Add Deep learning Eco code and update xref from TIGRFAMs to NCBIfam

ebi-uniprot · Sep 22, 2023 · f9dc5bc · f9dc5bc
1 parent c3f6bdc
commit f9dc5bc
Show file tree

Hide file tree

Showing 20 changed files with 30 additions and 25 deletions.
diff --git a/controlled-vocabulary/src/main/resources/META-INF/drlineconfiguration.json b/controlled-vocabulary/src/main/resources/META-INF/drlineconfiguration.json
@@ -1742,8 +1742,8 @@
 		]
 	},
 	{
-		"name": "TIGRFAMs",
-		"displayName": "TIGRFAMs",
+		"name": "NCBIfam",
+		"displayName": "NCBIfam",
 		"category": "FMD",
 		"uriLink": "https://www.ncbi.nlm.nih.gov/genome/annotation_prok/evidence/%id/",
 		"attributes": [		

diff --git a/controlled-vocabulary/src/test/resources/xdb/dr_ord b/controlled-vocabulary/src/test/resources/xdb/dr_ord
@@ -160,5 +160,5 @@ PRINTS 2
 SFLD 1
 SMART 2
 SUPFAM 2
-TIGRFAMs 2
+NCBIfam 2
 PROSITE 2
diff --git a/core-domain/src/main/java/org/uniprot/core/uniparc/SignatureDbType.java b/core-domain/src/main/java/org/uniprot/core/uniparc/SignatureDbType.java
@@ -17,7 +17,7 @@ public enum SignatureDbType implements EnumDisplay {
     SFLD("SFLD"),
     SMART("SMART"),
     SUPFAM("SUPFAM"),
-    TIGRFAMS("TIGRFAMs");
+    NCBIFAM("NCBIfam");
 
     private final String name;
 

diff --git a/core-domain/src/main/java/org/uniprot/core/uniprotkb/evidence/EvidenceCode.java b/core-domain/src/main/java/org/uniprot/core/uniprotkb/evidence/EvidenceCode.java
@@ -255,8 +255,13 @@ public enum EvidenceCode implements EnumDisplay {
             "Combinatorial",
             "combinatorial computational and experimental evidence used in automatic assertion",
             Collections.singletonList("Combined sources"),
-            EnumSet.of(Category.AUTOMATIC)); // replacing ECO_0000213
-    // from 2021.2 release
+            EnumSet.of(Category.AUTOMATIC)), // replacing ECO_0000213
+
+    ECO_0008006("ECO:0008006",
+            "Deep learning",
+            "deep learning method evidence used in automatic assertion",
+            Collections.singletonList("Automatic Annotation"),
+            EnumSet.of(Category.AUTOMATIC));
 
     private final String code;
     private final String name;

diff --git a/core-parser/src/main/java/org/uniprot/core/parser/tsv/uniparc/UniParcSequenceFeatureMap.java b/core-parser/src/main/java/org/uniprot/core/parser/tsv/uniparc/UniParcSequenceFeatureMap.java
@@ -30,7 +30,7 @@ public class UniParcSequenceFeatureMap implements NamedValueMap {
                             "SFLD",
                             "SMART",
                             "SUPFAM",
-                            "TIGRFAMs"));
+                            "NCBIfam"));
 
     private final List<SequenceFeature> features;
 
@@ -56,7 +56,7 @@ public Map<String, String> attributeValues() {
         map.put(FIELDS.get(10), getData(SignatureDbType.SFLD));
         map.put(FIELDS.get(11), getData(SignatureDbType.SMART));
         map.put(FIELDS.get(12), getData(SignatureDbType.SUPFAM));
-        map.put(FIELDS.get(13), getData(SignatureDbType.TIGRFAMS));
+        map.put(FIELDS.get(13), getData(SignatureDbType.NCBIFAM));
 
         return map;
     }

diff --git a/...rser/src/test/java/org/uniprot/core/parser/tsv/uniparc/UniParcSequenceFeatureMapTest.java b/...rser/src/test/java/org/uniprot/core/parser/tsv/uniparc/UniParcSequenceFeatureMapTest.java
@@ -59,7 +59,7 @@ void testFields() {
                         "SFLD",
                         "SMART",
                         "SUPFAM",
-                        "TIGRFAMs");
+                        "NCBIfam");
         assertEquals(UniParcSequenceFeatureMap.FIELDS, fields);
     }
 

diff --git a/ff-parser/src/test/resources/entryIT/A0A176EY13.txl b/ff-parser/src/test/resources/entryIT/A0A176EY13.txl
@@ -39,8 +39,8 @@ DR   Pfam; PF00590; TP_methylase; 1.
 DR   PIRSF; PIRSF036428; CobL; 1.
 DR   SUPFAM; SSF53335; SSF53335; 1.
 DR   SUPFAM; SSF53790; SSF53790; 1.
-DR   TIGRFAMs; TIGR02467; CbiE; 1.
-DR   TIGRFAMs; TIGR02469; CbiT; 1.
+DR   NCBIfam; NF02467; CbiE; 1.
+DR   NCBIfam; NF02469; CbiT; 1.
 PE   4: Predicted;
 KW   Complete proteome {ECO:0000313|Proteomes:UP000077043};
 KW   Methyltransferase {ECO:0000313|EMBL:KZY30980.1};

diff --git a/ff-parser/src/test/resources/entryIT/A0A2D8TK40.txl b/ff-parser/src/test/resources/entryIT/A0A2D8TK40.txl
@@ -35,7 +35,7 @@ DR   Pfam; PF00394; Cu-oxidase; 1.
 DR   Pfam; PF07731; Cu-oxidase_2; 1.
 DR   Pfam; PF07732; Cu-oxidase_3; 1.
 DR   SUPFAM; SSF49503; SSF49503; 3.
-DR   TIGRFAMs; TIGR01409; TAT_signal_seq; 1.
+DR   NCBIfam; NF01409; TAT_signal_seq; 1.
 DR   PROSITE; PS00080; MULTICOPPER_OXIDASE2; 1.
 DR   PROSITE; PS51318; TAT; 1.
 PE   4: Predicted;

diff --git a/ff-parser/src/test/resources/entryIT/A8EZU1.dat b/ff-parser/src/test/resources/entryIT/A8EZU1.dat
@@ -56,7 +56,7 @@ DR   InterPro; IPR023091; MetalPrtase_cat_dom_sf_prd.
 DR   InterPro; IPR002036; YbeY.
 DR   InterPro; IPR020549; YbeY_CS.
 DR   Pfam; PF02130; YbeY; 1.
-DR   TIGRFAMs; TIGR00043; TIGR00043; 1.
+DR   NCBIfam; NF00043; NF00043; 1.
 DR   PROSITE; PS01306; UPF0054; 1.
 PE   3: Inferred from homology;
 KW   Cytoplasm; Endonuclease; Hydrolase; Metal-binding; Nuclease;

diff --git a/ff-parser/src/test/resources/entryIT/A8EZU1_D6RDV7.dat b/ff-parser/src/test/resources/entryIT/A8EZU1_D6RDV7.dat
@@ -56,7 +56,7 @@ DR   InterPro; IPR023091; MetalPrtase_cat_dom_sf_prd.
 DR   InterPro; IPR002036; YbeY.
 DR   InterPro; IPR020549; YbeY_CS.
 DR   Pfam; PF02130; YbeY; 1.
-DR   TIGRFAMs; TIGR00043; TIGR00043; 1.
+DR   NCBIfam; NF00043; NF00043; 1.
 DR   PROSITE; PS01306; UPF0054; 1.
 PE   3: Inferred from homology;
 KW   Cytoplasm; Endonuclease; Hydrolase; Metal-binding; Nuclease;

diff --git a/ff-parser/src/test/resources/entryIT/A8EZU1_D6RDV7.dat.gz b/ff-parser/src/test/resources/entryIT/A8EZU1_D6RDV7.dat.gz
diff --git a/ff-parser/src/test/resources/entryIT/A8EZU1_ERROR_D6RDV7.dat b/ff-parser/src/test/resources/entryIT/A8EZU1_ERROR_D6RDV7.dat
@@ -56,7 +56,7 @@ DR   InterPro; IPR023091; MetalPrtase_cat_dom_sf_prd.
 DR   InterPro; IPR002036; YbeY.
 DR   InterPro; IPR020549; YbeY_CS.
 DR   Pfam; PF02130; YbeY; 1.
-DR   TIGRFAMs; TIGR00043; TIGR00043; 1.
+DR   NCBIfam; NF00043; NF00043; 1.
 DR   PROSITE; PS01306; UPF0054; 1.
 PE   3: Inferred from homology;
 KW   Cytoplasm; Endonuclease; Hydrolase; Metal-binding; Nuclease;
@@ -142,7 +142,7 @@ DR   InterPro; IPR023091; MetalPrtase_cat_dom_sf_prd.
 DR   InterPro; IPR002036; YbeY.
 DR   InterPro; IPR020549; YbeY_CS.
 DR   Pfam; PF02130; UPF0054; 1.
-DR   TIGRFAMs; TIGR00043; TIGR00043; 1.
+DR   NCBIfam; NF00043; NF00043; 1.
 DR   PROSITE; PS01306; UPF0054; 1.
 PE   3: Inferred from homology;
 KW   Complete proteome; Cytoplasm; Endonuclease; Hydrolase; Metal-binding;

diff --git a/ff-parser/src/test/resources/entryIT/A9N0W4.txl b/ff-parser/src/test/resources/entryIT/A9N0W4.txl
@@ -36,7 +36,7 @@ DR   InterPro; IPR001150; Gly_radical.
 DR   InterPro; IPR011140; Glycyl_radical_cofactor_GrcA.
 DR   Pfam; PF01228; Gly_radical; 1.
 DR   PIRSF; PIRSF000378; Gly_radicl_yfiD; 1.
-DR   TIGRFAMs; TIGR04365; spare_glycyl; 1.
+DR   NCBIfam; NF04365; spare_glycyl; 1.
 DR   PROSITE; PS00850; GLY_RADICAL_1; 1.
 DR   PROSITE; PS51149; GLY_RADICAL_2; 1.
 PE   3: Inferred from homology;

diff --git a/ff-parser/src/test/resources/entryIT/ERROR_ERROR.dat b/ff-parser/src/test/resources/entryIT/ERROR_ERROR.dat
@@ -56,7 +56,7 @@ DR   InterPro; IPR023091; MetalPrtase_cat_dom_sf_prd.
 DR   InterPro; IPR002036; YbeY.
 DR   InterPro; IPR020549; YbeY_CS.
 DR   Pfam; PF02130; UPF0054; 1.
-DR   TIGRFAMs; TIGR00043; TIGR00043; 1.
+DR   NCBIfam; NF00043; NF00043; 1.
 DR   PROSITE; PS01306; UPF0054; 1.
 PE   3: Inferred from homology;
 KW   Complete proteome; Cytoplasm; Endonuclease; Hydrolase; Metal-binding;
@@ -136,7 +136,7 @@ DR   InterPro; IPR023091; MetalPrtase_cat_dom_sf_prd.
 DR   InterPro; IPR002036; YbeY.
 DR   InterPro; IPR020549; YbeY_CS.
 DR   Pfam; PF02130; UPF0054; 1.
-DR   TIGRFAMs; TIGR00043; TIGR00043; 1.
+DR   NCBIfam; NF00043; NF00043; 1.
 DR   PROSITE; PS01306; UPF0054; 1.
 PE   3: Inferred from homology;
 KW   Complete proteome; Cytoplasm; Endonuclease; Hydrolase; Metal-binding;

diff --git a/ff-parser/src/test/resources/entryIT/O05204.dat b/ff-parser/src/test/resources/entryIT/O05204.dat
@@ -76,7 +76,7 @@ DR   Pfam; PF13192; Thioredoxin_3; 1.
 DR   PIRSF; PIRSF000238; AhpF; 1.
 DR   SUPFAM; SSF51905; SSF51905; 1.
 DR   SUPFAM; SSF52833; SSF52833; 2.
-DR   TIGRFAMs; TIGR03140; AhpF; 1.
+DR   NCBIfam; NF03140; AhpF; 1.
 DR   PROSITE; PS51354; GLUTAREDOXIN_2; 1.
 DR   PROSITE; PS00573; PYRIDINE_REDOX_2; 1.
 PE   3: Inferred from homology;

diff --git a/ff-parser/src/test/resources/entryIT/P55301.dat b/ff-parser/src/test/resources/entryIT/P55301.dat
@@ -97,7 +97,7 @@ DR   Pfam; PF01913; FTR; 1.
 DR   Pfam; PF02741; FTR_C; 1.
 DR   PIRSF; PIRSF006414; Ftr_formyl_trnsf; 1.
 DR   SUPFAM; SSF55112; SSF55112; 2.
-DR   TIGRFAMs; TIGR03119; one_C_fhcD; 1.
+DR   NCBIfam; NF03119; one_C_fhcD; 1.
 PE   1: Evidence at protein level;
 KW   3D-structure; Acyltransferase; Complete proteome; Cytoplasm;
 KW   Direct protein sequencing; Methanogenesis; One-carbon metabolism;

diff --git a/ff-parser/src/test/resources/entryIT/Q04664.dat b/ff-parser/src/test/resources/entryIT/Q04664.dat
@@ -101,7 +101,7 @@ DR   GO; GO:0000271; P:polysaccharide biosynthetic process; IEA:UniProtKB-KW.
 DR   InterPro; IPR003362; Bact_transf.
 DR   InterPro; IPR017475; EPS_sugar_tfrase.
 DR   Pfam; PF02397; Bac_transf; 1.
-DR   TIGRFAMs; TIGR03025; EPS_sugtrans; 1.
+DR   NCBIfam; NF03025; EPS_sugtrans; 1.
 PE   3: Inferred from homology;
 KW   Capsule biogenesis/degradation; Cell membrane; Complete proteome;
 KW   Exopolysaccharide synthesis; Membrane; Transferase; Transmembrane;

diff --git a/ff-parser/src/test/resources/entryIT/Q1MS15.txl b/ff-parser/src/test/resources/entryIT/Q1MS15.txl
@@ -61,7 +61,7 @@ DR   InterPro; IPR036467; LS/RS_sf.
 DR   PANTHER; PTHR21058; PTHR21058; 1.
 DR   Pfam; PF00885; DMRL_synthase; 1.
 DR   SUPFAM; SSF52121; SSF52121; 1.
-DR   TIGRFAMs; TIGR00114; lumazine-synth; 1.
+DR   NCBIfam; NF00114; lumazine-synth; 1.
 PE   3: Inferred from homology;
 KW   Reference proteome; Riboflavin biosynthesis; Transferase.
 FT   CHAIN           1..157

diff --git a/ff-parser/src/test/resources/entryIT/Q32K04.dat b/ff-parser/src/test/resources/entryIT/Q32K04.dat
@@ -77,7 +77,7 @@ DR   Pfam; PF02875; Mur_ligase_C; 1.
 DR   Pfam; PF08245; Mur_ligase_M; 1.
 DR   SUPFAM; SSF53244; SSF53244; 1.
 DR   SUPFAM; SSF53623; SSF53623; 1.
-DR   TIGRFAMs; TIGR01087; murD; 1.
+DR   NCBIfam; NF01087; murD; 1.
 **   PROSITE; PS00012; PHOSPHOPANTETHEINE; 1; FALSE_POS.
 **   PROSITE; PS51257; PROKAR_LIPOPROTEIN; 1; FALSE_POS.
 PE   3: Inferred from homology;

diff --git a/ff-parser/src/test/resources/entryIT/Q66GB9.txl b/ff-parser/src/test/resources/entryIT/Q66GB9.txl
@@ -55,7 +55,7 @@ DR   PANTHER; PTHR36918; PTHR36918; 1.
 DR   Pfam; PF02556; SecB; 1.
 DR   PRINTS; PR01594; SECBCHAPRONE.
 DR   SUPFAM; SSF54611; SSF54611; 1.
-DR   TIGRFAMs; TIGR00809; secB; 1.
+DR   NCBIfam; NF00809; secB; 1.
 PE   3: Inferred from homology;
 KW   Chaperone; Complete proteome; Cytoplasm; Protein transport; Translocation;
 KW   Transport.