#BEGIN
data:
gene: # a gene element/table is the collection
dbxref: FBgn0000001 # of all alleles (gene model instances)
name: motorhead
gene_genesynonym:
genesynonym:
gsynonym: lemmy
pub:
dbxref: FBrf00000001 # pub in which synonym is used
gene_genesynonym:
genesynonym:
gsynonym: CG11111
pub:
dbxref: FBrf00050001 # pub in which synonym is used
# (could be annotation paper)
fset:
# first we'll define the chromosome arm feature, on
# which all our examples are located
feature:
name: 2L
ftype: chromosome_arm
dbxref: FBsf12
residues: ATTT.......<20megabases>......GTTGGTT
featureprop:
pkey: is_allele_wildtype # wildtype sequence
pval: 1
# then lets define the wildtype/canonical gene model -
feature:
ftype: gene # gene model/instance aka allele
dbxref: FBal99 # FBals for features where type=gene?
name: motorhead[+] # auto assigned from gene + suffix
suffix: + # we don't have this field in db currently
source_feature: FBsf12 # seqfeatures have FBsfs?
gene_to_feature:
gene: FBgn0000001 # link to gene entity (symbol etc)
featureprop:
pkey: is_allele_wildtype
pval: 1
feature_cvterm: # GO terms *should* be linked to protein
cvterm: # but we still use gns for convenience.
termname: motor # (could do both - eg in warehouse/mart?)
dbxref: GO:0004773
# a gene model also includes exon structure etc; lets define these.
# the composition graph (feature_relationship entries) appears
# further on down
feature:
ftype: transcript
dbxref: FBtr15
name: motorhead-RA[+] # auto assigned from gene + allele + suffix
# [how do we name dicistronic trs?]
suffix: A # we don't have this field in db currently
source_feature: FBsf12
residues: GGTCCATGCTTAAGTCA............ATTTGAACC # *spliced* residues
feature:
ftype: exon
dbxref: FBsf201
name: motorhead-Ex1[+] # auto assigned from gene + allele + suffix
# [how do we name dicistronic exons?]
suffix: 1 # we don't have this field in db currently
source_feature: FBsf12
fmin: 1000
fmax: 3000
fstrand: 1
feature:
ftype: exon
dbxref: FBsf202
name: motorhead-Ex2[+] # auto assigned from gene + allele + suffix
# [how do we name dicistronic exons?]
suffix: 2 # we don't have this field in db currently
source_feature: FBsf12
fmin: 4000
fmax: 9000
fstrand: 1
feature:
ftype: CDS
dbxref: FBsf203
source_feature: FBsf12
residues: ATG.................TCG
feature:
ftype: CDS_exon
dbxref: FBsf204
source_feature: FBsf12
fmin: 1200
fmax: 3000
fstrand: 1
feature:
ftype: CDS_exon
dbxref: FBsf205
source_feature: FBsf12
fmin: 4000
fmax: 8800
fstrand: 1
feature:
ftype: translation
dbxref: FBpp5
name: motorhead-P1[+] # auto assigned from gene + allele + suffix
# [how do we name dicistronic exons?]
suffix: 1 # we don't have this field in db currently
residues: MVQQQVQVQV.....PQSC*
# we could have all kinds of stuff attached here:
# eg, GO function, mol weight, proteomic modules
# let's add a post-translationally modified protein
feature:
ftype: translation
dbxref: FBpp6
name: motorhead-P1-mod1.1[+] # auto assigned from gene + allele + suffix
suffix: 1.1 # we don't have this field in db currently
featureprop:
pkey: description
pval: modified motorhead
residues: MVQQQVQVQV.....PQSC*
feature:
ftype: protein_motif
dbxref: FBsf30008
name: motorhead-P1[+] kinesin motor domain
feature_cvterm:
cvterm:
termname: kinesis motor domain
dbxref: IPR001752
source_feature: FBpp5 # domain located relative to pp
fmin: 21
fmax: 183
fstrand: 1
# ^^^^
# ok, above is the canonical gene model on wildtype sequence
#
# now, we shall define any mutant alleles
feature:
ftype: gene # gene model/instance aka allele
dbxref: FBal345 # allele identifier
gene_to_feature:
gene: FBgn0000001 # alleles collected by gene entity
name: motorhead[12] # auto assigned from gene + suffix
suffix: 12
featureprop:
pkey: is_allele_wildtype
pval: 0 # mutant allele
feature_cvterm:
cvterm:
termname: X-ray # mutation method [see NOTE*]
# note: we *could* instantiate mutant transcript, translation etc
# but we won't bother here
feature:
ftype: gene # gene model/instance aka allele
dbxref: FBal346 # allele identifier
name: motorhead[ab] # auto assigned from gene + suffix
suffix: ab
gene_to_feature:
gene: FBgn0000001 # alleles collected by gene entity
featureprop:
pkey: is_allele_wildtype
pval: 0 # mutant allele
# any other features here - lets have one molecularly characterised
# mutation, which shall be the 'causative agent' of the
# allele immediately above. lets leave the other allele as being purely
# genetically/phenotypically characterised (ie no mutation feature)
feature:
name: motorhead{BG000001} # rules/triggers for this?
suffix: BG000001
ftype: insertion # subtype of general variation type
dbxref: FBti78
source_feature: FBsf12
fmin: 1582 # inserts into CDS exon
fmax: 1582
fstrand: 1
featureprop:
pkey: variation_type
pval: CDS
# lets have some more features in the region; one could be
# an oligonucleotide sequence localised to the genome; this
# oligo could have been used in a microarray experiment, for
# example. raw data could be attached to the oligo via
# a microarray module. conclusions could be transfered to
# the gene or transcript object via genome coordinate
# intersections with oligo
feature:
ftype: oligo
dbxref: FBol666 # PRIMARY identifier
source_feature: FBsf12
fmin: 8940 # made from 3' UTR
fmax: 8964
fstrand: 1
residues: ATATTAT.........GGGG
feature_dbxref: # EXTERNAL identifiers
dbxref:
dbname: Affy
accession: 000000123
# now we'll do the graph relating features to eachother
feature_relationship_set:
feature_relationship:
subjfeature: FBtr15 # transcript
objfeature: FBal99 # gene model / allele
type: Part-Of # compositional relationship
feature_relationship:
subjfeature: FBsf201 # exon
objfeature: FBtr15 # transcript
type: Part-Of
feature_relationship:
subjfeature: FBsf202 # exon
objfeature: FBtr15 # transcript
type: Part-Of
feature_relationship:
subjfeature: FBsf203 # CDS
objfeature: FBtr15 # transcript
type: Coded-By # ? use partof ?
feature_relationship:
subjfeature: FBpp5 # translation
objfeature: FBsf203 # CDS
type: Translated-From
feature_relationship:
subjfeature: FBpp6 # translation
objfeature: FBpp5 # translation (modified)
type: Produced-By
feature_relationship:
subjfeature: FBsf204 # CDS-exon
objfeature: FBsf203 # CDS
type: Part-Of
feature_relationship:
subjfeature: FBsf205 # CDS-exon
objfeature: FBsf203 # CDS
type: Part-Of
feature_relationship:
subjfeature: FBti78 # insertion
objfeature: FBal346 # mutant allele
type: Causes
feature_relationship:
subjfeature: FB #
objfeature: FB #
type:
# some basic phenotypic data for our 2 alleles
pset:
phenotype:
dbxref: FBph001
phenotype_cvterm:
cvterm:
termname: curly
phenotype_cvterm:
cvterm:
termname: wings
feature_phenotype:
feature: FBal345
phenotype:
dbxref: FBph002
phenotype_cvterm:
cvterm:
termname: lethal # note: dist between class and effect
phenotype_cvterm: # is implicit
cvterm:
termname: dominant
feature_phenotype:
feature: FBal346
#END