added several types and formats for kmer analysis

q2_amr/plugin_setup.py

@@ -41,8 +41,12 @@
     CARDKmerTXTFormat,
     CARDMAGsKmerAnalysisDirectoryFormat,
     CARDMAGsKmerAnalysisFormat,
-    CARDReadsKmerAnalysisDirectoryFormat,
-    CARDReadsKmerAnalysisFormat,
+    CARDMAGsKmerAnalysisJSONFormat,
+    CARDReadsAlleleKmerAnalysisDirectoryFormat,
+    CARDReadsAlleleKmerAnalysisFormat,
+    CARDReadsGeneKmerAnalysisDirectoryFormat,
+    CARDReadsGeneKmerAnalysisFormat,
+    CARDReadsKmerAnalysisJSONFormat,
     CARDWildcardIndexFormat,
     GapDNAFASTAFormat,
 )
@@ -51,6 +55,9 @@
     CARDAnnotation,
     CARDGeneAnnotation,
     CARDKmerDatabase,
+    CARDMAGsKmerAnalysis,
+    CARDReadsAlleleKmerAnalysis,
+    CARDReadsGeneKmerAnalysis,
 )
 
 citations = Citations.load("citations.bib", package="q2_amr")
@@ -243,15 +250,23 @@
 plugin.register_semantic_type_to_format(
     SampleData[CARDGeneAnnotation], artifact_format=CARDGeneAnnotationDirectoryFormat
 )
-
+plugin.register_semantic_type_to_format(
+    SampleData[CARDReadsGeneKmerAnalysis],
+    artifact_format=CARDReadsGeneKmerAnalysisDirectoryFormat,
+)
+plugin.register_semantic_type_to_format(
+    SampleData[CARDReadsAlleleKmerAnalysis],
+    artifact_format=CARDReadsAlleleKmerAnalysisDirectoryFormat,
+)
+plugin.register_semantic_type_to_format(
+    SampleData[CARDMAGsKmerAnalysis],
+    artifact_format=CARDMAGsKmerAnalysisDirectoryFormat,
+)
 plugin.register_formats(
     CARDKmerDatabaseDirectoryFormat,
     CARDKmerJSONFormat,
     CARDKmerTXTFormat,
-    CARDMAGsKmerAnalysisFormat,
     CARDMAGsKmerAnalysisDirectoryFormat,
-    CARDReadsKmerAnalysisFormat,
-    CARDReadsKmerAnalysisDirectoryFormat,
     GapDNAFASTAFormat,
     CARDWildcardIndexFormat,
     CARDAnnotationTXTFormat,
@@ -264,6 +279,13 @@
     CARDAnnotationStatsFormat,
     CARDAlleleAnnotationDirectoryFormat,
     CARDGeneAnnotationDirectoryFormat,
+    CARDMAGsKmerAnalysisFormat,
+    CARDMAGsKmerAnalysisJSONFormat,
+    CARDReadsAlleleKmerAnalysisFormat,
+    CARDReadsGeneKmerAnalysisFormat,
+    CARDReadsKmerAnalysisJSONFormat,
+    CARDReadsGeneKmerAnalysisDirectoryFormat,
+    CARDReadsAlleleKmerAnalysisDirectoryFormat,
 )
 
 importlib.import_module("q2_amr.types._transformer")

q2_amr/types/__init__.py

@@ -22,8 +22,12 @@
     CARDKmerTXTFormat,
     CARDMAGsKmerAnalysisDirectoryFormat,
     CARDMAGsKmerAnalysisFormat,
-    CARDReadsKmerAnalysisDirectoryFormat,
-    CARDReadsKmerAnalysisFormat,
+    CARDMAGsKmerAnalysisJSONFormat,
+    CARDReadsAlleleKmerAnalysisDirectoryFormat,
+    CARDReadsAlleleKmerAnalysisFormat,
+    CARDReadsGeneKmerAnalysisDirectoryFormat,
+    CARDReadsGeneKmerAnalysisFormat,
+    CARDReadsKmerAnalysisJSONFormat,
     CARDWildcardIndexFormat,
     GapDNAFASTAFormat,
 )
@@ -57,7 +61,11 @@
     "CARDWildcardIndexFormat",
     "CARDKmerDatabase",
     "CARDMAGsKmerAnalysisFormat",
+    "CARDMAGsKmerAnalysisJSONFormat",
     "CARDMAGsKmerAnalysisDirectoryFormat",
-    "CARDReadsKmerAnalysisFormat",
-    "CARDReadsKmerAnalysisDirectoryFormat",
+    "CARDReadsAlleleKmerAnalysisFormat",
+    "CARDReadsGeneKmerAnalysisFormat",
+    "CARDReadsKmerAnalysisJSONFormat",
+    "CARDReadsGeneKmerAnalysisDirectoryFormat",
+    "CARDReadsAlleleKmerAnalysisDirectoryFormat",
 ]

q2_amr/types/_format.py

@@ -454,34 +454,119 @@ def _validate_(self, level):
         self._validate()
 
 
+class CARDMAGsKmerAnalysisJSONFormat(model.TextFileFormat):
+    def _validate(self, n_records=None):
+        keys_exp = [
+            "ORF",
+            "contig",
+            "HSP",
+            "ARO_model",
+            "type_hit",
+            "#_of_kmers_in_sequence",
+            "#_of_AMR_kmers",
+            "taxonomic_info",
+            "genomic_info",
+        ]
+        with open(str(self)) as json_file:
+            dict = json.load(json_file)
+
+        keys_obs = list(next(iter(dict.values())).keys())
+
+        if keys_obs != keys_exp:
+            raise ValidationError(
+                "Keys do not match CARDMAGsKmerAnalysisJSONFormat format. Must consist "
+                "of the following values: "
+                + ", ".join(keys_exp)
+                + ".\n\nFound instead: "
+                + ", ".join(keys_obs)
+            )
+
+    def _validate_(self, level):
+        self._validate()
+
+
 class CARDMAGsKmerAnalysisDirectoryFormat(
     MultiDirValidationMixin, model.DirectoryFormat
 ):
     txt = model.FileCollection(
-        r"\d+mer_analysis_mags.txt$", format=CARDMAGsKmerAnalysisFormat
+        r".+\d+mer_analysis_rgi_summary\.txt$", format=CARDMAGsKmerAnalysisFormat
+    )
+    json = model.FileCollection(
+        r".+\d+mer_analysis\.json$", format=CARDMAGsKmerAnalysisJSONFormat
     )
 
     @txt.set_path_maker
     def txt_path_maker(self, sample_id, bin_id):
-        pattern = r"\d+mer_analysis_mags.txt$"
+        pattern = r"\d+mer_analysis_rgi_summary\.txt$"
         return f"{sample_id}/{bin_id}/{pattern}"
 
+    @json.set_path_maker
+    def json_path_maker(self, sample_id, bin_id):
+        pattern = r"\d+mer_analysis_mags\.json$"
+        return f"{sample_id}/{bin_id}/{pattern}"
 
-class CARDReadsKmerAnalysisFormat(model.TextFileFormat):
+
+class CARDReadsGeneKmerAnalysisFormat(model.TextFileFormat):
     def _validate(self, n_records=None):
         header_exp = [
-            "Reference Sequence / ARO term",
+            "ARO term",
             "Mapped reads with kmer DB hits",
-            "CARD kmer Prediction",
-            "Subsequent fields",
+            "CARD*kmer Prediction",
+            "Single species (chromosome) reads",
+            "Single species (chromosome or plasmid) reads",
+            "Single species (plasmid) reads",
+            "Single species (no genomic info) reads",
+            "Single genus (chromosome) reads",
+            "Single genus (chromosome or plasmid) reads",
+            "Single genus (plasmid) reads",
+            "Single genus (no genomic info) reads",
+            "Promiscuous plasmid reads",
+            "Unknown taxonomy (chromosome) reads",
+            "Unknown taxonomy (chromosome or plasmid) reads",
+            "Unknown taxonomy (no genomic info) reads",
         ]
 
         df = pd.read_csv(str(self), sep="\t")
         header_obs = list(df.columns)
         if not set(header_exp).issubset(set(header_obs)):
             raise ValidationError(
-                "Header line does not match CARDReadsKmerAnalysisFormat. Must contain"
-                "the following values: "
+                "Header line does not match CARDReadsGeneKmerAnalysisFormat. Must "
+                "contain the following values: "
+                + ", ".join(header_exp)
+                + ".\n\nFound instead: "
+                + ", ".join(header_obs)
+            )
+
+    def _validate_(self, level):
+        self._validate()
+
+
+class CARDReadsAlleleKmerAnalysisFormat(model.TextFileFormat):
+    def _validate(self, n_records=None):
+        header_exp = [
+            "Reference Sequence",
+            "Mapped reads with kmer DB hits",
+            "CARD*kmer Prediction",
+            "Single species (chromosome) reads",
+            "Single species (chromosome or plasmid) reads",
+            "Single species (plasmid) reads",
+            "Single species (no genomic info) reads",
+            "Single genus (chromosome) reads",
+            "Single genus (chromosome or plasmid) reads",
+            "Single genus (plasmid) reads",
+            "Single genus (no genomic info) reads",
+            "Promiscuous plasmid reads",
+            "Unknown taxonomy (chromosome) reads",
+            "Unknown taxonomy (chromosome or plasmid) reads",
+            "Unknown taxonomy (no genomic info) reads",
+        ]
+
+        df = pd.read_csv(str(self), sep="\t")
+        header_obs = list(df.columns)
+        if not set(header_exp).issubset(set(header_obs)):
+            raise ValidationError(
+                "Header line does not match CARDReadsAlleleKmerAnalysisFormat. Must "
+                "contain the following values: "
                 + ", ".join(header_exp)
                 + ".\n\nFound instead: "
                 + ", ".join(header_obs)
@@ -491,14 +576,64 @@ def _validate_(self, level):
         self._validate()
 
 
-class CARDReadsKmerAnalysisDirectoryFormat(
+class CARDReadsKmerAnalysisJSONFormat(model.TextFileFormat):
+    def _validate(self, n_records=None):
+        keys_exp = [
+            "reference",
+            "#_of_kmers_in_sequence",
+            "#_of_AMR_kmers",
+            "SAM_flag",
+            "MAPQ",
+            "taxonomic_info",
+            "genomic_info",
+        ]
+        with open(str(self)) as json_file:
+            dict = json.load(json_file)
+
+        keys_obs = list(next(iter(dict.values())).keys())
+
+        if keys_obs != keys_exp:
+            raise ValidationError(
+                "Keys do not match CARDReadsKmerAnalysisJSONFormat format. Must consist"
+                " of the following values: "
+                + ", ".join(keys_exp)
+                + ".\n\nFound instead: "
+                + ", ".join(keys_obs)
+            )
+
+    def _validate_(self, level):
+        self._validate()
+
+
+class CARDReadsAlleleKmerAnalysisDirectoryFormat(
     MultiDirValidationMixin, model.DirectoryFormat
 ):
     txt = model.FileCollection(
-        r"\d+mer_analysis_analysis_reads.txt$", format=CARDReadsKmerAnalysisFormat
+        r".+\d+mer_analysis\.allele\.txt$", format=CARDReadsAlleleKmerAnalysisFormat
+    )
+    json = model.FileCollection(
+        r".+\d+mer_analysis\.json$", format=CARDReadsKmerAnalysisJSONFormat
     )
 
     @txt.set_path_maker
-    def txt_path_maker(self, sample_id, bin_id):
-        pattern = r"kmer_\d+mer_analysis_analysis_reads.txt$"
-        return f"{sample_id}/{bin_id}/{pattern}"
+    def txt_path_maker(self, sample_id):
+        pattern = r"\d+mer_analysis\.allele\.txt$"
+        return f"{sample_id}/{pattern}"
+
+    @json.set_path_maker
+    def json_path_maker(self, sample_id):
+        pattern = r"\d+mer_analysis\.json$"
+        return f"{sample_id}/{pattern}"
+
+
+class CARDReadsGeneKmerAnalysisDirectoryFormat(
+    MultiDirValidationMixin, model.DirectoryFormat
+):
+    txt = model.FileCollection(
+        r".+\d+mer_analysis\.gene\.txt$", format=CARDReadsGeneKmerAnalysisFormat
+    )
+
+    @txt.set_path_maker
+    def txt_path_maker(self, sample_id):
+        pattern = r"\d+mer_analysis\.gene\.txt$"
+        return f"{sample_id}/{pattern}"

q2_amr/types/_type.py

@@ -10,8 +10,15 @@
 
 CARDDatabase = SemanticType("CARDDatabase")
 CARDKmerDatabase = SemanticType("CARDKmerDatabase")
-CARDMAGsKmerAnalysis = SemanticType("CARDMAGsKmerAnalysis")
-CARDReadsKmerAnalysis = SemanticType("CARDReadsKmerAnalysis")
+CARDMAGsKmerAnalysis = SemanticType(
+    "CARDMAGsKmerAnalysis", variant_of=SampleData.field["type"]
+)
+CARDReadsAlleleKmerAnalysis = SemanticType(
+    "CARDReadsAlleleKmerAnalysis", variant_of=SampleData.field["type"]
+)
+CARDReadsGeneKmerAnalysis = SemanticType(
+    "CARDReadsGeneKmerAnalysis", variant_of=SampleData.field["type"]
+)
 CARDAnnotation = SemanticType("CARDAnnotation", variant_of=SampleData.field["type"])
 CARDAlleleAnnotation = SemanticType(
     "CARDAlleleAnnotation", variant_of=SampleData.field["type"]

q2_amr/types/tests/data/61mer_analysis.allele.txt

@@ -0,0 +1,3 @@
+Reference Sequence	Mapped reads with kmer DB hits	CARD*kmer Prediction	Single species (chromosome) reads	Single species (chromosome or plasmid) reads	Single species (plasmid) reads	Single species (no genomic info) reads	Single genus (chromosome) reads	Single genus (chromosome or plasmid) reads	Single genus (plasmid) reads	Single genus (no genomic info) reads	Promiscuous plasmid reads	Unknown taxonomy (chromosome) reads	Unknown taxonomy (chromosome or plasmid) reads	Unknown taxonomy (no genomic info) reads
+ARO:3003550|ID:45|Name:mdtP|NCBI:AP009048.1	2										0	1	1	0
+ARO:3000796|ID:121|Name:mdtF|NCBI:U00096.1	2										0	2	0	0

q2_amr/types/tests/data/61mer_analysis.gene.txt

@@ -0,0 +1,3 @@
+ARO term	Mapped reads with kmer DB hits	CARD*kmer Prediction	Single species (chromosome) reads	Single species (chromosome or plasmid) reads	Single species (plasmid) reads	Single species (no genomic info) reads	Single genus (chromosome) reads	Single genus (chromosome or plasmid) reads	Single genus (plasmid) reads	Single genus (no genomic info) reads	Promiscuous plasmid reads	Unknown taxonomy (chromosome) reads	Unknown taxonomy (chromosome or plasmid) reads	Unknown taxonomy (no genomic info) reads
+mdtP	2										0	1	1	0
+mdtF	2										0	2	0	0

q2_amr/types/tests/data/mags_61mer_analysis.json

@@ -0,0 +1 @@
+{"k141_1617_82 # 105913 # 109473 # 1 # ID=42_82;partial=00;start_type=TTG;rbs_motif=AGGA;rbs_spacer=5-10bp;gc_cont=0.630": {"ORF": "k141_1617_82 # 105913 # 109473 # 1 # ID=42_82;partial=00;start_type=TTG;rbs_motif=AGGA;rbs_spacer=5-10bp;gc_cont=0.630", "contig": "k141_1617_82", "HSP": "gnl|BL_ORD_ID|4713|hsp_num:0", "ARO_model": "Bifidobacterium adolescentis rpoB mutants conferring resistance to rifampicin", "type_hit": "Perfect", "#_of_kmers_in_sequence": 3501, "#_of_AMR_kmers": 2274, "taxonomic_info": {"species": {"Bifidobacterium longum": 75, "Bifidobacterium dentium": 67, "Parascardovia denticolens": 3, "Bifidobacterium animalis": 7, "Bifidobacterium bifidum": 9}, "genus": {}}, "genomic_info": {"chr + plasmid": 0, "plasmid": 0, "chr": 234}}}

q2_amr/types/tests/data/reads_61mer_analysis.json

@@ -0,0 +1 @@
+{"NC_000913.3_208_0/1/1": {"reference": "ARO:3003550|ID:45|Name:mdtP|NCBI:AP009048.1", "#_of_kmers_in_sequence": 66, "#_of_AMR_kmers": 66, "SAM_flag": 83, "MAPQ": 193, "taxonomic_info": {"species": {}, "genus": {}}, "genomic_info": {"chr + plasmid": 18, "plasmid": 0, "chr": 48}}}