Difference between revisions of "GFF3 features (C. elegans)"

From WormBaseWiki
Jump to navigationJump to search
Line 163: Line 163:
 
  transposable_element_insertion_site:Mos_insertion_allele (variation)
 
  transposable_element_insertion_site:Mos_insertion_allele (variation)
  
'''CHANGES'''
 
  
WS177 - add more attributes, add pseudogenes, introns
+
== GFF2 coverage ==
WS176 - add Parent attribute to CDS:Coding_transcript
+
 
WS174 - start documentation
+
<pre>
 +
BY FEATURE
 +
==============================
 +
.:ALLELE 29143
 +
.:Clone_left_end 4420
 +
.:Clone_right_end 3461
 +
.:Sequence 3
 +
.:intron 1763
 +
.:oligo 46370
 +
AUGUSTUS:CDS 145788
 +
AUGUSTUS:five_prime_UTR 25766
 +
AUGUSTUS:single 1066
 +
AUGUSTUS:three_prime_UTR 24888
 +
Allele:SNP 178067
 +
Allele:complex_change_in_nucleotide_sequence 1817
 +
Allele:deletion 5084
 +
Allele:insertion 26
 +
Allele:sequence_variant 4
 +
Allele:substitution 3894
 +
Allele:transposable_element_insertion_site 1533
 +
BLAT_Caen_EST_BEST:expressed_sequence_match 359843
 +
BLAT_Caen_EST_OTHER:expressed_sequence_match 2400258
 +
BLAT_Caen_mRNA_BEST:expressed_sequence_match 1874
 +
BLAT_Caen_mRNA_OTHER:expressed_sequence_match 2971
 +
BLAT_EST_BEST:EST_match 1053771
 +
BLAT_EST_OTHER:EST_match 515321
 +
BLAT_NEMATODE:translated_nucleotide_match 1634503
 +
BLAT_NEMBASE:translated_nucleotide_match 329574
 +
BLAT_OST_BEST:expressed_sequence_match 106595
 +
BLAT_OST_OTHER:expressed_sequence_match 100527
 +
BLAT_RST_BEST:expressed_sequence_match 7408
 +
BLAT_RST_OTHER:expressed_sequence_match 5563
 +
BLAT_TC1_BEST:nucleotide_match 1057
 +
BLAT_TC1_OTHER:nucleotide_match 3516
 +
BLAT_WASHU:translated_nucleotide_match 584087
 +
BLAT_mRNA_BEST:cDNA_match 20354
 +
BLAT_mRNA_OTHER:cDNA_match 5411
 +
BLAT_ncRNA_BEST:nucleotide_match 5973
 +
BLAT_ncRNA_OTHER:nucleotide_match 566
 +
CGH_allele:deletion 250
 +
Chronogram:reagent 2020
 +
Coding_transcript:Transcript 27997
 +
Coding_transcript:coding_exon 179400
 +
Coding_transcript:exon 185895
 +
Coding_transcript:five_prime_UTR 20289
 +
Coding_transcript:intron 157895
 +
Coding_transcript:protein_coding_primary_transcript 3
 +
Coding_transcript:three_prime_UTR 18212
 +
Expr_pattern:reagent 2940
 +
Expr_profile:experimental_result_region 17360
 +
FGENESH:CDS 132760
 +
Genbank:region 6534
 +
GeneMarkHMM:CDS 24016
 +
GeneMarkHMM:coding_exon 132967
 +
GeneMarkHMM:exon 132967
 +
GenePair_STS:PCR_product 46262
 +
Genefinder:CDS 21182
 +
Genefinder:coding_exon 133896
 +
Genefinder:exon 133896
 +
Genefinder:intron 112714
 +
Genomic_canonical:region 3267
 +
Link:region 25
 +
Mos_insertion_allele:transposable_element_insertion_site 14305
 +
Non_coding_transcript:exon 719
 +
Non_coding_transcript:intron 616
 +
Non_coding_transcript:nc_primary_transcript 103
 +
Oligo_set:reagent 83900
 +
Orfeome:PCR_product 19389
 +
Promoterome:PCR_product 6598
 +
Pseudogene:Pseudogene 1551
 +
Pseudogene:exon 4580
 +
Pseudogene:intron 3029
 +
RNAi_primary:RNAi_reagent 155948
 +
RNAi_secondary:RNAi_reagent 14141
 +
RepeatMasker:repeat_region 117035
 +
SAGE_tag:SAGE_tag 111039
 +
SAGE_tag_genomic_unique:SAGE_tag 74833
 +
SAGE_tag_most_three_prime:SAGE_tag 5355
 +
SAGE_tag_unambiguously_mapped:SAGE_tag 69188
 +
SL1:SL1_acceptor_site 7745
 +
SL2:SL2_acceptor_site 2056
 +
TEC_RED:nucleotide_match 8341
 +
Transposon:transposable_element 111
 +
Transposon_CDS:coding_exon 690
 +
Transposon_CDS:exon 690
 +
Transposon_CDS:intron 404
 +
Transposon_CDS:transposable_element 286
 +
Vancouver_fosmid:region 12874
 +
WBPaper00032940|pmid19243610:DNAse_I_hypersensitivity 7095
 +
binding_site:PicTar 11184
 +
binding_site:binding_site 235
 +
binding_site:miRanda 71796
 +
binding_site_region:binding_site 4527
 +
cDNA_for_RNAi:experimental_result_region 2828
 +
curated:CDS 24114
 +
curated:coding_exon 155909
 +
curated:exon 155909
 +
curated:gene 23833
 +
curated:intron 131795
 +
dust:low_complexity_region 189135
 +
gene:gene 38211
 +
gene:processed_transcript 72172
 +
history:CDS 11285
 +
history:Pseudogene 86
 +
history:Transcript 71
 +
history:coding_exon 82742
 +
history:exon 83302
 +
history:intron 71862
 +
history:misc_feature 177
 +
inverted:inverted_repeat 100620
 +
jigsaw:CDS 20423
 +
jigsaw:coding_exon 123207
 +
jigsaw:exon 123207
 +
jigsaw:intron 102784
 +
landmark:gene 116
 +
mGENE:CDS 126500
 +
mGENE:five_prime_UTR 19316
 +
mGENE:three_prime_UTR 20099
 +
mSplicer_orf:CDS 26582
 +
mSplicer_orf:coding_exon 168585
 +
mSplicer_orf:exon 168585
 +
mSplicer_transcript:CDS 26582
 +
mSplicer_transcript:coding_exon 171688
 +
mSplicer_transcript:exon 171688
 +
mass_spec_genome:translated_nucleotide_match 136442
 +
miRNA:exon 160
 +
miRNA:miRNA_primary_transcript 160
 +
nGASP:CDS 123207
 +
nGASP:five_prime_UTR 18935
 +
nGASP:three_prime_UTR 19882
 +
ncRNA:RNAz 3672
 +
ncRNA:exon 15480
 +
ncRNA:intron 22
 +
ncRNA:ncRNA_primary_transcript 15458
 +
operon:operon 1148
 +
polyA_signal_sequence:polyA_signal_sequence 2454
 +
polyA_site:polyA_site 3028
 +
rRNA:exon 22
 +
rRNA:rRNA_primary_transcript 22
 +
scRNA:exon 1
 +
scRNA:scRNA_primary_transcript 1
 +
snRNA:exon 99
 +
snRNA:snRNA_primary_transcript 99
 +
snlRNA:exon 4
 +
snlRNA:snlRNA_primary_transcript 4
 +
snoRNA:exon 139
 +
snoRNA:snoRNA_primary_transcript 139
 +
tRNA:exon 22
 +
tRNA:tRNA_primary_transcript 22
 +
tRNAscan-SE-1.23:exon 638
 +
tRNAscan-SE-1.23:tRNA_primary_transcript 609
 +
tandem:tandem_repeat 53032
 +
twinscan:CDS 21681
 +
twinscan:coding_exon 124073
 +
twinscan:exon 124073
 +
twinscan:intron 102393
 +
waba_coding:nucleotide_match 306424
 +
waba_strong:nucleotide_match 407017
 +
waba_weak:nucleotide_match 970836
 +
wublastx:protein_match 3059127
 +
 
 +
 
 +
 
 +
BY OCCURRENCE
 +
==============================
 +
wublastx:protein_match 3059127
 +
BLAT_Caen_EST_OTHER:expressed_sequence_match 2400258
 +
BLAT_NEMATODE:translated_nucleotide_match 1634503
 +
BLAT_EST_BEST:EST_match 1053771
 +
waba_weak:nucleotide_match 970836
 +
BLAT_WASHU:translated_nucleotide_match 584087
 +
BLAT_EST_OTHER:EST_match 515321
 +
waba_strong:nucleotide_match 407017
 +
BLAT_Caen_EST_BEST:expressed_sequence_match 359843
 +
BLAT_NEMBASE:translated_nucleotide_match 329574
 +
waba_coding:nucleotide_match 306424
 +
dust:low_complexity_region 189135
 +
Coding_transcript:exon 185895
 +
Coding_transcript:coding_exon 179400
 +
Allele:SNP 178067
 +
mSplicer_transcript:exon 171688
 +
mSplicer_transcript:coding_exon 171688
 +
mSplicer_orf:coding_exon 168585
 +
mSplicer_orf:exon 168585
 +
Coding_transcript:intron 157895
 +
RNAi_primary:RNAi_reagent 155948
 +
curated:exon 155909
 +
curated:coding_exon 155909
 +
AUGUSTUS:CDS 145788
 +
mass_spec_genome:translated_nucleotide_match 136442
 +
Genefinder:exon 133896
 +
Genefinder:coding_exon 133896
 +
GeneMarkHMM:coding_exon 132967
 +
GeneMarkHMM:exon 132967
 +
FGENESH:CDS 132760
 +
curated:intron 131795
 +
mGENE:CDS 126500
 +
twinscan:coding_exon 124073
 +
twinscan:exon 124073
 +
nGASP:CDS 123207
 +
jigsaw:coding_exon 123207
 +
jigsaw:exon 123207
 +
RepeatMasker:repeat_region 117035
 +
Genefinder:intron 112714
 +
SAGE_tag:SAGE_tag 111039
 +
BLAT_OST_BEST:expressed_sequence_match 106595
 +
jigsaw:intron 102784
 +
twinscan:intron 102393
 +
inverted:inverted_repeat 100620
 +
BLAT_OST_OTHER:expressed_sequence_match 100527
 +
Oligo_set:reagent 83900
 +
history:exon 83302
 +
history:coding_exon 82742
 +
SAGE_tag_genomic_unique:SAGE_tag 74833
 +
gene:processed_transcript 72172
 +
history:intron 71862
 +
binding_site:miRanda 71796
 +
SAGE_tag_unambiguously_mapped:SAGE_tag 69188
 +
tandem:tandem_repeat 53032
 +
.:oligo 46370
 +
GenePair_STS:PCR_product 46262
 +
gene:gene 38211
 +
.:ALLELE 29143
 +
Coding_transcript:Transcript 27997
 +
mSplicer_orf:CDS 26582
 +
mSplicer_transcript:CDS 26582
 +
AUGUSTUS:five_prime_UTR 25766
 +
AUGUSTUS:three_prime_UTR 24888
 +
curated:CDS 24114
 +
GeneMarkHMM:CDS 24016
 +
curated:gene 23833
 +
twinscan:CDS 21681
 +
Genefinder:CDS 21182
 +
jigsaw:CDS 20423
 +
BLAT_mRNA_BEST:cDNA_match 20354
 +
Coding_transcript:five_prime_UTR 20289
 +
mGENE:three_prime_UTR 20099
 +
nGASP:three_prime_UTR 19882
 +
Orfeome:PCR_product 19389
 +
mGENE:five_prime_UTR 19316
 +
nGASP:five_prime_UTR 18935
 +
Coding_transcript:three_prime_UTR 18212
 +
Expr_profile:experimental_result_region 17360
 +
ncRNA:exon 15480
 +
ncRNA:ncRNA_primary_transcript 15458
 +
Mos_insertion_allele:transposable_element_insertion_site 14305
 +
RNAi_secondary:RNAi_reagent 14141
 +
Vancouver_fosmid:region 12874
 +
history:CDS 11285
 +
binding_site:PicTar 11184
 +
TEC_RED:nucleotide_match 8341
 +
SL1:SL1_acceptor_site 7745
 +
BLAT_RST_BEST:expressed_sequence_match 7408
 +
WBPaper00032940|pmid19243610:DNAse_I_hypersensitivity 7095
 +
Promoterome:PCR_product 6598
 +
Genbank:region 6534
 +
BLAT_ncRNA_BEST:nucleotide_match 5973
 +
BLAT_RST_OTHER:expressed_sequence_match 5563
 +
BLAT_mRNA_OTHER:cDNA_match 5411
 +
SAGE_tag_most_three_prime:SAGE_tag 5355
 +
Allele:deletion 5084
 +
Pseudogene:exon 4580
 +
binding_site_region:binding_site 4527
 +
.:Clone_left_end 4420
 +
Allele:substitution 3894
 +
ncRNA:RNAz 3672
 +
BLAT_TC1_OTHER:nucleotide_match 3516
 +
.:Clone_right_end 3461
 +
Genomic_canonical:region 3267
 +
Pseudogene:intron 3029
 +
polyA_site:polyA_site 3028
 +
BLAT_Caen_mRNA_OTHER:expressed_sequence_match 2971
 +
Expr_pattern:reagent 2940
 +
cDNA_for_RNAi:experimental_result_region 2828
 +
polyA_signal_sequence:polyA_signal_sequence 2454
 +
SL2:SL2_acceptor_site 2056
 +
Chronogram:reagent 2020
 +
BLAT_Caen_mRNA_BEST:expressed_sequence_match 1874
 +
Allele:complex_change_in_nucleotide_sequence 1817
 +
.:intron 1763
 +
Pseudogene:Pseudogene 1551
 +
Allele:transposable_element_insertion_site 1533
 +
operon:operon 1148
 +
AUGUSTUS:single 1066
 +
BLAT_TC1_BEST:nucleotide_match 1057
 +
Non_coding_transcript:exon 719
 +
Transposon_CDS:coding_exon 690
 +
Transposon_CDS:exon 690
 +
tRNAscan-SE-1.23:exon 638
 +
Non_coding_transcript:intron 616
 +
tRNAscan-SE-1.23:tRNA_primary_transcript 609
 +
BLAT_ncRNA_OTHER:nucleotide_match 566
 +
Transposon_CDS:intron 404
 +
Transposon_CDS:transposable_element 286
 +
CGH_allele:deletion 250
 +
binding_site:binding_site 235
 +
history:misc_feature 177
 +
miRNA:miRNA_primary_transcript 160
 +
miRNA:exon 160
 +
snoRNA:exon 139
 +
snoRNA:snoRNA_primary_transcript 139
 +
landmark:gene 116
 +
Transposon:transposable_element 111
 +
Non_coding_transcript:nc_primary_transcript 103
 +
snRNA:exon 99
 +
snRNA:snRNA_primary_transcript 99
 +
history:Pseudogene 86
 +
history:Transcript 71
 +
Allele:insertion 26
 +
Link:region 25
 +
ncRNA:intron 22
 +
rRNA:rRNA_primary_transcript 22
 +
tRNA:exon 22
 +
tRNA:tRNA_primary_transcript 22
 +
rRNA:exon 22
 +
snlRNA:exon 4
 +
Allele:sequence_variant 4
 +
snlRNA:snlRNA_primary_transcript 4
 +
Coding_transcript:protein_coding_primary_transcript 3
 +
.:Sequence 3
 +
scRNA:exon 1
 +
scRNA:scRNA_primary_transcript 1
 +
</pre>

Revision as of 06:40, 4 November 2009

This article describes features included in the C. elegans GFF3 files. For introduction information on the GFF3 files, please see GFF3 features article.

The WormBase C. elegans GFF3 files can be downloaded from:

ftp://ftp.wormbase.org/pub/wormbase/genomes/elegans/genome_feature_tables/GFF3

The attribute tags (column 9) for each feature group are listed in parenthesis. Some attributes listed for a feature group may not be available for each feature within the group.

Features

Protein Coding Genes

The top-level feature for protein-coding genes are:

Gene:Coding_transcript        (ID)

Protein coding genes contain one (or many):

mRNA:Coding_transcript        (ID,Parent,Note,cds,prediction_status,wormpep)


mRNAs consist of:

CDS                           (ID,Parent=mRNA ID,Note,status,wormpep)
five_prime_UTR                (ID,Parent=mRNA ID,Note,status,wormpep)
three_prime_UTR               (ID,Parent=mRNA ID,Note,status,wormpep)

Here's a full example, including alternative splicing in the UTR:

II      Gene    gene    7752566 7753442 .       -       .       ID=000001;Name=WBGene00015062;Alias=trx-1
II      Coding_transcript       mRNA    7752566 7753442 .       -       .       ID=000002;Name=B0228.5a;Parent=000001
II      Coding_transcript       three_prime_UTR 7752566 7752645 .       -       .       ID=000008;Parent=000002
II      Coding_transcript       three_prime_UTR 7752700 7752745 .       -       .       ID=000008;Parent=000002
II      Coding_transcript       CDS     7752746 7752814 .       -       0       ID=000009;Parent=000002
II      Coding_transcript       CDS     7752869 7752940 .       -       0       ID=000011;Parent=000002
II      Coding_transcript       CDS     7753212 7753418 .       -       0       ID=000013;Parent=000002
II      Coding_transcript       five_prime_UTR  7753419 7753442 .       -       .       ID=000014;Parent=000002

Predicted and Retired Genes

Predicted and retired genes are denoted by changing the source of the CDS. SHOULD THIS BE THE SOURCE OF THE GENE?

CDS:GeneMarkHMM                                    (ID)
CDS:Genefinder                                     (ID)
CDS:history                                        (ID)
CDS:twinscan                                       (ID)
  • Non-coding genes (some predicted): a Gene feature and an ncRNA feature is included. The source field for this group varies as listed below.
Genes:

gene:Non_coding_transcript                         (ID)
gene:RNAz                                          (ID)
gene:miRNA                                         (ID)
gene:ncRNA                                         (ID)
gene:rRNA                                          (ID)
gene:scRNA                                         (ID)
gene:snRNA                                         (ID)
gene:snlRNA                                        (ID)
gene:snoRNA                                        (ID)
gene:tRNA                                          (ID)
gene:tRNAscan-SE-1.23                              (ID)

ncRNAs:

ncRNA:Non_coding_transcript                        (ID,Parent,Note)
ncRNA:RNAz                                         (ID,Parent,Note)
ncRNA:miRNA                                        (ID,Parent,Note)
ncRNA:ncRNA                                        (ID,Parent,Note)
ncRNA:rRNA                                         (ID,Parent,Note)
ncRNA:scRNA                                        (ID,Parent,Note)
ncRNA:snRNA                                        (ID,Parent,Note)
ncRNA:snlRNA                                       (ID,Parent,Note)
ncRNA:snoRNA                                       (ID,Parent,Note)
ncRNA:tRNA                                         (ID,Parent,Note)
ncRNA:tRNAscan-SE-1.23                             (ID,Parent)

ncRNA features are parts of the Gene features.

The following features are parts of the mRNA features.

exon:Non_coding_transcript                         (Parent)
exon:miRNA                                         (Parent)
exon:ncRNA                                         (Parent)
exon:rRNA                                          (Parent)
exon:scRNA                                         (Parent)
exon:snRNA                                         (Parent)
exon:snlRNA                                        (Parent)
exon:snoRNA                                        (Parent)
exon:tRNA                                          (Parent)
exon:tRNAscan-SE-1.23                              (Parent)
intron:Coding_transcript                           (Parent,confirmed_cdna,confirmed_est,confirmed_false,confirmed_homology,
                                                    confirmed_inconsistent,confirmed_unknown,confirmed_utr)
intron:Non_coding_transcript                       (Parent,confirmed_cdna,confirmed_est,confirmed_false,confirmed_utr)
intron:ncRNA                                       (Parent,confirmed_est)
  • Alignment features: These features consist of multiple parts unified by a common ID attribute.
EST_match:BLAT_EST_BEST                            (ID,Target)
EST_match:BLAT_EST_OTHER                           (ID,Target)
RNAi_reagent:RNAi_primary                          (ID,Target)
RNAi_reagent:RNAi_secondary                        (ID,Target)
cDNA_match:BLAT_mRNA_BEST                          (ID,Target)
cDNA_match:BLAT_mRNA_OTHER                         (ID,Target)
expressed_sequence_match:BLAT_OST_BEST             (ID,Target)
expressed_sequence_match:BLAT_OST_OTHER            (ID,Target)
nucleotide_match:BLAT_TC1_BEST                     (ID,Target)
nucleotide_match:BLAT_TC1_OTHER                    (ID,Target)
nucleotide_match:BLAT_ncRNA_BEST                   (ID,Target)
nucleotide_match:BLAT_ncRNA_OTHER                  (ID,Target)
nucleotide_match:TEC_RED                           (ID,Target)
nucleotide_match:waba_coding                       (ID,Target)
nucleotide_match:waba_strong                       (ID,Target)
nucleotide_match:waba_weak                         (ID,Target)
protein_match:wublastx                             (ID,Target)
reagent:Expr_pattern                               (ID,Target)
repeat_region:RepeatMasker                         (ID,Target)
translated_nucleotide_match:BLAT_NEMATODE          (ID,Target,species)
translated_nucleotide_match:BLAT_NEMBASE           (ID,Target,species)
translated_nucleotide_match:BLAT_WASHU             (ID,Target,species)
translated_nucleotide_match:mass_spec_genome       (ID,Target,Note,cds_matches,protein_matches,times_observed)
  • Other: The remaining features are listed below.
PCR_product:GenePair_STS                           (pcr_product)
PCR_product:Orfeome                                (amplified,pcr_product)
PCR_product:Promoterome                            (pcr_product)
SAGE_tag:SAGE_tag                                  (count,gene,pseudogene,sequence,transcript)
SAGE_tag:SAGE_tag_genomic_unique                   (count,gene,sequence)
SAGE_tag:SAGE_tag_most_three_prime                 (count,gene,pseudogene,sequence,transcript)
SAGE_tag:SAGE_tag_unambiguously_mapped             (count,gene,pseudogene,sequence,transcript)
SNP:Allele                                         (rflp,status,variation)
binding_site:PicTar                                (Note)
binding_site:miRanda                               (Note)
chromosome:Reference                               (ID,Name)
clone_insert_end:misc_feature                      (clone)
clone_insert_start:misc_feature                    (clone)
complex_substitution:Allele                        (variation)
deletion:Allele                                    (variation)
experimental_result_region:Expr_profile            (expr_profile)
experimental_result_region:cDNA_for_RNAi           (sequence)
gene:landmark                                      (locus)
insertion:Allele                                   (variation)
inverted_repeat:inverted                           (Note)
oligo:misc_feature                                 (placeholder_attribute)
operon:operon                                      (operon)
polyA_signal_sequence:polyA_signal_sequence        (feature)
polyA_site:polyA_site                              (feature)
pseudogene:Pseudogene                              (ID)
pseudogene:history                                 (ID)
reagent:Oligo_set                                  (oligo_set)
region:Genbank                                     (genbank)
region:Genomic_canonical                           (Note,sequence)
region:Link                                        (sequence)
region:Vancouver_fosmid                            (sequence)
region:binding_site                                (feature)
sequence_variant:Allele                            (variation)
sequence_variant:misc_feature                      (allele)
substitution:Allele                                (variation)
tandem_repeat:tandem                               (Note)
trans_splice_acceptor_site:SL1                     (feature)
trans_splice_acceptor_site:SL2                     (feature)
transposable_element:Transposon                    (transposon)
transposable_element:Transposon_CDS                (cds)
transposable_element_insertion_site:Allele         (variation)
transposable_element_insertion_site:Mos_insertion_allele (variation)


GFF2 coverage

BY FEATURE
==============================
.:ALLELE	29143
.:Clone_left_end	4420
.:Clone_right_end	3461
.:Sequence	3
.:intron	1763
.:oligo	46370
AUGUSTUS:CDS	145788
AUGUSTUS:five_prime_UTR	25766
AUGUSTUS:single	1066
AUGUSTUS:three_prime_UTR	24888
Allele:SNP	178067
Allele:complex_change_in_nucleotide_sequence	1817
Allele:deletion	5084
Allele:insertion	26
Allele:sequence_variant	4
Allele:substitution	3894
Allele:transposable_element_insertion_site	1533
BLAT_Caen_EST_BEST:expressed_sequence_match	359843
BLAT_Caen_EST_OTHER:expressed_sequence_match	2400258
BLAT_Caen_mRNA_BEST:expressed_sequence_match	1874
BLAT_Caen_mRNA_OTHER:expressed_sequence_match	2971
BLAT_EST_BEST:EST_match	1053771
BLAT_EST_OTHER:EST_match	515321
BLAT_NEMATODE:translated_nucleotide_match	1634503
BLAT_NEMBASE:translated_nucleotide_match	329574
BLAT_OST_BEST:expressed_sequence_match	106595
BLAT_OST_OTHER:expressed_sequence_match	100527
BLAT_RST_BEST:expressed_sequence_match	7408
BLAT_RST_OTHER:expressed_sequence_match	5563
BLAT_TC1_BEST:nucleotide_match	1057
BLAT_TC1_OTHER:nucleotide_match	3516
BLAT_WASHU:translated_nucleotide_match	584087
BLAT_mRNA_BEST:cDNA_match	20354
BLAT_mRNA_OTHER:cDNA_match	5411
BLAT_ncRNA_BEST:nucleotide_match	5973
BLAT_ncRNA_OTHER:nucleotide_match	566
CGH_allele:deletion	250
Chronogram:reagent	2020
Coding_transcript:Transcript	27997
Coding_transcript:coding_exon	179400
Coding_transcript:exon	185895
Coding_transcript:five_prime_UTR	20289
Coding_transcript:intron	157895
Coding_transcript:protein_coding_primary_transcript	3
Coding_transcript:three_prime_UTR	18212
Expr_pattern:reagent	2940
Expr_profile:experimental_result_region	17360
FGENESH:CDS	132760
Genbank:region	6534
GeneMarkHMM:CDS	24016
GeneMarkHMM:coding_exon	132967
GeneMarkHMM:exon	132967
GenePair_STS:PCR_product	46262
Genefinder:CDS	21182
Genefinder:coding_exon	133896
Genefinder:exon	133896
Genefinder:intron	112714
Genomic_canonical:region	3267
Link:region	25
Mos_insertion_allele:transposable_element_insertion_site	14305
Non_coding_transcript:exon	719
Non_coding_transcript:intron	616
Non_coding_transcript:nc_primary_transcript	103
Oligo_set:reagent	83900
Orfeome:PCR_product	19389
Promoterome:PCR_product	6598
Pseudogene:Pseudogene	1551
Pseudogene:exon	4580
Pseudogene:intron	3029
RNAi_primary:RNAi_reagent	155948
RNAi_secondary:RNAi_reagent	14141
RepeatMasker:repeat_region	117035
SAGE_tag:SAGE_tag	111039
SAGE_tag_genomic_unique:SAGE_tag	74833
SAGE_tag_most_three_prime:SAGE_tag	5355
SAGE_tag_unambiguously_mapped:SAGE_tag	69188
SL1:SL1_acceptor_site	7745
SL2:SL2_acceptor_site	2056
TEC_RED:nucleotide_match	8341
Transposon:transposable_element	111
Transposon_CDS:coding_exon	690
Transposon_CDS:exon	690
Transposon_CDS:intron	404
Transposon_CDS:transposable_element	286
Vancouver_fosmid:region	12874
WBPaper00032940|pmid19243610:DNAse_I_hypersensitivity	7095
binding_site:PicTar	11184
binding_site:binding_site	235
binding_site:miRanda	71796
binding_site_region:binding_site	4527
cDNA_for_RNAi:experimental_result_region	2828
curated:CDS	24114
curated:coding_exon	155909
curated:exon	155909
curated:gene	23833
curated:intron	131795
dust:low_complexity_region	189135
gene:gene	38211
gene:processed_transcript	72172
history:CDS	11285
history:Pseudogene	86
history:Transcript	71
history:coding_exon	82742
history:exon	83302
history:intron	71862
history:misc_feature	177
inverted:inverted_repeat	100620
jigsaw:CDS	20423
jigsaw:coding_exon	123207
jigsaw:exon	123207
jigsaw:intron	102784
landmark:gene	116
mGENE:CDS	126500
mGENE:five_prime_UTR	19316
mGENE:three_prime_UTR	20099
mSplicer_orf:CDS	26582
mSplicer_orf:coding_exon	168585
mSplicer_orf:exon	168585
mSplicer_transcript:CDS	26582
mSplicer_transcript:coding_exon	171688
mSplicer_transcript:exon	171688
mass_spec_genome:translated_nucleotide_match	136442
miRNA:exon	160
miRNA:miRNA_primary_transcript	160
nGASP:CDS	123207
nGASP:five_prime_UTR	18935
nGASP:three_prime_UTR	19882
ncRNA:RNAz	3672
ncRNA:exon	15480
ncRNA:intron	22
ncRNA:ncRNA_primary_transcript	15458
operon:operon	1148
polyA_signal_sequence:polyA_signal_sequence	2454
polyA_site:polyA_site	3028
rRNA:exon	22
rRNA:rRNA_primary_transcript	22
scRNA:exon	1
scRNA:scRNA_primary_transcript	1
snRNA:exon	99
snRNA:snRNA_primary_transcript	99
snlRNA:exon	4
snlRNA:snlRNA_primary_transcript	4
snoRNA:exon	139
snoRNA:snoRNA_primary_transcript	139
tRNA:exon	22
tRNA:tRNA_primary_transcript	22
tRNAscan-SE-1.23:exon	638
tRNAscan-SE-1.23:tRNA_primary_transcript	609
tandem:tandem_repeat	53032
twinscan:CDS	21681
twinscan:coding_exon	124073
twinscan:exon	124073
twinscan:intron	102393
waba_coding:nucleotide_match	306424
waba_strong:nucleotide_match	407017
waba_weak:nucleotide_match	970836
wublastx:protein_match	3059127



BY OCCURRENCE
==============================
wublastx:protein_match	3059127
BLAT_Caen_EST_OTHER:expressed_sequence_match	2400258
BLAT_NEMATODE:translated_nucleotide_match	1634503
BLAT_EST_BEST:EST_match	1053771
waba_weak:nucleotide_match	970836
BLAT_WASHU:translated_nucleotide_match	584087
BLAT_EST_OTHER:EST_match	515321
waba_strong:nucleotide_match	407017
BLAT_Caen_EST_BEST:expressed_sequence_match	359843
BLAT_NEMBASE:translated_nucleotide_match	329574
waba_coding:nucleotide_match	306424
dust:low_complexity_region	189135
Coding_transcript:exon	185895
Coding_transcript:coding_exon	179400
Allele:SNP	178067
mSplicer_transcript:exon	171688
mSplicer_transcript:coding_exon	171688
mSplicer_orf:coding_exon	168585
mSplicer_orf:exon	168585
Coding_transcript:intron	157895
RNAi_primary:RNAi_reagent	155948
curated:exon	155909
curated:coding_exon	155909
AUGUSTUS:CDS	145788
mass_spec_genome:translated_nucleotide_match	136442
Genefinder:exon	133896
Genefinder:coding_exon	133896
GeneMarkHMM:coding_exon	132967
GeneMarkHMM:exon	132967
FGENESH:CDS	132760
curated:intron	131795
mGENE:CDS	126500
twinscan:coding_exon	124073
twinscan:exon	124073
nGASP:CDS	123207
jigsaw:coding_exon	123207
jigsaw:exon	123207
RepeatMasker:repeat_region	117035
Genefinder:intron	112714
SAGE_tag:SAGE_tag	111039
BLAT_OST_BEST:expressed_sequence_match	106595
jigsaw:intron	102784
twinscan:intron	102393
inverted:inverted_repeat	100620
BLAT_OST_OTHER:expressed_sequence_match	100527
Oligo_set:reagent	83900
history:exon	83302
history:coding_exon	82742
SAGE_tag_genomic_unique:SAGE_tag	74833
gene:processed_transcript	72172
history:intron	71862
binding_site:miRanda	71796
SAGE_tag_unambiguously_mapped:SAGE_tag	69188
tandem:tandem_repeat	53032
.:oligo	46370
GenePair_STS:PCR_product	46262
gene:gene	38211
.:ALLELE	29143
Coding_transcript:Transcript	27997
mSplicer_orf:CDS	26582
mSplicer_transcript:CDS	26582
AUGUSTUS:five_prime_UTR	25766
AUGUSTUS:three_prime_UTR	24888
curated:CDS	24114
GeneMarkHMM:CDS	24016
curated:gene	23833
twinscan:CDS	21681
Genefinder:CDS	21182
jigsaw:CDS	20423
BLAT_mRNA_BEST:cDNA_match	20354
Coding_transcript:five_prime_UTR	20289
mGENE:three_prime_UTR	20099
nGASP:three_prime_UTR	19882
Orfeome:PCR_product	19389
mGENE:five_prime_UTR	19316
nGASP:five_prime_UTR	18935
Coding_transcript:three_prime_UTR	18212
Expr_profile:experimental_result_region	17360
ncRNA:exon	15480
ncRNA:ncRNA_primary_transcript	15458
Mos_insertion_allele:transposable_element_insertion_site	14305
RNAi_secondary:RNAi_reagent	14141
Vancouver_fosmid:region	12874
history:CDS	11285
binding_site:PicTar	11184
TEC_RED:nucleotide_match	8341
SL1:SL1_acceptor_site	7745
BLAT_RST_BEST:expressed_sequence_match	7408
WBPaper00032940|pmid19243610:DNAse_I_hypersensitivity	7095
Promoterome:PCR_product	6598
Genbank:region	6534
BLAT_ncRNA_BEST:nucleotide_match	5973
BLAT_RST_OTHER:expressed_sequence_match	5563
BLAT_mRNA_OTHER:cDNA_match	5411
SAGE_tag_most_three_prime:SAGE_tag	5355
Allele:deletion	5084
Pseudogene:exon	4580
binding_site_region:binding_site	4527
.:Clone_left_end	4420
Allele:substitution	3894
ncRNA:RNAz	3672
BLAT_TC1_OTHER:nucleotide_match	3516
.:Clone_right_end	3461
Genomic_canonical:region	3267
Pseudogene:intron	3029
polyA_site:polyA_site	3028
BLAT_Caen_mRNA_OTHER:expressed_sequence_match	2971
Expr_pattern:reagent	2940
cDNA_for_RNAi:experimental_result_region	2828
polyA_signal_sequence:polyA_signal_sequence	2454
SL2:SL2_acceptor_site	2056
Chronogram:reagent	2020
BLAT_Caen_mRNA_BEST:expressed_sequence_match	1874
Allele:complex_change_in_nucleotide_sequence	1817
.:intron	1763
Pseudogene:Pseudogene	1551
Allele:transposable_element_insertion_site	1533
operon:operon	1148
AUGUSTUS:single	1066
BLAT_TC1_BEST:nucleotide_match	1057
Non_coding_transcript:exon	719
Transposon_CDS:coding_exon	690
Transposon_CDS:exon	690
tRNAscan-SE-1.23:exon	638
Non_coding_transcript:intron	616
tRNAscan-SE-1.23:tRNA_primary_transcript	609
BLAT_ncRNA_OTHER:nucleotide_match	566
Transposon_CDS:intron	404
Transposon_CDS:transposable_element	286
CGH_allele:deletion	250
binding_site:binding_site	235
history:misc_feature	177
miRNA:miRNA_primary_transcript	160
miRNA:exon	160
snoRNA:exon	139
snoRNA:snoRNA_primary_transcript	139
landmark:gene	116
Transposon:transposable_element	111
Non_coding_transcript:nc_primary_transcript	103
snRNA:exon	99
snRNA:snRNA_primary_transcript	99
history:Pseudogene	86
history:Transcript	71
Allele:insertion	26
Link:region	25
ncRNA:intron	22
rRNA:rRNA_primary_transcript	22
tRNA:exon	22
tRNA:tRNA_primary_transcript	22
rRNA:exon	22
snlRNA:exon	4
Allele:sequence_variant	4
snlRNA:snlRNA_primary_transcript	4
Coding_transcript:protein_coding_primary_transcript	3
.:Sequence	3
scRNA:exon	1
scRNA:scRNA_primary_transcript	1