# SOFA ontology terms acceptable as feature types in GFF3
# Automatically extracted from sofa.definition 8 June 2006

# SO:ke
# A biological feature that can be attributed to a region of biological
# sequence.

sequence_feature SO:0000110

# SO:ke
# The reverse complement of the primary transcript.

antisense_primary_transcript SO:0000645

# SO:ke
# Antisense RNA is RNA that is transcribed from the coding, rather than
# the template, strand of DNA. It is therefore complementary to mRNA.

antisense_RNA SO:0000644

# SO:ma
# A sequence that can autonomously replicate, as a plasmid, when
# transformed into a bacterial host.

ARS SO:0000436

# SO:ma
# A sequence of nucleotides that has been algorithmically derived from an
# alignment of two or more different sequences.

assembly SO:0000353

# SO:ke
# A region of sequence which may be used to manufacture a longer
# assembled, sequence.

assembly_component SO:0000143

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# A sequence segment located between the promoter and a structural gene
# that causes partial termination of transcription.

attenuator SO:0000140

# SO:ke
# A self spliced intron.

autocatalytically_spliced_intron SO:0000588

# SO:ke
# A region on the surface of a molecule that may interact with another
# molecule.

binding_site SO:0000409

# SO:ke
# 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.

branch_site SO:0000611

# Genomic DNA of immunoglobulin/T-cell receptor gene including C-region
# (and introns if present) with 5' UTR (SO:0000204) and 3' UTR
# (SO:0000205). http://imgt.cines.fr/ligmdb/LIGMlect?query=7

C_gene SO:0000478

# http://seqcore.brcf.med.umich.edu/doc/educ/dnapr/mbglossary/mbgloss.html
# 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.

cap SO:0000581

# SO:ke
# A match against cDNA sequence.

cDNA_match SO:0000689

# SO:ma
# A contiguous sequence which begins with, and includes, a start codon and
# ends with, and includes, a stop codon.

CDS SO:0000316

# SO:ke
# A region of chromosome where the spindle fibers attach during mitosis
# and meiosis.

centromere SO:0000577

# SO:ke
# A part of a chromosome that has structural function. 

chromosomal_structural_element SO:0000628

# http://biotech.icmb.utexas.edu/search/dict-search.mhtml
# Structural unit composed of long DNA molecule.

chromosome SO:0000340

# SO:ke
# Part of the primary transcript that is clipped off during processing.

clip SO:0000303

# http://www.geospiza.com/community/support/glossary/
# A piece of DNA that has been inserted in a vector so that it can be
# propagated in E. coli or some other organism.

clone SO:0000151

# SO:ke
# The end of the clone insert.

clone_end SO:0000103

# SO:ke
# The start of the clone insert.

clone_start SO:0000179

# http://genomics.phrma.org/lexicon/c.html
# 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.

codon SO:0000360

# http://www.ebi.ac.uk/mutations/recommendations/mutevent.html
# 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.

complex_substitution SO:1000005

# SO:ls
# A contiguous sequence derived from sequence assembly. Has no gaps, but
# may contain N's from unvailable bases.

contig SO:0000149

# SO:rd
# 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.

CpG_island SO:0000307

# SO:ma
# A nucleotide match against a sequence from another organism.

cross_genome_match SO:0000177

# Germline genomic DNA including D-region with 5' UTR and 3' UTR, also
# designated as D-segment.

D_gene SO:0000458

# SO:ke
# The sequence referred to by an entry in a databank such as Genbank or
# SwissProt.

databank_entry SO:2000061

# SO:ke
# A non-functional descendent of an exon.

decayed_exon SO:0000464

# SO:ke
# The sequence that is deleted.

deletion SO:0000159

# SO:ke
# The space between two bases in a sequence which marks the position where
# a deletion has occured.

deletion_junction SO:0000687

# SO:ke
# A repeat where the same sequence is repeated in the same direction.
# Example: GCTGA-----GCTGA.

direct_repeat SO:0000314

# SO:ke
# A repeat that is located at dispersed sites in the genome.

dispersed_repeat SO:0000658

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# 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.

enhancer SO:0000165

# SO:ma
# A non-coding RNA, usually with a specific secondary structure, that acts
# to regulate gene expression.

enzymatic_RNA SO:0000372

# http://genomics.phrma.org/lexicon/e.html
# Expressed Sequence Tag: The sequence of a single sequencing read from a
# cDNA clone or PCR product; typically a few hundred base pairs long.

EST SO:0000345

# SO:ke
# A match against an EST sequence.

EST_match SO:0000668

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# 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).

exon SO:0000147

# SO:ke
# The boundary between two exons in a processed transcript.

exon_junction SO:0000333

# SO:ke
# A region of sequence implicated in an experimental result.

experimental_result_region SO:0000703

# SO:ke
# A match to an EST or cDNA sequence.

expressed_sequence_match SO:0000102

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# A region at the 5' end of a mature transcript (preceding the initiation
# codon) that is not translated into a protein.

five_prime_UTR SO:0000204

# http://biotech.icmb.utexas.edu/search/dict-search.mhtml
# The DNA sequences extending on either side of a specific locus.

flanking_region SO:0000239

# SO:ke
# A gap in the sequence of known length. THe unkown bases are filled in
# with N's.

gap SO:0000730

# SO:rd
# 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

gene SO:0000704

# SO:ma
# A collection of related genes.

gene_group SO:0005855

# SO:ke
# A kind of regulatory region that regulates a gene_group such as an
# operon, rather than an individual gene. 

gene_group_regulatory_region SO:0000752

# SO:ls
# A set of subregions selected from sequence contigs which when
# concatenated form a nonredundant linear sequence.

golden_path SO:0000688

# SO:rd
# One of the pieces of sequence that make up a golden path.

golden_path_fragment SO:0000468

# http://www.sanger.ac.uk/Software/Rfam/browse/index.shtml
# 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.

group_II_intron SO:0000603

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00028
# 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.

group_I_intron SO:0000587

# http://www.rna.ucla.edu/index.html
# 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.

guide_RNA SO:0000602

# http:rnaworld.bio.ukans.edu/class/RNA/RNA00/RNA_World_3.html
# 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.

hammerhead_ribozyme SO:0000380

# SO:ke
# A region of sequence identified as having been inserted.

insertion SO:0000667

# SO:ke
# The junction where an insertion occurred.

insertion_site SO:0000366

# http:http://medical.webends.com/kw/Insulator%20Elements
# Nucleic acid regulatory sequences that limit or oppose the action of
# ENHANCER ELEMENTS and define the boundary between differentially
# regulated gene loci.

insulator SO:0000627

# SO:ke
# A viral sequence which has integrated into the host genome.

integrated_virus SO:0000113

# SO:ke
# The region between two known genes.

intergenic_region SO:0000605

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# A segment of DNA that is transcribed, but removed from within the
# transcript by splicing together the sequences (exons) on either side of
# it.

intron SO:0000188

# http://www.ebi.ac.uk/mutations/recommendations/mutevent.html
# A continuous nucleotide sequence is inverted in the same position.

inversion SO:1000036

# SO:ke
# The sequence is complementarily repeated on the opposite strand.
# Example: GCTGA-----TCAGC.

inverted_repeat SO:0000294

# Germline genomic DNA of an immunoglobulin/T-cell receptor gene
# including J-region with 5' UTR (SO:0000204) and 3' UTR (SO:0000205),
# also designated as J-segment.

J_gene SO:0000470

# Recombination signal including J-heptamer, J-spacer and J-nonamer in
# 5' of J-region of a J-gene or J-sequence

J_gene_recombination_feature SO:0000302

# SO:ke
# A junction refers to an interbase location of zero in a sequence.

junction SO:0000699

# SO:ke
# A region of sequence, aligned to another sequence with some statistical
# significance, using an algorithm such as BLAST or SIM4.

match SO:0000343

# SO:ke
# A part of a match, for example an hsp from blast isa match_part.

match_part SO:0000039

# SO:ke
# A collection of match parts

match_set SO:0000038

# http:www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html
# The coding sequence for the mature or final peptide or protein product
# following post-translational modification.

mature_peptide SO:0000419

# SO:ke
# A methylated adenine.

methylated_A SO:0000161

# SO:ke
# A nucleotide modified by methylation.

methylated_base_feature SO:0000306

# SO:ke
# A methylated deoxy-cytosine.

methylated_C SO:0000114

# http://www.informatics.jax.org/silver/glossary.shtml
# A very short unit sequence of DNA (2 to 4 bp) that is repeated multiple
# times in tandem.

microsatellite SO:0000289

# http://www.rerf.or.jp/eigo/glossary/minisate.htm
# A repetitive sequence spanning 500 to 20,000 base pairs (a repeat unit
# is 5 - 30 base pairs).

minisatellite SO:0000643

# PMID:12592000
# 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.

minus_10_signal SO:0000175

minus_35_signal SO:0000176

miRNA SO:0000276

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# A modified nucleotide, i.e. a nucleotide other than A, T, C. G or (in
# RNA) U.

modified_base_site SO:0000305

# SO:ma
# Messenger RNA is the intermediate molecule between DNA and protein. It 
# includes UTR and coding sequences. It does not contain introns.

mRNA SO:0000234

# SO:ke
# An mRNA sequence that does not encode for a protein rather the RNA
# molecule is the gene product.

ncRNA SO:0000655

# SO:ke
# A primary transcript that is never translated into a protein.

nc_primary_transcript SO:0000483

# SO:ke
# A region of the gene which is not transcribed.

non_transcribed_region SO:0000183

# SO:ma
# A region of nucleotide sequence targeting by a nuclease enzyme.

nuclease_sensitive_site SO:0000684

# SO:ke
# A match against a nucleotide sequence.

nucleotide_match SO:0000347

# SO:ke
# A region of nucleotide sequence corresponding to a known motif.

nucleotide_motif SO:0000714

# SO:ma
# A short oligonucleotide sequence, of length on the order of 10's of
# bases; either single or double stranded.

oligo SO:0000696

# SO:ma
# A regulatory element of an operon to which activators or repressors bind
# hereby effecting translation of genes in that operon.

operator SO:0000057

# SO:ma
# A group of contiguous genes transcribed as a single (polycistronic) mRNA
# from a single regulatory region.

operon SO:0000178

# SO:rb
# 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

ORF SO:0000236

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# The origin of replication; starting site for duplication of a nucleic
# acid molecule to give two identical copies.

origin_of_replication SO:0000296

# http:http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# A region of a DNA molecule whre transfer is initiated during the process
# of conjugation or mobilization.

origin_of_transfer SO:0000724

# SO:ke
# A region amplified by a PCR reaction.

PCR_product SO:0000006

# http://www.ebi.ac.uk/mutations/recommendations/mutevent.html
# A mutation event where a single DNA nucleotide changes into another
# nucleotide.

point_mutation SO:1000008

# SO:ke
# Sequence of about 100 nucleotides of A added to the 3' end of most
# eukaryotic mRNAs.

polyA_sequence SO:0000610

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# The recognition sequence necessary for endonuclease cleavage of an RNA
# transcript that is followed by polyadenylation; consensus=AATAAA.

polyA_signal_sequence SO:0000551

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# The site on an RNA transcript to which will be added adenine residues by
# post-transcriptional polyadenylation.

polyA_site SO:0000553

# SO:ma
# A sequence of amino acids linked by peptide bonds which may lack
# appreciable tertiary structure and may not be liable to irreversable
# denaturation.

polypeptide SO:0000104

# http://nar.oupjournals.org/cgi/content/full/25/4/888
# The polypyrimidine tract is one of the cis-acting sequence elements
# directing intron removal in pre-mRNA splicing.

polypyrimidine_tract SO:0000612

# SO:ke
# A region of sequence where there may have been an error in the assembly.

possible_assembly_error SO:0000702

# SO:ke
# A region of sequence where the validity of the base calling is
# questionable.

possible_base_call_error SO:0000701

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# 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).

primary_transcript SO:0000185

primary_transcript_region SO:0000835

# http://www.ornl.gov/TechResources/Human_Genome/publicat/primer2001/glossary.html
# A short preexisting polynucleotide chain to which new
# deoxyribonucleotides can be added by DNA polymerase.

primer SO:0000112

# SO:ke
# A transcript which has undergone processing to remove parts such as
# introns and transcribed_spacer_regions.

primer_binding_site SO:0005850

processed_transcript SO:0000233

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# The region on a DNA molecule involved in RNA polymerase binding to
# initiate transcription.

promoter SO:0000167

# SO:ke
# A primary transcript that, at least in part, encodes one or more
# proteins.

protein_coding_primary_transcript SO:0000120

# SO:ke
# A match against a protein sequence.

protein_match SO:0000349

# http://www.ucl.ac.uk/ ~ ucbhjow/b241/glossary.html
# 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).

pseudogene SO:0000336

# SO:rb
# The exon of a pseudogene.

pseudogenic_exon SO:0000507

# SO:cjm
# A non-functional descendent of a functional entitity.

pseudogenic_region SO:0000462

# SO:rb
# A transcript of a pseudogene

pseudogenic_transcript SO:0000516

# http://www.developmentalcell.com/content/article/abstract?uid=PIIS1534580703002284
# A small, 17-28-nt, small interfering RNA derived from transcripts
# ofrepetitive elements.

rasiRNA SO:0000454

# SO:rd
# 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.

read SO:0000150

# SO:rb
# 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.

reading_frame SO:0000717

# SO:ls
# A pair of sequencing reads in which the two members of the pair are
# related by originating at either end of a clone insert.

read_pair SO:0000007

# SO:ke
# A sequence used in experiment.

reagent SO:0000695

# SO:ke
# Continous sequence.

region SO:0000001

# http://www.genpromag.com/scripts/glossary.asp?LETTER=R
# A DNA sequence that controls the expression of a gene.

regulatory_region SO:0005836

# ISBN:0198506732
# A group of genes, whether linked as a cluster or not, that respond to a
# common regulatory signal.

regulon SO:1001284

# SO:ke
# A comment about the sequence.

remark SO:0000700

# SO:ke
# A group of characterized repeat sequences.

repeat_family SO:0000187

# SO:ke
# A region of sequence containing one or more repeat units.

repeat_region SO:0000657

# http://www.agron.missouri.edu/cgi-bin/sybgw_mdb/mdb3/Term/119
# Any of the individual polynucleotide sequences produced by digestion of
# DNA with a restriction endonuclease.

restriction_fragment SO:0000412

# PMID:6247908
# A polymorphism detectable by the size differences in DNA fragments
# generated by a restriction enzyme.

RFLP_fragment SO:0000193

# SO:ke
# Region in mRNA where ribosome assembles.

ribosome_entry_site SO:0000139

# SO:ma
# An RNA with catalytic activity.

ribozyme SO:0000374

# SO:rd
# A double stranded RNA duplex, at least 20bp long, used experimentally to
# inhibit gene function by RNA interference.

RNAi_reagent SO:0000337

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00030
# 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.

RNase_MRP_RNA SO:0000385

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00010
# 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.

RNase_P_RNA SO:0000386

# ISBN:0198506732
# RNA that comprises part of a ribosome, and that can provide both
# structural scaffolding and catalytic activity.

rRNA SO:0000252

# SO:ke
# 18S_rRNA -A large polynucleotide which functions as a part of the small
# subunit of the ribosome

rRNA_18S SO:0000407

# SO:ke
# A component of the large ribosomal subunit.

rRNA_28S SO:0000653

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00002
# 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.

rRNA_5.8S SO:0000375

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00001
# 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.

rRNA_5S SO:0000652

# http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=7570003&dopt=Abstract
# A short diagnostic sequence tag, serial analysis of gene expression
# (SAGE), that allows the quantitative and simultaneous analysis of a
# large number of transcripts.

SAGE_tag SO:0000326

# http:www.ebi.ac.uk/embl/WebFeat/align/scRNA_s.html
# Any one of several small cytoplasmic RNA moleculespresent in the
# cytoplasm and sometimes nucleus of a eukaryote.

scRNA SO:0000013

# SO:ke
# A region where the sequences differs from that of a specified sequence.

sequence_difference SO:0000413
sequence_conflict   SO:0001085

# Describes the positions in a sequence where the authors are unsure
# about the sequence assignment

sequence_uncertainty SO:0001086

# SO:ke
# A region of sequence where variation has been observed.
# was variation SO:0000109 but this is now obsoleted in SO

sequence_variant SO:0001060 SO:0000109

sequencing_information SO:0001082


# http:www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html
# The sequence for an N-terminal domain of a secreted protein; this domain
# is involved in attaching nascent polypeptide to the membrane leader
# sequence.

signal_peptide SO:0000418

# http://www.brunel.ac.uk/depts/bio/project/old_hmg/gloss3.htm#s
# Combination of short DNA sequence elements which suppress the
# transcription of an adjacent gene or genes.

silencer SO:0000625

# PMID:12592000
# 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.

siRNA SO:0000646

# SO:ma
# A non-coding RNA, usually with a specific secondary structure, that acts
# to regulate gene expression.

small_regulatory_ncRNA SO:0000370

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00012
# 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.

snoRNA SO:0000275

# http://www.cgr.ki.se/cgb/groups/brookes/Articles/essence_of_snps_article.pdf
# 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.

SNP SO:0000694

# PMID:11733745
# Small non-coding RNA in the nucleoplasm. A small nuclear RNA molecule
# involved in pre-mRNA splicing and processing

snRNA SO:0000274

# SO:ke
# An intron which is spliced by the spliceosome.

spliceosomal_intron SO:0000662

# http://www.ucl.ac.uk/ ~ ucbhjow/b241/glossary.html
# The junction between the 3 prime end of an intron and the following
# exon.

splice_acceptor_site SO:0000164

# http://www.ucl.ac.uk/ ~ ucbhjow/b241/glossary.html
# The junction between the 3 prime end of an exon and the following
# intron.

splice_donor_site SO:0000163

# SO:ke
# Region of a transcript that regulates splicing.

splice_enhancer SO:0000344

# SO:ke
# The position where intron is excised.

splice_site SO:0000162

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00017
# 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.

SRP_RNA SO:0000590

# PMID:11081512
# Non-coding RNAs of about 21 nucleotides in length that regulate temporal
# development; first discovered in C. elegans.

stRNA SO:0000649

# http://www.biospace.com
# 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.

STS SO:0000331

# http://www.ebi.ac.uk/mutations/recommendations/mutevent.html
# Any change in genomic DNA caused by a single event.

substitution SO:1000002

# SO:ls
# One or more contigs that have been ordered and oriented using end-read
# information. Contains gaps that are filled with N's.

supercontig SO:0000148

# SO:ke
# A nucleotide sequence that may be used to identify a larger sequence.

tag SO:0000324

# http://www.sci.sdsu.edu/ ~ smaloy/Glossary/T.html
# Two or more adjacent copies of a DNA sequence.

tandem_repeat SO:0000705

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00025
# The RNA component of telomerase, a reverse transcriptase that
# synthesises telomeric DNA.

telomerase_RNA SO:0000390

# SO:ma
# A specific structure at the end of a linear chromosome, required for the
# integrity and maintenence of the end,

telomere SO:0000624

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# The sequence of DNA located either at the end of the transcript that
# causes RNA polymerase to terminate transcription.

terminator SO:0000141

# SO:ke
# A region of a molecule that binds to a transcription factor.

TF_binding_site SO:0000235

# http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# A region at the 3' end of a mature transcript (following the stop codon)
# that is not translated into a protein.

three_prime_UTR SO:0000205

# CJM:SO
# A set of regions which overlap with minimal polymorphism to form a
# linear sequence.

tiling_path SO:0000472

# SO:ke
# A piece of sequence that makes up a tiling_path.SO:0000472.

tiling_path_fragment SO:0000474

# A tmRNA liberates a mRNA from a stalled ribosome. To accomplish this
# part of the tmRNA is used as a reading frame that ends in a
# translation stop signal. The broken mRNA is replaced in the ribosome
# by the tmRNA and translation of the tmRNA leads to addition of a
# proteolysis tag to the incomplete protein enabling recognition by a
# protease. Recently a number of permuted tmRNAs genes have been found
# encoded in two parts. TmRNAs have been identified in eubacteria and
# some chloroplasts but are absent from archeal and eukaryote nuclear
# genomes.

tmRNA  SO:0000584

# SO:ma
# An RNA synthesized on a DNA or RNA template by an RNA polymerase.

transcript SO:0000673

# SO:ke
# The site where transcription ends.

transcription_end_site SO:0000616

# SO:ke
# The site where transcription begins.

transcription_start_site SO:0000315

# http:http://www.ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html#line_types
# 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.

transit_peptide SO:0000725

# SO:ke
# A match against a translated sequence.

translated_nucleotide_match SO:0000181

# http://www.sci.sdsu.edu/ ~ smaloy/Glossary/T.html
# A transposon or insertion sequence. An element that can insert in a
# variety of DNA sequences.

transposable_element SO:0000101

# SO:ke
# The junction in a genome where a transposable_element has inserted.

transposable_element_insertion_site SO:0000368

# SO:ke
# The process that produces mature transcripts by combining exons of
# independent pre-mRNA molecules. The acceptor site lies on the 3' of
# these molecules.

trans_splice_acceptor_site SO:0000706

# ISBN:0198506732
# 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.

tRNA SO:0000253

# PMID:9622129
# 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.

U11_snRNA SO:0000398

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00007
# 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.

U12_snRNA SO:0000399

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00016
# 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.

U14_snRNA SO:0000403

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00003
# 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.

U1_snRNA SO:0000391

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00004
# 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.

U2_snRNA SO:0000392

# PMID:=12409455
# 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).

U4atac_snRNA SO:0000394

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00015
# 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.

U4_snRNA SO:0000393

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00020
# 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.

U5_snRNA SO:0000395

# http:http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=retrieve&db=pubmed&list_uids=1 2409455&dopt=Abstract
# 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).

U6atac_snRNA SO:0000397

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00015
# 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.

U6_snRNA SO:0000396

# FB:WG
# 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.

ultracontig SO:0000719

# SO:ke
# Messenger RNA sequences that are untranslated and lie five prime and
# three prime to sequences which are translated.

UTR SO:0000203

# Germline genomic DNA including L-part1, V-intron and V-exon, with the
# 5' UTR and 3' UTR.

V_gene SO:0000466

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00006
# 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.

vault_RNA SO:0000404

vertebrate_immune_system_gene_recombination_feature SO:0000301 SO:0000301_S_region

# Use for EMBL N_region
vertebrate_immune_system_gene_recombination_spacer SO:0000563

# Use for EMBL V_region
vertebrate_immunoglobulin_T_cell_receptor_rearranged_gene_cluster SO:0000938

# SO:ke
# A continous piece of sequence similar to the 'virtual contig' concept of
# ensembl.

virtual_sequence SO:0000499

# http://www.sanger.ac.uk/cgi-bin/Rfam/getacc?RF00019
# 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.

Y_RNA SO:0000405


####include Efeatures.gff