#SOFA release 2.0 OBO file

format-version: 1.0
date: 16:05:2005 14:00
saved-by: kareneilbeck
auto-generated-by: DAG-Edit 1.419 rev 3
default-namespace: sequence
remark: autogenerated-by\:   DAG-Edit version 1.417\nsaved-by\:       eilbeck\ndate\:         Tue May 11 15\:18\:44 PDT 2004\nversion\: $Revision\: 1.45 $
subsetdef: SOFA "SO feature annotation"
Format-version:1.0

[Term]
id: SO:0000000
name: Sequence_Ontology
subset: SOFA

[Term]
id: SO:0000001
name: region
def: "Continous sequence." [SO:ke]
subset: SOFA
synonym: "sequence" []
is_a: SO:0000110 ! located_sequence_feature

[Term]
id: SO:0000006
name: PCR_product
def: "A region amplified by a PCR reaction." [SO:ke]
subset: SOFA
synonym: "amplicon" []
is_a: SO:0000695 ! reagent

[Term]
id: SO:0000007
name: read_pair
def: "A pair of sequencing reads in which the two members of the pair are related by originating at either end of a clone insert." [SO:ls]
subset: SOFA
is_a: SO:0000143 ! assembly_component
relationship: part_of SO:0000149 ! contig

[Term]
id: SO:0000013
name: scRNA
def: "Any one of several small cytoplasmic RNA moleculespresent in the cytoplasm and sometimes nucleus of a eukaryote." [http:www.ebi.ac.uk/embl/WebFeat/align/scRNA_s.html]
subset: SOFA
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000038
name: match_set
def: "A collection of match parts" [SO:ke]
subset: SOFA
is_a: SO:0000343 ! match

[Term]
id: SO:0000039
name: match_part
def: "A part of a match\, for example an hsp from blast isa match_part." [SO:ke]
subset: SOFA
is_a: SO:0000343 ! match
relationship: part_of SO:0000038 ! match_set

[Term]
id: SO:0000057
name: operator
def: "A regulatory element of an operon to which activators or repressors bind hereby effecting translation of genes in that operon." [SO:ma]
subset: SOFA
is_a: SO:0000752 ! gene_group_regulatory_region

[Term]
id: SO:0000101
name: transposable_element
def: "A transposon or insertion sequence. An element that can insert in a variety of DNA sequences." [http://www.sci.sdsu.edu/ ~ smaloy/Glossary/T.html]
subset: SOFA
is_a: SO:0000187 ! repeat_family

[Term]
id: SO:0000102
name: expressed_sequence_match
def: "A match to an EST or cDNA sequence." [SO:ke]
subset: SOFA
is_a: SO:0000347 ! nucleotide_match

[Term]
id: SO:0000103
name: clone_end
def: "The end of the clone insert." [SO:ke]
subset: SOFA
is_a: SO:0000699 ! junction
relationship: part_of SO:0000151 ! clone

[Term]
id: SO:0000104
name: polypeptide
def: "A sequence of amino acids linked by peptide bonds which may lack appreciable tertiary structure and may not be liable to irreversable denaturation." [SO:ma]
subset: SOFA
relationship: derives_from SO:0000316 ! CDS

[Term]
id: SO:0000109
name: sequence_variant
def: "A region of sequence where variation has been observed." [SO:ke]
subset: SOFA
synonym: "mutation" []
is_a: SO:0000110 ! located_sequence_feature

[Term]
id: SO:0000110
name: located_sequence_feature
def: "A biological feature that can be attributed to a region of biological sequence." [SO:ke]
subset: SOFA
is_a: SO:0000000 ! Sequence_Ontology

[Term]
id: SO:0000112
name: primer
def: "A short preexisting polynucleotide chain to which new deoxyribonucleotides can be added by DNA polymerase." [http://www.ornl.gov/TechResources/Human_Genome/publicat/primer2001/glossary.html]
subset: SOFA
is_a: SO:0000696 ! oligo

[Term]
id: SO:0000113
name: integrated_virus
def: "A viral sequence which has integrated into the host genome." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000114
name: methylated_C
def: "A methylated deoxy-cytosine." [SO:ke]
subset: SOFA
is_a: SO:0000306 ! methylated_base_feature

[Term]
id: SO:0000120
name: protein_coding_primary_transcript
def: "A primary transcript that\, at least in part\, encodes one or more proteins." [SO:ke]
comment: May contain introns
subset: SOFA
synonym: "pre-mRNA" []
is_a: SO:0000185 ! primary_transcript

[Term]
id: SO:0000139
name: ribosome_entry_site
def: "Region in mRNA where ribosome assembles." [SO:ke]
comment: gene\\\:<gene_id>
subset: SOFA
relationship: part_of SO:0000203 ! UTR

[Term]
id: SO:0000140
name: attenuator
def: "A sequence segment located between the promoter and a structural gene that causes partial termination of transcription." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
is_a: SO:0000752 ! gene_group_regulatory_region
is_a: SO:0005836 ! regulatory_region

[Term]
id: SO:0000141
name: terminator
def: "The sequence of DNA located either at the end of the transcript that causes RNA polymerase to terminate transcription." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
is_a: SO:0000752 ! gene_group_regulatory_region
is_a: SO:0005836 ! regulatory_region

[Term]
id: SO:0000143
name: assembly_component
def: "A region of sequence which may be used to manufacture a longer assembled\, sequence." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000147
name: exon
def: "A region of the genome that codes for portion of spliced messenger RNA (SO\:0000234); may contain 5'-untranslated region (SO\:0000204)\, all open reading frames (SO\:0000236) and 3'-untranslated region (SO\:0000205)." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
relationship: part_of SO:0000673 ! transcript

[Term]
id: SO:0000148
name: supercontig
def: "One or more contigs that have been ordered and oriented using end-read information. Contains gaps that are filled with N's." [SO:ls]
subset: SOFA
synonym: "scaffold" []
is_a: SO:0000353 ! assembly
relationship: part_of SO:0000719 ! ultracontig

[Term]
id: SO:0000149
name: contig
def: "A contiguous sequence derived from sequence assembly. Has no gaps\, but may contain N's from unvailable bases." [SO:ls]
subset: SOFA
is_a: SO:0000143 ! assembly_component
is_a: SO:0000353 ! assembly
relationship: part_of SO:0000148 ! supercontig

[Term]
id: SO:0000150
name: read
def: "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." [SO:rd]
subset: SOFA
is_a: SO:0000143 ! assembly_component
relationship: part_of SO:0000149 ! contig

[Term]
id: SO:0000151
name: clone
def: "A piece of DNA that has been inserted in a vector so that it can be propagated in E. coli or some other organism." [http://www.geospiza.com/community/support/glossary/]
subset: SOFA
is_a: SO:0000695 ! reagent

[Term]
id: SO:0000159
name: deletion
def: "The sequence that is deleted." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region
is_a: SO:0000109 ! sequence_variant

[Term]
id: SO:0000161
name: methylated_A
def: "A methylated adenine." [SO:ke]
subset: SOFA
is_a: SO:0000306 ! methylated_base_feature

[Term]
id: SO:0000162
name: splice_site
def: "The position where intron is excised." [SO:ke]
subset: SOFA
is_a: SO:0000699 ! junction
relationship: part_of SO:0000185 ! primary_transcript

[Term]
id: SO:0000163
name: splice_donor_site
def: "The junction between the 3 prime end of an exon and the following intron." [http://www.ucl.ac.uk/ ~ ucbhjow/b241/glossary.html]
subset: SOFA
synonym: "donor" []
synonym: "donor_splice_site" []
is_a: SO:0000162 ! splice_site

[Term]
id: SO:0000164
name: splice_acceptor_site
def: "The junction between the 3 prime end of an intron and the following exon." [http://www.ucl.ac.uk/ ~ ucbhjow/b241/glossary.html]
subset: SOFA
synonym: "acceptor" []
synonym: "acceptor_splice_site" []
is_a: SO:0000162 ! splice_site

[Term]
id: SO:0000165
name: enhancer
def: "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." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
is_a: SO:0005836 ! regulatory_region

[Term]
id: SO:0000167
name: promoter
def: "The region on a DNA molecule involved in RNA polymerase binding to initiate transcription." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
is_a: SO:0005836 ! regulatory_region

[Term]
id: SO:0000177
name: cross_genome_match
def: "A nucleotide match against a sequence from another organism." [SO:ma]
subset: SOFA
is_a: SO:0000347 ! nucleotide_match

[Term]
id: SO:0000178
name: operon
def: "A group of contiguous genes transcribed as a single (polycistronic) mRNA from a single regulatory region." [SO:ma]
subset: SOFA
is_a: SO:0005855 ! gene_group

[Term]
id: SO:0000179
name: clone_start
def: "The start of the clone insert." [SO:ke]
subset: SOFA
is_a: SO:0000699 ! junction
relationship: part_of SO:0000151 ! clone

[Term]
id: SO:0000181
name: translated_nucleotide_match
def: "A match against a translated sequence." [SO:ke]
subset: SOFA
is_a: SO:0000347 ! nucleotide_match

[Term]
id: SO:0000183
name: non_transcribed_region
def: "A region of the gene which is not transcribed." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region
relationship: part_of SO:0000704 ! gene

[Term]
id: SO:0000185
name: primary_transcript
def: "The primary (initial\, unprocessed) transcript; includes five_prime_clip (SO\:0000555)\, five_prime_untranslated_region (SO\:0000204)\, open reading frames (SO\:0000236)\, introns (SO\:0000188) and three_prime_ untranslated_region (three_prime_UTR)\, and three_prime_clip (SO\:0000557)." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
synonym: "precursor_RNA" []
is_a: SO:0000673 ! transcript

[Term]
id: SO:0000187
name: repeat_family
def: "A group of characterized repeat sequences." [SO:ke]
subset: SOFA
is_a: SO:0000657 ! repeat_region

[Term]
id: SO:0000188
name: intron
def: "A segment of DNA that is transcribed\, but removed from within the transcript by splicing together the sequences (exons) on either side of it." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
relationship: part_of SO:0000185 ! primary_transcript

[Term]
id: SO:0000193
name: RFLP_fragment
def: "A polymorphism detectable by the size differences in DNA fragments generated by a restriction enzyme." [PMID:6247908]
subset: SOFA
synonym: "restriction_fragment_length_polymorphism" []
is_a: SO:0000412 ! restriction_fragment

[Term]
id: SO:0000203
name: UTR
def: "Messenger RNA sequences that are untranslated and lie five prime and three prime to sequences which are translated." [SO:ke]
subset: SOFA
synonym: "untranslated_region" []
relationship: part_of SO:0000234 ! mRNA

[Term]
id: SO:0000204
name: five_prime_UTR
def: "A region at the 5' end of a mature transcript (preceding the initiation codon) that is not translated into a protein." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
synonym: "five_prime_untranslated_region" []
is_a: SO:0000203 ! UTR

[Term]
id: SO:0000205
name: three_prime_UTR
def: "A region at the 3' end of a mature transcript (following the stop codon) that is not translated into a protein." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
synonym: "three_prime_untranslated_region" []
is_a: SO:0000203 ! UTR

[Term]
id: SO:0000233
name: processed_transcript
def: "A transcript which has undergone processing to remove parts such as introns and transcribed_spacer_regions." [SO:ke]
comment: A processed transcript cannot contain introns.
subset: SOFA
is_a: SO:0000673 ! transcript
relationship: derives_from SO:0000185 ! primary_transcript

[Term]
id: SO:0000234
name: mRNA
def: "Messenger RNA is the intermediate molecule between DNA and protein. It  includes UTR and coding sequences. It does not contain introns." [SO:ma]
comment: mRNA does not contain introns as it is a processd_transcript.\nThe equivalent kind of primary_transcript is protein_coding_primary_transcript (SO\:0000120) which may contain introns.
subset: SOFA
synonym: "messenger_RNA" []
is_a: SO:0000233 ! processed_transcript

[Term]
id: SO:0000235
name: TF_binding_site
def: "A region of a molecule that binds to a transcription factor." [SO:ke]
subset: SOFA
synonym: "transcription_factor_binding_site" []
is_a: SO:0005836 ! regulatory_region

[Term]
id: SO:0000236
name: ORF
def: "The inframe 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" [SO:ma, SO:rb]
comment: The definition was modified by Rama. This terms now basically is the same as a CDS. This must be revised.
subset: SOFA
synonym: "open_reading_frame" []
is_a: SO:0000717 ! reading_frame

[Term]
id: SO:0000239
name: flanking_region
def: "The DNA sequences extending on either side of a specific locus." [http://biotech.icmb.utexas.edu/search/dict-search.mhtml]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000252
name: rRNA
def: "RNA that comprises part of a ribosome\, and that can provide both structural scaffolding and catalytic activity." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types, ISBN:0198506732]
subset: SOFA
synonym: "ribsomal_RNA" []
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000253
name: tRNA
def: "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. tRNAs 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). tRNAs 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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00005, ISBN:0198506732]
subset: SOFA
synonym: "transfer_RNA" []
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000274
name: snRNA
def: "Small non-coding RNA in the nucleoplasm. A small nuclear RNA molecule involved in pre-mRNA splicing and processing" [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types, ems:WB, PMID:11733745]
subset: SOFA
synonym: "small_nuclear_RNA" []
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000275
name: snoRNA
def: "Small nucleolar RNAs (snoRNAs) are involved in the processing and modification of rRNA in the nucleolus. There are two main classes of snoRNAs\: the box C/D class\, and the box H/ACA class. U3 snoRNA is a member of the box C/D class. Indeed\, the box C/D element is a subset of the six short sequence elements found in all U3 snoRNAs\, namely boxes A\, A'\, B\, C\, C'\, and D. The U3 snoRNA secondary structure is characterised by a small 5' domain (with boxes A and A')\, and a larger 3' domain (with boxes B\, C\, C'\, and D)\, the two domains being linked by a single-stranded hinge. Boxes B and C form the B/C motif\, which appears to be exclusive to U3 snoRNAs\, and boxes C' and D form the C'/D motif. The latter is functionally similar to the C/D motifs found in other snoRNAs. The 5' domain and the hinge region act as a pre-rRNA-binding domain. The 3' domain has conserved protein-binding sites. Both the box B/C and box C'/D motifs are sufficient for nuclear retention of U3 snoRNA. The box C'/D motif is also necessary for nucleolar localization\, stability and hypermethylation of U3 snoRNA. Both box B/C and C'/D motifs are involved in specific protein interactions and are necessary for the rRNA processing functions of U3 snoRNA." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00012]
subset: SOFA
synonym: "small_nucleolar_RNA" []
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000276
name: miRNA
def: "Small\, ~22-nt\, RNA molecule that is the endogenous transcript of a miRNA gene. miRNAs are produced from precursor molecules (SO\:0000647) that can form local hairpin strcutures\, which ordinarily are processed (via the Dicer pathway) such that a single miRNA molecule accumulates from one arm of a hairpinprecursor molecule. miRNAs may trigger the cleavage of their target molecules oract as translational repressors." [PMID:12592000]
subset: SOFA
synonym: "micro_RNA" []
is_a: SO:0000370 ! small_regulatory_ncRNA

[Term]
id: SO:0000289
name: microsatellite
def: "A very short unit sequence of DNA (2 to 4 bp) that is repeated multiple times in tandem." [http://www.informatics.jax.org/silver/glossary.shtml]
subset: SOFA
is_a: SO:0000705 ! tandem_repeat

[Term]
id: SO:0000294
name: inverted_repeat
def: "The sequence is complementarily repeated on the opposite strand. Example\: GCTGA-----TCAGC." [SO:ke]
subset: SOFA
is_a: SO:0000657 ! repeat_region

[Term]
id: SO:0000296
name: origin_of_replication
def: "The origin of replication; starting site for duplication of a nucleic acid molecule to give two identical copies." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000303
name: clip
def: "Part of the primary transcript that is clipped off during processing." [SO:ke]
subset: SOFA
relationship: part_of SO:0000185 ! primary_transcript

[Term]
id: SO:0000305
name: modified_base_site
def: "A modified nucleotide\, i.e. a nucleotide other than A\, T\, C. G or (in RNA) U." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
comment: modified base\\\:<modified_base>
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000306
name: methylated_base_feature
def: "A nucleotide modified by methylation." [SO:ke]
subset: SOFA
is_a: SO:0000305 ! modified_base_site

[Term]
id: SO:0000307
name: CpG_island
def: "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." [SO:rd]
subset: SOFA
synonym: "CG_island" []
is_a: SO:0000001 ! region

[Term]
id: SO:0000314
name: direct_repeat
def: "A repeat where the same sequence is repeated in the same direction. Example\: GCTGA-----GCTGA." [SO:ke]
subset: SOFA
is_a: SO:0000657 ! repeat_region

[Term]
id: SO:0000315
name: transcription_start_site
def: "The site where transcription begins." [SO:ke]
subset: SOFA
synonym: "TSS" []
is_a: SO:0000699 ! junction
relationship: part_of SO:0000185 ! primary_transcript

[Term]
id: SO:0000316
name: CDS
def: "A contiguous sequence which begins with\, and includes\, a start codon and ends with\, and includes\, a stop codon." [SO:ma]
subset: SOFA
synonym: "coding_sequence" []
relationship: part_of SO:0000234 ! mRNA

[Term]
id: SO:0000324
name: tag
def: "A nucleotide sequence that may be used to identify a larger sequence." [SO:ke]
subset: SOFA
is_a: SO:0000695 ! reagent

[Term]
id: SO:0000326
name: SAGE_tag
def: "A short diagnostic sequence tag\, serial analysis of gene expression (SAGE)\, that allows the quantitative and simultaneous analysis of a large number of transcripts." [http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=7570003&dopt=Abstract]
subset: SOFA
is_a: SO:0000324 ! tag

[Term]
id: SO:0000331
name: STS
def: "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." [http://www.biospace.com]
subset: SOFA
synonym: "sequence_tag_site" []
is_a: SO:0000324 ! tag

[Term]
id: SO:0000333
name: exon_junction
def: "The boundary between two exons in a processed transcript." [SO:ke]
subset: SOFA
is_a: SO:0000699 ! junction
relationship: part_of SO:0000233 ! processed_transcript

[Term]
id: SO:0000336
name: pseudogene
def: "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)." [http://www.ucl.ac.uk/ ~ ucbhjow/b241/glossary.html]
subset: SOFA
is_a: SO:0000462 ! pseudogenic_region
relationship: non_functional_homolog_of SO:0000704 ! gene

[Term]
id: SO:0000337
name: RNAi_reagent
def: "A double stranded RNA duplex\, at least 20bp long\, used experimentally to inhibit gene function by RNA interference." [SO:rd]
subset: SOFA
is_a: SO:0000695 ! reagent
is_a: SO:0000696 ! oligo

[Term]
id: SO:0000340
name: chromosome
def: "Structural unit composed of long DNA molecule." [http://biotech.icmb.utexas.edu/search/dict-search.mhtml]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000343
name: match
def: "A region of sequence\, aligned to another sequence with some statistical significance\, using an algorithm such as BLAST or SIM4." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000344
name: splice_enhancer
def: "Region of a transcript that regulates splicing." [SO:ke]
subset: SOFA
is_a: SO:0005836 ! regulatory_region

[Term]
id: SO:0000345
name: EST
def: "Expressed Sequence Tag\: The sequence of a single sequencing read from a cDNA clone or PCR product; typically a few hundred base pairs long." [http://genomics.phrma.org/lexicon/e.html]
subset: SOFA
synonym: "expressed_sequence_tag" []
is_a: SO:0000695 ! reagent
relationship: derives_from SO:0000234 ! mRNA

[Term]
id: SO:0000347
name: nucleotide_match
def: "A match against a nucleotide sequence." [SO:ke]
subset: SOFA
is_a: SO:0000343 ! match

[Term]
id: SO:0000349
name: protein_match
def: "A match against a protein sequence." [SO:ke]
subset: SOFA
is_a: SO:0000343 ! match

[Term]
id: SO:0000353
name: assembly
def: "A sequence of nucleotides that has been algorithmically derived from an alignment of two or more different sequences." [SO:ma]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000360
name: codon
def: "A set of (usually) three nucleotide bases in a DNA or RNA sequence\, which together signify a unique amino acid or the termination of translation." [http://genomics.phrma.org/lexicon/c.html]
subset: SOFA
relationship: part_of SO:0000234 ! mRNA

[Term]
id: SO:0000366
name: insertion_site
def: "The junction where an insertion occurred." [SO:ke]
subset: SOFA
is_a: SO:0000109 ! sequence_variant
is_a: SO:0000699 ! junction

[Term]
id: SO:0000368
name: transposable_element_insertion_site
def: "The junction in a genome where a transposable_element has inserted." [SO:ke]
subset: SOFA
is_a: SO:0000366 ! insertion_site

[Term]
id: SO:0000370
name: small_regulatory_ncRNA
def: "A non-coding RNA\, usually with a specific secondary structure\, that acts to regulate gene expression." [SO:ma]
subset: SOFA
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000372
name: enzymatic_RNA
def: "A non-coding RNA\, usually with a specific secondary structure\, that acts to regulate gene expression." [SO:ma]
subset: SOFA
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000374
name: ribozyme
def: "An RNA with catalytic activity." [SO:ma]
subset: SOFA
is_a: SO:0000372 ! enzymatic_RNA

[Term]
id: SO:0000375
name: rRNA_5.8S
def: "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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00002]
subset: SOFA
synonym: "5.8S_rRNA" []
is_a: SO:0000252 ! rRNA

[Term]
id: SO:0000380
name: hammerhead_ribozyme
def: "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." [http:rnaworld.bio.ukans.edu/class/RNA/RNA00/RNA_World_3.html]
subset: SOFA
is_a: SO:0000374 ! ribozyme

[Term]
id: SO:0000385
name: RNase_MRP_RNA
def: "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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00030]
subset: SOFA
is_a: SO:0000372 ! enzymatic_RNA

[Term]
id: SO:0000386
name: RNase_P_RNA
def: "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 characterised 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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00010]
subset: SOFA
is_a: SO:0000374 ! ribozyme

[Term]
id: SO:0000390
name: telomerase_RNA
def: "The RNA component of telomerase\, a reverse transcriptase that synthesises telomeric DNA." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00025]
subset: SOFA
is_a: SO:0000372 ! enzymatic_RNA

[Term]
id: SO:0000391
name: U1_snRNA
def: "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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00003]
subset: SOFA
is_a: SO:0000274 ! snRNA

[Term]
id: SO:0000392
name: U2_snRNA
def: "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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00004]
subset: SOFA
is_a: SO:0000274 ! snRNA

[Term]
id: SO:0000393
name: U4_snRNA
def: "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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00015]
subset: SOFA
is_a: SO:0000274 ! snRNA

[Term]
id: SO:0000394
name: U4atac_snRNA
def: "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)." [PMID:=12409455]
subset: SOFA
is_a: SO:0000274 ! snRNA

[Term]
id: SO:0000395
name: U5_snRNA
def: "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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00020]
subset: SOFA
is_a: SO:0000274 ! snRNA

[Term]
id: SO:0000396
name: U6_snRNA
def: "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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00015]
subset: SOFA
is_a: SO:0000274 ! snRNA

[Term]
id: SO:0000397
name: U6atac_snRNA
def: "U6atac_snRNA -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)." [http:http\://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=retrieve&db=pubmed&list_uids=1 2409455&dopt=Abstract]
subset: SOFA
is_a: SO:0000274 ! snRNA

[Term]
id: SO:0000398
name: U11_snRNA
def: "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." [PMID:9622129]
subset: SOFA
is_a: SO:0000274 ! snRNA

[Term]
id: SO:0000399
name: U12_snRNA
def: "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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00007]
subset: SOFA
is_a: SO:0000274 ! snRNA

[Term]
id: SO:0000403
name: U14_snRNA
def: "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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00016]
subset: SOFA
is_a: SO:0000274 ! snRNA

[Term]
id: SO:0000404
name: vault_RNA
def: "A family of RNAs are found as part of the enigmatic vault ribonuceoprotein 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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00006]
subset: SOFA
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000405
name: Y_RNA
def: "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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00019]
subset: SOFA
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000407
name: rRNA_18S
def: "18S_rRNA -A large polynucleotide which functions as a part of the small subunit of the ribosome" [SO:ke]
subset: SOFA
synonym: "16S_rRNA" []
is_a: SO:0000252 ! rRNA

[Term]
id: SO:0000409
name: binding_site
def: "A region on the surface of a molecule that may interact with another molecule." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000412
name: restriction_fragment
def: "Any of the individual polynucleotide sequences produced by digestion of DNA with a restriction endonuclease." [http://www.agron.missouri.edu/cgi-bin/sybgw_mdb/mdb3/Term/119]
subset: SOFA
is_a: SO:0000695 ! reagent

[Term]
id: SO:0000413
name: sequence_difference
def: "A region where the sequences differs from that of a specified sequence." [SO:ke]
subset: SOFA
is_a: SO:0000700 ! remark

[Term]
id: SO:0000418
name: signal_peptide
def: "The sequence for an N-terminal domain of a secreted protein; this domain is involved in attaching nascent polypeptide to the membrane leader sequence." [http:www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html]
subset: SOFA
synonym: "signal peptide coding sequence" []
relationship: part_of SO:0000104 ! polypeptide

[Term]
id: SO:0000419
name: mature_peptide
def: "The coding sequence for the mature or final peptide or protein product following post-translational modification." [http:www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html]
subset: SOFA
relationship: part_of SO:0000104 ! polypeptide

[Term]
id: SO:0000436
name: ARS
def: "A sequence that can autonomously replicate\, as a plasmid\, when transformed into a bacterial host." [SO:ma]
subset: SOFA
synonym: "autonomously_replicating_sequence" []
is_a: SO:0000001 ! region

[Term]
id: SO:0000454
name: rasiRNA
def: "A small\, 17-28-nt\, small interfering RNA derived from transcripts ofrepetitive elements." [http://www.developmentalcell.com/content/article/abstract?uid=PIIS1534580703002284]
subset: SOFA
synonym: "repeat associated small interfering RNA" []
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000462
name: pseudogenic_region
def: "A non-functional descendent of a functional entitity." [SO:cjm]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000464
name: decayed_exon
def: "A non-functional descendent of an exon." [SO:ke]
subset: SOFA
is_a: SO:0000462 ! pseudogenic_region
relationship: non_functional_homolog_of SO:0000147 ! exon

[Term]
id: SO:0000468
name: golden_path_fragment
def: "One of the pieces of sequence that make up a golden path." [SO:rd]
subset: SOFA
is_a: SO:0000143 ! assembly_component
relationship: part_of SO:0000688 ! golden_path

[Term]
id: SO:0000472
name: tiling_path
def: "A set of regions which overlap with minimal polymorphism to form a linear sequence." [CJM:SO]
subset: SOFA
is_a: SO:0000353 ! assembly

[Term]
id: SO:0000474
name: tiling_path_fragment
def: "A piece of sequence that makes up a tiling_path.SO\:0000472." [SO:ke]
subset: SOFA
is_a: SO:0000143 ! assembly_component
relationship: part_of SO:0000472 ! tiling_path

[Term]
id: SO:0000483
name: nc_primary_transcript
def: "A primary transcript that is never translated into a protein." [SO:ke]
subset: SOFA
synonym: "noncoding_primary_transcript" []
is_a: SO:0000185 ! primary_transcript

[Term]
id: SO:0000499
name: virtual_sequence
def: "A continous piece of sequence similar to the 'virtual contig' concept of ensembl." [SO:ke]
subset: SOFA
is_a: SO:0000353 ! assembly

[Term]
id: SO:0000507
name: pseudogenic_exon
def: "The exon of a pseudogene." [SO:rb]
comment: Term added in response to request at SO meeting in August 2004 to allow the detailed annotation of pseudogenes.
subset: SOFA
is_a: SO:0000462 ! pseudogenic_region
relationship: non_functional_homolog_of SO:0000147 ! exon
relationship: part_of SO:0000516 ! pseudogenic_transcript

[Term]
id: SO:0000516
name: pseudogenic_transcript
def: "A transcript of a pseudogene" [SO:rb]
comment: Term added at the SO meeting in August 2004 to allow more detailed annotation of pseudogenes.
subset: SOFA
is_a: SO:0000462 ! pseudogenic_region
relationship: non_functional_homolog_of SO:0000673 ! transcript
relationship: part_of SO:0000336 ! pseudogene

[Term]
id: SO:0000551
name: polyA_signal_sequence
def: "The recognition sequence necessary for endonuclease cleavage of an RNA transcript that is followed by polyadenylation; consensus=AATAAA." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
is_a: SO:0005836 ! regulatory_region

[Term]
id: SO:0000553
name: polyA_site
def: "The site on an RNA transcript to which will be added adenine residues by post-transcriptional polyadenylation." [http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
is_a: SO:0000699 ! junction
relationship: part_of SO:0000233 ! processed_transcript

[Term]
id: SO:0000577
name: centromere
def: "A region of chromosome where the spindle fibers attach during mitosis and meiosis." [SO:ke]
subset: SOFA
is_a: SO:0000628 ! chromosomal_structural_element

[Term]
id: SO:0000581
name: cap
def: "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." [http://seqcore.brcf.med.umich.edu/doc/educ/dnapr/mbglossary/mbgloss.html]
subset: SOFA
relationship: adjacent_to SO:0000234 ! mRNA

[Term]
id: SO:0000587
name: group_I_intron
def: "Group I catalytic introns are large self-splicing ribozymes. They catalyse 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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00028]
subset: SOFA
is_a: SO:0000188 ! intron

[Term]
id: SO:0000588
name: autocatalytically_spliced_intron
def: "A self spliced intron." [SO:ke]
subset: SOFA
is_a: SO:0000188 ! intron
is_a: SO:0000374 ! ribozyme

[Term]
id: SO:0000590
name: SRP_RNA
def: "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." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00017]
subset: SOFA
synonym: "7S RNA" []
synonym: "signal_recognition_particle_RNA" []
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000602
name: guide_RNA
def: "A short 3'-uridylated RNA that can form a perfect duplex (except for the oligoU tail (SO\:0000609)) with a stretch of mature edited mRNA." [http://www.rna.ucla.edu/index.html]
subset: SOFA
synonym: "gRNA" []
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000603
name: group_II_intron
def: "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." [http://www.sanger.ac.uk/Software/Rfam/browse/index.shtml]
subset: SOFA
is_a: SO:0000188 ! intron

[Term]
id: SO:0000605
name: intergenic_region
def: "The region between two known genes." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000610
name: polyA_sequence
def: "Sequence of about 100 nucleotides of A added to the 3' end of most eukaryotic mRNAs." [SO:ke]
subset: SOFA
relationship: adjacent_to SO:0000234 ! mRNA

[Term]
id: SO:0000611
name: branch_site
def: "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." [SO:ke]
subset: SOFA
synonym: "branch_point" []
relationship: part_of SO:0000662 ! spliceosomal_intron

[Term]
id: SO:0000612
name: polypyrimidine_tract
def: "The polypyrimidine tract is one of the cis-acting sequence elements directing intron removal in pre-mRNA splicing." [http://nar.oupjournals.org/cgi/content/full/25/4/888]
subset: SOFA
relationship: part_of SO:0000662 ! spliceosomal_intron

[Term]
id: SO:0000616
name: transcription_end_site
def: "The site where transcription ends." [SO:ke]
subset: SOFA
is_a: SO:0000699 ! junction
relationship: part_of SO:0000185 ! primary_transcript

[Term]
id: SO:0000624
name: telomere
def: "A specific structure at the end of a linear chromosome\, required for the integrity and maintenence of the end\," [SO:ma]
subset: SOFA
is_a: SO:0000628 ! chromosomal_structural_element

[Term]
id: SO:0000625
name: silencer
def: "Combination of short DNA sequence elements which suppress the transcription of an adjacent gene or genes." [http://www.brunel.ac.uk/depts/bio/project/old_hmg/gloss3.htm#s]
subset: SOFA
is_a: SO:0005836 ! regulatory_region

[Term]
id: SO:0000627
name: insulator
def: "Nucleic acid regulatory sequences that limit or oppose the action of ENHANCER ELEMENTS and define the boundary between differentially regulated gene loci." [http:http\://medical.webends.com/kw/Insulator%20Elements]
subset: SOFA
synonym: "insulator_element" []
is_a: SO:0005836 ! regulatory_region

[Term]
id: SO:0000628
name: chromosomal_structural_element
def: "A part of a chromosome that has structural function. " [SO:ke]
subset: SOFA
relationship: part_of SO:0000340 ! chromosome

[Term]
id: SO:0000643
name: minisatellite
def: "A repetitive sequence spanning 500 to 20\,000 base pairs (a repeat unit is 5 - 30 base pairs)." [http://www.rerf.or.jp/eigo/glossary/minisate.htm]
subset: SOFA
is_a: SO:0000705 ! tandem_repeat

[Term]
id: SO:0000644
name: antisense_RNA
def: "Antisense RNA is RNA that is transcribed from the coding\, rather than the template\, strand of DNA. It is therefore complementary to mRNA." [SO:ke]
subset: SOFA
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000645
name: antisense_primary_transcript
def: "The reverse complement of the primary transcript." [SO:ke]
subset: SOFA
is_a: SO:0000185 ! primary_transcript

[Term]
id: SO:0000646
name: siRNA
def: "Small RNA molecule that is the product of a longerexogenous or endogenous dsRNA\, which is either a bimolecular duplexe or very longhairpin\, processed (via the Dicer pathway) such that numerous siRNAs accumulatefrom both strands of the dsRNA. sRNAs trigger the cleavage of their target molecules." [PMID:12592000]
subset: SOFA
synonym: "small_interfering_RNA" []
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000649
name: stRNA
def: "Non-coding RNAs of about 21 nucleotides in length that regulate temporal development; first discovered in C. elegans." [PMID:11081512]
subset: SOFA
synonym: "small_temporal_RNA" []
is_a: SO:0000655 ! ncRNA

[Term]
id: SO:0000652
name: rRNA_5S
def: "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 stabilises 5S rRNA until it is required for transcription." [http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00001]
subset: SOFA
is_a: SO:0000252 ! rRNA

[Term]
id: SO:0000653
name: rRNA_28S
def: "A component of the large ribosomal subunit." [SO:ke]
subset: SOFA
synonym: "23S_rRNA" []
synonym: "28S_rRNA" []
is_a: SO:0000252 ! rRNA

[Term]
id: SO:0000655
name: ncRNA
def: "An mRNA sequence that does not encode for a protein rather the RNA molecule is the gene product." [SO:ke]
comment: 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.
subset: SOFA
synonym: "noncoding_RNA" []
is_a: SO:0000233 ! processed_transcript

[Term]
id: SO:0000657
name: repeat_region
def: "A region of sequence containing one or more repeat units." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000658
name: dispersed_repeat
def: "A repeat that is located at dispersed sites in the genome." [SO:ke]
subset: SOFA
synonym: "interspersed_repeat" []
is_a: SO:0000657 ! repeat_region

[Term]
id: SO:0000662
name: spliceosomal_intron
def: "An intron which is spliced by the spliceosome." [SO:ke]
subset: SOFA
is_a: SO:0000188 ! intron

[Term]
id: SO:0000667
name: insertion
def: "A region of sequence identified as having been inserted." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region
is_a: SO:0000109 ! sequence_variant

[Term]
id: SO:0000668
name: EST_match
def: "A match against an EST sequence." [SO:ke]
subset: SOFA
is_a: SO:0000102 ! expressed_sequence_match

[Term]
id: SO:0000673
name: transcript
def: "An RNA synthesized on a DNA or RNA template by an RNA polymerase." [SO:ma]
subset: SOFA
relationship: member_of SO:0000704 ! gene

[Term]
id: SO:0000684
name: nuclease_sensitive_site
def: "A region of nucleotide sequence targeting by a nuclease enzyme." [SO:ma]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000687
name: deletion_junction
def: "The space between two bases in a sequence which marks the position where a deletion has occured." [SO:ke]
subset: SOFA
is_a: SO:0000109 ! sequence_variant
is_a: SO:0000699 ! junction

[Term]
id: SO:0000688
name: golden_path
def: "A set of subregions selected from sequence contigs which when concatenated form a nonredundant linear sequence." [SO:ls]
subset: SOFA
is_a: SO:0000353 ! assembly

[Term]
id: SO:0000689
name: cDNA_match
def: "A match against cDNA sequence." [SO:ke]
subset: SOFA
is_a: SO:0000102 ! expressed_sequence_match

[Term]
id: SO:0000694
name: SNP
def: "SNPs are single base pair positions in genomic DNA at which different sequence alternatives (alleles) exist in normal individuals in some population(s)\, wherein the least frequent allele has an abundance of 1% or greater." [http://www.cgr.ki.se/cgb/groups/brookes/Articles/essence_of_snps_article.pdf]
subset: SOFA
synonym: "single_nucleotide_polymorphism" []
is_a: SO:1000008 ! point_mutation

[Term]
id: SO:0000695
name: reagent
def: "A sequence used in experiment." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000696
name: oligo
def: "A short oligonucleotide sequence\, of length on the order of 10's of bases; either single or double stranded." [SO:ma]
subset: SOFA
synonym: "oligonucleotide" []
is_a: SO:0000695 ! reagent

[Term]
id: SO:0000699
name: junction
def: "A junction refers to an interbase location of zero in a sequence." [SO:ke]
subset: SOFA
synonym: "boundary" []
is_a: SO:0000110 ! located_sequence_feature

[Term]
id: SO:0000700
name: remark
def: "A comment about the sequence." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000701
name: possible_base_call_error
def: "A region of sequence where the validity of the base calling is questionable." [SO:ke]
subset: SOFA
is_a: SO:0000413 ! sequence_difference

[Term]
id: SO:0000702
name: possible_assembly_error
def: "A region of sequence where there may have been an error in the assembly." [SO:ke]
subset: SOFA
is_a: SO:0000413 ! sequence_difference

[Term]
id: SO:0000703
name: experimental_result_region
def: "A region of sequence implicated in an experimental result." [SO:ke]
subset: SOFA
is_a: SO:0000700 ! remark

[Term]
id: SO:0000704
name: gene
def: "A locatable region of genomic sequence\, corresponding to a unit of inheritance\, which is associated with regulatory regions\, transcribed regions and/or other functional sequence regions" [SO:rd]
subset: SOFA
is_a: SO:0000001 ! region
relationship: member_of SO:0005855 ! gene_group

[Term]
id: SO:0000705
name: tandem_repeat
def: "Two or more adjacent copies of a DNA sequence." [http://www.sci.sdsu.edu/ ~ smaloy/Glossary/T.html]
subset: SOFA
is_a: SO:0000657 ! repeat_region

[Term]
id: SO:0000706
name: trans_splice_acceptor_site
def: "The process that produces mature transcripts by combining exons of independent pre-mRNA molecules. The acceptor site lies on the 3' of these molecules." [SO:ke]
subset: SOFA
is_a: SO:0000164 ! splice_acceptor_site

[Term]
id: SO:0000714
name: nucleotide_motif
def: "A region of nucleotide sequence corresponding to a known motif." [SO:ke]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000717
name: reading_frame
def: "A nucleic acid sequence that when read as sequential triplets\, has the potential of encoding a sequential string of amino acids. It does not contain the start or stop codon." [SO:rb]
comment: This term was added after a request by SGD.\nAgust 2004. Modified after SO meeting in Cambridge to not include start or stop.
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:0000719
name: ultracontig
def: "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." [FB:WG]
subset: SOFA
is_a: SO:0000353 ! assembly

[Term]
id: SO:0000724
name: origin_of_transfer
def: "A region of a DNA molecule whre transfer is initiated during the process of conjugation or mobilization." [http:http\://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
subset: SOFA
synonym: "oriT" []
is_a: SO:0000001 ! region

[Term]
id: SO:0000725
name: transit_peptide
def: "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." [http:http\://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types]
comment: Added to bring SO inline with the embl ddbj genbank feature table.
subset: SOFA
relationship: part_of SO:0000104 ! polypeptide

[Term]
id: SO:0000730
name: gap
def: "A gap in the sequence of known length. THe unkown bases are filled in with N's." [SO:ke]
subset: SOFA
is_a: SO:0000699 ! junction
relationship: part_of SO:0000353 ! assembly

[Term]
id: SO:0000752
name: gene_group_regulatory_region
def: "A kind of regulatory region that regulates a gene_group such as an operon\, rather than an individual gene. " [SO:ke]
comment: This term was added so that gene_groups may have their own collection of regulators. It was necessary because gene groups are regulated by different kinds of regulatory regions than single genes.
is_a: SO:0005836 ! regulatory_region
relationship: member_of SO:0005855 ! gene_group

[Term]
id: SO:0005836
name: regulatory_region
def: "A DNA sequence that controls the expression of a gene." [http://www.genpromag.com/scripts/glossary.asp?LETTER=R]
subset: SOFA
is_a: SO:0000001 ! region
relationship: member_of SO:0000704 ! gene

[Term]
id: SO:0005855
name: gene_group
def: "A collection of related genes." [SO:ma]
subset: SOFA
is_a: SO:0000001 ! region

[Term]
id: SO:1000002
name: substitution
def: "Any change in genomic DNA caused by a single event." [http://www.ebi.ac.uk/mutations/recommendations/mutevent.html]
subset: SOFA
is_a: SO:0000001 ! region
is_a: SO:0000109 ! sequence_variant

[Term]
id: SO:1000005
name: complex_substitution
def: "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." [http://www.ebi.ac.uk/mutations/recommendations/mutevent.html]
subset: SOFA
is_a: SO:1000002 ! substitution

[Term]
id: SO:1000008
name: point_mutation
def: "A mutation event where a single DNA nucleotide changes into another nucleotide." [http://www.ebi.ac.uk/mutations/recommendations/mutevent.html]
subset: SOFA
is_a: SO:1000002 ! substitution

[Term]
id: SO:1000036
name: inversion
def: "A continuous nucleotide sequence is inverted in the same position." [http://www.ebi.ac.uk/mutations/recommendations/mutevent.html]
subset: SOFA
is_a: SO:0000001 ! region
is_a: SO:0000109 ! sequence_variant

[Term]
id: SO:1001284
name: regulon
def: "A group of genes\, whether linked as a cluster or not\, that respond to a common regulatory signal." [ISBN:0198506732]
subset: SOFA
is_a: SO:0005855 ! gene_group

[Term]
id: SO:2000061
name: databank_entry
def: "The sequence referred to by an entry in a databank such as Genbank or SwissProt." [SO:ke]
subset: SOFA
synonym: "accession" []
is_a: SO:0000695 ! reagent

[Typedef]
id: adjacent_to
name: adjacent_to
def: "A geometric operator\, specified in Egenhofer 1989. Two features meet if they share a junction on the sequence." [SO:ke]
comment: This relationship was originally called 'meets' but changed to adjacent_to to be in alignment with the OBO relationship ontology.
subset: SOFA
domain: SO:0000110
range: SO:0000110
is_symmetric: true

[Typedef]
id: derives_from
name: derives_from
subset: SOFA
is_transitive: true

[Typedef]
id: homologous_to
name: homologous_to
is_symmetric: true

[Typedef]
id: member_of
name: member_of
comment: A subtype of part_of.\ninverse is collection_of.\nWinston\, M\, Chaffin\, R\, Herrmann\: A taxonomy of part-whole relations. Cognitive Science 1987\, 11\:417-444.
subset: SOFA
is_a: part_of ! part_of

[Typedef]
id: non_functional_homolog_of
name: non_functional_homolog_of
def: "A relationship between a pseudogenic feature and its functional ancestor." [SO:ke]

[Typedef]
id: orthologous_to
name: orthologous_to
is_symmetric: true

[Typedef]
id: paralogous_to
name: paralogous_to
is_symmetric: true

[Typedef]
id: part_of
name: part_of
subset: SOFA
is_transitive: true

[Typedef]
id: similar_to
name: similar_to
is_symmetric: true