Updated manual curation for misannotated genes

CHANGELOG.md

@@ -10,6 +10,12 @@
 
 ### Manual curation
 - argannot_curation: (Tet)tetH:EF460464:6286-7839:1554 was incorrectly annotated as ARO:3004797 which is a beta-lactamase due to a loose RGI hit. This was manually curated to ARO:3000175.
+- deeparg, megares, resfinderfg & sarg curation: ARO:3004445 -> ARO:3005440, this was due to a change in the ARO and the ARO number for the RSA2 gene changing. **db_harmonisation must change to take this into account**
+
+#### Incorrectly curated genes.
+- Previously, these were directly mapped to drug classes. Correct parent ARO term has now been given.
+- resfinder_curation: grdA_1_QJX10702 -> 3007380 & EstDL136_1_JN242251 -> 3000557
+- megares_curation: MEG_2865|Drugs|Phenicol|Chloramphenicol_hydrolase|ESTD -> 3000557
 
 ## 0.4.0 - 10 June
 

argnorm/data/manual_curation/deeparg_curation.tsv

@@ -1,13 +1,14 @@
 Original ID	ARO	Gene Name in CARD	Description
-CP000034.1.gene2198.p01|FEATURES|ompF|multidrug|ompF	3000265	porin OmpF	
-AAB08925|FEATURES|tetU|tetracycline|tetU	3004650	tet(U)	
-CP000647.1.gene2517.p01|FEATURES|ompF|multidrug|ompF	3000265	porin OmpF	
-gi:504720116:ref:WP_014907218.1:|FEATURES|ompF|multidrug|ompF	3000265	porin OmpF	
-AM180355.1.gene2260.p01|FEATURES|ermC|MLS|ermC	3000250	ErmC	
-gi:501976562:ref:WP_012681429.1:|FEATURES|cystathionine_beta-lyase_patB|unclassified|cystathionine_beta-lyase_patB	3000025	patB	
-gi:447201629:ref:WP_001278885.1:|FEATURES|cob(I)alamin_adenolsyltransferase|unclassified|cob(I)alamin_adenolsyltransferase	0010004	RND type drug efflux	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2696896/
-gi:489831097:ref:WP_003734834.1:|FEATURES|cystathionine_beta-lyase_patB|unclassified|cystathionine_beta-lyase_patB	3000025	patB	
-gi:685904080:ref:WP_031644138.1:|FEATURES|cystathionine_beta-lyase_patB|unclassified|cystathionine_beta-lyase_patB	3000025	patB	
-NP_253005.1|FEATURES|MvaT|multidrug|MvaT	3004069	MvaT	
-NP_417544.5|FEATURES|patA|fluoroquinolone|patA	3000024	patA	
-NP_416340.1|FEATURES|mgrB|multidrug|mgrB	3003820	mgrB	
+CP000034.1.gene2198.p01|FEATURES|ompF|multidrug|ompF	3000265	porin OmpF      	
+AAB08925|FEATURES|tetU|tetracycline|tetU	3004650	tet(U)  	
+CP000647.1.gene2517.p01|FEATURES|ompF|multidrug|ompF	3000265	porin OmpF  	
+gi:504720116:ref:WP_014907218.1:|FEATURES|ompF|multidrug|ompF	3000265	porin OmpF      	
+AM180355.1.gene2260.p01|FEATURES|ermC|MLS|ermC	3000250	ErmC    	
+gi:501976562:ref:WP_012681429.1:|FEATURES|cystathionine_beta-lyase_patB|unclassified|cystathionine_beta-lyase_patB	3000025	patB    	
+gi:447201629:ref:WP_001278885.1:|FEATURES|cob(I)alamin_adenolsyltransferase|unclassified|cob(I)alamin_adenolsyltransferase	10004	RND type drug efflux	https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2696896/
+gi:489831097:ref:WP_003734834.1:|FEATURES|cystathionine_beta-lyase_patB|unclassified|cystathionine_beta-lyase_patB	3000025	patB    	
+gi:685904080:ref:WP_031644138.1:|FEATURES|cystathionine_beta-lyase_patB|unclassified|cystathionine_beta-lyase_patB	3000025	patB    	
+NP_253005.1|FEATURES|MvaT|multidrug|MvaT	3004069	MvaT    	
+NP_417544.5|FEATURES|patA|fluoroquinolone|patA	3000024	patA    	
+NP_416340.1|FEATURES|mgrB|multidrug|mgrB	3003820	mgrB    	
+AUW34359.1|FEATURES|RSA-2|beta-lactam|RSA-2	3005440	RSA2 beta-lactamase	ARO number of RSA2 had been changed.

argnorm/data/manual_curation/megares_curation.tsv

@@ -1,7 +1,7 @@
 Original ID	ARO	Description
 MEG_8443|Drugs|Pleuromutilin|Pleuromutilin-resistant_23S_rRNA_mutation|P23S|RequiresSNPConfirmation	3005083	
 MEG_4060|Metals|Multi-metal_resistance|Multi-metal_resistance_protein|MREA		Metal resistance. No mapping
-MEG_2865|Drugs|Phenicol|Chloramphenicol_hydrolase|ESTD	3000387	
+MEG_2865|Drugs|Phenicol|Chloramphenicol_hydrolase|ESTD	3000557	
 MEG_1732|Drugs|Lipopeptides|Daptomycin-resistant_mutant|CLS|RequiresSNPConfirmation	3003092	
 MEG_2933|Drugs|Mycobacterium_tuberculosis-specific_Drug|Para-aminosalicylic_acid_resistant_mutant|FOLC|RequiresSNPConfirmation	3004157	
 MEG_8700|Multi-compound|Biocide_and_metal_resistance|Biocide_and_metal_ABC_efflux_pumps|SITABCD		Metal + Biocide resistance. No mapping
@@ -86,3 +86,4 @@ MEG_2429|Drugs|betalactams|Class_A_betalactamases|CTX	3001943
 MEG_5148|Drugs|betalactams|Class_D_betalactamases|OXA	3001555	
 MEG_7604|Drugs|Glycopeptides|VanD-type_accessory_protein|VANYD	3002957	
 MEG_8253|Drugs|MLS|Macrolide-resistant_23S_rRNA_mutation|MLS23S|RequiresSNPConfirmation	3004836	
+MEG_6148|Drugs|betalactams|Class_A_betalactamases|RSA	3005440	ARO number of RSA2 had been changed.

argnorm/data/manual_curation/resfinder_curation.tsv

@@ -9,7 +9,7 @@ VanC2XY_1_EU151754	glycopeptide resistance gene cluster VanC	3000246	https://www
 VanHAX_PT_1_DQ018710	glycopeptide resistance gene cluster VanA	3000236	https://www.ncbi.nlm.nih.gov/nuccore/DQ018710.1	5109-7715	Part of VanA cluster (ARO:3000236)
 VanHAX_PA_1_DQ018711	glycopeptide resistance gene cluster VanA	3000236	https://www.ncbi.nlm.nih.gov/nuccore/DQ018711.1?report=fasta	3168-5750	Part of VanA cluster (ARO:3000236)
 VanHAX_PT_2_AY926880	glycopeptide resistance gene cluster VanA	3000236	https://www.ncbi.nlm.nih.gov/nuccore/AY926880.2?report=fasta	2771-5377	Part of VanA cluster (ARO:3000236)
-dldHA2X_1_AL939117	D-Ala-D-Ala ligase	3003970	https://www.ncbi.nlm.nih.gov/nuccore/AL939117.1	53343-56013	
+dldHA2X_1_AL939117	D-Ala-D-Ala ligase	3003970	https://www.ncbi.nlm.nih.gov/nuccore/AL939117.1	53343-56013 	
 VanHBX_1_AF192329	glycopeptide resistance gene cluster VanB	3000238	https://www.ncbi.nlm.nih.gov/nuccore/AF192329	27871-30477	Part of VanB cluster (ARO:3000238)
 VanHBX_2_U35369	glycopeptide resistance gene cluster VanB	3000238	https://www.ncbi.nlm.nih.gov/nuccore/U35369.1?report=fasta	4007-6613	"Part of VanB cluster (ARO:3000238). Contains ARO:3002943, ARO:3002950"
 VanC4XY_1_EU151752	glycopeptide resistance gene cluster VanC	3000246	https://www.ncbi.nlm.nih.gov/nuccore/EU151752.1?report=fasta	29-1650	Part of VanC cluster (ARO:3000246)
@@ -45,6 +45,6 @@ qepA1_1_AB263754	QepA2	3004103			Reverse complement in resfinder db.
 tet(43)_1_GQ244501	tet(43)	3000573			Reverse complement in resfinder db.
 blaSPG-1_1_KP109680	SPG-1	3003720			
 blaBIM-1_1_CP016446	BlaB	3004201			
-grdA_1_QJX10702		3007382			Parent ARO mapping
+grdA_1_QJX10702		3007380			Parent ARO mapping
 aac(3)-I_1_AJ877225	AAC(3)-I	3007384			
-EstDL136_1_JN242251		3000387			Parent ARO mapping
+EstDL136_1_JN242251		3000557			Parent ARO mapping

argnorm/data/manual_curation/resfinderfg_curation.tsv

@@ -1,2 +1,4 @@
-Original ID	ARO	Gene Name in CARD
-UDP-N-acetylmuramoyl-tripeptide--D-alanyl-D-alanine ligase|KF629588.1|pediatric_fecal_sample|CYC	3003970	D-Ala-D-Ala ligase
+Original ID	ARO	Gene Name in CARD	Description
+UDP-N-acetylmuramoyl-tripeptide--D-alanyl-D-alanine ligase|KF629588.1|pediatric_fecal_sample|CYC	3003970	D-Ala-D-Ala ligase	
+Beta-lactamase OXA-1|KU544700.1|sewage|CAZ	3005440	RSA2 beta-lactamase	ARO number of RSA2 had been changed.
+Beta-lactamase OXA-1|MG739504.1|river|AMP	3005440	RSA2 beta-lactamase	ARO number of RSA2 had been changed.

argnorm/data/manual_curation/sarg_curation.tsv

@@ -1,3 +1,4 @@
-Original ID	ARO	Gene Name in CARD
-gb|AAG57600.1|ARO:3000318|mphB	3000318	mphB
-AM180355.1.gene2260.p01	3000250	ErmC
+Original ID	ARO	Gene Name in CARD	Description
+gb|AAG57600.1|ARO:3000318|mphB	3000318	mphB	
+AM180355.1.gene2260.p01	3000250	ErmC	
+gb|AUW34359.1|ARO:3004445|RSA-2	3005440	RSA2 beta-lactamase	ARO number of RSA2 had been changed.