diff options
| author | Pjotr Prins | 2023-11-19 14:55:26 +0100 |
|---|---|---|
| committer | Pjotr Prins | 2024-03-02 17:11:14 -0600 |
| commit | 7a241fac2234c1d0cc50bc5574cff6d4b859ee75 (patch) | |
| tree | 2dba009f8a51f7def7a28af1984521dcf82fcddb | |
| parent | 1aeb9bb244874b1137364c46c292a166d7b6e40a (diff) | |
| download | genenetwork2-7a241fac2234c1d0cc50bc5574cff6d4b859ee75.tar.gz | |
doc: databasing
| -rw-r--r-- | doc/database.org | 39 |
1 files changed, 23 insertions, 16 deletions
diff --git a/doc/database.org b/doc/database.org index d408f5ca..8bf2a404 100644 --- a/doc/database.org +++ b/doc/database.org @@ -24,54 +24,62 @@ select table_name,round(((data_length + index_length) / 1024 / 1024), 2) `Size i +-------------------------+------------+ | table_name | Size in MB | +-------------------------+------------+ -| ProbeSetData | 59358.80 | DataStrainValues <- id, strain, value -| SnpAll | 15484.67 | +| ProbeSetData | 59358.80 | DataStrainValues (5G traits) <- id, strain, value | ProbeData | 22405.44 | mRNAStrainValues <- individual probe data (mRNA) [GN1,GN3] -| SnpPattern | 9177.05 | | ProbeSetSE | 14551.02 | ProbeSetStrainError <- SE values aligns with ProbeSetData -| QuickSearch | 5972.86 | | ProbeSetXRef | 4532.89 | PrecomputeLRS <- precomputed LRS values -| LCorrRamin3 | 18506.53 | | ProbeSE | 6263.83 | DataStrainError <- trait SE [GN3] | ProbeSet | 2880.21 | ProbeSetInfo <- trait, e.g. 100001_at +| ProbeSetFreeze | 0.22 | DatasetInfo <- dataset, e.g. "Hippocampus_BXD_Jun06" | Probe | 2150.30 | ProbeInfo <- trait info incl sequence +| Phenotype | 6.50 | PhenotypeMeta <- "Hippocampus weight" +| ProbeXRef | 743.38 | ProbeFreezeDataIDs <- link ProbeFreezeId,ProbeId with DataId +| Datasets | 2.31 | DatasetMeta <- "Data generated by..." +| NStrain | 4.80 | StrainCountDataId <- Strains used in dataset +| Strain | 1.07 | StrainNames <- with species ID and alias +| TissueProbeSetData | 74.42 | <- link Id,TissueID with value +| TissueProbeSetXRef | 14.73 | +| PublishData | 22.54 | PublishStrainValues <- id, strainId, value (3M traits) +| PublishSE | 4.71 | Published SE (300K traits) +| PublishXRef | 2.18 | List of changes on editing data (mostly Rob) ++-------------------------+------------+ + +Less commonly used tables: + ++-------------------------+------------+ +| table_name | Size in MB | ++-------------------------+------------+ +| LCorrRamin3 | 18506.53 | +| SnpAll | 15484.67 | +| SnpPattern | 9177.05 | +| QuickSearch | 5972.86 | | GenoData | 3291.91 | | CeleraINFO_mm6 | 989.80 | | pubmedsearch | 1032.50 | -| ProbeXRef | 743.38 | ProbeFreezeDataIDs <- link ProbeFreezeId,ProbeId with DataId | GeneRIF_BASIC | 448.54 | | BXDSnpPosition | 224.44 | | EnsemblProbe | 133.66 | | EnsemblProbeLocation | 105.49 | | Genbank | 37.71 | -| TissueProbeSetData | 74.42 | <- link Id,TissueID with value | AccessLog | 42.38 | | GeneList | 34.11 | | Geno | 33.90 | | MachineAccessLog | 28.34 | | IndelAll | 22.42 | -| PublishData | 22.54 | PublishStrainValues <- Id,StrainId,value -| TissueProbeSetXRef | 14.73 | | ProbeH2 | 13.26 | | GenoXRef | 22.83 | | TempData | 8.35 | | GeneList_rn3 | 5.54 | | GORef | 4.97 | -| Phenotype | 6.50 | PhenotypeMeta <- "Hippocampus weight" | temporary | 3.59 | | InfoFiles | 3.32 | | Publication | 3.42 | | Homologene | 5.69 | -| Datasets | 2.31 | DatasetMeta <- "Data generated by..." | GeneList_rn33 | 2.61 | -| PublishSE | 4.71 | | GeneRIF | 2.18 | | Vlookup | 1.87 | | H2 | 2.18 | -| PublishXRef | 2.18 | -| NStrain | 4.80 | StrainCountDataId <- Strains used in dataset | IndelXRef | 2.91 | -| Strain | 1.07 | StrainNames <- with species ID and alias | GeneMap_cuiyan | 0.51 | | user_collection | 0.30 | | CaseAttributeXRef | 0.44 | @@ -79,7 +87,6 @@ select table_name,round(((data_length + index_length) / 1024 / 1024), 2) `Size i | GeneIDXRef | 0.77 | | Docs | 0.17 | | News | 0.17 | -| ProbeSetFreeze | 0.22 | -> dataset, e.g. "Hippocampus_M430_V2_BXD_PDNN_Jun06" | GeneRIFXRef | 0.24 | | Sample | 0.06 | | login | 0.06 | |