|
This section describes the format of each table in
autoSql format.
Affymetrix 10K SNP Details
table affy10KDetails
"Information representing the Affymetrix 10K Mapping Array"
(
string affyId; "Affymetrix SNP id"
string rsId; "RS identifier (some are null)"
string tscId; "TSC identifier (some are null)"
char[2] baseA; "The first allele (A)"
char[2] baseB; "The second allele (B)"
char[34] sequenceA; "The A allele with flanking sequence"
char[34] sequenceB; "The B allele with flanking sequence"
char[8] enzyme; "The enzyme that was used to prepare the sample (HindIII
or XbaI)"
)
Affymetrix 120K SNP Array Information
table affyGenoDetails
"Information representing the Affymetrix 120K SNP array"
(
uint affyId; "Affymetrix SNP id"
uint rsId; "RS identifier (some are null)"
char[2] baseA; "The first allele (A)"
char[2] baseB; "The second allele (B)"
char[34] sequenceA; "The A allele with flanking sequence"
char[34] sequenceB; "The B allele with flanking sequence"
char[8] enzyme; "The enzyme that was used to prepare the sample (HindIII
or XbaI)"
float minFreq; "The minimum allele frequency"
float hetzyg; "The heterozygosity from all observations"
float avHetSE; "The Standard Error for the average heterozygosity (not
used)"
char[2] NA04477; "Individual 01"
char[2] NA04479; "Individual 02"
char[2] NA04846; "Individual 03"
char[2] NA11036; "Individual 04"
char[2] NA11038; "Individual 05"
char[2] NA13056; "Individual 06"
char[2] NA17011; "Individual 07"
char[2] NA17012; "Individual 08"
char[2] NA17013; "Individual 09"
char[2] NA17014; "Individual 10"
char[2] NA17015; "Individual 11"
char[2] NA17016; "Individual 12"
char[2] NA17101; "Individual 13"
char[2] NA17102; "Individual 14"
char[2] NA17103; "Individual 15"
char[2] NA17104; "Individual 16"
char[2] NA17105; "Individual 17"
char[2] NA17106; "Individual 18"
char[2] NA17201; "Individual 19"
char[2] NA17202; "Individual 20"
char[2] NA17203; "Individual 21"
char[2] NA17204; "Individual 22"
char[2] NA17205; "Individual 23"
char[2] NA17206; "Individual 24"
char[2] NA17207; "Individual 25"
char[2] NA17208; "Individual 26"
char[2] NA17210; "Individual 27"
char[2] NA17211; "Individual 28"
char[2] NA17212; "Individual 29"
char[2] NA17213; "Individual 30"
char[2] PD01; "Individual 31"
char[2] PD02; "Individual 32"
char[2] PD03; "Individual 33"
char[2] PD04; "Individual 34"
char[2] PD05; "Individual 35"
char[2] PD06; "Individual 36"
char[2] PD07; "Individual 37"
char[2] PD08; "Individual 38"
char[2] PD09; "Individual 39"
char[2] PD10; "Individual 40"
char[2] PD11; "Individual 41"
char[2] PD12; "Individual 42"
char[2] PD13; "Individual 43"
char[2] PD14; "Individual 44"
char[2] PD15; "Individual 45"
char[2] PD16; "Individual 46"
char[2] PD17; "Individual 47"
char[2] PD18; "Individual 48"
char[2] PD19; "Individual 49"
char[2] PD20; "Individual 50"
char[2] PD21; "Individual 51"
char[2] PD22; "Individual 52"
char[2] PD23; "Individual 53"
char[2] PD24; "Individual 54"
)
Affymetrix Transcriptome
table affyTranscriptome
"Describes (x,y) pairs of samples"
ushort bin; "A field to speed indexing"
string chrom; "Chromosome alignment is on"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Unique index given to each block of samples"
uint score; "Overall block score from 0 to 1000"
char[1] strand; "Strand: + or -"
uint sampleCount; "Number of samples in this block"
uint[sampleCount] samplePosition; "Base position of each sample in this
block, relative to chromStart"
uint[sampleCount] sampleHeight; "Score for each sample (y-value) from 0 to
1000"
)
Alternative Splicing
table altGraphX
"An alternatively-spliced gene graph"
(
string tName; "Name of target sequence, often a chrom"
int tStart; "First bac touched by graph"
int tEnd; "Start position in first bac"
string name; "Human readable name"
uint id; "Unique ID"
char[2] strand; "+ or - strand"
uint vertexCount; "Number of vertices in graph"
ubyte[vertexCount] vTypes; "Type for each vertex"
int[vertexCount] vPositions; "Position in target for each vertex"
uint edgeCount; "Number of edges in graph"
int[edgeCount] edgeStarts; "Array with start vertex of edges"
int[edgeCount] edgeEnds; "Array with end vertex of edges"
table evidence[edgeCount] evidence; "Array of evidence tables containing references
to mRNAs that support a particular edge"
int[edgeCount] edgeTypes; "Type for each edge, ggExon, ggIntron, etc"
int mrnaRefCount; "Number of supporting mRNAs"
string[mrnaRefCount] mrnaRefs; "Ids of mrnas supporting this"
int[mrnaRefCount] mrnaTissues; "Ids of tissues that mrnas come from, indexes
into tissue table"
int[mrnaRefCount] mrnaLibs; "Ids of libraries that mrnas come from, indexes
into library table"
)
Atlas Oncology Site
table atlasOncoGene
"Table used to link into ATLAS Oncology site"
(
string locusSymbol; "LocusLink Symbol"
string atlasGene; "ATLAS Gene"
string otherGene; "Other gene"
string url; "URL for corresonding ATLAS web page"
)
Bactig Positions
table bactigPos
"Bactig positions in chromosome coordinates (bed 4 +)."
(
string chrom; "Chromosome"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Bactig"
string startContig; "First contig in this bactig"
string endContig; "Last contig in this bactig"
)
BGI (Beijing Genomics Institute) SNPs
table bgiSnp
"Beijing Genomics Institute SNP information as bed 4 +"
(
string chrom; "Chromosome"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "BGI SNP name: snp.superctg.ctg.pos.type.strainID"
char[1] snpType; "S (substitution), I (insertion), or D (deletion)"
uint readStart; "Start position in alternate allele read"
uint readEnd; "End position in alternate allele read"
uint qualChr; "Quality score in reference assembly"
uint qualReads; "Quality score in alternate allele read"
string snpSeq; "'X->Y' or indel sequence"
string readName; "Name of alternate allele read"
char[1] readDir; "Direction of read relative to reference"
char[4] inBroiler; "SNP found in Broiler strain? yes, no or n/a if not covered"
char[4] inLayer; "SNP found in Layer strain? yes, no or n/a if not covered"
char[4] inSilkie; "SNP found in Silkie strain? yes, no or n/a if not covered"
string primerL; "Left primer sequence"
string primerR; "Right primer sequence"
char[1] questionM; "L for dubious indels, H for other indels and SNPs"
string extra; "Additional information"
)
Bio Cyc Pathway Map
table bioCycMapDesc
"Decription of BioCyc pathway maps"
(
string mapID; "BioCyc pathway map"
string description; "BioCyc pathway map description"
)
Bio Cyc Pathway
table bioCycPathway
"BioCyc Pathway to Known Gene cross reference"
(
string kgID; "Known Gene ID"
string geneID; "Gene (RefSeq) ID"
string mapID; "BioCyc pathway map ID"
)
Blast Output
The following definition is used for several tables that contain blast
for various organisms.
table blastTab
"Tab-delimited blast output file"
(
string query; "Name of query sequence"
string target; "Name of target sequence"
float identity; "Percent identity"
uint aliLength; "Length of alignment"
uint mismatch; "Number of mismatches"
uint gapOpen; "Number of gap openings"
uint qStart; "Start in query (0 based)"
uint qEnd; "End in query (non-inclusive)"
uint tStart; "Start in target (0 based)"
uint tEnd; "End in target (non-inclusive)"
double eValue; "Expectation value"
double bitScore; "Bit score"
)
Browser Extensible Data (BED)
The following definition is used for several tables, which may use 4 or more of
the fields.
table bed
"Browser extensible data"
(
string chrom; "Chromosome or FPC contig"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Name of item"
uint score; "Score from 0-1000"
char[1] strand; "+ or -"
uint thickStart; "Start of where display should be thick (start codon)"
uint thickEnd; "End of where display should be thick (stop codon)"
uint reserved; "Always zero for now"
int blockCount; "Number of blocks (a block contains no gaps)"
int[blockCount] blockSizes; "Comma-separated list of block sizes"
int[blockCount] blockStarts; "Start positions relative to chromStart."
int expCount; "Number of experiments."
int[expCount] expIds; "Experiment IDs."
int[expCount] expScores; "Experiment scores."
)
Celera Coverage
table celeraCoverage
"Summary of large genomic Duplications from Celera Data"
(
string chrom; "Chromosome or FPC contig"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Source of information"
)
Celera Duplications
table celeraDupPositive
"Summary of large genomic Duplications from Celera Data"
(
string chrom; "Chromosome or FPC contig"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Celera accession name"
string fullname; "Celera accession full name"
float fracMatch; "Fraction of matching bases"
float bpalign; "Base pair alignment score"
)
Celera Overlay
table celeraOverlay
"Celera assembly overlay in the public (NCBI) assembly"
(
string chrom; "Chromosome"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Other chromosome and start"
string otherChrom; "Other chromosome"
uint otherStart; "Start in other chromosome"
uint otherEnd; "End in other chromosome"
char orient; "Strand/orientation (F or R)"
char field1; "? (always M)"
char field2; "? (r or u)"
string localId; "?"
string parentInfo; "?"
string refId; "Reference ID"
uint refStart; "Start position in reference"
uint refLength; "Length in reference"
byte refOrient; "Strand/orientation in reference (-1 or 1)"
string queryId; "Query ID"
uint queryStart; "Start position in query"
uint queryLength; "Length in query"
byte queryOrient; "Strand/orientation in query (-1 or 1)"
)
CGAP Alias
table cgapAlias
"Associates CGAP pathway IDs with gene symbols or mRNA accessions"
(
string cgapID; "CGAP pathway ID"
string alias; "Gene symbol or mRNA"
)
CGAP/BioCarta Pathway Descriptions
table cgapBiocDesc
"CGAP/BioCarta pathway description"
(
string mapID; "CGAP/BioCarta pathway map ID"
string description; "Description"
)
CGAP/BioCarta Pathway Cross-Reference
table cgapBiocPathway
"CGAP BioCarta pathway cross reference"
(
string cgapID; "CGAP pathway ID"
string mapID; "BioCarta pathway ID"
)
Chain Alignments
table chain
"Summary info about a chain of alignments"
(
double score; "Score of chain"
string tName; "Target sequence name"
uint tSize; "Target sequence size"
uint tStart; "Alignment start position in target"
uint tEnd; "Alignment end position in target"
string qName; "Query sequence name"
uint qSize; "Query sequence size"
char qStrand; "Query strand"
uint qStart; "Alignment start position in query"
uint qEnd; "Alignment end position in query"
uint id; "Chain ID"
}
Chain Link
table chainLink
"Alignment block in chain"
(
string tName; "Target sequence name"
uint tStart; "Alignment start position in target"
uint tEnd; "Alignment end position in target"
uint qStart; "Start in query"
uint chainId; "Chain ID in chain table"
)
Chimp/Human Simple Differences
table chimpSimpleDiff
"Simple differences between the chimp and human genome assemblies"
(
string chrom; "Chromosome number"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string tseq; "Target sequence (A,T,C,G)"
string qseq; "Query sequence (A,T,C,G)"
)
Chromosome Band Information
table cytoBand
"Describes the positions of cytogenetic bands within a chromosome"
(
string chrom; "Chromosome number"
uint chromStart; "Start position in genoSeq"
uint chromEnd; "End position in genoSeq"
string name; "Name of cytogenetic band"
string gieStain; "Giesma stain results"
)
Chromosome Information
table chromInfo
"Chromosome names and sizes"
(
string chrom; "Chromosome name"
uint size; "Chromosome size"
string fileName; "Chromosome file (raw one byte per base)"
)
Clone Fragment Positions
table chrN_gl
"Fragment positions in golden path"
(
ushort bin; "A field to speed indexing added to many
tables August 2001"
uint matches; "Number of bases that match that aren't repeats"
uint misMatches; "Number of bases that don't match"
string frag; "Fragment name"
uint start; "Start position in golden path"
uint end; "End position in golden path"
char[1] strand; "+ or - for strand"
)
Clone Information
table clonePos
"A clone's position and other info."
(
string name; "Name of clone including version"
uint seqSize; "base count not including gaps"
ubyte phase; "htg phase"
string chrom; "Chromosome name"
uint chromStart; "Start in chromosome"
uint chromEnd; "End in chromosome"
char[1] stage; "F/D/P for finished/draft/predraft"
string faFile; "File with sequence."
)
Contamination Information
table contamination
"Contamination in assembly (bed 4 +)"
(
string chrom; "Chromosome"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Name (type of contamination: E.coli, vector etc)"
string acc; "NCBI accession where contamination was found"
string ctg; "Alternate name (e.g. WGS contig name)"
int len; "Length of contaminated portion of sequence"
)
Contig/Accession Map
table contigAcc
"Maps a contig to its accession."
(
string contig; "Contig name"
string acc; "GenBank accession"
)
Contig Information
table ctgPos
"Where a contig is inside of a chromosome."
(
string contig; "Name of contig"
uint size; "Size of contig"
string chrom; "Chromosome name"
uint chromStart; "Start in chromosome"
uint chromEnd; "End in chromosome"
)
Contig Information (Expanded)
table ctgPos2
"Where a contig is inside of a chromosome including contig type information."
(
string contig; "Name of contig"
uint size; "Size of contig"
string chrom; "Chromosome name"
uint chromStart; "Start in chromosome"
uint chromEnd; "End in chromosome"
char[1] type; "(W)GS contig, (F)inished, (P)redraft, (D)raft, (O)ther"
)
CpG Islands
table cpgIsland
"Describes CpG Islands of 50 bases or more that are at least 50% G/C"
(
string chrom; "Chromosome or FPC contig"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "CpG Island"
uint minLength; "Minimum Island Length"
uint cpgNum; "Number of CpGs in island"
uint gcNum; "Number of C and G in island"
uint perCpg; "Percentage of island that is CpG"
uint perGc; "Percentage of island that is C or G"
)
CpG Islands (Extended)
table cpgIslandExt
"Describes the CpG Islands (includes observed/expected ratio)"
(
string chrom; "Chromosome or FPC contig"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "CpG Island"
uint length; "Island Length"
uint cpgNum; "Number of CpGs in island"
uint gcNum; "Number of C and G in island"
uint perCpg; "Percentage of island that is CpG"
uint perGc; "Percentage of island that is C or G"
float obsExp; "Ratio of observed(cpgNum) to expected(numC*numG/length)
CpG in island"
)
dbSnpRS
table dbSnpRS
"Information from dbSNP at the reference SNP level"
(
uint rsId; "RS identifier"
float avHet; "Average heterozygosity from all observations"
float avHetSE; "Standard Error for the average heterozygosity from all
observations"
string valid; "Validation status of the SNP"
char[1] base1; "Base of the first allele"
char[1] base2; "Base of the second allele"
string assembly; "Sequence in the ucsc assembly"
string alternate; "Sequence of the alternate allele"
)
DNA Motif
table dnaMotif
"A gapless DNA motif"
(
string name; "Motif name"
int columnCount; "Count of columns in motif"
float[columnCount] aProb; "Probability of A's in each column"
float[columnCount] cProb; "Probability of C's in each column"
float[columnCount] gProb; "Probability of G's in each column"
float[columnCount] tProb; "Probability of T's in each column"
)
DupSpMrna
table dupSpMrna
"Duplicate mRNA/Protein entries that have identical CDS structures"
(
string mrnaID; "mRNA ID name"
string proteinID; "Protein ID from SwissProt"
string dupMrnaID; "mRNA ID of duplicated entry"
string dupProteinId; "Protein ID of duplicated entry"
)
EncodeRegionInfo
table encodeRegionInfo
"Descriptive, assembly-independent information about ENCODE regions"
(
string name; "Name of region"
string descr; "Description (gene region, random pick, etc.)"
)
Ensembl Gene XRef
table ensGtp
"Associates Ensembl gene, transcript, and protein IDs"
(
string gene; "Gene ID"
string transcript; "Transcript ID"
string protein; "Protein ID"
)
EnsemblXref
table ensemblXref
"Cross-reference info between transcript entries and translation entries of Ensembl
genes"
(
string db; "Ensembl Database"
int gene_id; "Gene ID number"
string gene_name; "Gene name in database"
int transcript_id; "Transcript ID number"
string transcript_name; "Transcript name in database"
uint translation_id; "Translation ID number"
string translation_name; "Translation name in database"
string external_db; "External database"
string external_name; "External status"
)
EnsemblXref2
table ensemblXref2
"Cross-reference info between transcript entries and translation entries of Ensembl
genes (alternative table used in some assemblies)"
(
string transcript_name; "Transcript name"
string translation_name; "Translation name"
)
EnsemblXref3
table ensemblXref3
"A cross-reference table for Ensembl Genes."
(
string gene; "Ensembl gene ID"
string geneVer; "Ensembl gene ID version number"
string transcript; "Ensembl transcript ID"
string transcriptVer; "Ensembl transcript ID version number"
string protein; "Ensembl protein ID"
string proteinVer; "Ensembl protein version number"
string tremblAcc; "TrEMBL protein accession number"
string swissDisplayId; "Swiss-Prot protein display ID"
string swissAcc; "Swiss-Prot protein accession number"
)
Ensembl gene_xref Table
Ensemble gene_xref table downloaded directly from the Ensembl ftp site (18.34
release 11/04). Refer to the Ensembl site for details. CAUTION: Ensembl sometimes
changes its table definitions and some fields may not contain the data that the
name indicates, e.g. translation_name.
table ensGeneXref
"Table gene_xref downloaded from Ensembl"
(
string db; "#"
string analysis; "#"
string type; "#"
int gene_id; "#"
string gene_name; "#"
int[5] gene_version; "#"
int transcript_id; "#"
string transcript_name; "#"
int[5] transcript_version; "#"
int[5] translation_name; "#"
int translation_id; "#"
int[5] translation_version; "#"
string external_db; "#"
string external_name; "#"
char[10] external_status; "#"
)
Ensembl transcript Table
Ensembl transcript table downloaded directly from the Ensembl ftp site (18.34
release 11/04). Refer to the Ensembl site for details. CAUTION: Ensembl
sometimes changes its table definitions and some fields may not contain the data
that the name indicates.
table ensTranscript
"Table transcript downloaded from Ensembl"
(
int id; "#"
string db; "#"
string analysis; "#"
string type; "#"
int transcript_id; "#"
string transcript_name; "#"
int transcript_version; "#"
string chr_name; "#"
int chr_start; "#"
int chr_end; "#"
int chr_strand; "#"
int coding_start; "#"
int coding_end; "#"
int translation_id; "#"
string translation_name; "#"
string translation_version; "#"
int gene_id; "#"
string gene_name; "#"
int gene_version; "#"
lstring exon_structure; "#"
lstring exon_ids; "#"
string external_db; "#"
string external_name; "#"
char[10] external_status; "#"
)
Exofish Information
table exoFish
"An evolutionarily conserved region (ecore) with Tetroadon"
(
string chrom; "Chromosome or FPC contig"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Just a dummy dot"
uint score; "Score from 0 to 1000"
)
Exonerate Mouse Homologies
Last used Apr. 2001.
table exoMouse
"A rough alignment - not detailed"
(
string chrom; "Chromosome or FPC contig"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Name of other sequence"
uint score; "Score from 0 to 1000"
char[1] strand; " or -"
uint otherStart; "Start in other sequence"
uint otherEnd; "End in other sequence"
)
Experiment Record
table expRecord
"Minimal descriptive data for an experiment in the browser"
(
uint id; "Internal id of experiment"
string name; "Name of experiment"
lstring description; "Description of experiment"
lstring url; "URL relevant to experiment"
lstring ref; "Reference for experiment"
lstring credit; "Who to credit with experiment"
uint numExtras; "Number of extra things"
lstring[numExtras] extras; "Extra things of interest, i.e. classifications"
)
Expression Data
table expData
"Expression data (no mapping, just spots)"
(
string name; "Name of gene/target/probe etc."
uint expCount; "Number of scores"
float[expCount] expScores; "Scores. May be absolute or relative ratio"
)
Expression Distance Between 2 Genes
table expDistance
"Distance between two genes in expression space"
(
string query; "Name of one gene"
string target; "Name of other gene"
float distance; "Distance in expression space, always >= 0"
)
FISH Clones
table fishClones
"Describes the positions of fishClones in the assembly"
(
string chrom; "Chromosome number"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Name of clone"
uint score; "Always 1000"
uint placeCount; "Number of times FISH'd"
string[placeCount] bandStarts; "Start FISH band"
string[placeCount] bandEnds; "End FISH band"
string[placeCount] labs; "Lab where clone FISH'd"
string placeType; "How clone was placed on the sequence assembly"
uint accCount; "Number of accessions associated with the clone"
string[accCount] accNames; "Accession associated with clone"
uint stsCount; "Number of STS markers associated with this clone"
string[stsCount] stsNames; "Names of STS markers"
uint beCount; "Number of BAC end sequences associated with this
clone"
string[beCount] beNames; "Accessions of BAC ends"
)
FlyBase Accessions Linked to SwissProt Accessions
table flyBaseSwissProt
"FlyBase acc to SwissProt acc, plus some other SwissProt info"
(
string flyBaseId; "FlyBase FBgn ID"
string swissProtId; "SwissProt ID"
string spGeneName; "Gene name from SwissProt (long)"
string spSymbol; "Symbolic-looking gene ID from SwissProt"
)
FlyBase Alleles
table fbAllele
"The alleles of a gene"
(
int id; "Allele ID"
string geneId; "FlyBase ID of gene"
string name; "Allele name"
)
FlyBase Gene Synonyms
table fbSynonym
"Links all the names we call a gene to its FlyBase ID"
(
string geneId; "FlyBase ID"
string name; "A name (synonym or real)"
)
FlyBase Genes
table fbGene
"Links FlyBase IDs, gene symbols and gene names"
(
string geneId; "FlyBase ID"
string geneSym; "Short gene symbol"
string geneName; "Gene name - up to a couple of words"
)
FlyBase Genes Cross-Reference (2004)
table flyBase2004Xref
"FlyBase cross references circa late 2004 (dm2/4.0; dp3/1.0 uses a subset)"
(
string name; "FlyBase annotation gene ID"
string symbol; "Symbolic gene name"
lstring synonyms; "Comma-separated list of synonyms"
string fbtr; "FlyBase FBtr acc"
string fbgn; "FlyBase FBgn acc"
string fbpp; "FlyBase FBpp acc"
string fban; "FlyBase FBan acc"
string type; "Annotation type (for noncoding only)"
)
FlyBase Genes Linked to BDGP Transcript IDs
table fbTranscript
"Links FlyBase gene IDs and BDGP transcript IDs"
(
string geneId; "FlyBase gene ID"
string transcriptId; "BDGP Transcript ID"
)
FlyBase Genes Linked to GO IDs
table fbGo
"Links FlyBase gene IDs and GO IDs/aspects"
(
string geneId; "FlyBase gene ID"
string goId; "GO ID"
string aspect; "P (process), F (function) or C (cellular component)"
)
FlyBase Observed Phenotype in Mutant
table fbPhenotype
"Observed phenotype in mutant. Sometimes contains gene function info"
(
string geneId; "FlyBase gene ID"
int fbAllele; "ID in fbAllele table or 0 if not allele-specific"
int fbRef; "ID in fbRef table"
lstring text; "Descriptive text"
)
FlyBase Reference
table fbRef
"A literature or sometimes database reference"
(
int id; "Reference ID"
lstring text; "Usually begins with FlyBase ref ID, but not always"
)
FlyBase Role of Gene in Wildtype
table fbRole
"Role of gene in wildType"
(
string geneId; "FlyBase gene ID"
int fbAllele; "ID in fbAllele table or 0 if not allele-specific"
int fbRef; "ID in fbRef table"
lstring text; "Descriptive text"
)
FlyReg Data
table flyreg
"Flyreg data from Casey Bergman"
(
string chrom; "Chromosome"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Factor"
string target; "Target"
uint pmid; "PubMed ID"
)
FlyReg Data (version 2)
table flyreg
"Flyreg data (version 2) from Casey Bergman"
(
string chrom; "Chromosome"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Factor"
string target; "Target"
uint pmid; "PubMed ID"
uint fpid; "Footprint ID -- stable ID across versions"
)
Fosmid End Pairs
table fosEndPairs
"Positions of end pairs for fosmids"
(
short bin; "Bin number for browser speedup"
string chrom; "Chromosome"
uint chromStart; "Start position of fosmid in chromosome"
uint chromEnd; "End position of fosmid in chromosome"
string name; "Name of fosmid"
uint score; "Score = 1000/(# of times fosmid appears in assembly)"
char[1] strand; "Value should be + or -"
string pslTable; "Table which contains corresponding PSL records for linked
features"
uint lfCount; "Number of linked features in the series"
uint[lfCount] lfStarts; "Comma-separated list of start positions of each linked
feature in genomic"
uint[lfCount] lfSizes; "Comma-separated list of sizes of each linked feature
in genomic"
string[lfCount] lfNames; "Comma-separated list of names of linked features"
)
Gap Positions
table chrN_gap
"Gaps in golden path"
(
ushort bin; "A field to speed indexing added to many
tables August 2001"
uint matches; "Number of bases that match that aren't repeats"
uint misMatches; "Number of bases that don't match"
string chrom; "which chromosome"
uint chromStart; "start position in chromosome"
uint chromEnd; "end position in chromosome"
int ix; "ix of this fragment (useless)"
char[1] n; "always 'N'"
uint size; "size of gap"
string type; "contig, clone, fragment, etc."
string bridge; "yes, no, mrna, bacEndPair, etc."
)
GC Content
table gcPercent
"Displays GC content in 20Kb non-overlapping blocks for genome"
(
string chrom; "Chromosome number"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Constant string GC"
uint gcPpt; "Average number of G and C per 1000 bases"
)
GenBank Protein Annotations
table gbProtAnn
"Protein Annotations from GenPept mat_peptide fields"
(
string chrom; "Chromosome"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Name of item"
string product; "Protein product name"
string note; "Note (may be empty)"
string proteinId; "GenBank protein accession(.version)"
uint giId; "GenBank db_xref number"
)
Gene Bands
table geneBands
"Band locations of known genes"
(
string name; "Gene name (HUGO Gene Nomenclature Committee symbol, if possible)"
string mrnaAcc; "RefSeq mRNA accession"
int count; "Number of times this accession maps to the genome"
string[count] bands; "List of chromosome bands to which it maps"
)
Gene Boundaries as Defined by RNA and Spliced
EST Clusters
table rnaCluster
"Gene boundaries deduced from clustering spliced ESTs and mRNAs against the genome"
(
smallint bin; "Index"
string chrom; "Chromosome or FPC contig"
uint chromStart; "Start position in chromosome"
uint chromEnd; "End position in chromosome"
string name; "Name of item"
uint score; "Score from 0-1000"
char[1] strand; "+ or -"
uint thickStart; "Start of where display should be thick (start codon)"
uint thickEnd; "End of where display should be thick (stop codon)"
uint reserved; "Always zero for now"
int blockCount; "Number of blocks (a block contains no gaps)"
longblob blockSizes; "Size of each block"
longblob chromStarts; "Start position of each block in chromosome"
)
Gene Predictions and RefSeq Genes
The following definition is used for gene prediction tables. In
alternative-splicing situations, each transcript has a row in this table.
table genePred
"A gene prediction."
(
string name; "Name of gene"
string chrom; | 