Regular Expressions accepted by UniProt for use in the 'with' field

From GO Wiki
Jump to: navigation, search


   { prefix => 'UniProt(?:KB)?', id => '[A-Z][0-9][A-Z0-9]{3}[0-9]((-([0-9]+)|:PRO_[0-9]{10}))?' },
   { prefix => 'CGD', id => '(CAL|CAF)[0-9]{7}' },
   { prefix => 'SGD', id => 'S[0-9]{9}' },
   { prefix => 'dictyBase', id => 'DDB_G[0-9]{7}' },
   { prefix => 'FB', id => 'FBgn[0-9]{7}' },
   { prefix => 'GeneDB_Spombe|PomBase', id => 'SP[A-Z0-9]+\.[A-Za-z0-9]+' },
   { prefix => 'GeneDB_Pfalciparum', id => 'SP[A-Z0-9]+\.[A-Za-z0-9]+' },
   { prefix => 'GeneDB_Lmajor', id => 'LmjF\.\d+\.\d+' },
   { prefix => 'GeneDB_Tbrucei', id => 'Tb\d+\.\d+\.\d+' },
   { prefix => 'AGI_LocusCode', id => 'AT[MC0-5]G[0-9]{5}(\.[0-9]{1})?', case_sensitive => 'N', canonical_prefix => 'AGI_LocusCode' },
   { prefix => 'TAIR', id => 'gene:[0-9]{7,12}', case_sensitive => 'N', canonical_prefix => 'TAIR' },
   { prefix => 'TAIR', id => 'locus:[0-9]{7}', case_sensitive => 'N', canonical_prefix => 'TAIR' },
   { prefix => 'WB', id => 'WBGene[0-9]{8}' },
   { prefix => 'WB', id => 'WBVar[0-9]{8}' },
   { prefix => 'WB', id => 'WP:CE[0-9]{5}' },
   { prefix => 'ZFIN', id => 'ZDB-GENE-[0-9]{6}-[0-9]+' },
   { prefix => 'ZFIN', id => 'ZDB-GENO-[0-9]{6}-[0-9]+' },
   { prefix => 'ZFIN', id => 'ZDB-MRPHLNO-[0-9]{6}-[0-9]+' },
   { prefix => 'CHEBI', id => '[0-9]{5}', case_sensitive => 'N', canonical_prefix => 'CHEBI' },
   { prefix => 'JCVI_GenProp', id => 'GenProp[0-9]{4}' },
   { prefix => 'RGD', id => '[0-9]{4,7}' },
   { prefix => 'PubChem_Compound', id => '[0-9]+' },
   { prefix => 'MGI', id => 'MGI:[0-9]{5,}' },
   { prefix => 'protein_id', id => '[A-Z]{3}[0-9]{5}(\.[0-9]+)?' },
   { prefix => 'RefSeq', id => '[A-Z]{2}_[0-9]{4,10}(\.[0-9]+)?' },
   { prefix => 'NCBI_gi', id => '[0-9]{6,}' },
   { prefix => 'PDB', id => '[A-Za-z0-9]{4}' },
   { prefix => 'ENSEMBL', id => 'ENS[A-Z0-9]{10,17}' },
   { prefix => 'GR', id => '[A-Z][0-9][A-Z0-9]{3}[0-9]' },
   { prefix => 'GR_PROTEIN', id => '[A-Z][0-9][A-Z0-9]{3}[0-9]' },
   { prefix => 'EcoliWiki', id => '[A-Za-z]{3,4}' }, 
   { prefix => 'EcoCyc', id => 'EG[0-9]{5}' },
   { prefix => 'ECOGENE', id => 'EG[0-9]{5}' },
   { prefix => 'EchoBASE', id => 'EB[0-9]{4}' },
   { prefix => 'JCVI_GenProp', id => 'GenProp[0-9]{4}' },
   { prefix => 'PubChem_Substance', id => '[0-9]{4,}' },
   { prefix => 'PIR', id => '[A-Z]{1}[0-9]{5}' },
   { prefix => 'KEGG_LIGAND', id => '[A-Z]{1}[0-9]{3,}' },
   { prefix => 'EMBL', id => '([A-Z]{1}[0-9]{5})|([A-Z]{2}[0-9]{6})|([A-Z]{4}[0-9]{8,9})' },
   { prefix => 'MaizeGDB_Locus', id => '[A-Za-z][A-Za-z0-9]*' },
   { prefix => 'NCBI_GP', id => '[A-Z]{3}[0-9]{5}(\.[0-9]+)?' },
   { prefix => 'GenBank|GB', id => '([A-Z]{1}[0-9]{5})|([A-Z]{2}[0-9]{6})|([A-Z]{4}[0-9]{8,9})' },
   { prefix => 'ECK', id => 'ECK[0-9]{4}' },
   { prefix => 'ECOGENE', id => 'EG[0-9]{5}' }