# Feature types for SwissProt output

# From the Swiss-Prot users manual
# http://www.expasy.org/sprot/userman.html#FT_keys
# Last checked 2 Jun 2006

# Many features are plain text with a final qualifier in brackets We
# can represent these with /note plus a /comment for the part in
# brackets. 

# We could also implement specific qualifiers for each special format
# so we can parser the details for each feature, But what to do about
# new GFF versions of the same features with possibly bad formatting?

#############################################################
# The first type is used as the default if no match is found
#############################################################


# The introduction of these new feature keys allows to establish a clear
# sorting order for feature tables. The following order is used:
#
# 1. Molecule processing
#      * INIT_MET, SIGNAL, PROPEP, TRANSIT, CHAIN, PEPTIDE
# 2. Regions
#      * TOPO_DOM, TRANSMEM
#      * DOMAIN, REPEAT
#      * CA_BIND, ZN_FING, DNA_BIND, NP_BIND
#      * REGION
#      * COILED
#      * MOTIF
#      * COMPBIAS
# 3. Sites
#      * ACT_SITE
#      * METAL
#      * BINDING
#      * SITE
# 4. Amino acid modifications (pre and PTM)
#      * SE_CYS
#      * MOD_RES
#      * LIPID
#      * CARBOHYD
#      * DISULFID
#      * CROSSLNK
# 5. Natural variations
#      * VARSPLIC
#      * VARIANT
# 6. Experimental info
#      * MUTAGEN
#      * UNSURE
#      * CONFLICT
#      * NON_CONS
#      * NON_STD
#      * NON_TER
# 7. Secondary structure
#       * HELIX, TURN, STRAND
#
# Keys of equal priority (listed on one line above) are ordered
# according to sequence positions.

# REGION - Extent of a region of interest in the sequence

REGION  SO:0000839
	/note
	/comment

# ACT_SITE - Amino acid(s) involved in the activity of an enzyme.

ACT_SITE SO:0001104
	/note
	/comment

# BINDING  -  Binding  site  for any chemical group  (co-enzyme,  prosthetic
# group, etc.).
# The chemical nature of the group is given in the description field

BINDING SO:0000409
	/note
	/comment

# CA_BIND - Extent of a calcium-binding region.

CA_BIND SO:0001094
	/note
	/comment

# CARBOHYD - Glycosylation site.
# This key describes the occurrence of the attachment of a  glycan (mono- or
# polysaccharide) to a residue of the protein:
# 
# o The type of linkage (C- N- or O-linked) to the protein is indicated.
# o If  the nature of the reducing terminal sugar is known, its abbreviation
#   is   shown   between   parenthesis.  If  three  dots  "..."  follow  the
#   abbreviation this indicates extension of the carbohydrate chain.
#   Conversely the absence of the dots indicate that a single monosaccharide
#   is linked.
# Examples of CARBOHYD key feature lines:
# 
# FT   CARBOHYD     52     52       N-LINKED (GLCNAC...) (POTENTIAL).
# FT   CARBOHYD    162    162       O-LINKED (GLCNAC).
# FT   CARBOHYD     10     10       O-LINKED (GALNAC...) (BY SIMILARITY).
# FT   CARBOHYD     34     34       C-LINKED (MAN).

CARBOHYD MOD:00693
	/note
	/comment
	/ftid

# CHAIN - Extent of a polypeptide chain in the mature protein.

# In Swiss-Prot, it is present:
# For proteins that are not processed
# (those for which the mature protein sequence corresponds to the
# translated cDNA sequence) the CHAIN covers the whole protein
# sequence
# For processed proteins, it describes the mature part of the protein
# once preprotein parts such as propeptides and signal sequences have
# been removed
#
# For TrEMBL, it is present only in those entries where the submitters
# to the nucleotide sequence databases have provided this information
# for processed proteins.

CHAIN   SO:0000419
	/note
	/comment
	/ftid


# COILED - Extent of a coiled-coil region

COILED  SO:0001080
	/note
	/comment

# COMPBIAS - Extent of a compositionally biased region

COMPBIAS SO:0001066
	/note
	/comment

# CONFLICT - Different papers report differing sequences.
# note usually begins MISSING or SEQ -> NEW (description optional)

CONFLICT SO:0001085
	/note
	/comment

# CROSSLNK - Posttranslationally formed amino acid bonds.
# The 'FROM' and 'TO' endpoints designate the two residues, which are
# linked by an intrachain bond, and the description field indicates
# the nature of the cross-link. If the 'FROM' and 'TO' endpoints are
# identical, the amino acid bond is an interchain one. The name of the
# linked peptide is indicated in the description field.
 
CROSSLNK SO:0001087
	/note
	/comment

# DISULFID - Disulfide bond.
# The 'FROM' and 'TO' endpoints represent the two residues which are
# linked by an intra-chain disulfide bond. If the 'FROM' and 'TO'
# endpoints are identical, the disulfide bond is an interchain one and
# the description field indicates the nature of the cross-link.

DISULFID SO:0001088
	/note
	/comment

# DNA_BIND - Extent of a DNA-binding region.
# The nature of the DNA-binding region is given in the description field. 

DNA_BIND SO:0100020
	/note
	/comment

# DOMAIN - Extent of a domain, which is defined as a specific
# combination of secondary structures organized into a characteristic
# three-dimensional structure or fold.
#
# The domain type is given in the description field. If there exist
#   several copies of a domain, the domains are numbered.

DOMAIN  SO:0000417 SO:0001081
	/note
	/comment

# HELIX -  DSSP secondary structure

HELIX   SO:0001117
	/note
	/comment

# INIT_MET - Initiator methionine.

# This feature key is usually associated with a zero value in the 'FROM'
# and 'TO' fields to indicate that the initiator methionine has been
# cleaved off and is not shown in the sequence. Usually there is no
# annotation in such cases.

# It is not used when the initiator methionine is not cleaved off except
# in the event of internal alternative initiation sites. Example:
# annotation "For isoform Cytoplasmic."


INIT_MET SO:0000691
	/note
	/comment

# LIPID  - Covalent binding of a lipidic moiety
# note is attached group name (optional comment)
# known names are:

#MYRISTATE          Myristate group attached through an amide bond to the
#                   N-terminal glycine residue of the mature form of a
#                   protein [1,2] or to an internal lysine residue
#
#PALMITATE          Palmitate group attached through a thioether bond to a
#                   cysteine residue or through an ester bond to a serine
#                   or threonine residue [1,2]
#
#FARNESYL           Farnesyl group attached through a thioether bond to a
#                   cysteine residue [3,4]
#
#GERANYL-GERANYL    Geranyl-geranyl group attached through a thioether bond
#                   to a cysteine residue [3,4]
#
#GPI-ANCHOR         Glycosyl-phosphatidylinositol (GPI) group linked to the
#                   alpha-carboxyl group of the C-terminal residue of the
#                   mature form of a protein [5,6]
#
#DIACYLGLYCERIDE    Glyceryl group bearing two ester-linked fatty acids
#                   attached through a thioether bond to the
#                   N-terminal cysteine of the mature form of a
#                   prokaryotic lipoprotein
#
#ARCHAEOL           Archaeol (2,3-di-O-phytanyl-sn-glycerol) lipid
#                   group attached through an thioether bond to the
#                   N-terminal cysteine of the mature form of a
#                   archaeal lipoprotein     
#
#N-OCTANOATE        n-octanoate group linked through an ester bond to
#                   a serine residue
#
#CHOLESTEROL        Cholesterol group attached through an ester bond
#                   to the C-terminal glycine of the mature form of a protein

LIPID   MOD:01155
	/note
	/comment

# METAL - Binding site for a metal ion.
# The description field indicates the nature of the metal

METAL   SO:0001092
	/note
	/comment

# MOD_RES  Post-translational modification of a residue.
# note usually <modification> (description)
# Most common codes are:

#ACETYLATION                 N-terminal or other
#AMIDATION                   Generally at the C-terminal of a mature active
#                            peptide
#BLOCKED                     Undetermined N- or C-terminal blocking group
#FORMYLATION                 Of the N-terminal methionine
#GAMMA-CARBOXYGLUTAMIC ACID  Of glutamate
#HYDROXYLATION               Of asparagine, aspartic acid, proline or lysine
#METHYLATION                 Generally of lysine or arginine
#PHOSPHORYLATION             Of serine, threonine, tyrosine, aspartic acid
#                            of histidine
#PYRROLIDONE CARBOXYLIC ACID N-terminal glutamate which has formed an
#                            internal cyclic lactam
#SULFATATION                 Generally of tyrosine

MOD_RES MOD:01156
	/note
	/comment

# MOTIF - Short (up to 20 amino acids) sequence motif of biological interest

MOTIF   SO:0001067_motif
	/note
	/comment

# MUTAGEN - Site which has been experimentally altered.
# mutagen note usually SEQ ->NEW: description or "Missing: functional change"

MUTAGEN SO:0001148
	/note
	/comment

# NON_CONS - Non-consecutive residues.
# Indicates  that  two residues in a sequence are not consecutive  and  that
# there  are  a  number of unsequenced residues between  them.

NON_CONS SO:0001083
	/note
	/comment

# NON_STD - Non-standard aminoacid used for pyrrolysine

NON_STD  SO:0000884
	/note
	/comment

# NON_TER  - The residue at an extremity of the sequence is not the terminal
# residue.

NON_TER SO:0001084
	/note
	/comment

# NP_BIND - Extent of a nucleotide phosphate binding region.

# The nature of the nucleotide phosphate is indicated in the
# description field.

NP_BIND SO:0100018_np_bind
	/note
	/comment

# PEPTIDE - Extent of a released active peptide.

PEPTIDE SO:0001064
	/note
	/comment
	/ftid

# PROPEP - Extent of a propeptide.

PROPEP  SO:0001062
	/note
	/comment
	/ftid

# REPEAT - Extent of an internal sequence repetition.

REPEAT  SO:0001068
	/note
	/comment

# SE_CYS - Selenocysteine
# This key describes the occurrence of a selenocysteine in the sequence record

SE_CYS  SO:0000885 MOD:00031
	/note
	/comment

# SIGNAL - Extent of a signal sequence (prepeptide).

SIGNAL  SO:0000418
	/note
	/comment

# SIMILAR - Extent of a similarity with another protein sequence.

SIMILAR SO:0000857
	/note
	/comment


# SITE - Any interesting single amino-acid site on the sequence, that
# is not defined by another feature key. It can also apply to an amino
# acid bond which is represented by the positions of the two flanking
# amino acids.


SITE    SO:0000839_site
	/note
	/comment

# STRAND -  DSSP secondary structure

STRAND  SO:0001111
	/note
	/comment

# THIOETH - Thioether bond.
# The  'FROM' and 'TO' endpoints represent the two residues which are linked
# by the thioether bond.

THIOETH MOD:00687
	/note
	/comment

# THIOLEST - Thiolester bond.
# The  'FROM' and 'TO' endpoints represent the two residues which are linked
# by the thiolester bond.

THIOLEST MOD:00395
	/note
	/comment

# TRANSIT  -  Extent  of  a  transit peptide (mitochondrial, chloroplastic,
# thylakoid, cyanelle or for a microbody).


# TOPO_DOM - Topological domain
# New added 26-May-06

# Annotated with cellular component where domain is normally located
# e.g. "Cytoplasmic" or "Mitochondrial matrix (potential)"

TOPO_DOM SO:0001072
	/note
	/comment

TRANSIT SO:0000725
	/note
	/comment

# TRANSMEM - Extent of a transmembrane region.

TRANSMEM SO:0001077
	/note
	/comment

# TURN -  DSSP secondary structure

TURN    SO:0001128
	/note
	/comment

# UNSURE - Uncertainties in the sequence
# Used  to describe region(s) of a sequence for which the authors are unsure
# about the sequence assignment.

UNSURE  SO:0001086
	/note
	/comment

# VARIANT - Authors report that sequence variants exist.
# replaced by VAR_SEQ, except for RNA editing recorded in the note

VARIANT SO:0001147_variant
	/note
	/comment
	/ftid

# VAR_SEQ - Description  of  sequence variants  produced  by  alternative
# splicing, alternative promoter usage, ribosomal frameshifting

VAR_SEQ SO:0001147_var_seq
	/note
	/comment
	/ftid

# VARSPLIC - Description  of  sequence variants  produced  by  alternative
# splicing.

VARSPLIC SO:0001147_varsplic
	/note
	/comment

# ZN_FING - Extent of a zinc finger region.
# The zinc finger 'category' is indicated in the description field.

ZN_FING  SO:0100020_zn_fing
	/note
	/comment