ADD groot normalier tests & documentation

BigDataBiology · Aug 7, 2024 · 2d62163 · 2d62163
1 parent 65c7e30
commit 2d62163
Show file tree

Hide file tree

Showing 30 changed files with 626 additions and 22 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -4,6 +4,7 @@
 
 - argNorm has been included as an nf-core module: https://nf-co.re/modules/argnorm/
 - Use atomic writing for outputs
+- Support GROOT v1.1.2
 
 ### New Features
 

diff --git a/README.md b/README.md
@@ -43,6 +43,7 @@ The `resistance_to_drug_classes` column will contain ARO numbers of the broader
 - [ABRicate](https://github.com/tseemann/abricate) (v1.0.1) with NCBI (v3.6), ResFinder (v4.1.11), MEGARes (v2.0), ARG-ANNOT (v5), ResFinderFG (v2)
 - [ResFinder](https://bitbucket.org/genomicepidemiology/resfinder/src/master/) (v4.0)
 - [AMRFinderPlus](https://github.com/ncbi/amr) (v3.10.30)
+- [GROOT](https://github.com/will-rowe/groot) (v1.1.2)
 
 ## Installation
 argNorm can be installed using pip:
@@ -72,6 +73,7 @@ The only positional argument required is `tool` which can be:
 - `abricate`
 - `resfinder`
 - `amrfinderplus`
+- `groot`
 
 The available options are:
 - `-h` or `--help`: shows available options and exits.
@@ -82,6 +84,7 @@ The available options are:
     - DeepARG (`deeparg`)
     - MEGARes (`megares`)
     - ARG-ANNOT (`argannot`)
+    - `groot-core-db`, `groot-db`, `groot-resfinder`, `groot-argannot`, `groot-card`
 - `--hamronized`: use this if the input is hamronized by [hAMRonization](https://github.com/pha4ge/hAMRonization)
 - `-i` or `--input`: path to the annotation result
 - `-o` or `--output`: the file to save normalization results
@@ -90,17 +93,20 @@ Use `argnorm -h` or `argnorm --help` to see available options.
 
 ```bash
 >argnorm -h
-usage: argnorm [-h] [--db {sarg,ncbi,resfinder,deeparg,megares,argannot}] [--hamronized] [-i INPUT] [-o OUTPUT] {argsoap,abricate,deeparg,resfinder,amrfinderplus}
+usage: argnorm [-h]
+               [--db {sarg,ncbi,resfinder,deeparg,megares,argannot,resfinderfg,groot-argannot,groot-resfinder,groot-db,groot-core-db,groot-card}]
+               [--hamronized] [-i INPUT] [-o OUTPUT]
+               {argsoap,abricate,deeparg,resfinder,amrfinderplus,groot}
 
 argNorm normalizes ARG annotation results from different tools and databases to the same ontology, namely ARO (Antibiotic Resistance Ontology).
 
 positional arguments:
-  {argsoap,abricate,deeparg,resfinder,amrfinderplus}
+  {argsoap,abricate,deeparg,resfinder,amrfinderplus,groot}
                         The tool you used to do ARG annotation.
 
-options:
+optional arguments:
   -h, --help            show this help message and exit
-  --db {sarg,ncbi,resfinder,deeparg,megares,argannot}
+  --db {sarg,ncbi,resfinder,deeparg,megares,argannot,resfinderfg,groot-argannot,groot-resfinder,groot-db,groot-core-db,groot-card}
                         The database you used to do ARG annotation.
   --hamronized          Use this if the input is hamronized (processed using the hAMRonization tool)
   -i INPUT, --input INPUT

diff --git a/argnorm/lib.py b/argnorm/lib.py
@@ -12,7 +12,24 @@
 MAPPING_TABLE_ARO_COL = 'ARO'
 TARGET_ARO_COL = 'ARO'
 
-DATABASES = ['argannot', 'deeparg', 'megares', 'ncbi', 'resfinder', 'resfinderfg', 'sarg']
+DATABASES = [
+    'argannot', 
+    'deeparg', 
+    'megares', 
+    'ncbi', 
+    'resfinder', 
+    'resfinderfg', 
+    'sarg',
+    'groot',
+]
+
+groot_ref_databases = [
+    'groot-db',
+    'groot-core-db',
+    'groot-argannot',
+    'groot-resfinder',
+    'groot-card',
+] 
 
 _ROOT = os.path.abspath(os.path.dirname(__file__))
 _ARO = None
@@ -62,24 +79,40 @@ def get_aro_mapping_table(database):
     aro_mapping_table['ARO'] = aro_mapping_table['ARO'].map(lambda a: f'ARO:{a}', na_action='ignore')
     return aro_mapping_table
 
-def map_to_aro(gene, database):
+def map_to_aro(gene, database, groot_ref_db=None):
     """
     Description: Gets ARO mapping for a specific gene in a database.
 
     Parameters:
         gene (str): The original ID of the gene as mentioned in source database.
-        database (str): name of database. Can be: argannot, deeparg, megares, ncbi, resfinderfg and sarg
+        database (str): name of database. Can be: argannot, deeparg, megares, ncbi, resfinderfg, sarg, and groot
+        groot_ref_db (str, optional): name of reference db used by groot. Can be groot-argannot, groot-resfinder, groot-card, groot-core-db, or groot-db
 
     Returns:
         ARO[result] (pronto.term.Term): A pronto term with the ARO number of input gene. ARO number can be accessed using 'id' attribute and gene name can be accessed using 'name' attribute.
 
         If ARO mapping is doesn't exist, None is returned.
     """
 
-    if database not in ['ncbi', 'deeparg', 'resfinder', 'sarg', 'megares', 'argannot']:
+    if database not in DATABASES:
         raise Exception(f'{database} is not a supported database.')
+    if 'groot' in database and not groot_ref_db in groot_ref_databases:
+        raise Exception(f'{groot_ref_db} is not a valid groot reference database')
 
     mapping_table = get_aro_mapping_table(database)
+
+    # Preprocess input gene & mapping table original ids if groot is being used
+    if 'groot' in database:
+        if groot_ref_db == 'groot-argannot':
+            gene = gene.split('~~~')[-1]
+            mapping_table.index = mapping_table.index.map(lambda x: ':'.join(str(x).split(':')[1:3]))
+        if groot_ref_db == 'groot-card':
+            gene = gene.split('.')[0]
+        if groot_ref_db in ['groot-db', 'groot-core-db']:
+            if 'card' in gene.lower():
+                gene = gene.split('|')[-1]
+            else:
+                gene = gene.split('__')[1]
 
     try:
         result = mapping_table.loc[gene, 'ARO']

diff --git a/argnorm/normalizers.py b/argnorm/normalizers.py
@@ -182,13 +182,13 @@ def get_input_ids(self, itable):
             col = 0
 
         if self.database == 'groot-argannot':
-            return itable[col].map(lambda x: x.split('~~~')[-1])
-        if self.database == 'groot-resfinder':
-            return itable[col]
+            return itable[col].map(lambda x: x.split('~~~')[-1])            
         if self.database == 'groot-card':
             return itable[col].map(lambda x: x.split('.')[0])
-        if self.database == 'groot-db' or self.database == 'groot-core-db':
+        if self.database in ['groot-db', 'groot-core-db']:
             return itable[col].map(self.preprocess_groot_db_inputs)
+
+        return itable[col]
 
     def preprocess_ref_genes(self, ref_genes):
         if self.database == 'groot-argannot':

diff --git a/docs/api.md b/docs/api.md
@@ -11,6 +11,7 @@ A list of supported databases.
 #### Parameters
 * gene (str): The original ID of the gene as mentioned in source database.
 * database (str): name of database. Can be: argannot, deeparg, megares, ncbi, resfinderfg and sarg
+* groot_ref_db (str, optional): name of reference database used by groot. Can be: groot-argannot, groot-resfinder, groot-card, groot-db, or groot-core-db
 
 #### Returns
 * pronto.term.Term: A pronto term with the ARO number of input gene. ARO number can be accessed using 'id' attribute and gene name can be accessed using 'name' attribute. 
@@ -20,15 +21,19 @@ A list of supported databases.
 #### Example
 
 ```
-# Mapping the `ARR-2_1_HQ141279` gene from the `resfinder` database to the ARO
 from argnorm.lib import map_to_aro
+
+# Mapping the `ARR-2_1_HQ141279` gene from the `resfinder` database to the ARO
 print(map_to_aro('ARR-2_1_HQ141279', 'resfinder'))
+
+# Mapping the `argannot~~~(Bla)cfxA4~~~AY769933:1-966` gene in `groot` using the `groot-argannot` reference database
+print(map_to_aro('argannot~~~(Bla)cfxA4~~~AY769933:1-966', 'groot', 'groot-argannot'))
 ```
 
 ### argnorm.lib.get_aro_mapping_table(): gets ARO mapping table for a specific database
 
 #### Parameters 
-* database (str): name of database. Can be: argannot, deeparg, megares, ncbi, resfinderfg and sarg
+* database (str): name of database. Can be: argannot, deeparg, megares, ncbi, resfinderfg, sarg or groot
 
 #### Returns
 * pandas.DataFrame: A pandas dataframe with ARGs mapped to AROs.
@@ -81,17 +86,18 @@ print(drugs_to_drug_classes(['ARO:0000030', 'ARO:0000051', 'ARO:0000069', 'ARO:3
 Normalizers classes for specific tools which normalize ARG annotation outputs. Same functionality as CLI.
 
 All normalizers have 2 parameters:
-* database (str): name of database. Can be: argannot, deeparg, megares, ncbi, resfinderfg and sarg.
+* database (str): name of database. Can be: argannot, deeparg, megares, ncbi, resfinderfg, sarg, groot-db, groot-core-db, groot-card, groot-argannot, and groot-resfinder.
 * is_hamronized (bool, False by default): whether or not the ARG annotation output has been processed by the hamronization package.
 
-> Note: the database parameter only needs to be specified for AbricateNormalizer. ncbi, deeparg, resfinder, sarg, megares, argannot, resfinderfg are the supported databases.
+> Note: the database parameter only needs to be specified for AbricateNormalizer and GrootNormalizer. ncbi, deeparg, resfinder, sarg, megares, argannot, resfinderfg are the supported databases for AbricateNormalizer and groot-db, groot-core-db, groot-argannot, groot-resfinder, and groot-card are the supported databases for GrootNormalizer.
 
 Available normalizers:
 * argnorm.normalizers.ARGSOAPNormalizer
 * argnorm.normalizers.DeepARGNormalizer
 * argnorm.normalizers.ResFinderNormalizer
 * argnorm.normalizers.AMRFinderPlusNormalizer
 * argnorm.normalizers.AbricateNormalizer
+* argnorm.normalizers.GrootNormalizer
 
 ### Methods
 

diff --git a/docs/cli.md b/docs/cli.md
@@ -147,4 +147,19 @@ 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
 
 argnorm amrfinderplus -i examples/hamronized/amrfinderplus.ncbi.orfs.tsv -o outputs/hamronized/amrfinderplus.ncbi.orfs.tsv
+```
+
+### GROOT
+```bash
+argnorm groot -i examples/raw/groot.argannot.tsv -o outputs/raw/groot.argannot.tsv --db groot-argannot
+argnorm groot -i examples/raw/groot.resfinder.tsv -o outputs/raw/groot.resfinder.tsv --db groot-resfinder
+argnorm groot -i examples/raw/groot.card.tsv -o outputs/raw/groot.card.tsv --db groot-card
+argnorm groot -i examples/raw/groot.groot-db.tsv -o outputs/raw/groot.groot-db.tsv --db groot-db
+argnorm groot -i examples/raw/groot.groot-core-db.tsv -o ouptuts/raw/groot.groot-core-db.tsv --db groot-core-db
+
+argnorm groot -i examples/hamronized/groot.argannot.tsv -o outputs/hamronized/groot.argannot.tsv --db groot-argannot --hamronized
+argnorm groot -i examples/hamronized/groot.resfinder.tsv -o outputs/hamronized/groot.resfinder.tsv --db groot-resfinder --hamronized
+argnorm groot -i examples/hamronized/groot.card.tsv -o outputs/hamronized/groot.card.tsv --db groot-card --hamronized
+argnorm groot -i examples/hamronized/groot.groot-db.tsv -o outputs/hamronized/groot.groot-db.tsv --db groot-db --hamronized
+argnorm groot -i examples/hamronized/groot.groot-core-db.tsv -o outputs/hamronized/groot.groot-core-db.tsv --db groot-core-db --hamronized
 ```
diff --git a/examples/hamronized/groot.argannot.tsv b/examples/hamronized/groot.argannot.tsv
@@ -0,0 +1,13 @@
+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
+groot.argannot.tsv	argannot~~~(Bla)cfiA9~~~AB087234:1-750	argannot~~~(Bla)cfiA9~~~AB087234:1-750	groot	v	argannot~~~(Bla)cfiA9~~~AB087234:1-750	groot	v	gene_presence_detected			79.0																750								
+groot.argannot.tsv	argannot~~~(Tet)Tet-40~~~AM419751:14211-15431	argannot~~~(Tet)Tet-40~~~AM419751:14211-15431	groot	v	argannot~~~(Tet)Tet-40~~~AM419751:14211-15431	groot	v	gene_presence_detected			315.0																1221								
+groot.argannot.tsv	argannot~~~(MLS)ErmF~~~M14730:241-1041	argannot~~~(MLS)ErmF~~~M14730:241-1041	groot	v	argannot~~~(MLS)ErmF~~~M14730:241-1041	groot	v	gene_presence_detected			321.0																801								
+groot.argannot.tsv	argannot~~~(AGly)Aph7~~~GG774704:686456-687373	argannot~~~(AGly)Aph7~~~GG774704:686456-687373	groot	v	argannot~~~(AGly)Aph7~~~GG774704:686456-687373	groot	v	gene_presence_detected			254.0																918								
+groot.argannot.tsv	argannot~~~(Bla)cfxA2~~~AF504910:1-966	argannot~~~(Bla)cfxA2~~~AF504910:1-966	groot	v	argannot~~~(Bla)cfxA2~~~AF504910:1-966	groot	v	gene_presence_detected			338.0																966								
+groot.argannot.tsv	argannot~~~(MLS)ErmB~~~M11180:714-1451	argannot~~~(MLS)ErmB~~~M11180:714-1451	groot	v	argannot~~~(MLS)ErmB~~~M11180:714-1451	groot	v	gene_presence_detected			178.0																738								
+groot.argannot.tsv	argannot~~~(Tet)TetQ~~~Z21523:362-2287	argannot~~~(Tet)TetQ~~~Z21523:362-2287	groot	v	argannot~~~(Tet)TetQ~~~Z21523:362-2287	groot	v	gene_presence_detected			539.0																1974								
+groot.argannot.tsv	argannot~~~(Bla)cfxA5~~~AY769934:28-993	argannot~~~(Bla)cfxA5~~~AY769934:28-993	groot	v	argannot~~~(Bla)cfxA5~~~AY769934:28-993	groot	v	gene_presence_detected			449.0																966								
+groot.argannot.tsv	argannot~~~(Bla)OXA-347~~~JN086160:1583-2407	argannot~~~(Bla)OXA-347~~~JN086160:1583-2407	groot	v	argannot~~~(Bla)OXA-347~~~JN086160:1583-2407	groot	v	gene_presence_detected			191.0																825								
+groot.argannot.tsv	argannot~~~(Tet)TetW~~~AJ222769:3687-5606	argannot~~~(Tet)TetW~~~AJ222769:3687-5606	groot	v	argannot~~~(Tet)TetW~~~AJ222769:3687-5606	groot	v	gene_presence_detected			203.0																1920								
+groot.argannot.tsv	argannot~~~(Tet)Tet-32~~~DQ647324:181-2100	argannot~~~(Tet)Tet-32~~~DQ647324:181-2100	groot	v	argannot~~~(Tet)Tet-32~~~DQ647324:181-2100	groot	v	gene_presence_detected			148.0																1920								
+groot.argannot.tsv	argannot~~~(Bla)cfxA4~~~AY769933:1-966	argannot~~~(Bla)cfxA4~~~AY769933:1-966	groot	v	argannot~~~(Bla)cfxA4~~~AY769933:1-966	groot	v	gene_presence_detected			450.0																966								
diff --git a/examples/hamronized/groot.card.tsv b/examples/hamronized/groot.card.tsv
@@ -0,0 +1,27 @@
+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
+groot.card.tsv	Mef(En2)	Mef(En2).3004659.AF251288	groot	v	Mef(En2).3004659.AF251288.1.794-2000.5539	groot	v	gene_presence_detected			135.0																1206								
+groot.card.tsv	rrsB	rrsB.3003410.U00096	groot	v	rrsB.3003410.U00096.4166659-4168200.3242	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	rrsB	rrsB.3003396.U00096	groot	v	rrsB.3003396.U00096.4166659-4168200.3233	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	Escherichia_coli_16S	Escherichia_coli_16S.3003223.U00096	groot	v	Escherichia_coli_16S.3003223.U00096.4166659-4168200.3234	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	ErmB	ErmB.3000375.AF242872	groot	v	ErmB.3000375.AF242872.1.2131-2878.5430	groot	v	gene_presence_detected			194.0																747								
+groot.card.tsv	rrnB	rrnB.3003411.U00096	groot	v	rrnB.3003411.U00096.4166659-4168200.3236	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	rrsB	rrsB.3003402.U00096	groot	v	rrsB.3003402.U00096.4166659-4168200.3235	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	rrnB	rrnB.3003406.U00096	groot	v	rrnB.3003406.U00096.4166659-4168200.3237	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	tet(40)	tet(40).3000567.AM419751	groot	v	tet(40).3000567.AM419751.14210-15431.5150	groot	v	gene_presence_detected			315.0																1221								
+groot.card.tsv	aadS	aadS.3004683.M72415	groot	v	aadS.3004683.M72415.1.1120-1984.5568	groot	v	gene_presence_detected			199.0																864								
+groot.card.tsv	CfxA4	CfxA4.3003005.AY769933	groot	v	CfxA4.3003005.AY769933.0-966.1592	groot	v	gene_presence_detected			450.0																966								
+groot.card.tsv	rrnB	rrnB.3003377.U00096	groot	v	rrnB.3003377.U00096.4166659-4168200.3239	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	OXA-347	OXA-347.3001777.JN086160	groot	v	OXA-347.3001777.JN086160.1582-2407.4583	groot	v	gene_presence_detected			191.0																825								
+groot.card.tsv	rrsB	rrsB.3003376.U00096	groot	v	rrsB.3003376.U00096.4166659-4168200.3240	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	rrsB	rrsB.3003408.U00096	groot	v	rrsB.3003408.U00096.4166659-4168200.3241	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	tetQ	tetQ.3000191.Z21523	groot	v	tetQ.3000191.Z21523.0-1974.476	groot	v	gene_presence_detected			539.0																1974								
+groot.card.tsv	rrsB	rrsB.3003399.U00096	groot	v	rrsB.3003399.U00096.4166659-4168200.3232	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	tetW	tetW.3000194.AJ222769	groot	v	tetW.3000194.AJ222769.3.3686-5606.5145	groot	v	gene_presence_detected			203.0																1920								
+groot.card.tsv	CfxA5	CfxA5.3003096.AY769934	groot	v	CfxA5.3003096.AY769934.27-993.1669	groot	v	gene_presence_detected			449.0																966								
+groot.card.tsv	CfxA3	CfxA3.3003003.AF472622	groot	v	CfxA3.3003003.AF472622.52-1018.1514	groot	v	gene_presence_detected			519.0																966								
+groot.card.tsv	rrsB	rrsB.3003405.U00096	groot	v	rrsB.3003405.U00096.4166659-4168200.3231	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	rrsH	rrsH.3003372.U00096	groot	v	rrsH.3003372.U00096.223771-225312.3228	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	rrsB	rrsB.3003397.U00096	groot	v	rrsB.3003397.U00096.4166659-4168200.3230	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	ErmF	ErmF.3000498.M17124	groot	v	ErmF.3000498.M17124.1181-1982.593	groot	v	gene_presence_detected			321.0																801								
+groot.card.tsv	rrsB	rrsB.3003403.U00096	groot	v	rrsB.3003403.U00096.4166659-4168200.3238	groot	v	gene_presence_detected			95.0																1542								
+groot.card.tsv	CfxA2	CfxA2.3003002.AF118110	groot	v	CfxA2.3003002.AF118110.1.71-1037.4470	groot	v	gene_presence_detected			450.0																966