preferred = 1) sub
group by source_id),
gfp_any
as (select source_id,
substr(STRING_AGG(product, ', ' order by product), 1, 4000) as product
from (select distinct gf.source_id, gfp.product
from dots.GeneFeature gf, apidb.GeneFeatureProduct gfp
- where gfp.na_feature_id = gf.na_feature_id)
+ where gfp.na_feature_id = gf.na_feature_id) sub
group by source_id),
tp_preferred
as (select source_id,
@@ -3023,7 +2806,7 @@ tablespace indx
from dots.GeneFeature gf, dots.Transcript t, apidb.TranscriptProduct tp
where t.parent_id = gf.na_feature_id
and tp.na_feature_id = t.na_feature_id
- and tp.is_preferred = 1)
+ and tp.is_preferred = 1) sub
group by source_id),
gf_product
as (select source_id, product
@@ -3035,7 +2818,7 @@ tablespace indx
from (select distinct gf.source_id, tp.product
from dots.GeneFeature gf, dots.Transcript t, apidb.TranscriptProduct tp
where t.parent_id = gf.na_feature_id
- and tp.na_feature_id = t.na_feature_id)
+ and tp.na_feature_id = t.na_feature_id) sub
group by source_id),
t_product
as (select source_id,
@@ -3043,9 +2826,10 @@ tablespace indx
from (select gf.source_id, t.product
from dots.GeneFeature gf, dots.Transcript t
where t.parent_id = gf.na_feature_id
- and t.product is not null)
- group by source_id)
- select gf.source_id,
+ and t.product is not null) sub
+ group by source_id)
+ select '&ORG_ABBREV' as org_abbrev,
+ gf.source_id,
coalesce(gfp_preferred.product, gfp_any.product, tp_preferred.product,
gf.product, tp_any.product, t_product.product)
as product
@@ -3066,57 +2850,41 @@ tablespace indx
-
+
The BFMV for the gene record. Each gene gets a single record, which
stores all its attributes.
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
Each record represents one SNP. Widely used in the model, as well as in
the creation of several other tuning tables, Includes only NGS SNPs.
+
@@ -3286,10 +3021,10 @@ tablespace indx
AS (SELECT feature_source_id, is_reversed, na_feature_id
FROM apidb.FeatureLocation
WHERE is_top_level = 1 and feature_type = 'GeneFeature')
- SELECT chromosome_info.project_id,
+ SELECT '&ORG_ABBREV' as org_abbrev,
+ '&PROJECT_ID' as project_id,
ed.name as dataset,
- sequence.na_sequence_id,
- sequence.source_id as seq_source_id,
+ sequence.source_id as sequence_source_id,
snp.location,
snp.source_id,
snp.reference_strain,
@@ -3316,11 +3051,9 @@ tablespace indx
coalesce(stop_codon_snps.has_stop_codon, 0) AS has_stop_codon,
case when snp.reference_aa is null then 1 else 0 end as is_noncoding_snp,
fl.feature_source_id as gene_source_id,
- fl.na_feature_id as gene_na_feature_id,
CASE fl.is_reversed WHEN 0 THEN 'forward' WHEN 1 THEN 'reverse' ELSE null END as gene_strand,
CAST(SUBSTR(sequence.sequence, snp.location::integer - 30, 30) AS VARCHAR(30)) AS lflank,
CAST(SUBSTR(sequence.sequence, snp.location::integer + 1, 30) AS VARCHAR(30)) AS rflank,
- chromosome_info.organism as organism,
chromosome_info.ncbi_tax_id,
chromosome_info.chromosome,
chromosome_info.chromosome_order_num
@@ -3336,7 +3069,7 @@ tablespace indx
WHERE edr.external_database_release_id = snp.external_database_release_id
AND ed.external_database_id = edr.external_database_id
AND sequence.na_sequence_id = snp.na_sequence_id
- AND chromosome_info.na_sequence_id = snp.na_sequence_id
+ AND chromosome_info.source_id = sequence.source_id -- WAS chromosome_info.na_sequence_id = snp.na_sequence_id
ORDER BY edr.external_database_release_id, sequence.na_sequence_id, snp.location
]]>
@@ -3356,7 +3089,7 @@ tablespace indx
@@ -3369,7 +3102,7 @@ tablespace indx
@@ -3383,11 +3116,10 @@ tablespace indx
-
+
Each row represents one EST. Used widely in the model, and to make the
tuning tables BlastTypes, OrganismAbbreviationBlast, and OrganismAttributes.
-
@@ -3396,12 +3128,11 @@ tablespace indx
-
-
+
@@ -3454,7 +3184,7 @@ tablespace indx
-
+
Each row represents a colocated EST alignment - gene pair. Used by the
model, by generateGeneMetrics, and in the creation of the
OrganismAttributes tuning table
@@ -3467,16 +3197,22 @@ tablespace indx
+
= 0
AND query_sequence.na_sequence_id = ba.query_na_sequence_id
AND query_sequence.sequence_ontology_id = so.ontology_term_id
- AND so.name = 'EST'
- AND ba.target_na_sequence_id = sequence.na_sequence_id
+ AND so.source_id = 'SO:0000345' --EST
+ AND ba.target_na_sequence_id = target_sequence.na_sequence_id
+ AND sequence.source_id = target_sequence.source_id
+ AND ba.query_taxon_id = t.taxon_id
]]>
@@ -3959,22 +3706,22 @@ tablespace indx
-
+
Used by gene queries, as well as by generateGeneMetrics. Also an input
to OrganismAttributes.
+
-
+
Each record maps a gene onto a subcellular location. Used by
GenesBySubcellularLocalization.
@@ -4035,7 +3784,7 @@ tablespace indx
-
+
Like dots.SimilaritySpan, except that for sequences that are mapped by
SequencePiece into parts of other sequences, both locations are stored.
Used by GBrowse, and also in the creation of the Blastx tuning table.
@@ -4080,7 +3829,8 @@ tablespace indx
-
+
SNP Chip only, such as Plasmo barcode, 3k_chp and hd_array
Each record represents one SNP. Widely used in the model, as well as in
the creation of several other tuning tables
-
@@ -4171,19 +3921,17 @@ tablespace indx
-
-
-
-
@@ -4276,20 +4014,20 @@ tablespace indx
-
+
this otherwise-unneeded tuning table, which depends on SnpAttributesDoTS,
exists so that the view SnpChipAttributes can be created as a side-effect
@@ -4316,48 +4054,47 @@ tablespace indx
-
+
Each record stores a Blastp similarity of a gene. Used by the gene-page
Blastp table.
-
+
@@ -4406,7 +4143,8 @@ tablespace indx
-
+
Each record stores the transcript sequence of one gene. Used by the
gene record and the sequence retrieval tool. Propagated to the portal.
@@ -4535,7 +4273,7 @@ tablespace indx
@@ -4549,7 +4287,7 @@ tablespace indx
-
+
Each record stores the coding sequence of one gene. Used by the
gene record and the sequence retrieval tool. Propagated to the portal.
@@ -4559,12 +4297,12 @@ tablespace indx
@@ -4576,54 +4314,51 @@ tablespace indx
-
+
Each record stores the coding sequence of one gene. Used by the
gene record and the sequence retrieval tool, as well as by
buildTrackOldAnnotationTT. Propagated to the portal.
-
-
+
Each record stores the nucleotide sequence for one genomic sequence
that is "official" (in the sense that it can be instantiated as a WDK
sequence record. Used by generatePathoLogicFile and the sequence
retrieval tool Propagated to portal instances.
-
-
@@ -4635,26 +4370,23 @@ tablespace indx
-
- Each record stores the nucleotide sequence of an EST, for use by the
+
+ Each record stores the nucleotide sequence of an EST, as well as project_id, for use by the
relevant attribute query in the WDK EST record. Propagated to portal
instances.
-
-
@@ -5805,7 +5537,7 @@ tablespace indx
-
+
Properties table for ChEBI Compounds.
@@ -5842,7 +5574,7 @@ tablespace indx
-
+
The BFMV for the compound WDK record type. Used by the model for the
compound record and queries, as well as in the creation of the
PathwayCompounds tuning table. Propagated to portal instances.
@@ -5878,7 +5610,7 @@ tablespace indx
-
+
Alias table for Compounds.
Compound column is the source_id from CompoundAttributes (chEBI_ID).
ID can have this same ID, or mapping KEGG ID, or Name, or Synonym.
@@ -5927,7 +5659,7 @@ tablespace indx
-
+
Each record represents a 5-tuple of (reaction, compound, pathway,
enzyme, type). Used extensively in the model for pathway-related
queries, as well as by getImageMap.pl.
@@ -6031,7 +5763,7 @@ tablespace indx
-
+
Aggregates reactions irrespective of pathway. Required to determine if BioCyc reactions are reversible. Used extensively in the model in conjunction with pathwaycompounds for pathway related queries
@@ -6559,7 +6291,7 @@ tablespace indx
-
+
for use in GenesByReactionCompounds question
@@ -6889,15 +6621,15 @@ tablespace indx
WITH rnaseqgenes AS (
SELECT p.DATASET_NAME
, p.source_id as gene_source_id
- , ga.sequence_id as sequence_id
+ , ga.na_sequence_source_id as sequence_id
, row_number() over (partition by p.dataset_name
- order by p.max_value, p.source_id, ga.sequence_id) as rn
+ order by p.max_value, p.source_id, ga.na_sequence_source_id) as rn
FROM profile p, geneattributes ga
WHERE dataset_type = 'transcript_expression' and dataset_subtype = 'rnaseq'
AND p.source_id = ga.source_id
), proteomicsgenes as (
SELECT ga.gene_source_id,
- ga.SEQUENCE_ID,
+ ga.na_sequence_source_id,
ga.protein_source_id,
d.name,
row_number() over(partition by d.name
@@ -6923,7 +6655,7 @@ tablespace indx
, dnt.name
, dsp.name as dataset_presenter_name
, sa.source_id as sequence_source_id
- , pg.sequence_id as p_sequence_source_id
+G , pg.sequence_id as p_sequence_source_id
, pg.gene_source_id as p_gene_id
, pg.protein_source_id as p_protein_id
, rg.sequence_id as r_sequence_source_id
@@ -7021,7 +6753,7 @@ tablespace indx
-
+
@@ -7030,29 +6762,28 @@ tablespace indx
= 1.5
) t
GROUP BY gene_source_id, project_id, sequence_id, haplotype_block_name,
- start_min, end_max, start_max, end_min, organism
+ start_min, end_max, start_max, end_min
]]>
@@ -8422,23 +8153,23 @@ tablespace indx
-
+
Materialization of GeneTables.GeneModelDump.
-
-
@@ -8520,7 +8251,7 @@ tablespace indx
-
+
Info from dots.ExternalAaSequence records for BLAT alignments
@@ -8528,18 +8259,19 @@ tablespace indx
@@ -8681,7 +8413,7 @@ tablespace indx
-
+
for GeneTables.RodMalPhenotypeTable
@@ -8697,7 +8429,7 @@ tablespace indx
AS (SELECT DISTINCT ga.source_id, ga.project_id, pm.source_id as rmgmid,
pm.pubmed_id, pm.modification_type as mod_type,
pm.is_successful as suc_of_gen_mod,
- pm.mutation_description, ot.name,
+ pm.mutation_description, ot.source_id as ontology_source_id,
SUBSTR(pr.phenotype_post_composition, 4000, 1) as phenotype1,
SUBSTR(pr.phenotype_post_composition, 4000, 4001) as phenotype2,
pm.has_multiple_mutations AS multiple, na.NA_FEATURE_ID as id,
@@ -8709,7 +8441,7 @@ tablespace indx
apidb.NaFeaturePhenotypeModel na
WHERE pm.phenotype_model_id = pr.phenotype_model_id
AND na.phenotype_model_id = pm.phenotype_model_id
- AND na.na_feature_id = ga.na_feature_id
+ AND '&ORG_ABBREV_' || na.na_feature_id = ga.internal_feature_id
),
knockdown
AS (SELECT DISTINCT genes.source_id, mods.phenotype_model_id as model_id
@@ -8719,7 +8451,7 @@ tablespace indx
AND m.phenotype_model_id = nod.phenotype_model_id
AND mods.phenotype_model_id = nod.phenotype_model_id
AND m.id != nod.na_feature_id
- AND genes.na_feature_id = nod.na_feature_id
+ AND genes.internal_feature_id = '&ORG_ABBREV_' || nod.na_feature_id
AND m.source_id != genes.source_id
-- AND mods.has_multiple_mutations = 1
),
@@ -8734,7 +8466,7 @@ tablespace indx
ELSE 'YES'
END AS suc_of_gen_mod,
CAST(m.mutation_description AS VARCHAR(150)) AS mutation_description,
- CAST(string_agg(m.name, ', ' ORDER BY m.name)
+ CAST(string_agg(m.ontology_source_id, ', ' ORDER BY m.ontology_source_id)
AS VARCHAR(250)) AS life_cycle_stage,
CONCAT(phenotype1,phenotype2) AS phenotype,
m.phenotype_model_id
@@ -8743,7 +8475,7 @@ tablespace indx
m.suc_of_gen_mod, m.mutation_description, m.phenotype1,
m.phenotype2,m.phenotype_model_id
)
- SELECT results.*,
+ SELECT '&ORG_ABBREV' as org_abbrev, results.*,
CAST(knockdown.source_id AS VARCHAR(30)) as other_source_id
FROM results
LEFT JOIN knockdown ON results.phenotype_model_id = knockdown.model_id
@@ -8853,12 +8585,13 @@ tablespace indx
-
+
for TranscriptAttributes.InterproColumns
+
@@ -8888,7 +8621,7 @@ tablespace indx
SELECT DISTINCT
dr.primary_identifier as primary_id,
dr.remark, xd1.name as interpro_name, ta.source_id
- FROM TranscriptAttributes ta, dots.AaLocation al,
+ FROM TranscriptAttributes ta, dots.AaLocation al, dots.TranslatedAASequence tas,
sres.ExternalDatabaseRelease xdr1, sres.ExternalDatabase xd1,
sres.ExternalDatabaseRelease xdr3, sres.ExternalDatabase xd3,
sres.DbRef dr, dots.DbRefAaFeature draf, dots.DomainFeature df
@@ -8898,7 +8631,8 @@ tablespace indx
'PFAM', 'PIRSF', 'PROSITEPROFILES',
'SMART', 'SUPERFAMILY', 'TIGRFAM'
)
- AND ta.aa_sequence_id = df.aa_sequence_id
+ AND ta.protein_source_id = tas.source_id
+ AND tas.aa_sequence_id = df.aa_sequence_id
AND df.aa_feature_id = draf.aa_feature_id
AND df.aa_feature_id = al.aa_feature_id
AND draf.db_ref_id = dr.db_ref_id
@@ -8909,7 +8643,8 @@ tablespace indx
) t
GROUP BY source_id
)
- SELECT source_id,
+ SELECT '&ORG_ABBREV' as org_abbrev,
+ source_id,
substr(interpro_id, 1, 200)||substr(interpro2_id, 1, 200) as interpro_id,
substr(interpro_description, 1, 3000)||substr(interpro2_description, 1, 3000) as interpro_description,
substr(pfam_id, 1, 200) as pfam_id,
@@ -8946,13 +8681,14 @@ tablespace indx
-
+
semicolon-delimited list of formatted genomic locations for each gene
+
@@ -8994,53 +8731,54 @@ tablespace indx
@@ -9322,7 +9060,7 @@ tablespace indx
-
+
Links AlphaFold entries to gene ids where Uniprot ids are directly assigned
@@ -9344,7 +9082,7 @@ tablespace indx
@@ -9564,4 +9302,4 @@ tablespace indx
]]>
-
\ No newline at end of file
+
diff --git a/Model/vp2TuningTablesEffort/findNonTuningTables b/Model/vp2TuningTablesEffort/findNonTuningTables
new file mode 100755
index 0000000000..5a62dca2a8
--- /dev/null
+++ b/Model/vp2TuningTablesEffort/findNonTuningTables
@@ -0,0 +1,16 @@
+#!/usr/bin/perl
+use strict;
+
+my %h;
+while () {
+ next unless /^tables: '(.+)'/;
+ my @a = split(/, /, $1);
+ foreach my $t (@a) {
+ $h{$t} = 1;
+ }
+}
+foreach my $t (sort keys %h) {
+ next if $t =~/apidbtuning/;
+ print STDOUT "$t\n";
+}
+
diff --git a/Model/vp2TuningTablesEffort/nonTuningTables b/Model/vp2TuningTablesEffort/nonTuningTables
new file mode 100644
index 0000000000..918487784d
--- /dev/null
+++ b/Model/vp2TuningTablesEffort/nonTuningTables
@@ -0,0 +1,87 @@
+apidb.chrcopynumber
+apidb.compoundmassspecresult
+apidb.compoundpeaks
+apidb.compoundpeakschebi
+apidb.crisprphenotype
+apidb.datasource
+apidb.externalresourceurl
+apidb.featurelocation
+apidb.genefeatureproduct
+apidb.geneinteraction
+apidb.gff3
+apidb.massspecsummary
+apidb.nafeaturehaploblock
+apidb.nafeaturephenotype
+apidb.nafeaturephenotypemodel
+apidb.ontologytermresult
+apidb.organism
+apidb.pathwayreactionxref
+apidb.phenotypegrowthrate
+apidb.phenotypemodel
+apidb.phenotyperesult
+apidb.phenotypescore
+apidb.rflpgenotype
+apidb.seqedit
+apidb.sequencevariation
+apidb.transcriptproduct
+chebi.chemical_data
+chebi.compounds
+chebi.names
+chebi.structures
+core.tableinfo
+dots.aafeature
+dots.aalocation
+dots.aasequence
+dots.aasequenceenzymeclass
+dots.blatalignment
+dots.chromosomeelementfeature
+dots.dbrefaafeature
+dots.dbrefnafeature
+dots.dbrefnasequence
+dots.domainfeature
+dots.epitopefeature
+dots.est
+dots.externalnasequence
+dots.genefeature
+dots.goassocinstevidcode
+dots.isolatefeature
+dots.isolatesource
+dots.lowcomplexityaafeature
+dots.lowcomplexitynafeature
+dots.massspecfeature
+dots.motifaasequence
+dots.nafeature
+dots.nafeaturecomment
+dots.nalocation
+dots.nasequence
+dots.secondarystructure
+dots.secondarystructurecall
+dots.similarity
+dots.snpfeature
+dots.tandemrepeatfeature
+dots.transcript
+dots.translatedaafeature
+results.compoundmassspec
+results.nafeaturediffresult
+results.nafeatureexpression
+results.nafeaturehostresponse
+results.seqvariation
+sres.bibliographicreference
+sres.contact
+sres.dbref
+sres.enzymeclass
+sres.externaldatabase
+sres.externaldatabaserelease
+sres.geneticcode
+sres.ontologyrelationship
+sres.ontologyterm
+sres.pathway
+sres.taxon
+sres.taxonname
+study.output
+study.protocolappnode
+study.protocolappparam
+study.protocolparam
+study.study
+study.studybibref
+study.studylink
diff --git a/Model/vp2TuningTablesEffort/tableGroups.yml b/Model/vp2TuningTablesEffort/tableGroups.yml
index 00950515ae..079684f73b 100644
--- a/Model/vp2TuningTablesEffort/tableGroups.yml
+++ b/Model/vp2TuningTablesEffort/tableGroups.yml
@@ -2,6 +2,7 @@
ID: 1
queries: datasetVQ.extDbNames
tables: apidb.datasource
+comment: do not need apidb.datasource (redundant)
---
ID: 2
queries: organismVQ.CNV
@@ -14,58 +15,72 @@ tables: 'apidb.datasource, sres.taxon, sres.taxonname'
ID: 4
queries: GeneId.GenesBySequenceSourceId
tables: apidb.featurelocation
+comment: add a view for this. should include onto source id.
---
ID: 5
queries: SequenceTables.Centromere
tables: 'apidb.featurelocation, sres.ontologyterm'
+comment: use above view
---
ID: 6
queries: 'GeneVQ.MetadataQuery_ncraOR74A_phenotype_GeneImage_NAFeaturePhenotypeImage_RSRC, GeneVQ.OntologyQuery_ncraOR74A_phenotype_GeneImage_NAFeaturePhenotypeImage_RSRC, GeneVQ.MetadataQuery_PHI-base_curated_phenotype_NAFeaturePhenotypeGeneric_RSRC, GeneVQ.OntologyQuery_PHI-base_curated_phenotype_NAFeaturePhenotypeGeneric_RSRC'
tables: 'apidb.nafeaturephenotype, study.study, study.studylink'
+comment: create new view. should be able to join the study stuff in orgDB. (not CNV, SNP, antibodymicroarry, chipchip, chipseq)
---
ID: 7
queries: GeneId.GenesByOldAnnotation
tables: apidb.oldannotation
+comment: create new view. is this only used by jbrowse, if so, use gff instead.
---
ID: 8
queries: 'GeneVQ.MetadataQuery_pberANKA_phenotype_Bushnell_functional_profiling_RSRC, GeneVQ.PhenotypeGrowthRate'
tables: apidb.phenotypegrowthrate
+comment: create new view.
---
ID: 9
queries: GeneVQ.MetadataQuery_ncraOR74A_phenotype_knockout_mutants_RSRC
tables: apidb.phenotypemutants
+comment: create new view.
---
ID: 10
queries: 'GeneVQ.MetadataQuery_PhenotypeScore, GeneVQ.OntologyQuery_PhenotypeScore'
tables: 'apidb.phenotypescore, sres.externaldatabase, sres.externaldatabaserelease, study.protocolappnode, study.study, study.studylink'
+comment: create new tuning table. this is pure orgDB.
---
ID: 11
queries: GeneVQ.PhenotypeScoreDataset
tables: 'apidb.phenotypescore, sres.externaldatabase, sres.externaldatabaserelease, study.study, study.studylink'
+comment: same table as above
---
ID: 12
queries: rflpGenotypeVQ.withIsolates
tables: apidb.rflpgenotype
+comment: make new view
---
ID: 13
queries: CommentTables.GeneComments
tables: 'apidbtuning.annotatedgenomesummary, apidbtuning.geneattributes, apidbtuning.transcriptattributes, dots.dbrefnafeature, sres.dbref, sres.externaldatabase, sres.externaldatabaserelease'
+comment: what is this query doing?
---
ID: 14
queries: GeneAttributes.OrganismAbbrev
tables: 'apidbtuning.apolloid, apidbtuning.geneattributes, apidb.organism'
+comment: create view for apidb.organism.
---
ID: 15
queries: GeneId.GenesByChIPchip
tables: 'apidbtuning.chipchiptranscript, study.protocolappnode'
+comment: ?
---
ID: 16
queries: CompoundAttributes.DefaultStructure
tables: 'apidbtuning.compoundattributes, apidbtuning.compoundid, chebi.structures'
+comment: need tuning view for chebi
---
ID: 17
queries: 'CompoundTables.MassSpecGraphsDataTableTriTryp, CompoundTables.MassSpecGraphsDataTablePlasmoDB'
tables: 'apidbtuning.compoundattributes, apidbtuning.datasetpresenter, apidb.compoundmassspecresult, apidb.compoundpeaks, apidb.compoundpeakschebi, chebi.compounds, study.protocolappnode'
+comment: talk to kathryn. might be extra cruft in the mass spec queries
---
ID: 18
queries: CompoundIds.CompoundsByPathway
@@ -194,6 +209,7 @@ tables: 'apidbtuning.datasetpresenter, apidbtuning.externaldbdatasetpresenter, s
ID: 49
queries: TranscriptAttributes.HasProteomics
tables: 'apidbtuning.datasetpresenter, apidbtuning.geneattributes, apidb.datasource, apidb.massspecsummary, sres.externaldatabase, sres.externaldatabaserelease'
+comment: DELETED
---
ID: 50
queries: GeneAttributes.ProteinExpressionPtracks
@@ -210,6 +226,7 @@ tables: 'apidbtuning.datasetpresenter, apidbtuning.msmodifiedpeptidesummary, api
ID: 53
queries: TranscriptAttributes.ProteinGTracks
tables: 'apidbtuning.datasetpresenter, apidbtuning.msmodifiedpeptidesummary, apidbtuning.transcriptattributes, apidb.datasource, apidb.massspecsummary, dots.secondarystructure, sres.externaldatabase, sres.externaldatabaserelease'
+comment: DELETED
---
ID: 54
queries: GeneId.GenesByISM
@@ -266,6 +283,7 @@ tables: 'apidbtuning.gbrowsetracksorganism, apidbtuning.genomicseqattributes, ap
ID: 67
queries: TranscriptAttributes.DnaGTracks
tables: 'apidbtuning.gbrowsetracksorganism, apidbtuning.transcriptattributes, apidb.massspecsummary'
+comment: DELETED
---
ID: 68
queries: TranscriptAttributes.HasQuantitativeProteomics
@@ -358,6 +376,7 @@ tables: 'apidbtuning.geneattributes, apidbtuning.taxonspecies, apidb.datasource,
ID: 90
queries: GeneTables.PreferredProducts
tables: 'apidbtuning.geneattributes, apidbtuning.transcriptattributes, apidb.genefeatureproduct, apidb.transcriptproduct, dots.genefeature, dots.goassocinstevidcode, dots.transcript, sres.ontologyterm'
+comment: no longer used.
---
ID: 91
queries: GeneAttributes.PbrowseOrganismAbbrev