Add tests in test_arg_category for genes that require regulates, …

…`part_of`, or `participates_in` ARO relationships to be mapped to drugs Added ARO:3003548, ARO:3000826, and ARO:3003066 to 'test_confers_resistance_to()` in `test_arg_category.py`. These were previously not mapped to any drugs. Also updated example outputs in the `outputs` directory to reflect update drug categorization. Several genes are now actually mapped to drugs rather than being directly mapped to drug classes with `confers_resistance_to()`.
BigDataBiology · Jan 27, 2025 · 614ad55 · 614ad55
1 parent c66c3a9
commit 614ad55
Show file tree

Hide file tree

Showing 12 changed files with 3,686 additions and 3,680 deletions.
diff --git a/outputs/hamronized/abricate.argannot.tsv b/outputs/hamronized/abricate.argannot.tsv
diff --git a/outputs/hamronized/abricate.megares.tsv b/outputs/hamronized/abricate.megares.tsv
diff --git a/outputs/hamronized/abricate.ncbi.tsv b/outputs/hamronized/abricate.ncbi.tsv
diff --git a/outputs/hamronized/abricate.resfinderfg.tsv b/outputs/hamronized/abricate.resfinderfg.tsv
diff --git a/outputs/hamronized/amrfinderplus.ncbi.orfs.tsv b/outputs/hamronized/amrfinderplus.ncbi.orfs.tsv
@@ -1,7 +1,7 @@
 # argNorm version: 0.6.0
 input_file_name	gene_symbol	gene_name	reference_database_name	reference_database_version	reference_accession	analysis_software_name	analysis_software_version	genetic_variation_type	antimicrobial_agent	coverage_percentage	coverage_depth	coverage_ratio	drug_class	input_gene_length	input_gene_start	input_gene_stop	input_protein_length	input_protein_start	input_protein_stop	input_sequence_id	nucleotide_mutation	nucleotide_mutation_interpretation	predicted_phenotype	predicted_phenotype_confidence_level	amino_acid_mutation	amino_acid_mutation_interpretation	reference_gene_length	reference_gene_start	reference_gene_stop	reference_protein_length	reference_protein_start	reference_protein_stop	resistance_mechanism	strand_orientation	sequence_identity	ARO	confers_resistance_to	resistance_to_drug_classes
 amrfinderplus.ncbi.orfs.tsv	tet(40)	tetracycline efflux MFS transporter Tet(40)	NCBI Reference Gene Database	2023-Nov-01	WP_009247026.1	amrfinderplus	3.10.30	gene_presence_detected	TETRACYCLINE	100.0			TETRACYCLINE		160	1377	406			k119_2904										406				+	99.51	ARO:3000567	ARO:0000051	ARO:3000050
-amrfinderplus.ncbi.orfs.tsv	vanH-D	D-lactate dehydrogenase VanH-D	NCBI Reference Gene Database	2023-Nov-01	WP_063856705.1	amrfinderplus	3.10.30	gene_presence_detected	VANCOMYCIN	54.8			GLYCOPEPTIDE		12	542	177			k119_33901										323				-	100.0	ARO:3002944	ARO:3000081	ARO:3000081
+amrfinderplus.ncbi.orfs.tsv	vanH-D	D-lactate dehydrogenase VanH-D	NCBI Reference Gene Database	2023-Nov-01	WP_063856705.1	amrfinderplus	3.10.30	gene_presence_detected	VANCOMYCIN	54.8			GLYCOPEPTIDE		12	542	177			k119_33901										323				-	100.0	ARO:3002944	ARO:0000028,ARO:0000029	ARO:3000081,ARO:3000081
 amrfinderplus.ncbi.orfs.tsv	tet(Q)	tetracycline resistance ribosomal protection protein Tet(Q)	NCBI Reference Gene Database	2023-Nov-01	WP_063856407.1	amrfinderplus	3.10.30	gene_presence_detected	TETRACYCLINE	100.0			TETRACYCLINE		11179	13101	641			k119_36643										641				+	99.38	ARO:3000191	ARO:0000051,ARO:0000069,ARO:3000152,ARO:3000528,ARO:3000667,ARO:3000668	ARO:3000050,ARO:3000050,ARO:3000050,ARO:3000050,ARO:3000050,ARO:3000050
 amrfinderplus.ncbi.orfs.tsv	bexA	multidrug efflux MATE transporter BexA	NCBI Reference Gene Database	2023-Nov-01	BAB64566.1	amrfinderplus	3.10.30	gene_presence_detected	EFFLUX	80.36			EFFLUX		18	1085	356			k119_41685										443				-	92.98	ARO:3003953	ARO:0000045,ARO:3000662	ARO:0000001,ARO:3005386
 amrfinderplus.ncbi.orfs.tsv	lnu(C)	lincosamide nucleotidyltransferase Lnu(C)	NCBI Reference Gene Database	2023-Nov-01	WP_063851341.1	amrfinderplus	3.10.30	gene_presence_detected	LINCOSAMIDE	100.0			LINCOSAMIDE		234	725	164			k119_46979										164				-	97.56	ARO:3002837	ARO:0000046	ARO:0000017

diff --git a/outputs/hamronized/args-oap.sarg.reads.tsv b/outputs/hamronized/args-oap.sarg.reads.tsv
diff --git a/outputs/hamronized/deeparg.deeparg.orfs.tsv b/outputs/hamronized/deeparg.deeparg.orfs.tsv
diff --git a/outputs/raw/abricate.megares.tsv b/outputs/raw/abricate.megares.tsv
@@ -1,7 +1,7 @@
 # argNorm version: 0.6.0
 #FILE	SEQUENCE	START	END	STRAND	GENE	COVERAGE	COVERAGE_MAP	GAPS	%COVERAGE	%IDENTITY	DATABASE	ACCESSION	PRODUCT	RESISTANCE	ARO	confers_resistance_to	resistance_to_drug_classes
 GMGC10.wastewater.95nr.test_10k.fna.gz_block_0001.fna.gz	GMGC10.015_877_632.UNKNOWN	14	300	-	QACEDELTA1	61-348/348	..======/======	1/1	82.47	99.65	megares	MEG_5829	Multi-compound:Drug_and_biocide_resistance:Drug_and_biocide_SMR_efflux_pumps:QACEDELTA1				
-GMGC10.wastewater.95nr.test_10k.fna.gz_block_0004.fna.gz	GMGC10.007_463_324.HNS	1	414	+	HNS	1-414/414	===============	0/0	100.0	96.38	megares	MEG_3271	Drugs:Multi-drug_resistance:Multi-drug_RND_efflux_pumps:HNS		ARO:3000676		
+GMGC10.wastewater.95nr.test_10k.fna.gz_block_0004.fna.gz	GMGC10.007_463_324.HNS	1	414	+	HNS	1-414/414	===============	0/0	100.0	96.38	megares	MEG_3271	Drugs:Multi-drug_resistance:Multi-drug_RND_efflux_pumps:HNS		ARO:3000676	ARO:0000006,ARO:0000011,ARO:0000032,ARO:0000036,ARO:0000051,ARO:0000056,ARO:3000008,ARO:3000662	ARO:0000000,ARO:0000001,ARO:0000001,ARO:3000007,ARO:3000007,ARO:3000007,ARO:3000007,ARO:3000050
 GMGC10.wastewater.95nr.test_10k.fna.gz_block_0005.fna.gz	GMGC10.005_321_079.HYFJ	1	477	+	MPHB	1-477/477	===============	0/0	100.0	97.69	megares	MEG_4033	Drugs:MLS:Macrolide_phosphotransferases:MPHB		ARO:3000318	ARO:0000006,ARO:0000027,ARO:0000057,ARO:0000065,ARO:3000145,ARO:3000156,ARO:3000158,ARO:3000176,ARO:3000867	ARO:0000000,ARO:0000000,ARO:0000000,ARO:0000000,ARO:0000000,ARO:0000000,ARO:0000000,ARO:0000000,ARO:0000000
 GMGC10.wastewater.95nr.test_10k.fna.gz_block_0005.fna.gz	GMGC10.043_155_950.EMRE	106	453	+	QACEDELTA1	1-348/348	===============	0/0	100.0	100.0	megares	MEG_5829	Multi-compound:Drug_and_biocide_resistance:Drug_and_biocide_SMR_efflux_pumps:QACEDELTA1				
 GMGC10.wastewater.95nr.test_10k.fna.gz_block_0006.fna.gz	GMGC10.034_105_239.FOLA	1	498	+	DFRA	1-498/498	===============	0/0	100.0	99.8	megares	MEG_2551	Drugs:Trimethoprim:Dihydrofolate_reductase:DFRA		ARO:3002858	ARO:3000188	ARO:3000171

diff --git a/outputs/raw/amrfinderplus.ncbi.orfs.tsv b/outputs/raw/amrfinderplus.ncbi.orfs.tsv
@@ -1,7 +1,7 @@
 # argNorm version: 0.6.0
 Protein identifier	Contig id	Start	Stop	Strand	Gene symbol	Sequence name	Scope	Element type	Element subtype	Class	Subclass	Method	Target length	Reference sequence length	% Coverage of reference sequence	% Identity to reference sequence	Alignment length	Accession of closest sequence	Name of closest sequence	HMM id	HMM description	ARO	confers_resistance_to	resistance_to_drug_classes
 	k119_2904	160	1377	+	tet(40)	tetracycline efflux MFS transporter Tet(40)	core	AMR	AMR	TETRACYCLINE	TETRACYCLINE	BLASTX	406	406	100.0	99.51	406	WP_009247026.1	tetracycline efflux MFS transporter Tet(40)			ARO:3000567	ARO:0000051	ARO:3000050
-	k119_33901	12	542	-	vanH-D	D-lactate dehydrogenase VanH-D	core	AMR	AMR	GLYCOPEPTIDE	VANCOMYCIN	PARTIAL_CONTIG_ENDX	177	323	54.8	100.0	177	WP_063856705.1	D-lactate dehydrogenase VanH-D			ARO:3002944	ARO:3000081	ARO:3000081
+	k119_33901	12	542	-	vanH-D	D-lactate dehydrogenase VanH-D	core	AMR	AMR	GLYCOPEPTIDE	VANCOMYCIN	PARTIAL_CONTIG_ENDX	177	323	54.8	100.0	177	WP_063856705.1	D-lactate dehydrogenase VanH-D			ARO:3002944	ARO:0000028,ARO:0000029	ARO:3000081,ARO:3000081
 	k119_36643	11179	13101	+	tet(Q)	tetracycline resistance ribosomal protection protein Tet(Q)	core	AMR	AMR	TETRACYCLINE	TETRACYCLINE	BLASTX	641	641	100.0	99.38	641	WP_063856407.1	tetracycline resistance ribosomal protection protein Tet(Q)			ARO:3000191	ARO:0000051,ARO:0000069,ARO:3000152,ARO:3000528,ARO:3000667,ARO:3000668	ARO:3000050,ARO:3000050,ARO:3000050,ARO:3000050,ARO:3000050,ARO:3000050
 	k119_41685	18	1085	-	bexA	multidrug efflux MATE transporter BexA	plus	AMR	AMR	EFFLUX	EFFLUX	PARTIALX	356	443	80.36	92.98	356	BAB64566.1	multidrug efflux MATE transporter BexA			ARO:3003953	ARO:0000045,ARO:3000662	ARO:0000001,ARO:3005386
 	k119_46979	234	725	-	lnu(C)	lincosamide nucleotidyltransferase Lnu(C)	core	AMR	AMR	LINCOSAMIDE	LINCOSAMIDE	BLASTX	164	164	100.0	97.56	164	WP_063851341.1	lincosamide nucleotidyltransferase Lnu(C)			ARO:3002837	ARO:0000046	ARO:0000017