diff --git a/INSDC_SO_mappings.txt b/INSDC_SO_mappings.txt new file mode 100644 index 0000000..444f1b2 --- /dev/null +++ b/INSDC_SO_mappings.txt @@ -0,0 +1,151 @@ +feature_key qualifier qualifier_value SO_term SO_synonym +3'UTR three_prime_UTR INSDC_feature:3'UTR (exact) +5'UTR five_prime_UTR INSDC_feature:5'UTR (exact) +assembly_gap gap INSDC_feature:assembly_gap (narrow) +C_region C_gene_segment INSDC_feature:C_region (exact) +CDS CDS INSDC_feature:CDS (exact) +CDS /pseudo pseudogenic_CDS INSDC_feature:CDS (broad), INSDC_qualifier:pseudo (exact) +centromere centromere INSDC_feature:centromere (exact) +D_segment D_gene_segment INSDC_feature:D_segment (exact) +D-loop D_loop INSDC_feature:D-loop (exact) +exon exon INSDC_feature:exon (exact) +gap gap INSDC_feature:gap (exact) +gene gene INSDC_feature:gene (exact) +gene /pseudo pseudogene INSDC_feature:gene (broad), INSDC_qualifier:pseudo (exact) +gene /pseudogene processed processed_pseudogene INSDC_feature:gene (broad), INSDC_qualifier:processed (exact) +gene /pseudogene unprocessed non_processed_pseudogene INSDC_feature:gene (broad), INSDC_qualifier:unprocessed (exact) +gene /pseudogene unitary unitary_pseudogene INSDC_feature:gene (broad), INSDC_qualifier:unitary (exact) +gene /pseudogene allelic allelic_pseudogene INSDC_feature:gene (broad), INSDC_qualifier:allelic (exact) +gene /pseudogene unknown pseudogene INSDC_feature:gene (broad), INSDC_qualifier:unknown (exact) +iDNA iDNA INSDC_feature:iDNA (exact) +intron intron INSDC_feature:intron (exact) +J_segment J_gene_segment INSDC_feature:J_segment (exact) +mat_peptide mature_protein_region INSDC_feature:mat_peptide (exact) +misc_binding binding_site INSDC_feature:misc_binding (exact) +misc_difference sequence_difference INSDC_feature:misc_difference (exact) +misc_feature /feat_class conserved_region conserved_region INSDC_feature:misc_feature (broad), INSDC_note:conserved_region (exact) +misc_feature /feat_class nucleotide_motif nucleotide_motif INSDC_feature:misc_feature (broad), INSDC_note:nucleotide_motif (exact) +misc_feature /feat_class biological_region biological_region INSDC_feature:misc_feature (broad), INSDC_note:biological_region (exact) +misc_feature /feat_class CAGE_cluster CAGE_cluster INSDC_feature:misc_feature (broad), INSDC_note:CAGE_cluster (exact) +misc_feature /feat_class replication_start_site replication_start_site INSDC_feature:misc_feature (broad), INSDC_note:replication_start_site (exact) +misc_feature /feat_class transcription_start_site TSS INSDC_feature:misc_feature (broad), INSDC_note:transcription_start_site (exact) +misc_feature /feat_class sequence_alteration sequence_alteration INSDC_feature:misc_feature (broad), INSDC_note:sequence_alteration (exact) +misc_feature /feat_class sequence_feature sequence_feature INSDC_feature:misc_feature (exact), INSDC_note:sequence_feature (exact) +misc_feature /feat_class nucleotide_cleavage_site nucleotide_cleavage_site INSDC_feature:misc_feature (broad), INSDC_note:nucleotide_cleavage_site (exact) +misc_feature /feat_class repeat_instability_region repeat_instability_region INSDC_feature:misc_feature (broad), INSDC_note:repeat_instability_region (exact) +misc_feature /feat_class sequence_comparison sequence_comparison INSDC_feature:misc_feature (broad), INSDC_note:sequence_comparison (exact) +misc_feature /feat_class other sequence_feature INSDC_feature:misc_feature (exact), INSDC_note:other (exact) +misc_feature sequence_feature INSDC_feature:misc_feature (exact) +misc_recomb /recombination_class chromosome_breakpoint chromosome_breakpoint INSDC_feature:misc_recomb (broad), INSDC_qualifier:chromosome_breakpoint (exact) +misc_recomb /recombination_class meiotic meiotic_recombination_region INSDC_feature:misc_recomb (broad), INSDC_qualifier:meiotic (exact) +misc_recomb /recombination_class mitotic mitotic_recombination_region INSDC_feature:misc_recomb (broad), INSDC_qualifier:mitotic (exact) +misc_recomb /recombination_class non_allelic_homologous non_allelic_homologous_recombination_region INSDC_feature:misc_recomb (broad), INSDC_qualifier:non_allelic_homologous (exact) +misc_recomb /recombination_class meiotic_recombination meiotic_recombination_region INSDC_feature:misc_recomb (broad), INSDC_qualifier:meiotic_recombination (exact), INSDC_qualifier:meiotic (exact) +misc_recomb /recombination_class mitotic_recombination mitotic_recombination_region INSDC_feature:misc_recomb (broad), INSDC_qualifier:mitotic_recombination (exact), INSDC_qualifier:mitotic (exact) +misc_recomb /recombination_class non_allelic_homologous_recombination non_allelic_homologous_recombination_region INSDC_feature:misc_recomb (broad), INSDC_qualifier:non_allelic_homologous_recombination (exact), INSDC_qualifier:non_allelic_homologous (exact) +misc_recomb /recombination_class other recombination_feature INSDC_feature:misc_recomb (exact), INSDC_qualifier:other (exact) +misc_RNA transcript INSDC_feature:misc_RNA (broad) +misc_RNA /pseudo or /pseudogene pseudogenic_transcript INSDC_feature:misc_RNA (broad), INSDC_qualifier:pseudo (exact) +misc_structure sequence_secondary_structure INSDC_feature:misc_structure (exact) +mobile_element mobile_genetic_element INSDC_feature:mobile_element (exact) +modified_base modified_DNA_base INSDC_feature:modified_base (exact) +mRNA mRNA INSDC_feature:mRNA (exact) +N_region N_region INSDC_feature:N_region (exact) +ncRNA /ncRNA_class antisense_RNA antisense_RNA INSDC_feature:ncRNA (broad), INSDC_qualifier:antisense_RNA (exact) +ncRNA /ncRNA_class autocatalytically_spliced_intron autocatalytically_spliced_intron INSDC_feature:ncRNA (broad), INSDC_qualifier:autocatalytically_spliced_intron (exact) +ncRNA /ncRNA_class guide_RNA guide_RNA INSDC_feature:ncRNA (broad), INSDC_qualifier:guide_RNA (exact) +ncRNA /ncRNA_class hammerhead_ribozyme hammerhead_ribozyme INSDC_feature:ncRNA (broad), INSDC_qualifier:hammerhead_ribozyme (exact) +ncRNA /ncRNA_class lncRNA lnc_RNA INSDC_feature:ncRNA (broad), INSDC_qualifier:lncRNA (exact) +ncRNA /ncRNA_class miRNA miRNA INSDC_feature:ncRNA (broad), INSDC_qualifier:miRNA (exact) +ncRNA /ncRNA_class other ncRNA INSDC_qualifier:other (broad) +ncRNA /ncRNA_class piRNA piRNA INSDC_feature:ncRNA (broad), INSDC_qualifier:piRNA (exact) +ncRNA /ncRNA_class rasiRNA rasiRNA INSDC_feature:ncRNA (broad), INSDC_qualifier:rasiRNA (exact) +ncRNA /ncRNA_class ribozyme ribozyme INSDC_feature:ncRNA (broad), INSDC_qualifier:ribozyme (exact) +ncRNA /ncRNA_class RNase_MRP_RNA RNase_MRP_RNA INSDC_feature:ncRNA (broad), INSDC_qualifier:RNase_MRP_RNA (exact) +ncRNA /ncRNA_class RNase_P_RNA RNase_P_RNA INSDC_feature:ncRNA (broad), INSDC_qualifier:RNase_P_RNA (exact) +ncRNA /ncRNA_class scRNA scRNA INSDC_feature:ncRNA (broad), INSDC_qualifier:scRNA (exact) +ncRNA /ncRNA_class siRNA siRNA INSDC_feature:ncRNA (broad), INSDC_qualifier:siRNA (exact) +ncRNA /ncRNA_class snoRNA snoRNA INSDC_feature:ncRNA (broad), INSDC_qualifier:snoRNA (exact) +ncRNA /ncRNA_class snRNA snRNA INSDC_feature:ncRNA (broad), INSDC_qualifier:snRNA (exact) +ncRNA /ncRNA_class SRP_RNA SRP_RNA INSDC_feature:ncRNA (broad), INSDC_qualifier:SRP_RNA (exact) +ncRNA /ncRNA_class telomerase_RNA telomerase_RNA INSDC_feature:ncRNA (broad), INSDC_qualifier:telomerase_RNA (exact) +ncRNA /ncRNA_class vault_RNA vault_RNA INSDC_feature:ncRNA (broad), INSDC_qualifier:vault_RNA (exact) +ncRNA /ncRNA_class Y_RNA Y_RNA INSDC_feature:ncRNA (broad), INSDC_qualifier:Y_RNA (exact) +operon operon INSDC_feature:operon (exact) +oriT oriT INSDC_feature:oriT (exact) +polyA_site polyA_site INSDC_feature:polyA_site (exact) +precursor_RNA primary_transcript INSDC_feature:precursor_RNA (exact) +prim_transcript primary_transcript INSDC_feature:prim_transcript (exact) +primer_bind primer_binding_site INSDC_feature:primer_bind (exact) +propeptide propeptide INSDC_feature:propeptide (exact) +protein_bind protein_binding_site INSDC_feature:protein_bind (exact) +region /SO_type biological_region biological_region INSDC_misc_feature (broad), INSDC_note:biological_region (exact) +regulatory /regulatory_class attenuator attenuator INSDC_feature:regulatory (broad), INSDC_qualifier:attenuator (exact) +regulatory /regulatory_class CAAT_signal CAAT_signal INSDC_feature:regulatory (broad), INSDC_qualifier:CAAT_signal (exact) +regulatory /regulatory_class DNase_I_hypersensitive_site DNAseI_hypersensitive_site INSDC_feature:regulatory (broad), INSDC_qualifier:DNAsel_hypersensitive_site (exact) +regulatory /regulatory_class enhancer enhancer INSDC_feature:regulatory (broad), INSDC_qualifier:enhancer (exact) +regulatory /regulatory_class enhancer_blocking_element enhancer_blocking_element INSDC_feature:regulatory (broad), INSDC_qualifier:enhancer_blocking_element (exact) +regulatory /regulatory_class GC_signal GC_rich_promoter_region INSDC_feature:regulatory (broad), INSDC_qualifier:GC_rich_promoter_region (exact) +regulatory /regulatory_class imprinting_control_region imprinting_control_region INSDC_feature:regulatory (broad), INSDC_qualifier:imprinting_control_region (exact) +regulatory /regulatory_class insulator insulator INSDC_feature:regulatory (broad), INSDC_qualifier:insulator (exact) +regulatory /regulatory_class locus_control_region locus_control_region INSDC_feature:regulatory (broad), INSDC_qualifier:locus_control_region (exact) +regulatory /regulatory_class matrix_attachment_region matrix_attachment_site INSDC_feature:regulatory (broad), INSDC_qualifier:matrix_attachment_region (exact) +regulatory /regulatory_class minus_10_signal minus_10_signal INSDC_feature:regulatory (broad), INSDC_qualifier:minus_10_signal (exact) +regulatory /regulatory_class minus_35_signal minus_35_signal INSDC_feature:regulatory (broad), INSDC_qualifier:minus_35_signal (exact) +regulatory /regulatory_class other regulatory_region INSDC_feature:regulatory (broad), INSDC_qualifier:other (exact) +regulatory /regulatory_class polyA_signal_sequence polyA_signal_sequence INSDC_feature:regulatory (broad), INSDC_qualifier:polyA_signal_sequence (exact) +regulatory /regulatory_class promoter promoter INSDC_feature:regulatory (broad), INSDC_qualifier:promoter (exact) +regulatory /regulatory_class recoding_stimulatory_region recoding_stimulatory_region INSDC_feature:regulatory (broad), INSDC_qualifier:recoding_stimulatory_region (exact) +regulatory /regulatory_class replication_regulatory_region replication_regulatory_region INSDC_feature:regulatory (broad), INSDC_qualifier:replication_regulatory_region (exact) +regulatory /regulatory_class response_element response_element INSDC_feature:regulatory (broad), INSDC_qualifier:response_element (exact) +regulatory /regulatory_class ribosome_binding_site ribosome_entry_site INSDC_feature:regulatory (broad),INSDC_qualifier:ribosome_binding_site (exact) +regulatory /regulatory_class riboswitch riboswitch INSDC_feature:regulatory (broad), INSDC_qualifier:riboswitch (exact) +regulatory /regulatory_class silencer silencer INSDC_feature:regulatory (broad), INSDC_qualifier:silencer (exact) +regulatory /regulatory_class TATA_box TATA_box INSDC_feature:regulatory (broad), INSDC_qualifier:TATA_box (exact) +regulatory /regulatory_class terminator terminator INSDC_feature:regulatory (broad), INSDC_qualifier:terminator (exact) +regulatory /regulatory_class transcriptional_cis_regulatory_region transcriptional_cis_regulatory_region INSDC_feature:regulatory (broad), INSDC_qualifier:transcriptional_cis_regulatory_region (exact) +rep_origin origin_of_replication INSDC_feature:rep_origin (exact) +repeat_region /rpt_type tandem tandem_repeat INSDC_feature:repeat_region (broad), INSDC_qualifier:tandem (exact) +repeat_region /rpt_type inverted inverted_repeat INSDC_feature:repeat_region (broad), INSDC_qualifier:inverted (exact) +repeat_region /rpt_type flanking flanking_repeat INSDC_feature:repeat_region (broad), INSDC_qualifier:flanking (exact) +repeat_region /rpt_type terminal terminal_repeat INSDC_feature:repeat_region (broad), INSDC_qualifier:terminal (exact) +repeat_region /rpt_type long_terminal_repeat long_terminal_repeat INSDC_feature:repeat_region (broad), INSDC_qualifier:long_terminal_repeat (exact) +repeat_region /rpt_type direct direct_repeat INSDC_feature:repeat_region (broad), INSDC_qualifier:direct (exact) +repeat_region /rpt_type dispersed dispersed_repeat INSDC_feature:repeat_region (broad), INSDC_qualifier:dispersed (exact) +repeat_region /rpt_type nested nested_repeat INSDC_feature:repeat_region (broad), INSDC_qualifier:nested (exact) +repeat_region /rpt_type non_ltr_retrotransposon_polymeric_tract non_LTR_retrotransposon_polymeric_tract INSDC_feature:repeat_region (broad),INSDC_qualifier:non_ltr_retrotransposon_polymeric_tract (exact) +repeat_region /rpt_type x_element_combinatorial_repeat X_element_combinatorial_repeat INSDC_feature:repeat_region (broad), INSDC_qualifier:x_element_combinatorial_repeat (exact) +repeat_region /rpt_type y_prime_element Y_prime_element INSDC_feature:repeat_region (broad), INSDC_qualifier:Y_prime_element (exact) +repeat_region /rpt_type telomeric_repeat telomeric_repeat INSDC_feature:repeat_region (broad), INSDC_qualifier:telomeric_repeat (exact) +repeat_region /rpt_type centromeric_repeat centromeric_repeat INSDC_feature:repeat_region (broad), INSDC_qualifier:centromeric_repeat (exact) +repeat_region /rpt_type other repeat_region INSDC_feature:repeat_region (broad), INSDC_qualifier:other (exact) +repeat_region /satellite satellite satellite_DNA INSDC_feature:repeat_region (broad), INSDC_qualifier:satellite (exact) +repeat_region /satellite microsatellite microsatellite INSDC_feature:repeat_region (broad), INSDC_qualifier:microsatellite (exact) +repeat_region /satellite minisatellite minisatellite INSDC_feature:repeat_region (broad), INSDC_qualifier:minisatellite (exact) +rRNA rRNA INSDC_feature:rRNA (exact) +rRNA /pseudo pseudogenic_rRNA INSDC_feature:rRNA (broad), INSDC_qualifier:pseudo (exact) +rRNA /pseudogene processed processed_pseudogenic_rRNA INSDC_feature:rRNA (broad), INSDC_qualifier:processed (exact) +rRNA /pseudogene unprocessed unprocessed_pseudogenic_rRNA INSDC_feature:rRNA (broad), INSDC_qualifier:unprocessed (exact) +rRNA /pseudogene unitary unitary_pseudogenic_rRNA INSDC_feature:rRNA (broad), INSDC_qualifier:unitary (exact) +rRNA /pseudogene allelic allelic_pseudogenic_rRNA INSDC_feature:rRNA (broad), INSDC_qualifier:allelic (exact) +rRNA /pseudogene unknown pseudogenic_rRNA INSDC_qualifier:unknown (broad) +S_region S_region INSDC_feature:S_region (exact) +sig_peptide signal_peptide INSDC_feature:sig_peptide (exact) +source sequence_source INSDC_feature:source (exact) +stem_loop stem_loop INSDC_feature:stem_loop (exact) +STS STS INSDC_feature:STS (exact) +telomere telomere INSDC_feature:telomere (exact) +tmRNA tmRNA INSDC_feature:tmRNA (exact) +transit_peptide transit_peptide INSDC_feature:transit_peptide (exact) +tRNA tRNA INSDC_feature:tRNA (exact) +tRNA /pseudo pseudogenic_tRNA INSDC_feature:tRNA (broad), INSDC_qualifier:pseudo (exact) +tRNA /pseudogene processed processed_pseudogenic_tRNA INSDC_feature:tRNA (broad), INSDC_qualifier:processed (exact) +tRNA /pseudogene unprocessed unprocessed_pseudogenic_tRNA INSDC_feature:tRNA (broad), INSDC_qualifier:unprocessed (exact) +tRNA /pseudogene unitary unitary_pseudogenic_tRNA INSDC_feature:tRNA (broad), INSDC_qualifier:unitary (exact) +tRNA /pseudogene allelic allelic_pseudogenic_tRNA INSDC_feature:tRNA (broad), INSDC_qualifier:allelic (exact) +tRNA /pseudogene unknown pseudogenic_tRNA INSDC_qualifier:unknown (broad) +tRNA /trans_splicing trans_spliced_transcript INSDC_feature:tRNA (broad), INSDC_qualifier:trans_splicing (exact) +unsure sequence_uncertainty INSDC_feature:unsure (exact) +V_region V_region INSDC_feature:V_region (exact) +V_segment V_gene_segment INSDC_feature:V_segment (exact) +variation sequence_alteration INSDC_feature:variation (exact)