<?xml version="1.0" encoding="UTF-8"?>
<obo>
<source>
<source_id>sofa_2_4_3.obo</source_id>
<source_type>file</source_type>
<source_fullpath>sofa_2_4_3.obo</source_fullpath>
<source_path>sofa_2_4_3.obo</source_path>
<source_md5>7620bd03a9ff824fd0b5e7cce5d24ea2</source_md5>
<source_mtime>1275600643</source_mtime>
<source_parsetime>1275600978</source_parsetime>
</source>
<header>
<format-version>1.2</format-version>
<date>01:06:2010 10:46</date>
<saved-by>kareneilbeck</saved-by>
<auto-generated-by>OBO-Edit 2.1-beta3</auto-generated-by>
<subsetdef>
<id>biosapiens</id>
<name>biosapiens protein feature ontology</name>
</subsetdef>
<subsetdef>
<id>SOFA</id>
<name>SO feature annotation</name>
</subsetdef>
<synonymtypedef>
<id>aa1</id>
<name>amino acid 1 letter code</name>
</synonymtypedef>
<synonymtypedef>
<id>aa3</id>
<name>amino acid 3 letter code</name>
</synonymtypedef>
<synonymtypedef>
<id>AAMOD</id>
<name>amino acid modification</name>
</synonymtypedef>
<synonymtypedef>
<id>BS</id>
<name>biosapiens</name>
</synonymtypedef>
<synonymtypedef>
<id>dbsnp</id>
<name>dbsnp variant terms</name>
</synonymtypedef>
<synonymtypedef>
<id>ebi_variants</id>
<name>ensembl variant terms</name>
</synonymtypedef>
<synonymtypedef>
<id>RNAMOD</id>
<name>RNA modification</name>
<scope>EXACT</scope>
</synonymtypedef>
<default-namespace>sequence</default-namespace>
<remark>autogenerated-by\: DAG-Edit version 1.417\nsaved-by\: eilbeck\ndate\: Tue May 11 15\:18\:44 PDT 2004\nversion\: $Revision\: 1.45 $</remark>
</header>
<term>
<id>SO:0000000</id>
<name>Sequence_Ontology</name>
<subset>SOFA</subset>
<is_obsolete>1</is_obsolete>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000001</id>
<name>region</name>
<def>
<defstr>A sequence_feature with an extent greater than zero. A nucleotide region is composed of bases and a polypeptide region is composed of amino acids.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>sequence</synonym_text>
</synonym>
<is_a>SO:0000110</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000004</id>
<name>interior_coding_exon</name>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>interior coding exon</synonym_text>
</synonym>
<is_a>SO:0000195</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000005</id>
<name>satellite_DNA</name>
<def>
<defstr>The many tandem repeats (identical or related) of a short basic repeating unit; many have a base composition or other property different from the genome average that allows them to be separated from the bulk (main band) genomic DNA.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>satellite DNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Satellite_DNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000705</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000006</id>
<name>PCR_product</name>
<def>
<defstr>A region amplified by a PCR reaction.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. This term is now located in OBI, with the following ID OBI_0000406.</comment>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>amplicon</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>PCR product</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/RAPD</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000695</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000007</id>
<name>read_pair</name>
<def>
<defstr>A pair of sequencing reads in which the two members of the pair are related by originating at either end of a clone insert.</defstr>
<dbxref>
<acc>ls</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>read-pair</synonym_text>
</synonym>
<is_a>SO:0000143</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000149</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000013</id>
<name>scRNA</name>
<def>
<defstr>Any one of several small cytoplasmic RNA molecules present in the cytoplasm and sometimes nucleus of a Eukaryote.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/WebFeat/align/scRNA_s.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small cytoplasmic RNA</synonym_text>
</synonym>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000038</id>
<name>match_set</name>
<def>
<defstr>A collection of match parts.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_obsolete>1</is_obsolete>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000039</id>
<name>match_part</name>
<def>
<defstr>A part of a match, for example an hsp from blast is a match_part.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>match part</synonym_text>
</synonym>
<is_a>SO:0001410</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000343</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000050</id>
<name>gene_part</name>
<def>
<defstr>A part of a gene, that has no other route in the ontology back to region. This concept is necessary for logical inference as these parts must have the properties of region. It also allows us to associate all the parts of genes with a gene.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_obsolete>1</is_obsolete>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000057</id>
<name>operator</name>
<def>
<defstr>A regulatory element of an operon to which activators or repressors bind thereby effecting translation of genes in that operon.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>operator segment</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Operator_(biology)#Operator</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000752</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000059</id>
<name>nuclease_binding_site</name>
<def>
<defstr>A region of a molecule that binds to a nuclease.</defstr>
<dbxref>
<acc>cb</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>nuclease binding site</synonym_text>
</synonym>
<is_a>SO:0000410</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000101</id>
<name>transposable_element</name>
<def>
<defstr>A transposon or insertion sequence. An element that can insert in a variety of DNA sequences.</defstr>
<dbxref>
<acc>http://www.sci.sdsu.edu/~smaloy/Glossary/T.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>transposable element</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>transposon</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Transposable_element</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001039</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000102</id>
<name>expressed_sequence_match</name>
<def>
<defstr>A match to an EST or cDNA sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>expressed sequence match</synonym_text>
</synonym>
<is_a>SO:0000347</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000103</id>
<name>clone_insert_end</name>
<def>
<defstr>The end of the clone insert.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>clone insert end</synonym_text>
</synonym>
<is_a>SO:0000699</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000753</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000104</id>
<name>polypeptide</name>
<alt_id>SO:0000358</alt_id>
<def>
<defstr>A sequence of amino acids linked by peptide bonds which may lack appreciable tertiary structure and may not be liable to irreversible denaturation.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology. The term 'protein' was merged with 'polypeptide'. Although 'protein' was a sequence_attribute and therefore meant to describe the quality rather than an actual feature, it was being used erroneously. It is replaced by 'peptidyl' as the polymer attribute.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>protein</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Polypeptide</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001411</is_a>
<relationship>
<type>derives_from</type>
<to>SO:0000316</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000109</id>
<name>sequence_variant_obs</name>
<def>
<defstr>A sequence_variant is a non exact copy of a sequence_feature or genome exhibiting one or more sequence_alteration.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>mutation</synonym_text>
</synonym>
<is_obsolete>1</is_obsolete>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000110</id>
<name>sequence_feature</name>
<def>
<defstr>An extent of biological sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>located sequence feature</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>located_sequence_feature</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>sequence feature</synonym_text>
</synonym>
<namespace>sequence</namespace>
<is_root>1</is_root>
</term>
<term>
<id>SO:0000112</id>
<name>primer</name>
<def>
<defstr>A short preexisting polynucleotide chain to which new deoxyribonucleotides can be added by DNA polymerase.</defstr>
<dbxref>
<acc>http://www.ornl.gov/TechResources/Human_Genome/publicat/primer2001/glossary.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>DNA primer</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>primer oligonucleotide</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>primer polynucleotide</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>primer sequence</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Primer_(molecular_biology)</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000441</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000113</id>
<name>proviral_region</name>
<def>
<defstr>A viral sequence which has integrated into a host genome.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>proviral region</synonym_text>
</synonym>
<synonym scope="related">
<synonym_text>proviral sequence</synonym_text>
</synonym>
<is_a>SO:0001039</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000114</id>
<name>methylated_C</name>
<def>
<defstr>A methylated deoxy-cytosine.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>methylated C</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>methylated cytosine</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>methylated cytosine base</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>methylated cytosine residue</synonym_text>
</synonym>
<is_a>SO:0000306</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000120</id>
<name>protein_coding_primary_transcript</name>
<def>
<defstr>A primary transcript that, at least in part, encodes one or more proteins.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>May contain introns.</comment>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>pre mRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>protein coding primary transcript</synonym_text>
</synonym>
<is_a>SO:0000185</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000139</id>
<name>ribosome_entry_site</name>
<def>
<defstr>Region in mRNA where ribosome assembles.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>ribosome entry site</synonym_text>
</synonym>
<is_a>SO:0000837</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000203</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000140</id>
<name>attenuator</name>
<def>
<defstr>A sequence segment located within the five prime end of an mRNA that causes premature termination of translation.</defstr>
<dbxref>
<acc>as</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>attenuator sequence</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Attenuator</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0005836</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000234</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000141</id>
<name>terminator</name>
<def>
<defstr>The sequence of DNA located either at the end of the transcript that causes RNA polymerase to terminate transcription.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>terminator sequence</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Terminator_(genetics)</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0005836</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000673</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000143</id>
<name>assembly_component</name>
<def>
<defstr>A region of known length which may be used to manufacture a longer region.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>assembly component</synonym_text>
</synonym>
<is_a>SO:0001410</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000147</id>
<name>exon</name>
<def>
<defstr>A region of the transcript sequence within a gene which is not removed from the primary RNA transcript by RNA splicing.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Exon</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000833</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000148</id>
<name>supercontig</name>
<def>
<defstr>One or more contigs that have been ordered and oriented using end-read information. Contains gaps that are filled with N's.</defstr>
<dbxref>
<acc>ls</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>scaffold</synonym_text>
</synonym>
<is_a>SO:0000353</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000719</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000149</id>
<name>contig</name>
<def>
<defstr>A contiguous sequence derived from sequence assembly. Has no gaps, but may contain N's from unavailable bases.</defstr>
<dbxref>
<acc>ls</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Contig</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000143</is_a>
<is_a>SO:0000353</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000148</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000150</id>
<name>read</name>
<def>
<defstr>A sequence obtained from a single sequencing experiment. Typically a read is produced when a base calling program interprets information from a chromatogram trace file produced from a sequencing machine.</defstr>
<dbxref>
<acc>rd</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_a>SO:0000143</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000149</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000151</id>
<name>clone</name>
<def>
<defstr>A piece of DNA that has been inserted in a vector so that it can be propagated in a host bacterium or some other organism.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Clone_(genetics)</acc>
<dbname>http</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000695</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000159</id>
<name>deletion</name>
<alt_id>SO:1000033</alt_id>
<def>
<defstr>The point at which one or more contiguous nucleotides were excised.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>deleted_sequence</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>nucleotide deletion</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>nucleotide_deletion</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Nucleotide_deletion</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001059</is_a>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000161</id>
<name>methylated_A</name>
<def>
<defstr>A modified RNA base in which adenine has been methylated.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>methylated A</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>methylated adenine</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>methylated adenine base</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>methylated adenine residue</synonym_text>
</synonym>
<is_a>SO:0000306</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000162</id>
<name>splice_site</name>
<def>
<defstr>Consensus region of primary transcript bordering junction of splicing. A region that overlaps exactly 2 base and adjacent_to splice_junction.</defstr>
<dbxref>
<acc>cjm</acc>
<dbname>SO</dbname>
</dbxref>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>With spliceosomal introns, the splice sites bind the spliceosomal machinery.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>splice site</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Splice_site</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000835</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000163</id>
<name>five_prime_cis_splice_site</name>
<def>
<defstr>Intronic 2 bp region bordering the exon, at the 5' edge of the intron. A splice_site that is downstream_adjacent_to exon and starts intron.</defstr>
<dbxref>
<acc>http://www.ucl.ac.uk/~ucbhjow/b241/glossary.html</acc>
<dbname>URL</dbname>
</dbxref>
<dbxref>
<acc>cjm</acc>
<dbname>SO</dbname>
</dbxref>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>5' splice site</synonym_text>
</synonym>
<synonym scope="related">
<synonym_text>donor</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>donor splice site</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>five prime splice site</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>splice donor site</synonym_text>
</synonym>
<is_a>SO:0001419</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000164</id>
<name>three_prime_cis_splice_site</name>
<def>
<defstr>Intronic 2 bp region bordering the exon, at the 3' edge of the intron. A splice_site that is upstream_adjacent_to exon and finishes intron.</defstr>
<dbxref>
<acc>http://www.ucl.ac.uk/~ucbhjow/b241/glossary.html</acc>
<dbname>URL</dbname>
</dbxref>
<dbxref>
<acc>cjm</acc>
<dbname>SO</dbname>
</dbxref>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>3' splice site</synonym_text>
</synonym>
<synonym scope="related">
<synonym_text>acceptor</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>acceptor splice site</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>splice acceptor site</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>three prime splice site</synonym_text>
</synonym>
<is_a>SO:0001419</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000165</id>
<name>enhancer</name>
<def>
<defstr>A cis-acting sequence that increases the utilization of (some) eukaryotic promoters, and can function in either orientation and in any location (upstream or downstream) relative to the promoter.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>An enhancer may participate in an enhanceosome GO:0034206. A protein-DNA complex formed by the association of a distinct set of general and specific transcription factors with a region of enhancer DNA. The cooperative assembly of an enhanceosome confers specificity of transcriptional regulation. This comment is a place holder should we start to make cross products with GO.</comment>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Enhancer_(genetics)</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000727</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000167</id>
<name>promoter</name>
<def>
<defstr>A regulatory_region composed of the TSS(s) and binding sites for TF_complexes of the basal transcription machinery.</defstr>
<dbxref>
<acc>regcreative</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology. The region on a DNA molecule involved in RNA polymerase binding to initiate transcription.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>promoter sequence</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Promoter</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001055</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000177</id>
<name>cross_genome_match</name>
<def>
<defstr>A nucleotide match against a sequence from another organism.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>cross genome match</synonym_text>
</synonym>
<is_a>SO:0000347</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000178</id>
<name>operon</name>
<def>
<defstr>A group of contiguous genes transcribed as a single (polycistronic) mRNA from a single regulatory region.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Operon</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0005855</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000179</id>
<name>clone_insert_start</name>
<def>
<defstr>The start of the clone insert.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>clone insert start</synonym_text>
</synonym>
<is_a>SO:0000699</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000753</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000181</id>
<name>translated_nucleotide_match</name>
<def>
<defstr>A match against a translated sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>translated nucleotide match</synonym_text>
</synonym>
<is_a>SO:0000347</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000183</id>
<name>non_transcribed_region</name>
<def>
<defstr>A region of the gene which is not transcribed.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>non transcribed region</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>non-transcribed sequence</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>nontranscribed region</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>nontranscribed sequence</synonym_text>
</synonym>
<is_a>SO:0000842</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000185</id>
<name>primary_transcript</name>
<def>
<defstr>A transcript that in its initial state requires modification to be functional.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>precursor RNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>primary transcript</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Primary_transcript</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000673</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000187</id>
<name>repeat_family</name>
<def>
<defstr>A group of characterized repeat sequences.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_obsolete>1</is_obsolete>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000188</id>
<name>intron</name>
<def>
<defstr>A region of a primary transcript that is transcribed, but removed from within the transcript by splicing together the sequences (exons) on either side of it.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Intron</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000835</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000193</id>
<name>RFLP_fragment</name>
<def>
<defstr>A DNA fragment used as a reagent to detect the polymorphic genomic loci by hybridizing against the genomic DNA digested with a given restriction enzyme.</defstr>
<dbxref>
<acc>pj</acc>
<dbname>GOC</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>restriction fragment length polymorphism</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>RFLP</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>RFLP fragment</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Restriction_fragment_length_polymorphism</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000412</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000195</id>
<name>coding_exon</name>
<def>
<defstr>An exon whereby at least one base is part of a codon (here, 'codon' is inclusive of the stop_codon).</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>coding exon</synonym_text>
</synonym>
<is_a>SO:0000147</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000196</id>
<name>five_prime_coding_exon_coding_region</name>
<def>
<defstr>The sequence of the five_prime_coding_exon that codes for protein.</defstr>
<dbxref>
<acc>cjm</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>five prime exon coding region</synonym_text>
</synonym>
<is_a>SO:0001215</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000200</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000197</id>
<name>three_prime_coding_exon_coding_region</name>
<def>
<defstr>The sequence of the three_prime_coding_exon that codes for protein.</defstr>
<dbxref>
<acc>cjm</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>three prime exon coding region</synonym_text>
</synonym>
<is_a>SO:0001215</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000198</id>
<name>noncoding_exon</name>
<def>
<defstr>An exon that does not contain any codons.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>noncoding exon</synonym_text>
</synonym>
<is_a>SO:0000147</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000200</id>
<name>five_prime_coding_exon</name>
<def>
<defstr>The 5' most coding exon.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>5' coding exon</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>five prime coding exon</synonym_text>
</synonym>
<is_a>SO:0000195</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000203</id>
<name>UTR</name>
<def>
<defstr>Messenger RNA sequences that are untranslated and lie five prime or three prime to sequences which are translated.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>untranslated region</synonym_text>
</synonym>
<is_a>SO:0000836</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000204</id>
<name>five_prime_UTR</name>
<def>
<defstr>A region at the 5' end of a mature transcript (preceding the initiation codon) that is not translated into a protein.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>5' UTR</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>five prime UTR</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>five_prime_untranslated_region</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/5'_UTR</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000203</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000205</id>
<name>three_prime_UTR</name>
<def>
<defstr>A region at the 3' end of a mature transcript (following the stop codon) that is not translated into a protein.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>three prime untranslated region</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>three prime UTR</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Three_prime_untranslated_region</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000203</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000209</id>
<name>rRNA_primary_transcript</name>
<def>
<defstr>A primary transcript encoding a ribosomal RNA.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>ribosomal RNA primary transcript</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>rRNA primary transcript</synonym_text>
</synonym>
<is_a>SO:0000483</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000233</id>
<name>mature_transcript</name>
<def>
<defstr>A transcript which has undergone the necessary modifications, if any, for its function. In eukaryotes this includes, for example, processing of introns, cleavage, base modification, and modifications to the 5' and/or the 3' ends, other than addition of bases. In bacteria functional mRNAs are usually not modified.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>A processed transcript cannot contain introns.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>mature transcript</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Mature_transcript</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000673</is_a>
<relationship>
<type>derives_from</type>
<to>SO:0000185</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000234</id>
<name>mRNA</name>
<def>
<defstr>Messenger RNA is the intermediate molecule between DNA and protein. It includes UTR and coding sequences. It does not contain introns.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>An mRNA does not contain introns as it is a processed_transcript. The equivalent kind of primary_transcript is protein_coding_primary_transcript (SO:0000120) which may contain introns. This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>messenger RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/MRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000233</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000235</id>
<name>TF_binding_site</name>
<def>
<defstr>A region of a molecule that binds a TF complex [GO:0005667].</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>TF binding site</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>transcription factor binding site</synonym_text>
</synonym>
<is_a>SO:0000410</is_a>
<is_a>SO:0005836</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000236</id>
<name>ORF</name>
<def>
<defstr>The in-frame interval between the stop codons of a reading frame which when read as sequential triplets, has the potential of encoding a sequential string of amino acids. TER(NNN)nTER.</defstr>
<dbxref>
<acc>rb</acc>
<dbname>SGD</dbname>
</dbxref>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>The definition was modified by Rama. ORF is defined by the sequence, whereas the CDS is defined according to whether a polypeptide is made. This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>open reading frame</synonym_text>
</synonym>
<is_a>SO:0000717</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000239</id>
<name>flanking_region</name>
<def>
<defstr>The sequences extending on either side of a specific region.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>flanking region</synonym_text>
</synonym>
<is_a>SO:0001412</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000252</id>
<name>rRNA</name>
<def>
<defstr>RNA that comprises part of a ribosome, and that can provide both structural scaffolding and catalytic activity.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
<dbxref>
<acc>0198506732</acc>
<dbname>ISBN</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>ribosomal ribonucleic acid</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>ribosomal RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/RRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<relationship>
<type>derives_from</type>
<to>SO:0000209</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000253</id>
<name>tRNA</name>
<def>
<defstr>Transfer RNA (tRNA) molecules are approximately 80 nucleotides in length. Their secondary structure includes four short double-helical elements and three loops (D, anti-codon, and T loops). Further hydrogen bonds mediate the characteristic L-shaped molecular structure. Transfer RNAs have two regions of fundamental functional importance: the anti-codon, which is responsible for specific mRNA codon recognition, and the 3' end, to which the tRNA's corresponding amino acid is attached (by aminoacyl-tRNA synthetases). Transfer RNAs cope with the degeneracy of the genetic code in two manners: having more than one tRNA (with a specific anti-codon) for a particular amino acid; and 'wobble' base-pairing, i.e. permitting non-standard base-pairing at the 3rd anti-codon position.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00005</acc>
<dbname>URL</dbname>
</dbxref>
<dbxref>
<acc>0198506732</acc>
<dbname>ISBN</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>transfer ribonucleic acid</synonym_text>
</synonym>
<synonym scope="related">
<synonym_text>transfer RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/TRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000274</id>
<name>snRNA</name>
<def>
<defstr>A small nuclear RNA molecule involved in pre-mRNA splicing and processing.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
<dbxref>
<acc>11733745</acc>
<dbname>PMID</dbname>
</dbxref>
<dbxref>
<acc>ems</acc>
<dbname>WB</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small nuclear RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/SnRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000275</id>
<name>snoRNA</name>
<def>
<defstr>A snoRNA (small nucleolar RNA) is any one of a class of small RNAs that are associated with the eukaryotic nucleus as components of small nucleolar ribonucleoproteins. They participate in the processing or modifications of many RNAs, mostly ribosomal RNAs (rRNAs) though snoRNAs are also known to target other classes of RNA, including spliceosomal RNAs, tRNAs, and mRNAs via a stretch of sequence that is complementary to a sequence in the targeted RNA.</defstr>
<dbxref>
<acc>kgc</acc>
<dbname>GOC</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small nucleolar RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/SnoRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000276</id>
<name>miRNA</name>
<def>
<defstr>Small, ~22-nt, RNA molecule that is the endogenous transcript of a miRNA gene. Micro RNAs are produced from precursor molecules (SO:0000647) that can form local hairpin structures, which ordinarily are processed (via the Dicer pathway) such that a single miRNA molecule accumulates from one arm of a hairpin precursor molecule. Micro RNAs may trigger the cleavage of their target molecules or act as translational repressors.</defstr>
<dbxref>
<acc>12592000</acc>
<dbname>PMID</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>micro RNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>microRNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/MiRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000370</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000289</id>
<name>microsatellite</name>
<def>
<defstr>A repeat_region containing repeat_units (2 to 4 bp) that is repeated multiple times in tandem.</defstr>
<dbxref>
<acc>http://www.informatics.jax.org/silver/glossary.shtml</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>microsatellite locus</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>microsatellite marker</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>VNTR</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Microsatellite</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000005</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000294</id>
<name>inverted_repeat</name>
<def>
<defstr>The sequence is complementarily repeated on the opposite strand. It is a palindrome, and it may, or may not be hyphenated. Examples: GCTGATCAGC, or GCTGA-----TCAGC.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>inverted repeat</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>inverted repeat sequence</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Inverted_repeat</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000657</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000296</id>
<name>origin_of_replication</name>
<def>
<defstr>The origin of replication; starting site for duplication of a nucleic acid molecule to give two identical copies.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>ori</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>origin of replication</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Origin_of_replication</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001411</is_a>
<relationship>
<type>part_of</type>
<to>SO:0001235</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000303</id>
<name>clip</name>
<def>
<defstr>Part of the primary transcript that is clipped off during processing.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_a>SO:0000835</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000305</id>
<name>modified_base</name>
<def>
<defstr>A modified nucleotide, i.e. a nucleotide other than A, T, C. G.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Modified base:<modified_base>.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>modified base site</synonym_text>
</synonym>
<is_a>SO:0001720</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000306</id>
<name>methylated_base_feature</name>
<def>
<defstr>A nucleotide modified by methylation.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>methylated base feature</synonym_text>
</synonym>
<is_a>SO:0000305</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000307</id>
<name>CpG_island</name>
<def>
<defstr>Regions of a few hundred to a few thousand bases in vertebrate genomes that are relatively GC and CpG rich; they are typically unmethylated and often found near the 5' ends of genes.</defstr>
<dbxref>
<acc>rd</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>CG island</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>CpG island</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/CpG_island</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000314</id>
<name>direct_repeat</name>
<def>
<defstr>A repeat where the same sequence is repeated in the same direction. Example: GCTGA-----GCTGA.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>direct repeat</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Direct_repeat</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000657</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000315</id>
<name>TSS</name>
<def>
<defstr>The first base where RNA polymerase begins to synthesize the RNA transcript.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>transcription start site</synonym_text>
</synonym>
<is_a>SO:0000835</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000316</id>
<name>CDS</name>
<def>
<defstr>A contiguous sequence which begins with, and includes, a start codon and ends with, and includes, a stop codon.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>coding sequence</synonym_text>
</synonym>
<is_a>SO:0000836</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000318</id>
<name>start_codon</name>
<def>
<defstr>First codon to be translated by a ribosome.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>initiation codon</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>start codon</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Start_codon</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000360</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000319</id>
<name>stop_codon</name>
<def>
<defstr>In mRNA, a set of three nucleotides that indicates the end of information for protein synthesis.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>stop codon</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Stop_codon</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000360</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000324</id>
<name>tag</name>
<def>
<defstr>A nucleotide sequence that may be used to identify a larger sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_a>SO:0000696</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000325</id>
<name>rRNA_large_subunit_primary_transcript</name>
<def>
<defstr>A primary transcript encoding a large ribosomal subunit RNA.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>rRNA large subunit primary transcript</synonym_text>
</synonym>
<is_a>SO:0000209</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000326</id>
<name>SAGE_tag</name>
<def>
<defstr>A short diagnostic sequence tag, serial analysis of gene expression (SAGE), that allows the quantitative and simultaneous analysis of a large number of transcripts.</defstr>
<dbxref>
<acc>http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&amp;db=PubMed&amp;list_uids=7570003&amp;dopt=Abstract</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>SAGE tag</synonym_text>
</synonym>
<is_a>SO:0000324</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000330</id>
<name>conserved_region</name>
<def>
<defstr>Region of sequence similarity by descent from a common ancestor.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>conserved region</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Conserved_region</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001410</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000331</id>
<name>STS</name>
<def>
<defstr>Short (typically a few hundred base pairs) DNA sequence that has a single occurrence in a genome and whose location and base sequence are known.</defstr>
<dbxref>
<acc>http://www.biospace.com</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>sequence tag site</synonym_text>
</synonym>
<is_a>SO:0000324</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000332</id>
<name>coding_conserved_region</name>
<def>
<defstr>Coding region of sequence similarity by descent from a common ancestor.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>coding conserved region</synonym_text>
</synonym>
<is_a>SO:0000330</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000333</id>
<name>exon_junction</name>
<def>
<defstr>The boundary between two exons in a processed transcript.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>exon junction</synonym_text>
</synonym>
<is_a>SO:0000699</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000233</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000334</id>
<name>nc_conserved_region</name>
<def>
<defstr>Non-coding region of sequence similarity by descent from a common ancestor.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>nc conserved region</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>noncoding conserved region</synonym_text>
</synonym>
<is_a>SO:0000330</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000336</id>
<name>pseudogene</name>
<def>
<defstr>A sequence that closely resembles a known functional gene, at another locus within a genome, that is non-functional as a consequence of (usually several) mutations that prevent either its transcription or translation (or both). In general, pseudogenes result from either reverse transcription of a transcript of their "normal" paralog (SO:0000043) (in which case the pseudogene typically lacks introns and includes a poly(A) tail) or from recombination (SO:0000044) (in which case the pseudogene is typically a tandem duplication of its "normal" paralog).</defstr>
<dbxref>
<acc>http://www.ucl.ac.uk/~ucbhjow/b241/glossary.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Pseudogene</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000462</is_a>
<relationship>
<type>non_functional_homolog_of</type>
<to>SO:0000704</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000337</id>
<name>RNAi_reagent</name>
<def>
<defstr>A double stranded RNA duplex, at least 20bp long, used experimentally to inhibit gene function by RNA interference.</defstr>
<dbxref>
<acc>rd</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>RNAi reagent</synonym_text>
</synonym>
<is_a>SO:0000442</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000340</id>
<name>chromosome</name>
<def>
<defstr>Structural unit composed of a nucleic acid molecule which controls its own replication through the interaction of specific proteins at one or more origins of replication.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Chromosome</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001235</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000341</id>
<name>chromosome_band</name>
<def>
<defstr>A cytologically distinguishable feature of a chromosome, often made visible by staining, and usually alternating light and dark.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>chromosome band</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>cytoband</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>cytological band</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Cytological_band</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000830</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000343</id>
<name>match</name>
<def>
<defstr>A region of sequence, aligned to another sequence with some statistical significance, using an algorithm such as BLAST or SIM4.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_a>SO:0001410</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000344</id>
<name>splice_enhancer</name>
<def>
<defstr>Region of a transcript that regulates splicing.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>splice enhancer</synonym_text>
</synonym>
<is_a>SO:0001056</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000345</id>
<name>EST</name>
<def>
<defstr>A tag produced from a single sequencing read from a cDNA clone or PCR product; typically a few hundred base pairs long.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>expressed sequence tag</synonym_text>
</synonym>
<is_a>SO:0000324</is_a>
<relationship>
<type>derives_from</type>
<to>SO:0000234</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000347</id>
<name>nucleotide_match</name>
<def>
<defstr>A match against a nucleotide sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>nucleotide match</synonym_text>
</synonym>
<is_a>SO:0000343</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000349</id>
<name>protein_match</name>
<def>
<defstr>A match against a protein sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>protein match</synonym_text>
</synonym>
<is_a>SO:0000343</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000353</id>
<name>sequence_assembly</name>
<def>
<defstr>A sequence of nucleotides that has been algorithmically derived from an alignment of two or more different sequences.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>sequence assembly</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Sequence_assembly</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001248</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000360</id>
<name>codon</name>
<def>
<defstr>A set of (usually) three nucleotide bases in a DNA or RNA sequence, which together code for a unique amino acid or the termination of translation and are contained within the CDS.</defstr>
<dbxref>
<acc>http://www.everythingbio.com/glos/definition.php?word=codon</acc>
<dbname>URL</dbname>
</dbxref>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Codon</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000851</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000366</id>
<name>insertion_site</name>
<def>
<defstr>The junction where an insertion occurred.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>insertion site</synonym_text>
</synonym>
<is_a>SO:0000699</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000368</id>
<name>transposable_element_insertion_site</name>
<def>
<defstr>The junction in a genome where a transposable_element has inserted.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>transposable element insertion site</synonym_text>
</synonym>
<is_a>SO:0000366</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000370</id>
<name>small_regulatory_ncRNA</name>
<def>
<defstr>A non-coding RNA, usually with a specific secondary structure, that acts to regulate gene expression.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small regulatory ncRNA</synonym_text>
</synonym>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000372</id>
<name>enzymatic_RNA</name>
<def>
<defstr>An RNA sequence that has catalytic activity with or without an associated ribonucleoprotein.</defstr>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</def>
<comment>This was moved to be a child of transcript (SO:0000673) because some enzymatic RNA regions are part of primary transcripts and some are part of processed transcripts.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>enzymatic RNA</synonym_text>
</synonym>
<is_a>SO:0000673</is_a>
<intersection_of>
<to>SO:0000673</to>
</intersection_of>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000374</id>
<name>ribozyme</name>
<def>
<defstr>An RNA with catalytic activity.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Ribozyme</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000372</is_a>
<intersection_of>
<to>SO:0000372</to>
</intersection_of>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000375</id>
<name>rRNA_5_8S</name>
<def>
<defstr>5_8S ribosomal RNA (5. 8S rRNA) is a component of the large subunit of the eukaryotic ribosome. It is transcribed by RNA polymerase I as part of the 45S precursor that also contains 18S and 28S rRNA. Functionally, it is thought that 5.8S rRNA may be involved in ribosome translocation. It is also known to form covalent linkage to the p53 tumour suppressor protein. 5_8S rRNA is also found in archaea.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00002</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>5.8S LSU rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>5.8S ribosomal RNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>5.8S rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>rRNA 5 8S</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/5.8S_ribosomal_RNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000651</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000380</id>
<name>hammerhead_ribozyme</name>
<def>
<defstr>A small catalytic RNA motif that catalyzes self-cleavage reaction. Its name comes from its secondary structure which resembles a carpenter's hammer. The hammerhead ribozyme is involved in the replication of some viroid and some satellite RNAs.</defstr>
<dbxref>
<acc>http://rnaworld.bio.ku.edu/class/RNA/RNA00/RNA_World_3.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>hammerhead ribozyme</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Hammerhead_ribozyme</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000715</is_a>
<intersection_of>
<to>SO:0000715</to>
</intersection_of>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000385</id>
<name>RNase_MRP_RNA</name>
<def>
<defstr>The RNA molecule essential for the catalytic activity of RNase MRP, an enzymatically active ribonucleoprotein with two distinct roles in eukaryotes. In mitochondria it plays a direct role in the initiation of mitochondrial DNA replication. In the nucleus it is involved in precursor rRNA processing, where it cleaves the internal transcribed spacer 1 between 18S and 5.8S rRNAs.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00030</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>RNase MRP RNA</synonym_text>
</synonym>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000386</id>
<name>RNase_P_RNA</name>
<def>
<defstr>The RNA component of Ribonuclease P (RNase P), a ubiquitous endoribonuclease, found in archaea, bacteria and eukarya as well as chloroplasts and mitochondria. Its best characterized activity is the generation of mature 5 prime ends of tRNAs by cleaving the 5 prime leader elements of precursor-tRNAs. Cellular RNase Ps are ribonucleoproteins. RNA from bacterial RNase Ps retains its catalytic activity in the absence of the protein subunit, i.e. it is a ribozyme. Isolated eukaryotic and archaeal RNase P RNA has not been shown to retain its catalytic function, but is still essential for the catalytic activity of the holoenzyme. Although the archaeal and eukaryotic holoenzymes have a much greater protein content than the bacterial ones, the RNA cores from all the three lineages are homologous. Helices corresponding to P1, P2, P3, P4, and P10/11 are common to all cellular RNase P RNAs. Yet, there is considerable sequence variation, particularly among the eukaryotic RNAs.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00010</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>RNase P RNA</synonym_text>
</synonym>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000390</id>
<name>telomerase_RNA</name>
<def>
<defstr>The RNA component of telomerase, a reverse transcriptase that synthesizes telomeric DNA.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00025</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>telomerase RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Telomerase_RNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000391</id>
<name>U1_snRNA</name>
<def>
<defstr>U1 is a small nuclear RNA (snRNA) component of the spliceosome (involved in pre-mRNA splicing). Its 5' end forms complementary base pairs with the 5' splice junction, thus defining the 5' donor site of an intron. There are significant differences in sequence and secondary structure between metazoan and yeast U1 snRNAs, the latter being much longer (568 nucleotides as compared to 164 nucleotides in human). Nevertheless, secondary structure predictions suggest that all U1 snRNAs share a 'common core' consisting of helices I, II, the proximal region of III, and IV.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00003</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small nuclear RNA U1</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>snRNA U1</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U1 small nuclear RNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U1 snRNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/U1_snRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000274</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000392</id>
<name>U2_snRNA</name>
<def>
<defstr>U2 is a small nuclear RNA (snRNA) component of the spliceosome (involved in pre-mRNA splicing). Complementary binding between U2 snRNA (in an area lying towards the 5' end but 3' to hairpin I) and the branchpoint sequence (BPS) of the intron results in the bulging out of an unpaired adenine, on the BPS, which initiates a nucleophilic attack at the intronic 5' splice site, thus starting the first of two transesterification reactions that mediate splicing.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00004</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small nuclear RNA U2</synonym_text>
<dbxref>
<acc>CB</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>snRNA U2</synonym_text>
<dbxref>
<acc>CB</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U2 small nuclear RNA</synonym_text>
<dbxref>
<acc>CB</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U2 snRNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/U2_snRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000274</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000393</id>
<name>U4_snRNA</name>
<def>
<defstr>U4 small nuclear RNA (U4 snRNA) is a component of the major U2-dependent spliceosome. It forms a duplex with U6, and with each splicing round, it is displaced from U6 (and the spliceosome) in an ATP-dependent manner, allowing U6 to refold and create the active site for splicing catalysis. A recycling process involving protein Prp24 re-anneals U4 and U6.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00015</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small nuclear RNA U4</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>snRNA U4</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U4 small nuclear RNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U4 snRNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/U4_snRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000274</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000394</id>
<name>U4atac_snRNA</name>
<def>
<defstr>An snRNA required for the splicing of the minor U12-dependent class of eukaryotic nuclear introns. It forms a base paired complex with U6atac_snRNA (SO:0000397).</defstr>
<dbxref>
<acc>=12409455</acc>
<dbname>PMID</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small nuclear RNA U4atac</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>snRNA U4atac</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U4atac small nuclear RNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U4atac snRNA</synonym_text>
</synonym>
<is_a>SO:0000274</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000395</id>
<name>U5_snRNA</name>
<def>
<defstr>U5 RNA is a component of both types of known spliceosome. The precise function of this molecule is unknown, though it is known that the 5' loop is required for splice site selection and p220 binding, and that both the 3' stem-loop and the Sm site are important for Sm protein binding and cap methylation.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00020</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small nuclear RNA U5</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>snRNA U5</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U5 small nuclear RNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U5 snRNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/U5_snRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000274</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000396</id>
<name>U6_snRNA</name>
<def>
<defstr>U6 snRNA is a component of the spliceosome which is involved in splicing pre-mRNA. The putative secondary structure consensus base pairing is confined to a short 5' stem loop, but U6 snRNA is thought to form extensive base-pair interactions with U4 snRNA.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00015</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small nuclear RNA U6</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>snRNA U6</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U6 small nuclear RNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U6 snRNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/U6_snRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000274</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000397</id>
<name>U6atac_snRNA</name>
<def>
<defstr>U6atac_snRNA is an snRNA required for the splicing of the minor U12-dependent class of eukaryotic nuclear introns. It forms a base paired complex with U4atac_snRNA (SO:0000394).</defstr>
<dbxref>
<acc>http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=retrieve&amp;db=pubmed&amp;list_uids=12409455&amp;dopt=Abstract</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>snRNA U6atac</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U6atac small nuclear RNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U6atac snRNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<is_a>SO:0000274</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000398</id>
<name>U11_snRNA</name>
<def>
<defstr>U11 snRNA plays a role in splicing of the minor U12-dependent class of eukaryotic nuclear introns, similar to U1 snRNA in the major class spliceosome it base pairs to the conserved 5' splice site sequence.</defstr>
<dbxref>
<acc>9622129</acc>
<dbname>PMID</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small nuclear RNA U11</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>snRNA U11</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U11 small nuclear RNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U11 snRNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/U11_snRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000274</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000399</id>
<name>U12_snRNA</name>
<def>
<defstr>The U12 small nuclear (snRNA), together with U4atac/U6atac, U5, and U11 snRNAs and associated proteins, forms a spliceosome that cleaves a divergent class of low-abundance pre-mRNA introns.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00007</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small nuclear RNA U12</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>snRNA U12</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U12 small nuclear RNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>U12 snRNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/U12_snRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000274</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000403</id>
<name>U14_snoRNA</name>
<alt_id>SO:0005839</alt_id>
<def>
<defstr>U14 small nucleolar RNA (U14 snoRNA) is required for early cleavages of eukaryotic precursor rRNAs. In yeasts, this molecule possess a stem-loop region (known as the Y-domain) which is essential for function. A similar structure, but with a different consensus sequence, is found in plants, but is absent in vertebrates.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00016</acc>
<dbname>URL</dbname>
</dbxref>
<dbxref>
<acc>2551119</acc>
<dbname>PMID</dbname>
</dbxref>
</def>
<comment>An evolutionarily conserved eukaryotic low molecular weight RNA capable of intermolecular hybridization with both homologous and heterologous 18S rRNA.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small nucleolar RNA U14</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>snoRNA U14</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>U14 small nucleolar RNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>U14 snoRNA</synonym_text>
</synonym>
<is_a>SO:0000593</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000404</id>
<name>vault_RNA</name>
<def>
<defstr>A family of RNAs are found as part of the enigmatic vault ribonucleoprotein complex. The complex consists of a major vault protein (MVP), two minor vault proteins (VPARP and TEP1), and several small untranslated RNA molecules. It has been suggested that the vault complex is involved in drug resistance.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00006</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>vault RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Vault_RNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000405</id>
<name>Y_RNA</name>
<def>
<defstr>Y RNAs are components of the Ro ribonucleoprotein particle (Ro RNP), in association with Ro60 and La proteins. The Y RNAs and Ro60 and La proteins are well conserved, but the function of the Ro RNP is not known. In humans the RNA component can be one of four small RNAs: hY1, hY3, hY4 and hY5. These small RNAs are predicted to fold into a conserved secondary structure containing three stem structures. The largest of the four, hY1, contains an additional hairpin.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00019</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>Y RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Y_RNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000407</id>
<name>rRNA_18S</name>
<def>
<defstr>A large polynucleotide in eukaryotes, which functions as the small subunit of the ribosome.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>18S ribosomal RNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>18S rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>rRNA 18S</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/18S_ribosomal_RNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000650</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000409</id>
<name>binding_site</name>
<alt_id>BS:00033</alt_id>
<def>
<defstr>A region on the surface of a molecule that may interact with another molecule. When applied to polypeptides: Amino acids involved in binding or interactions. It can also apply to an amino acid bond which is represented by the positions of the two flanking amino acids.</defstr>
<dbxref>
<acc>GAR</acc>
<dbname>EBIBS</dbname>
</dbxref>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>Discrete.</comment>
<subset>biosapiens</subset>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>binding_or_interaction_site</synonym_text>
</synonym>
<synonym scope="related">
<synonym_text>site</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Binding_site</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000410</id>
<name>protein_binding_site</name>
<def>
<defstr>A region of a molecule that binds to a protein.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>protein binding site</synonym_text>
</synonym>
<is_a>SO:0000409</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000412</id>
<name>restriction_fragment</name>
<def>
<defstr>A region of polynucleotide sequence produced by digestion with a restriction endonuclease.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>restriction fragment</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Restriction_fragment</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000143</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000413</id>
<name>sequence_difference</name>
<def>
<defstr>A region where the sequence differs from that of a specified sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>sequence difference</synonym_text>
</synonym>
<is_a>SO:0000700</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000418</id>
<name>signal_peptide</name>
<alt_id>BS:00159</alt_id>
<def>
<defstr>The signal_peptide is a short region of the peptide located at the N-terminus that directs the protein to be secreted or part of membrane components.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Old def before biosapiens:The sequence for an N-terminal domain of a secreted protein; this domain is involved in attaching nascent polypeptide to the membrane leader sequence.</comment>
<subset>biosapiens</subset>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>signal</synonym_text>
<dbxref>
<acc>feature_type</acc>
<dbname>uniprot</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>signal peptide</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>signal peptide coding sequence</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Signal_peptide</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001527</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000419</id>
<name>mature_protein_region</name>
<alt_id>BS:00149</alt_id>
<def>
<defstr>The polypeptide sequence that remains when the cleaved peptide regions have been cleaved from the immature peptide.</defstr>
<dbxref>
<acc>GAR</acc>
<dbname>EBIBS</dbname>
</dbxref>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
<dbxref>
<acc>cb</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term mature peptide, merged with the biosapiens term mature protein region and took that to be the new name. Old def: The coding sequence for the mature or final peptide or protein product following post-translational modification.</comment>
<subset>biosapiens</subset>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>chain</synonym_text>
<dbxref>
<acc>feature_type</acc>
<dbname>uniprot</dbname>
</dbxref>
</synonym>
<synonym scope="related">
<synonym_text>mature peptide</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>mature protein region</synonym_text>
</synonym>
<is_a>SO:0000839</is_a>
<relationship>
<type>part_of</type>
<to>SO:0001063</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000436</id>
<name>ARS</name>
<def>
<defstr>A sequence that can autonomously replicate, as a plasmid, when transformed into a bacterial host.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>autonomously replicating sequence</synonym_text>
</synonym>
<is_a>SO:0000296</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000441</id>
<name>ss_oligo</name>
<def>
<defstr>A single stranded oligonucleotide.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>single strand oligo</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>single strand oligonucleotide</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>single stranded oligonucleotide</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>ss oligo</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>ss oligonucleotide</synonym_text>
</synonym>
<is_a>SO:0000696</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000442</id>
<name>ds_oligo</name>
<def>
<defstr>A double stranded oligonucleotide.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>double stranded oligonucleotide</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>ds oligo</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>ds-oligonucleotide</synonym_text>
</synonym>
<is_a>SO:0000696</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000454</id>
<name>rasiRNA</name>
<def>
<defstr>A 17-28-nt, small interfering RNA derived from transcripts of repetitive elements.</defstr>
<dbxref>
<acc>http://www.developmentalcell.com/content/article/abstract?uid=PIIS1534580703002284</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>repeat associated small interfering RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/RasiRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000462</id>
<name>pseudogenic_region</name>
<def>
<defstr>A non-functional descendent of a functional entity.</defstr>
<dbxref>
<acc>cjm</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>pseudogenic region</synonym_text>
</synonym>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000464</id>
<name>decayed_exon</name>
<def>
<defstr>A non-functional descendant of an exon.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>decayed exon</synonym_text>
</synonym>
<is_a>SO:0000462</is_a>
<relationship>
<type>non_functional_homolog_of</type>
<to>SO:0000147</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000468</id>
<name>golden_path_fragment</name>
<def>
<defstr>One of the pieces of sequence that make up a golden path.</defstr>
<dbxref>
<acc>rd</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>golden path fragment</synonym_text>
</synonym>
<is_a>SO:0000143</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000688</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000472</id>
<name>tiling_path</name>
<def>
<defstr>A set of regions which overlap with minimal polymorphism to form a linear sequence.</defstr>
<dbxref>
<acc>cjm</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>tiling path</synonym_text>
</synonym>
<is_a>SO:0000353</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000474</id>
<name>tiling_path_fragment</name>
<def>
<defstr>A piece of sequence that makes up a tiling_path (SO:0000472).</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>tiling path fragment</synonym_text>
</synonym>
<is_a>SO:0000143</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000472</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000483</id>
<name>nc_primary_transcript</name>
<def>
<defstr>A primary transcript that is never translated into a protein.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>nc primary transcript</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>noncoding primary transcript</synonym_text>
</synonym>
<is_a>SO:0000185</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000484</id>
<name>three_prime_coding_exon_noncoding_region</name>
<def>
<defstr>The sequence of the 3' exon that is not coding.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>three prime coding exon noncoding region</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>three_prime_exon_noncoding_region</synonym_text>
</synonym>
<is_a>SO:0001214</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000486</id>
<name>five_prime_coding_exon_noncoding_region</name>
<def>
<defstr>The sequence of the 5' exon preceding the start codon.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>five prime coding exon noncoding region</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>five_prime_exon_noncoding_region</synonym_text>
</synonym>
<is_a>SO:0001214</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000200</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000499</id>
<name>virtual_sequence</name>
<def>
<defstr>A continuous piece of sequence similar to the 'virtual contig' concept of the Ensembl database.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>virtual sequence</synonym_text>
</synonym>
<is_a>SO:0000353</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000502</id>
<name>transcribed_region</name>
<def>
<defstr>A region of sequence that is transcribed. This region may cover the transcript of a gene, it may emcompas the sequence covered by all of the transcripts of a alternately spliced gene, or it may cover the region transcribed by a polycistronic transcript. A gene may have 1 or more transcribed regions and a transcribed_region may belong to one or more genes.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This concept cam about as a direct result of the SO meeting August 2004.nThe exact nature of the relationship between transcribed_region and gene is still up for discussion. We are going with 'associated_with' for the time being.</comment>
<subset>SOFA</subset>
<is_obsolete>1</is_obsolete>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000551</id>
<name>polyA_signal_sequence</name>
<def>
<defstr>The recognition sequence necessary for endonuclease cleavage of an RNA transcript that is followed by polyadenylation; consensus=AATAAA.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>poly(A) signal</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>polyA signal sequence</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>polyadenylation termination signal</synonym_text>
</synonym>
<is_a>SO:0005836</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000553</id>
<name>polyA_site</name>
<def>
<defstr>The site on an RNA transcript to which will be added adenine residues by post-transcriptional polyadenylation.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>polyA cleavage site</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>polyA site</synonym_text>
</synonym>
<synonym scope="related">
<synonym_text>polyadenylation site</synonym_text>
</synonym>
<is_a>SO:0000837</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000205</to>
</relationship>
<relationship>
<type>part_of</type>
<to>SO:0000233</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000577</id>
<name>centromere</name>
<def>
<defstr>A region of chromosome where the spindle fibers attach during mitosis and meiosis.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Centromere</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000628</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000581</id>
<name>cap</name>
<def>
<defstr>A structure consisting of a 7-methylguanosine in 5'-5' triphosphate linkage with the first nucleotide of an mRNA. It is added post-transcriptionally, and is not encoded in the DNA.</defstr>
<dbxref>
<acc>http://seqcore.brcf.med.umich.edu/doc/educ/dnapr/mbglossary/mbgloss.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/5%27_cap</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000587</id>
<name>group_I_intron</name>
<def>
<defstr>Group I catalytic introns are large self-splicing ribozymes. They catalyze their own excision from mRNA, tRNA and rRNA precursors in a wide range of organisms. The core secondary structure consists of 9 paired regions (P1-P9). These fold to essentially two domains, the P4-P6 domain (formed from the stacking of P5, P4, P6 and P6a helices) and the P3-P9 domain (formed from the P8, P3, P7 and P9 helices). Group I catalytic introns often have long ORFs inserted in loop regions.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00028</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>GO:0000372.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>group I intron</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Group_I_intron</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000588</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000588</id>
<name>autocatalytically_spliced_intron</name>
<def>
<defstr>A self spliced intron.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>autocatalytically spliced intron</synonym_text>
</synonym>
<is_a>SO:0000188</is_a>
<intersection_of>
<to>SO:0000188</to>
</intersection_of>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000590</id>
<name>SRP_RNA</name>
<def>
<defstr>The signal recognition particle (SRP) is a universally conserved ribonucleoprotein. It is involved in the co-translational targeting of proteins to membranes. The eukaryotic SRP consists of a 300-nucleotide 7S RNA and six proteins: SRPs 72, 68, 54, 19, 14, and 9. Archaeal SRP consists of a 7S RNA and homologues of the eukaryotic SRP19 and SRP54 proteins. In most eubacteria, the SRP consists of a 4.5S RNA and the Ffh protein (a homologue of the eukaryotic SRP54 protein). Eukaryotic and archaeal 7S RNAs have very similar secondary structures, with eight helical elements. These fold into the Alu and S domains, separated by a long linker region. Eubacterial SRP is generally a simpler structure, with the M domain of Ffh bound to a region of the 4.5S RNA that corresponds to helix 8 of the eukaryotic and archaeal SRP S domain. Some Gram-positive bacteria (e.g. Bacillus subtilis), however, have a larger SRP RNA that also has an Alu domain. The Alu domain is thought to mediate the peptide chain elongation retardation function of the SRP. The universally conserved helix which interacts with the SRP54/Ffh M domain mediates signal sequence recognition. In eukaryotes and archaea, the SRP19-helix 6 complex is thought to be involved in SRP assembly and stabilizes helix 8 for SRP54 binding.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00017</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>7S RNA</synonym_text>
</synonym>
<synonym scope="related">
<synonym_text>signal recognition particle RNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>SRP RNA</synonym_text>
</synonym>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000593</id>
<name>C_D_box_snoRNA</name>
<def>
<defstr>Most box C/D snoRNAs also contain long (>10 nt) sequences complementary to rRNA. Boxes C and D, as well as boxes C' and D', are usually located in close proximity, and form a structure known as the box C/D motif. This motif is important for snoRNA stability, processing, nucleolar targeting and function. A small number of box C/D snoRNAs are involved in rRNA processing; most, however, are known or predicted to serve as guide RNAs in ribose methylation of rRNA. Targeting involves direct base pairing of the snoRNA at the rRNA site to be modified and selection of a rRNA nucleotide a fixed distance from box D or D'.</defstr>
<dbxref>
<acc>http://www.bio.umass.edu/biochem/rna-sequence/Yeast_snoRNA_Database/snoRNA_DataBase.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>box C/D snoRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>C D box snoRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>C/D box snoRNA</synonym_text>
</synonym>
<is_a>SO:0000275</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000602</id>
<name>guide_RNA</name>
<def>
<defstr>A short 3'-uridylated RNA that can form a duplex (except for its post-transcriptionally added oligo_U tail (SO:0000609)) with a stretch of mature edited mRNA.</defstr>
<dbxref>
<acc>http://www.rna.ucla.edu/index.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>gRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>guide RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Guide_RNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000603</id>
<name>group_II_intron</name>
<def>
<defstr>Group II introns are found in rRNA, tRNA and mRNA of organelles in fungi, plants and protists, and also in mRNA in bacteria. They are large self-splicing ribozymes and have 6 structural domains (usually designated dI to dVI). A subset of group II introns also encode essential splicing proteins in intronic ORFs. The length of these introns can therefore be up to 3kb. Splicing occurs in almost identical fashion to nuclear pre-mRNA splicing with two transesterification steps. The 2' hydroxyl of a bulged adenosine in domain VI attacks the 5' splice site, followed by nucleophilic attack on the 3' splice site by the 3' OH of the upstream exon. Protein machinery is required for splicing in vivo, and long range intron-intron and intron-exon interactions are important for splice site positioning. Group II introns are further sub-classified into groups IIA and IIB which differ in splice site consensus, distance of bulged A from 3' splice site, some tertiary interactions, and intronic ORF phylogeny.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/Software/Rfam/browse/index.shtml</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>GO:0000373.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>group II intron</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Group_II_intron</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000588</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000605</id>
<name>intergenic_region</name>
<def>
<defstr>A region containing or overlapping no genes that is bounded on either side by a gene, or bounded by a gene and the end of the chromosome.</defstr>
<dbxref>
<acc>cjm</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>intergenic region</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Intergenic_region</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000610</id>
<name>polyA_sequence</name>
<def>
<defstr>Sequence of about 100 nucleotides of A added to the 3' end of most eukaryotic mRNAs.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>polyA sequence</synonym_text>
</synonym>
<is_a>SO:0001411</is_a>
<relationship>
<type>adjacent_to</type>
<to>SO:0000234</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000611</id>
<name>branch_site</name>
<def>
<defstr>A pyrimidine rich sequence near the 3' end of an intron to which the 5'end becomes covalently bound during nuclear splicing. The resulting structure resembles a lariat.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>branch point</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>branch site</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>branch_point</synonym_text>
</synonym>
<is_a>SO:0000841</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000612</id>
<name>polypyrimidine_tract</name>
<def>
<defstr>The polypyrimidine tract is one of the cis-acting sequence elements directing intron removal in pre-mRNA splicing.</defstr>
<dbxref>
<acc>http://nar.oupjournals.org/cgi/content/full/25/4/888</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>polypyrimidine tract</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Polypyrimidine_tract</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000841</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000616</id>
<name>transcription_end_site</name>
<def>
<defstr>The base where transcription ends.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>transcription end site</synonym_text>
</synonym>
<is_a>SO:0000835</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000624</id>
<name>telomere</name>
<def>
<defstr>A specific structure at the end of a linear chromosome, required for the integrity and maintenance of the end.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>telomeric DNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>telomeric sequence</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Telomere</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000628</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000625</id>
<name>silencer</name>
<def>
<defstr>A regulatory region which upon binding of transcription factors, suppress the transcription of the gene or genes they control.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Silencer_(DNA)</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000727</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000627</id>
<name>insulator</name>
<def>
<defstr>A transcriptional cis regulatory region that when located between a CM and a gene's promoter prevents the CRM from modulating that genes expression.</defstr>
<dbxref>
<acc>regcreative</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>insulator element</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Insulator_(genetics)</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001055</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000628</id>
<name>chromosomal_structural_element</name>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>chromosomal structural element</synonym_text>
</synonym>
<is_a>SO:0000830</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000643</id>
<name>minisatellite</name>
<def>
<defstr>A repeat region containing tandemly repeated sequences having a unit length of 10 to 40 bp.</defstr>
<dbxref>
<acc>http://www.informatics.jax.org/silver/glossary.shtml</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Minisatellite</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000005</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000644</id>
<name>antisense_RNA</name>
<def>
<defstr>Antisense RNA is RNA that is transcribed from the coding, rather than the template, strand of DNA. It is therefore complementary to mRNA.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>antisense RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Antisense_RNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<relationship>
<type>derives_from</type>
<to>SO:0000645</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000645</id>
<name>antisense_primary_transcript</name>
<def>
<defstr>The reverse complement of the primary transcript.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>antisense primary transcript</synonym_text>
</synonym>
<is_a>SO:0000185</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000646</id>
<name>siRNA</name>
<def>
<defstr>A small RNA molecule that is the product of a longer exogenous or endogenous dsRNA, which is either a bimolecular duplex or very long hairpin, processed (via the Dicer pathway) such that numerous siRNAs accumulate from both strands of the dsRNA. SRNAs trigger the cleavage of their target molecules.</defstr>
<dbxref>
<acc>12592000</acc>
<dbname>PMID</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small interfering RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/SiRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000649</id>
<name>stRNA</name>
<def>
<defstr>Non-coding RNAs of about 21 nucleotides in length that regulate temporal development; first discovered in C. elegans.</defstr>
<dbxref>
<acc>11081512</acc>
<dbname>PMID</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small temporal RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/StRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000655</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000650</id>
<name>small_subunit_rRNA</name>
<def>
<defstr>Ribosomal RNA transcript that structures the small subunit of the ribosome.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>small subunit rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>SSU RNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>SSU rRNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<is_a>SO:0000252</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000651</id>
<name>large_subunit_rRNA</name>
<def>
<defstr>Ribosomal RNA transcript that structures the large subunit of the ribosome.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>large subunit rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>LSU RNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>LSU rRNA</synonym_text>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</synonym>
<is_a>SO:0000252</is_a>
<relationship>
<type>derives_from</type>
<to>SO:0000325</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000652</id>
<name>rRNA_5S</name>
<def>
<defstr>5S ribosomal RNA (5S rRNA) is a component of the large ribosomal subunit in both prokaryotes and eukaryotes. In eukaryotes, it is synthesised by RNA polymerase III (the other eukaryotic rRNAs are cleaved from a 45S precursor synthesised by RNA polymerase I). In Xenopus oocytes, it has been shown that fingers 4-7 of the nine-zinc finger transcription factor TFIIIA can bind to the central region of 5S RNA. Thus, in addition to positively regulating 5S rRNA transcription, TFIIIA also stabilizes 5S rRNA until it is required for transcription.</defstr>
<dbxref>
<acc>http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00001</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>5S LSU rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>5S ribosomal RNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>5S rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>rRNA 5S</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/5S_ribosomal_RNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000651</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000653</id>
<name>rRNA_28S</name>
<def>
<defstr>A component of the large ribosomal subunit.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>28S LSU rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>28S ribosomal RNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>28S rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>rRNA 28S</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/28S_ribosomal_RNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000651</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000655</id>
<name>ncRNA</name>
<def>
<defstr>An RNA transcript that does not encode for a protein rather the RNA molecule is the gene product.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>A ncRNA is a processed_transcript, so it may not contain parts such as transcribed_spacer_regions that are removed in the act of processing. For the corresponding primary_transcripts, please see term SO:0000483 nc_primary_transcript.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>noncoding RNA</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/NcRNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000233</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000657</id>
<name>repeat_region</name>
<def>
<defstr>A region of sequence containing one or more repeat units.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>repeat region</synonym_text>
</synonym>
<is_a>SO:0001412</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000658</id>
<name>dispersed_repeat</name>
<def>
<defstr>A repeat that is located at dispersed sites in the genome.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>dispersed repeat</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>interspersed repeat</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Interspersed_repeat</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000657</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000662</id>
<name>spliceosomal_intron</name>
<def>
<defstr>An intron which is spliced by the spliceosome.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>GO:0000398.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>spliceosomal intron</synonym_text>
</synonym>
<is_a>SO:0000188</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000667</id>
<name>insertion</name>
<alt_id>SO:1000034</alt_id>
<def>
<defstr>The sequence of one or more nucleotides added between two adjacent nucleotides in the sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>nucleotide insertion</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>nucleotide_insertion</synonym_text>
</synonym>
<is_a>SO:0001059</is_a>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000668</id>
<name>EST_match</name>
<def>
<defstr>A match against an EST sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>EST match</synonym_text>
</synonym>
<is_a>SO:0000102</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000673</id>
<name>transcript</name>
<def>
<defstr>An RNA synthesized on a DNA or RNA template by an RNA polymerase.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/RNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000831</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000684</id>
<name>nuclease_sensitive_site</name>
<def>
<defstr>A region of nucleotide sequence targeted by a nuclease enzyme.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>nuclease sensitive site</synonym_text>
</synonym>
<is_a>SO:0000059</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000687</id>
<name>deletion_junction</name>
<def>
<defstr>The space between two bases in a sequence which marks the position where a deletion has occurred.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>deletion junction</synonym_text>
</synonym>
<is_a>SO:0000699</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000688</id>
<name>golden_path</name>
<def>
<defstr>A set of subregions selected from sequence contigs which when concatenated form a nonredundant linear sequence.</defstr>
<dbxref>
<acc>ls</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>golden path</synonym_text>
</synonym>
<is_a>SO:0000353</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000689</id>
<name>cDNA_match</name>
<def>
<defstr>A match against cDNA sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>cDNA match</synonym_text>
</synonym>
<is_a>SO:0000102</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000694</id>
<name>SNP</name>
<def>
<defstr>SNPs are single base pair positions in genomic DNA at which different sequence alternatives exist in normal individuals in some population(s), wherein the least frequent variant has an abundance of 1% or greater.</defstr>
<dbxref>
<acc>cb</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>single nucleotide polymorphism</synonym_text>
</synonym>
<is_a>SO:0001483</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000695</id>
<name>reagent</name>
<def>
<defstr>A sequence used in experiment.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>Requested by Lynn Crosby, jan 2006.</comment>
<subset>SOFA</subset>
<is_a>SO:0001409</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000696</id>
<name>oligo</name>
<def>
<defstr>A short oligonucleotide sequence, of length on the order of 10's of bases; either single or double stranded.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>oligonucleotide</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Oligonucleotide</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000695</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000699</id>
<name>junction</name>
<def>
<defstr>A sequence_feature with an extent of zero.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>A junction is a boundary between regions. A boundary has an extent of zero.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>boundary</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>breakpoint</synonym_text>
</synonym>
<is_a>SO:0000110</is_a>
<disjoint_from>SO:0000001</disjoint_from>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000700</id>
<name>remark</name>
<def>
<defstr>A comment about the sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_a>SO:0001410</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000701</id>
<name>possible_base_call_error</name>
<def>
<defstr>A region of sequence where the validity of the base calling is questionable.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>possible base call error</synonym_text>
</synonym>
<is_a>SO:0000413</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000702</id>
<name>possible_assembly_error</name>
<def>
<defstr>A region of sequence where there may have been an error in the assembly.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>possible assembly error</synonym_text>
</synonym>
<is_a>SO:0000413</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000703</id>
<name>experimental_result_region</name>
<def>
<defstr>A region of sequence implicated in an experimental result.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>experimental result region</synonym_text>
</synonym>
<is_a>SO:0000700</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000704</id>
<name>gene</name>
<def>
<defstr>A region (or regions) that includes all of the sequence elements necessary to encode a functional transcript. A gene may include regulatory regions, transcribed regions and/or other functional sequence regions.</defstr>
<dbxref>
<acc>immuno_workshop</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term is mapped to MGED. Do not obsolete without consulting MGED ontology. A gene may be considered as a unit of inheritance.</comment>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Gene</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001411</is_a>
<relationship>
<type>member_of</type>
<to>SO:0005855</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000705</id>
<name>tandem_repeat</name>
<def>
<defstr>Two or more adjcent copies of a region (of length greater than 1).</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>tandem repeat</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Tandem_repeat</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<xref_analog>
<acc>http://www.sci.sdsu.edu/~smaloy/Glossary/T.html</acc>
<dbname>URL</dbname>
</xref_analog>
<is_a>SO:0000657</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000706</id>
<name>trans_splice_acceptor_site</name>
<def>
<defstr>The 3' splice site of the acceptor primary transcript.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This region contains a polypyridine tract and AG dinucleotide in some organisms and is UUUCAG in C. elegans.</comment>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>3' trans splice site</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>trans splice acceptor site</synonym_text>
</synonym>
<is_a>SO:0001420</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000714</id>
<name>nucleotide_motif</name>
<def>
<defstr>A region of nucleotide sequence corresponding to a known motif.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>nucleotide motif</synonym_text>
</synonym>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000715</id>
<name>RNA_motif</name>
<def>
<defstr>A motif that is active in RNA sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>RNA motif</synonym_text>
</synonym>
<is_a>SO:0000714</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000717</id>
<name>reading_frame</name>
<def>
<defstr>A nucleic acid sequence that when read as sequential triplets, has the potential of encoding a sequential string of amino acids. It need not contain the start or stop codon.</defstr>
<dbxref>
<acc>rb</acc>
<dbname>SGD</dbname>
</dbxref>
</def>
<comment>This term was added after a request by SGD. August 2004. Modified after SO meeting in Cambridge to not include start or stop.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>reading frame</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Reading_frame</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001410</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000719</id>
<name>ultracontig</name>
<def>
<defstr>An ordered and oriented set of scaffolds based on somewhat weaker sets of inferential evidence such as one set of mate pair reads together with supporting evidence from ESTs or location of markers from SNP or microsatellite maps, or cytogenetic localization of contained markers.</defstr>
<dbxref>
<acc>WG</acc>
<dbname>FB</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_a>SO:0000353</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000724</id>
<name>oriT</name>
<def>
<defstr>A region of a DNA molecule where transfer is initiated during the process of conjugation or mobilization.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>origin of transfer</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Origin_of_transfer</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000296</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000725</id>
<name>transit_peptide</name>
<alt_id>BS:00055</alt_id>
<def>
<defstr>The transit_peptide is a short region at the N-terminus of the peptide that directs the protein to an organelle (chloroplast, mitochondrion, microbody or cyanelle).</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Added to bring SO inline with the embl ddbj genbank feature table. Old definition before biosapiens: The coding sequence for an N-terminal domain of a nuclear-encoded organellar protein. This domain is involved in post translational import of the protein into the organelle.</comment>
<subset>biosapiens</subset>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>signal</synonym_text>
</synonym>
<synonym scope="related">
<synonym_text>transit</synonym_text>
<dbxref>
<acc>feature_type</acc>
<dbname>uniprot</dbname>
</dbxref>
</synonym>
<synonym scope="exact">
<synonym_text>transit peptide</synonym_text>
</synonym>
<is_a>SO:0001527</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000727</id>
<name>CRM</name>
<def>
<defstr>A regulatory_region where more than 1 TF_binding_site together are regulatorily active.</defstr>
<dbxref>
<acc>SG</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>Requested by Stepen Grossmann Dec 2004.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>cis regulatory module</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>TF module</synonym_text>
</synonym>
<is_a>SO:0001055</is_a>
<intersection_of>
<to>SO:0001055</to>
</intersection_of>
<intersection_of>
<type>has_part</type>
<to>SO:0000235</to>
</intersection_of>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000730</id>
<name>gap</name>
<def>
<defstr>A gap in the sequence of known length. The unknown bases are filled in with N's.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_a>SO:0000143</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000353</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000752</id>
<name>gene_group_regulatory_region</name>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>gene group regulatory region</synonym_text>
</synonym>
<is_a>SO:0005836</is_a>
<relationship>
<type>member_of</type>
<to>SO:0005855</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000753</id>
<name>clone_insert</name>
<def>
<defstr>The region of sequence that has been inserted and is being propogated by the clone.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>clone insert</synonym_text>
</synonym>
<is_a>SO:0000695</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000151</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000777</id>
<name>pseudogenic_rRNA</name>
<def>
<defstr>A non functional descendent of an rRNA.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>Added Jan 2006 to allow the annotation of the pseudogenic rRNA by flybase. Non-functional is defined as its transcription is prevented due to one or more mutatations.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>pseudogenic rRNA</synonym_text>
</synonym>
<is_a>SO:0000462</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000778</id>
<name>pseudogenic_tRNA</name>
<def>
<defstr>A non functional descendent of a tRNA.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>Added Jan 2006 to allow the annotation of the pseudogenic tRNA by flybase. Non-functional is defined as its transcription is prevented due to one or more mutatations.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>pseudogenic tRNA</synonym_text>
</synonym>
<is_a>SO:0000462</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000830</id>
<name>chromosome_part</name>
<def>
<defstr>A region of a chromosome.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This is a manufactured term, that serves the purpose of allow the parts of a chromosome to have an is_a path to the root.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>chromosome part</synonym_text>
</synonym>
<is_a>SO:0001411</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000340</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000831</id>
<name>gene_member_region</name>
<def>
<defstr>A region of a gene.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>A manufactured term used to allow the parts of a gene to have an is_a path to the root.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>gene member region</synonym_text>
</synonym>
<is_a>SO:0001411</is_a>
<relationship>
<type>member_of</type>
<to>SO:0000704</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000833</id>
<name>transcript_region</name>
<def>
<defstr>A region of a transcript.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term was added to provide a grouping term for the region parts of transcript, thus giving them an is_a path back to the root.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>transcript region</synonym_text>
</synonym>
<is_a>SO:0001411</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000673</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000834</id>
<name>mature_transcript_region</name>
<def>
<defstr>A region of a mature transcript.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>A manufactured term to collect together the parts of a mature transcript and give them an is_a path to the root.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>mature transcript region</synonym_text>
</synonym>
<is_a>SO:0000833</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000835</id>
<name>primary_transcript_region</name>
<def>
<defstr>A part of a primary transcript.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term was added to provide a grouping term for the region parts of primary_transcript, thus giving them an is_a path back to the root.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>primary transcript region</synonym_text>
</synonym>
<is_a>SO:0000833</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000185</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000836</id>
<name>mRNA_region</name>
<def>
<defstr>A region of an mRNA.</defstr>
<dbxref>
<acc>cb</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This term was added to provide a grouping term for the region parts of mRNA, thus giving them an is_a path back to the root.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>mRNA region</synonym_text>
</synonym>
<is_a>SO:0000834</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000234</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000837</id>
<name>UTR_region</name>
<def>
<defstr>A region of UTR.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>A region of UTR. This term is a grouping term to allow the parts of UTR to have an is_a path to the root.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>UTR region</synonym_text>
</synonym>
<is_a>SO:0000836</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000839</id>
<name>polypeptide_region</name>
<alt_id>BS:00124</alt_id>
<alt_id>BS:00331</alt_id>
<def>
<defstr>Biological sequence region that can be assigned to a specific subsequence of a polypeptide.</defstr>
<dbxref>
<acc>GAR</acc>
<dbname>SO</dbname>
</dbxref>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>Added to allow the polypeptide regions to have is_a paths back to the root.</comment>
<subset>biosapiens</subset>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>positional</synonym_text>
</synonym>
<synonym scope="related">
<synonym_text>positional polypeptide feature</synonym_text>
</synonym>
<synonym scope="narrow">
<synonym_text>region</synonym_text>
<dbxref>
<acc>feature_type</acc>
<dbname>uniprot</dbname>
</dbxref>
</synonym>
<synonym scope="related">
<synonym_text>region or site annotation</synonym_text>
</synonym>
<synonym scope="narrow">
<synonym_text>site</synonym_text>
<dbxref>
<acc>feature_type</acc>
<dbname>uniprot</dbname>
</dbxref>
</synonym>
<is_a>SO:0001411</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000104</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000841</id>
<name>spliceosomal_intron_region</name>
<def>
<defstr>A region within an intron.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>A terms added to allow the parts of introns to have is_a paths to the root.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>spliceosomal intron region</synonym_text>
</synonym>
<is_a>SO:0000835</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000662</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000842</id>
<name>gene_component_region</name>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>gene component region</synonym_text>
</synonym>
<is_a>SO:0001411</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000704</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000851</id>
<name>CDS_region</name>
<def>
<defstr>A region of a CDS.</defstr>
<dbxref>
<acc>cb</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>CDS region</synonym_text>
</synonym>
<is_a>SO:0000836</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000316</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0000852</id>
<name>exon_region</name>
<def>
<defstr>A region of an exon.</defstr>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>exon region</synonym_text>
</synonym>
<is_a>SO:0000833</is_a>
<relationship>
<type>part_of</type>
<to>SO:0000147</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001000</id>
<name>rRNA_16S</name>
<def>
<defstr>A large polynucleotide in Bacteria and Archaea, which functions as the small subunit of the ribosome.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>16S ribosomal RNA</synonym_text>
</synonym>
<synonym scope="related">
<synonym_text>16S rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>16S SSU RNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>rRNA 16S</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/16S_ribosomal_RNA</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000650</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001001</id>
<name>rRNA_23S</name>
<def>
<defstr>A large polynucleotide in Bacteria and Archaea, which functions as the large subunit of the ribosome.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>23S LSU rRNA</synonym_text>
</synonym>
<synonym scope="related">
<synonym_text>23S ribosomal RNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>23S rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>rRNA 23S</synonym_text>
</synonym>
<is_a>SO:0000651</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001002</id>
<name>rRNA_25S</name>
<def>
<defstr>A large polynucleotide which functions as part of the large subunit of the ribosome in some eukaryotes.</defstr>
<dbxref>
<acc>cb</acc>
<dbname>RSC</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>25S LSU rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>25S ribosomal RNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>25S rRNA</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>rRNA 25S</synonym_text>
</synonym>
<is_a>SO:0000651</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001019</id>
<name>copy_number_variation</name>
<def>
<defstr>A variation that increases or decreases the copy number of a given region.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>CNP</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>CNV</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>copy number polymorphism</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>copy number variation</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Copy_number_variation</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001059</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001037</id>
<name>mobile_genetic_element</name>
<def>
<defstr>A nucleotide region with either intra-genome or intracellular moblity, of varying length, which often carry the information necessary for transfer and recombination with the host genome.</defstr>
<dbxref>
<acc>14681355</acc>
<dbname>PMID</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>MGE</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>mobile genetic element</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Mobile_genetic_element</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001411</is_a>
<intersection_of>
<to>SO:0000001</to>
</intersection_of>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001039</id>
<name>integrated_mobile_genetic_element</name>
<def>
<defstr>An MGE that is integrated into the host chromosome.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>integrated mobile genetic element</synonym_text>
</synonym>
<is_a>SO:0001037</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001055</id>
<name>transcriptional_cis_regulatory_region</name>
<def>
<defstr>A regulatory_region that modulates the transcription of a gene or genes.</defstr>
<dbxref>
<acc>regcreative</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>transcriptional cis regulatory region</synonym_text>
</synonym>
<is_a>SO:0005836</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001056</id>
<name>splicing_regulatory_region</name>
<def>
<defstr>A regulatory_region that modulates splicing.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>splicing regulatory region</synonym_text>
</synonym>
<is_a>SO:0005836</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001059</id>
<name>sequence_alteration</name>
<alt_id>SO:1000004</alt_id>
<alt_id>SO:1000007</alt_id>
<def>
<defstr>A sequence_alteration is a sequence_feature whose extent is the deviation from another sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>Merged with partially characterized change in nucleotide sequence.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>partially characterised change in DNA sequence</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>partially_characterised_change_in_DNA_sequence</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>sequence alteration</synonym_text>
</synonym>
<is_a>SO:0000110</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001063</id>
<name>immature_peptide_region</name>
<alt_id>BS:00129</alt_id>
<def>
<defstr>An immature_peptide_region is the extent of the peptide after it has been translated and before any processing occurs.</defstr>
<dbxref>
<acc>GAR</acc>
<dbname>EBIBS</dbname>
</dbxref>
</def>
<comment>Range.</comment>
<subset>biosapiens</subset>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>immature_peptide_region</synonym_text>
</synonym>
<is_a>SO:0000839</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001214</id>
<name>noncoding_region_of_exon</name>
<def>
<defstr>The maximal intersection of exon and UTR.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>An exon either containing but not starting with a start codon or containing but not ending with a stop codon will be partially coding and partially non coding.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>noncoding region of exon</synonym_text>
</synonym>
<is_a>SO:0000852</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001215</id>
<name>coding_region_of_exon</name>
<def>
<defstr>The region of an exon that encodes for protein sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>An exon containing either a start or stop codon will be partially coding and partially non coding.</comment>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>coding region of exon</synonym_text>
</synonym>
<is_a>SO:0000852</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001235</id>
<name>replicon</name>
<def>
<defstr>A region containing at least one unique origin of replication and a unique termination site.</defstr>
<dbxref>
<acc>0716719207</acc>
<dbname>ISBN</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Replicon_(genetics)</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001236</id>
<name>base</name>
<def>
<defstr>A base is a sequence feature that corresponds to a single unit of a nucleotide polymer.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Nucleobase</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001248</id>
<name>assembly</name>
<def>
<defstr>A region of the genome of known length that is composed by ordering and aligning two or more different regions.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Genome_assembly#Genome_assembly</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001410</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001409</id>
<name>biomaterial_region</name>
<def>
<defstr>A region which is intended for use in an experiment.</defstr>
<dbxref>
<acc>cb</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>biomaterial region</synonym_text>
</synonym>
<is_a>SO:0000001</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001410</id>
<name>experimental_feature</name>
<def>
<defstr>A region which is the result of some arbitrary experimental procedure. The procedure may be carried out with biological material or inside a computer.</defstr>
<dbxref>
<acc>cb</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>analysis feature</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>experimental output artefact</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>experimental_output_artefact</synonym_text>
</synonym>
<is_a>SO:0000001</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001411</id>
<name>biological_region</name>
<def>
<defstr>A region defined by its disposition to be involved in a biological process.</defstr>
<dbxref>
<acc>cb</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>biological region</synonym_text>
</synonym>
<is_a>SO:0000001</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001412</id>
<name>topologically_defined_region</name>
<def>
<defstr>A region that is defined according to its relations with other regions within the same sequence.</defstr>
<dbxref>
<acc>cb</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>topologically defined region</synonym_text>
</synonym>
<is_a>SO:0000001</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001419</id>
<name>cis_splice_site</name>
<def>
<defstr>Intronic 2 bp region bordering exon. A splice_site that adjacent_to exon and overlaps intron.</defstr>
<dbxref>
<acc>cjm</acc>
<dbname>SO</dbname>
</dbxref>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>cis splice site</synonym_text>
</synonym>
<is_a>SO:0000162</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001420</id>
<name>trans_splice_site</name>
<def>
<defstr>Primary transcript region bordering trans-splice junction.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>trans splice site</synonym_text>
</synonym>
<is_a>SO:0000162</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001483</id>
<name>SNV</name>
<def>
<defstr>SNVs are single base pair positions in genomic DNA at which different sequence alternatives exist.</defstr>
<dbxref>
<acc>bm</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>single nucleotide variant</synonym_text>
</synonym>
<is_a>SO:1000002</is_a>
<created_by>kareneilbeck</created_by>
<creation_date>2009-10-08T11:37:49Z</creation_date>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001527</id>
<name>peptide_localization_signal</name>
<def>
<defstr>A region of peptide sequence used to target the polypeptide molecule to a specific organelle.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>localization signal</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>peptide localization signal</synonym_text>
</synonym>
<is_a>SO:0000839</is_a>
<created_by>kareneilbeck</created_by>
<creation_date>2010-03-11T02:15:05Z</creation_date>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0001720</id>
<name>epigenetically_modified_region</name>
<def>
<defstr>A biological region implicated in inherited changes caused by mechanisms other than changes in the underlying DNA sequence.</defstr>
<dbxref>
<acc>http://en.wikipedia.org/wiki/Epigenetics</acc>
<dbname>URL</dbname>
</dbxref>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>epigenetically modified region</synonym_text>
</synonym>
<is_a>SO:0001411</is_a>
<intersection_of>
<to>SO:0001411</to>
</intersection_of>
<created_by>kareneilbeck</created_by>
<creation_date>2010-03-27T12:02:29Z</creation_date>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0005836</id>
<name>regulatory_region</name>
<def>
<defstr>A DNA sequence that controls the expression of a gene.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>regulatory region</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Regulatory_region</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0000831</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0005855</id>
<name>gene_group</name>
<def>
<defstr>A collection of related genes.</defstr>
<dbxref>
<acc>ma</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>gene group</synonym_text>
</synonym>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:0100011</id>
<name>cleaved_peptide_region</name>
<def>
<defstr>The cleaved_peptide_regon is the a region of peptide sequence that is cleaved during maturation.</defstr>
<dbxref>
<acc>GAR</acc>
<dbname>EBIBS</dbname>
</dbxref>
</def>
<comment>Range.</comment>
<subset>biosapiens</subset>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>cleaved peptide region</synonym_text>
</synonym>
<is_a>SO:0000839</is_a>
<relationship>
<type>part_of</type>
<to>SO:0001063</to>
</relationship>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:1000002</id>
<name>substitution</name>
<def>
<defstr>Any change in genomic DNA caused by a single event.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/mutations/recommendations/mutevent.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_a>SO:0001059</is_a>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:1000005</id>
<name>complex_substitution</name>
<def>
<defstr>When no simple or well defined DNA mutation event describes the observed DNA change, the keyword "complex" should be used. Usually there are multiple equally plausible explanations for the change.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/mutations/recommendations/mutevent.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>complex substitution</synonym_text>
</synonym>
<is_a>SO:1000002</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:1000008</id>
<name>point_mutation</name>
<def>
<defstr>A single nucleotide change which has occurred at the same position of a corresponding nucleotide in a reference sequence.</defstr>
<dbxref>
<acc>immuno_workshop</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="exact">
<synonym_text>point mutation</synonym_text>
</synonym>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Point_mutation</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0001483</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:1000036</id>
<name>inversion</name>
<def>
<defstr>A continuous nucleotide sequence is inverted in the same position.</defstr>
<dbxref>
<acc>http://www.ebi.ac.uk/mutations/recommendations/mutevent.html</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_a>SO:0001059</is_a>
<is_a>SO:0001411</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:1001284</id>
<name>regulon</name>
<def>
<defstr>A group of genes, whether linked as a cluster or not, that respond to a common regulatory signal.</defstr>
<dbxref>
<acc>0198506732</acc>
<dbname>ISBN</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<xref_analog>
<acc>http://en.wikipedia.org/wiki/Regulon</acc>
<dbname>URL</dbname>
<name>wiki</name>
</xref_analog>
<is_a>SO:0005855</is_a>
<namespace>sequence</namespace>
</term>
<term>
<id>SO:2000061</id>
<name>databank_entry</name>
<def>
<defstr>The sequence referred to by an entry in a databank such as Genbank or SwissProt.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<synonym scope="related">
<synonym_text>accession</synonym_text>
</synonym>
<synonym scope="exact">
<synonym_text>databank entry</synonym_text>
</synonym>
<is_a>SO:0000695</is_a>
<namespace>sequence</namespace>
</term>
<typedef>
<id>adjacent_to</id>
<name>adjacent_to</name>
<def>
<defstr>A geometric operator, specified in Egenhofer 1989. Two features meet if they share a junction on the sequence.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>associated_with</id>
<name>associated_with</name>
<comment>This relationship is vague and up for discussion.</comment>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>complete_evidence_for_feature</id>
<name>complete_evidence_for_feature</name>
<def>
<defstr>B is complete_evidence_for_feature A if the extent (5' and 3' boundaries) and internal boundaries of B fully support the extent and internal boundaries of A.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>If A is a feature with multiple regions such as a multi exon transcript, the supporting EST evidence is complete if each of the regions is supported by an equivalent region in B. Also there must be no extra regions in B that are not represented in A. This relationship was requested by jeltje on the SO term tracker. The thread for the discussion is available can be accessed via tracker ID:1917222.</comment>
<is_transitive>1</is_transitive>
<is_a>evidence_for_feature</is_a>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>derives_from</id>
<name>derives_from</name>
<subset>SOFA</subset>
<is_transitive>1</is_transitive>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>edited_from</id>
<name>edited_from</name>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T02:19:45Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>edited_to</id>
<name>edited_to</name>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T02:19:11Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>evidence_for_feature</id>
<name>evidence_for_feature</name>
<def>
<defstr>B is evidence_for_feature A, if an instance of B supports the existence of A.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>This relationship was requested by nlw on the SO term tracker. The thread for the discussion is available can be accessed via tracker ID:1917222.</comment>
<is_transitive>1</is_transitive>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>exemplar_of</id>
<name>exemplar_of</name>
<def>
<defstr>X is exemplar of Y if X is the best evidence for Y.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>Tracker id: 2594157.</comment>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>genome_of</id>
<name>genome_of</name>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>guided_by</id>
<name>guided_by</name>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T02:27:04Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>guides</id>
<name>guides</name>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T02:27:24Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>has_genome_location</id>
<name>has_genome_location</name>
<is_obsolete>1</is_obsolete>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>has_intergral_part</id>
<name>has_integral_part</name>
<def>
<defstr>X has_integral_part Y if and only if: X has_part Y and Y part_of X.</defstr>
<dbxref>
<acc>http://precedings.nature.com/documents/3495/version/1</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Example: mRNA has_integral_part CDS.</comment>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T12:01:46Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>has_origin</id>
<name>has_origin</name>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>has_part</id>
<name>has_part</name>
<def>
<defstr>Inverse of part_of.</defstr>
<dbxref>
<acc>http://precedings.nature.com/documents/3495/version/1</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Example: operon has_part gene.</comment>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>has_quality</id>
<name>has_quality</name>
<comment>The relationship between a feature and an attribute.</comment>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>homologous_to</id>
<name>homologous_to</name>
<subset>SOFA</subset>
<is_symmetric>1</is_symmetric>
<is_a>similar_to</is_a>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>integral_part_of</id>
<name>integral_part_of</name>
<def>
<defstr>X integral_part_of Y if and only if: X part_of Y and Y has_part X.</defstr>
<dbxref>
<acc>http://precedings.nature.com/documents/3495/version/1</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Example: exon integral_part_of transcript.</comment>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T12:03:28Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>member_of</id>
<name>member_of</name>
<comment>A subtype of part_of. Inverse is collection_of. Winston, M, Chaffin, R, Herrmann: A taxonomy of part-whole relations. Cognitive Science 1987, 11:417-444.</comment>
<subset>SOFA</subset>
<is_transitive>1</is_transitive>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>non_functional_homolog_of</id>
<name>non_functional_homolog_of</name>
<def>
<defstr>A relationship between a pseudogenic feature and its functional ancestor.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<subset>SOFA</subset>
<is_a>homologous_to</is_a>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>orthologous_to</id>
<name>orthologous_to</name>
<subset>SOFA</subset>
<is_symmetric>1</is_symmetric>
<is_a>homologous_to</is_a>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>paralogous_to</id>
<name>paralogous_to</name>
<subset>SOFA</subset>
<is_symmetric>1</is_symmetric>
<is_a>homologous_to</is_a>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>part_of</id>
<name>part_of</name>
<def>
<defstr>X part_of Y if X is a subregion of Y.</defstr>
<dbxref>
<acc>http://precedings.nature.com/documents/3495/version/1</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Example: amino_acid part_of polypeptide.</comment>
<subset>SOFA</subset>
<is_transitive>1</is_transitive>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>partial_evidence_for_feature</id>
<name>partial_evidence_for_feature</name>
<def>
<defstr>B is partial_evidence_for_feature A if the extent of B supports part_of but not all of A.</defstr>
<dbxref>
<acc>ke</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<is_a>evidence_for_feature</is_a>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>position_of</id>
<name>position_of</name>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>processed_from</id>
<name>processed_from</name>
<def>
<defstr>Inverse of processed_into.</defstr>
<dbxref>
<acc>http://precedings.nature.com/documents/3495/version/1</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Example: miRNA processed_from miRNA_primary_transcript.</comment>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T12:14:00Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>processed_into</id>
<name>processed_into</name>
<def>
<defstr>X is processed_into Y if a region X is modified to create Y.</defstr>
<dbxref>
<acc>http://precedings.nature.com/documents/3495/version/1</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Example: miRNA_primary_transcript processed into miRNA.</comment>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T12:15:02Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>recombined_from</id>
<name>recombined_from</name>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T02:21:03Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>recombined_to</id>
<name>recombined_to</name>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T02:20:07Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>regulated_by</id>
<name>regulated_by</name>
<is_obsolete>1</is_obsolete>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>sequence_of</id>
<name>sequence_of</name>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>similar_to</id>
<name>similar_to</name>
<subset>SOFA</subset>
<is_symmetric>1</is_symmetric>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>trans_spliced_from</id>
<name>trans_spliced_from</name>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T02:22:14Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>trans_spliced_to</id>
<name>trans_spliced_to</name>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T02:22:00Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>transcribed_from</id>
<name>transcribed_from</name>
<def>
<defstr>X is transcribed_from Y if X is synthesized from template Y.</defstr>
<dbxref>
<acc>http://precedings.nature.com/documents/3495/version/1</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Example: primary_transcript transcribed_from gene.</comment>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T12:05:39Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>transcribed_to</id>
<name>transcribed_to</name>
<def>
<defstr>Inverse of transcribed_from.</defstr>
<dbxref>
<acc>http://precedings.nature.com/documents/3495/version/1</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Example: gene transcribed_to primary_transcript.</comment>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T12:08:24Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>translates_to</id>
<name>translates_to</name>
<def>
<defstr>Inverse of translation _of.</defstr>
<dbxref>
<acc>http://precedings.nature.com/documents/3495/version/1</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Example: codon translates_to amino_acid.</comment>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T12:11:53Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>translation_of</id>
<name>translation_of</name>
<def>
<defstr>X is translation of Y if X is translated by ribosome to create Y.</defstr>
<dbxref>
<acc>http://precedings.nature.com/documents/3495/version/1</acc>
<dbname>URL</dbname>
</dbxref>
</def>
<comment>Example: Polypeptide translation_of CDS.</comment>
<created_by>kareneilbeck</created_by>
<creation_date>2009-08-19T12:09:59Z</creation_date>
<namespace>sequence</namespace>
</typedef>
<typedef>
<id>variant_of</id>
<name>variant_of</name>
<def>
<defstr>A' is a variant (mutation) of A = definition every instance of A' is either an immediate mutation of some instance of A, or there is a chain of immediate mutation processes linking A' to some instance of A.</defstr>
<dbxref>
<acc>immuno_workshop</acc>
<dbname>SO</dbname>
</dbxref>
</def>
<comment>Added to SO during the immunology workshop, June 2007. This relationship was approved by Barry Smith.</comment>
<namespace>sequence</namespace>
</typedef>
</obo>