hamronized resfinder.resfinder.orfs.tsv from raw directory. changed i…

…nput gene col for hamronized in normalizers

argnorm/normalizers.py

@@ -275,7 +275,7 @@ def _set_input_gene_col(self):
         Always adapt this method to the input data format.
         """
         if self.is_hamronized:
-            self._input_gene_col = ''  # TODO add here.
+            self._input_gene_col = 'gene_symbol'  # TODO add here.
         else:
             self._input_gene_col = 'Accession no.'
 

docs/index.md

@@ -2,7 +2,7 @@
 
 [![Python package](https://github.com/BigDataBiology/argNorm/actions/workflows/python-package.yml/badge.svg)](https://github.com/BigDataBiology/argNorm/actions/workflows/python-package.yml)
 [![Downloads](https://pepy.tech/badge/argNorm)](https://pepy.tech/project/argNorm)
-![](https://img.shields.io/badge/status-alpha-red?style=flat) 
+![](https://img.shields.io/badge/status-alpha-red?style=flat)
 
 Antibiotic resistance gene (ARG) normalization by mapping to the [antibiotic resistance ontology (ARO)](https://obofoundry.org/ontology/aro.html) by CARD.
 
@@ -15,7 +15,7 @@ Thus, `argNorm` normalizes the _output vocabulary_ of these tools by mapping all
 
 This is a beta-quality implementation (subject to changes and some bugs may remain), but you're welcomed to try it and provide feedback.
 
-We welcome your feedback on the [Issues Page](https://github.com/BigDataBiology/argNorm/issues). 
+We welcome your feedback on the [Issues Page](https://github.com/BigDataBiology/argNorm/issues).
 
 ## Supported tools
 
@@ -83,4 +83,4 @@ argnorm resfinder -i examples/raw/resfinder.resfinder.reads.tsv -o outputs/raw/r
 
 argnorm amrfinderplus -i examples/raw/amrfinderplus.ncbi.orfs.tsv -o outputs/raw/amrfinderplus.ncbi.orfs.tsv
 
-```
+```

examples/hamronized/resfinder.resfinder.orfs.tsv

@@ -0,0 +1,14 @@
+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
+resfinder.resfinder.orfs.tsv	aph(3')-III	aph(3')-III	resfinder	4.1.0	M26832	resfinder	0.0.1	gene_presence_detected		100.0			Aminoglycoside resistance		204	998				k119_48139 flag=1 multi=7.0000 len=1034							795							+	100.0
+resfinder.resfinder.orfs.tsv	ant(6)-Ia	ant(6)-Ia	resfinder	4.1.0	KF864551	resfinder	0.0.1	gene_presence_detected		100.0			Aminoglycoside resistance		617	1483				k119_64006 flag=0 multi=37.0000 len=1517							867							-	100.0
+resfinder.resfinder.orfs.tsv	erm(B)	erm(B)	resfinder	4.1.0	U18931	resfinder	0.0.1	gene_presence_detected		100.0			Macrolide resistance		24647	25384				k119_84636 flag=0 multi=44.9396 len=29273							738							+	100.0
+resfinder.resfinder.orfs.tsv	lnu(C)	lnu(C)	resfinder	4.1.0	AY928180	resfinder	0.0.1	gene_presence_detected		100.0			Lincosamide resistance		231	725				k119_46979 flag=1 multi=6.0000 len=2214							495							+	98.99
+resfinder.resfinder.orfs.tsv	erm(F)	erm(F)	resfinder	4.1.0	M17808	resfinder	0.0.1	gene_presence_detected		100.0			Macrolide resistance		73	873				k119_66841 flag=0 multi=55.0000 len=875							801							+	100.0
+resfinder.resfinder.orfs.tsv	cat	cat	resfinder	4.1.0	M35190	resfinder	0.0.1	gene_presence_detected		100.0			Phenicol resistance		1975	2598				k119_95290 flag=3 multi=26.0047 len=5640							624							+	96.96
+resfinder.resfinder.orfs.tsv	tet(Q)	tet(Q)	resfinder	4.1.0	L33696	resfinder	0.0.1	gene_presence_detected		99.94807892004154			Tetracycline resistance		8574	10499				k119_48273 flag=0 multi=99.8140 len=13795							1927							-	90.61
+resfinder.resfinder.orfs.tsv	tet(X)	tet(X)	resfinder	4.1.0	M37699	resfinder	0.0.1	gene_presence_detected		100.0			Tetracycline resistance		12370	13536				k119_48273 flag=0 multi=99.8140 len=13795							1167							+	99.91
+resfinder.resfinder.orfs.tsv	tet(O)	tet(O)	resfinder	4.1.0	M20925	resfinder	0.0.1	gene_presence_detected		100.0			Tetracycline resistance		978	2897				k119_60190 flag=1 multi=13.0000 len=3573							1920							-	99.43
+resfinder.resfinder.orfs.tsv	tet(Q)	tet(Q)	resfinder	4.1.0	L33696	resfinder	0.0.1	gene_presence_detected		100.0			Tetracycline resistance		11179	13104				k119_36643 flag=0 multi=62.4691 len=39287							1926							+	99.69
+resfinder.resfinder.orfs.tsv	tet(32)	tet(32)	resfinder	4.1.0	EF626943	resfinder	0.0.1	gene_presence_detected		100.0			Tetracycline resistance		121	2040				k119_69070 flag=0 multi=12.9788 len=11428							1920							+	99.74
+resfinder.resfinder.orfs.tsv	tet(W)	tet(W)	resfinder	4.1.0	AJ427422	resfinder	0.0.1	gene_presence_detected		100.0			Tetracycline resistance		21199	23118				k119_9485 flag=0 multi=25.2509 len=23983							1920							+	100.0
+resfinder.resfinder.orfs.tsv	tet(40)	tet(40)	resfinder	4.1.0	FJ158002	resfinder	0.0.1	gene_presence_detected		100.0			Tetracycline resistance		160	1380				k119_2904 flag=1 multi=9.0000 len=1720							1221							-	99.84