7adb1d36b6e6f5ce11d882f348af4b1194ad17b6 max Wed Apr 7 01:05:10 2021 -0700 comitting a few changes to the uniprot pipeline to make it more stable for ottomatization, but also to get the filters to work correctly, refs #27069 diff --git src/hg/utils/otto/uniprot/bed12UniProtFullSeqBgp.as src/hg/utils/otto/uniprot/bed12UniProtFullSeqBgp.as new file mode 100644 index 0000000..0e85e61 --- /dev/null +++ src/hg/utils/otto/uniprot/bed12UniProtFullSeqBgp.as @@ -0,0 +1,48 @@ +table bed12BgpUniProtAnnot +"Browser extensible data (12 fields), eight fields for bigGenePred support, plus extra fields (dbName-pmids, not used by all UniProt subtracks) with UniProt-specific information" + ( + string chrom; "Chromosome (or contig, scaffold, etc.)" + 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; "Used as itemRgb as of 2004-11-22" + int blockCount; "Number of blocks" + int[blockCount] blockSizes; "Comma separated list of block sizes" + int[blockCount] chromStarts; "Start positions relative to chromStart" + + string name2; "Alternative/human readable name" + string cdsStartStat; "Status of CDS start annotation (none, unknown, incomplete, or complete)" + string cdsEndStat; "Status of CDS end annotation (none, unknown, incomplete, or complete)" + int[blockCount] exonFrames; "Exon frame {0,1,2}, or -1 if no frame for exon" + string type; "Transcript type" + string geneName; "Primary identifier for gene" + string geneName2; "Alternative/human-readable gene name" + string geneType; "Gene type" + + string acc; "UniProt main accession" + lstring uniprotName; "UniProt main record name" + string status; "UniProt status" + lstring accList; "UniProt all accessions" + lstring isoIds; "UniProt isoform accessions" + + lstring protFullNames; "UniProt protein name" + lstring protShortNames; "UniProt protein short name" + lstring protAltFullNames; "UniProt alternative names" + lstring protAltShortNames; "UniProt alternative short names" + lstring geneNameDupl; "UniProt gene name" + lstring geneSynonyms; "UniProt gene synonyms" + lstring functionText; "UniProt function" + + lstring hgncSym; "HGNC Gene Symbol" + lstring hgncId; "HGNC ID" + lstring refSeq; "RefSeq IDs" + lstring refSeqProt; "RefSeq Protein IDs" + lstring entrezGene; "NCBI Entrez Gene" + lstring ensGene; "Ensembl Gene IDs" + lstring ensTrans; "Ensembl Transcript IDs" + lstring ensProt; "Ensembl Protein IDs" + )