XspecT 0.4.0__py3-none-any.whl → 0.4.1__py3-none-any.whl

xspect/main.py

@@ -18,6 +18,7 @@ from xspect.models.probabilistic_filter_mlst_model import (
 )
 from xspect.model_management import (
     get_genus_model,
+    get_model_metadata,
     get_models,
     get_species_model,
 )
@@ -41,7 +42,6 @@ def web():
 @cli.group()
 def models():
     """Model management commands."""
-    pass
 
 
 @models.command(
@@ -77,7 +77,6 @@ def list_models():
 @models.group()
 def train():
     """Train models."""
-    pass
 
 
 @train.command(
@@ -191,10 +190,12 @@ def train_mlst(choose_schemes):
 )
 def classify_seqs():
     """Classification commands."""
-    pass
 
 
-@classify_seqs.command()
+@classify_seqs.command(
+    name="genus",
+    help="Classify samples using a genus model.",
+)
 @click.option(
     "-g",
     "--genus",
@@ -217,7 +218,7 @@ def classify_seqs():
     type=click.Path(dir_okay=True, file_okay=True),
     default=Path(".") / f"result_{uuid4()}.json",
 )
-def genus(model_genus, input_path, output_path):
+def classify_genus(model_genus, input_path, output_path):
     """Classify samples using a genus model."""
     click.echo("Classifying...")
     genus_model = get_genus_model(model_genus)
@@ -226,7 +227,10 @@ def genus(model_genus, input_path, output_path):
     click.echo(f"Result saved as {output_path}.")
 
 
-@classify_seqs.command()
+@classify_seqs.command(
+    name="species",
+    help="Classify samples using a species model.",
+)
 @click.option(
     "-g",
     "--genus",
@@ -252,10 +256,10 @@ def genus(model_genus, input_path, output_path):
 @click.option(
     "--sparse-sampling-step",
     type=int,
-    help="Sparse sampling step size (e. g. only every 500th kmer for '--sparse-sampling-step 500').",
+    help="Sparse sampling step (e. g. only every 500th kmer for '--sparse-sampling-step 500').",
     default=1,
 )
-def species(model_genus, input_path, output_path, sparse_sampling_step):
+def classify_species(model_genus, input_path, output_path, sparse_sampling_step):
     """Classify samples using a species model."""
     click.echo("Classifying...")
     species_model = get_species_model(model_genus)
@@ -302,7 +306,6 @@ def classify_mlst(input_path, output_path):
 )
 def filter_seqs():
     """Filter commands."""
-    pass
 
 
 @filter_seqs.command(
@@ -336,6 +339,7 @@ def filter_seqs():
     type=float,
     help="Threshold for filtering (default: 0.7).",
     default=0.7,
+    prompt=True,
 )
 def filter_genus(model_genus, input_path, output_path, threshold):
     """Filter samples using a genus model."""
@@ -368,12 +372,10 @@ def filter_genus(model_genus, input_path, output_path, threshold):
     prompt=True,
 )
 @click.option(
-    # todo: this should be a choice of the species in the model w/ display names
     "-s",
     "--species",
     "model_species",
     help="Species of the model to filter for.",
-    prompt=True,
 )
 @click.option(
     "-i",
@@ -392,11 +394,36 @@ def filter_genus(model_genus, input_path, output_path, threshold):
 @click.option(
     "--threshold",
     type=float,
-    help="Threshold for filtering (default: 0.7).",
+    help="Threshold for filtering (default: 0.7). Use -1 to filter for the highest scoring species.",
     default=0.7,
+    prompt=True,
 )
 def filter_species(model_genus, model_species, input_path, output_path, threshold):
     """Filter a sample using the species model."""
+
+    available_species = get_model_metadata(f"{model_genus}-species")["display_names"]
+    available_species = {
+        id: name.replace(f"{model_genus} ", "")
+        for id, name in available_species.items()
+    }
+    if not model_species:
+        sorted_available_species = sorted(available_species.values())
+        model_species = click.prompt(
+            f"Please enter the species name: {model_genus}",
+            type=click.Choice(sorted_available_species, case_sensitive=False),
+        )
+    if model_species not in available_species.values():
+        raise click.BadParameter(
+            f"Species '{model_species}' not found in the {model_genus} species model."
+        )
+
+    # get the species ID from the name
+    model_species = [
+        id
+        for id, name in available_species.items()
+        if name.lower() == model_species.lower()
+    ][0]
+
     click.echo("Filtering...")
     species_model = get_species_model(model_genus)
     result = species_model.predict(Path(input_path))

xspect/model_management.py

@@ -2,7 +2,6 @@
 
 from json import loads, dumps
 from pathlib import Path
-from xspect.models.probabilistic_filter_model import ProbabilisticFilterModel
 from xspect.models.probabilistic_single_filter_model import (
     ProbabilisticSingleFilterModel,
 )
@@ -24,23 +23,10 @@ def get_species_model(genus):
     return species_filter_model
 
 
-def get_model_by_slug(model_slug: str):
-    """Get a model by its slug."""
-    model_path = get_xspect_model_path() / (model_slug + ".json")
-    model_metadata = get_model_metadata(model_path)
-    if model_metadata["model_class"] == "ProbabilisticSingleFilterModel":
-        return ProbabilisticSingleFilterModel.load(model_path)
-    if model_metadata["model_class"] == "ProbabilisticFilterSVMModel":
-        return ProbabilisticFilterSVMModel.load(model_path)
-    if model_metadata["model_class"] == "ProbabilisticFilterModel":
-        return ProbabilisticFilterModel.load(model_path)
-    raise ValueError(f"Model class {model_metadata['model_class']} not recognized.")
-
-
 def get_model_metadata(model: str | Path):
     """Get the metadata of a model."""
     if isinstance(model, str):
-        model_path = get_xspect_model_path() / (model + ".json")
+        model_path = get_xspect_model_path() / (model.lower() + ".json")
     elif isinstance(model, Path):
         model_path = model
     else:

xspect/models/result.py

@@ -58,16 +58,28 @@ class ModelResult:
         return total_hits
 
     def get_filter_mask(self, label: str, filter_threshold: float) -> dict[str, bool]:
-        """Return a mask for filtered subsequences."""
-        if filter_threshold < 0 or filter_threshold > 1:
+        """Return a mask for filtered subsequences.
+
+        The mask is a dictionary with subsequence names as keys and boolean values
+        indicating whether the subsequence is above the filter threshold for the given label.
+        A value of -1 for filter_threshold indicates that the subsequence with the maximum score
+        for the given label should be returned.
+        """
+        if filter_threshold < 0 and not filter_threshold == -1 or filter_threshold > 1:
             raise ValueError("The filter threshold must be between 0 and 1.")
 
         scores = self.get_scores()
         scores.pop("total")
-        return {
-            subsequence: score[label] >= filter_threshold
-            for subsequence, score in scores.items()
-        }
+        if not filter_threshold == -1:
+            return {
+                subsequence: score[label] >= filter_threshold
+                for subsequence, score in scores.items()
+            }
+        else:
+            return {
+                subsequence: score[label] == max(score.values())
+                for subsequence, score in scores.items()
+            }
 
     def get_filtered_subsequence_labels(
         self, label: str, filter_threshold: float = 0.7

{xspect-0.4.0.dist-info → xspect-0.4.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: XspecT
-Version: 0.4.0
+Version: 0.4.1
 Summary: Tool to monitor and characterize pathogens using Bloom filters.
 License: MIT License
         
@@ -54,6 +54,7 @@ Requires-Dist: sphinx-autobuild; extra == "docs"
 Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
 Requires-Dist: pytest-cov; extra == "test"
+Requires-Dist: httpx; extra == "test"
 Dynamic: license-file
 
 # XspecT - Acinetobacter Species Assignment Tool

{xspect-0.4.0.dist-info → xspect-0.4.1.dist-info}/RECORD

@@ -3,8 +3,8 @@ xspect/definitions.py,sha256=fVn_li_s2hriOSGJ69o_H8H-vkw1znvkryhBj7WMnF4,1219
 xspect/download_models.py,sha256=y1wFJZa1xOJfvUP78zKkRs46O-WqKBL90vmo5AYUio0,853
 xspect/fastapi.py,sha256=DOef3MqWPdBmdYBo8Z9SPmWrbJHOsQxQe3GrC4f__Rc,3165
 xspect/file_io.py,sha256=YmfoKEQdHHEi8dO2G5Kt4tSNi5LuWW0VZ74pyYRHiTo,5937
-xspect/main.py,sha256=uVj1fooDU5WW8sMug5YPwuAphb8zd3PDpNFNlTIyXBw,11155
-xspect/model_management.py,sha256=LItMidbfxZfttEZHa8da_nnkwkH7XVLWDM0uVrFUZ0Q,3753
+xspect/main.py,sha256=twIn48wPDFOEejQroYN8JM8a40naEqT_BUgrMAwwYck,12154
+xspect/model_management.py,sha256=UbmAr3YOZ4oy_9iVvApCLstYHGkcmneHEC_yftRIqCI,3010
 xspect/ncbi.py,sha256=sSJO3g8n89Qw6UJjAy13bpjOcIGSquTKNKVHNUMbDeM,10072
 xspect/train.py,sha256=7I7-inWGJe_VDzII9dLZ8U-8SUCZDIrhb-eNOZEyfss,10703
 xspect/mlst_feature/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -15,10 +15,10 @@ xspect/models/probabilistic_filter_mlst_model.py,sha256=JMc0yBJPo7J9b-GpvhDmzhwW
 xspect/models/probabilistic_filter_model.py,sha256=l8mhcRgHPso7qIgI56buCnE3ZleO3gPWOZEpgrycOBA,10029
 xspect/models/probabilistic_filter_svm_model.py,sha256=xXimcv3iWnG1JiFyrk6UqkP9hFIxWGDdb__fRdQYwro,6245
 xspect/models/probabilistic_single_filter_model.py,sha256=yxWnCt4IP-3ZRLP4pRA3f2VTHc0_4g17PDCyOFayDDg,4090
-xspect/models/result.py,sha256=fhTS43XYAIkNiiAMyNpaif0kM4Ab3xLBnVJnutkOuFU,3400
-xspect-0.4.0.dist-info/licenses/LICENSE,sha256=bhBGDKIRUVwYIHGOGO5hshzuVHyqFJajvSOA3XXOLKI,1094
-xspect-0.4.0.dist-info/METADATA,sha256=mmsNmdiRqOC0RCBe7yW6oofue2OctwErCWVyiJD86nI,4439
-xspect-0.4.0.dist-info/WHEEL,sha256=ck4Vq1_RXyvS4Jt6SI0Vz6fyVs4GWg7AINwpsaGEgPE,91
-xspect-0.4.0.dist-info/entry_points.txt,sha256=L7qliX3pIuwupQxpuOSsrBJCSHYPOPNEzH8KZKQGGUw,43
-xspect-0.4.0.dist-info/top_level.txt,sha256=hdoa4cnBv6OVzpyhMmyxpJxEydH5n2lDciy8urc1paE,7
-xspect-0.4.0.dist-info/RECORD,,
+xspect/models/result.py,sha256=ELWiDlQPlxNG7ceLpth60Z_Hb1ZdopDJ3vgHBPgSRm8,3989
+xspect-0.4.1.dist-info/licenses/LICENSE,sha256=bhBGDKIRUVwYIHGOGO5hshzuVHyqFJajvSOA3XXOLKI,1094
+xspect-0.4.1.dist-info/METADATA,sha256=BLTAPyNGEjUxxFUqGvdgyFy8T0p9b8w8IOBbUBvnv28,4477
+xspect-0.4.1.dist-info/WHEEL,sha256=ck4Vq1_RXyvS4Jt6SI0Vz6fyVs4GWg7AINwpsaGEgPE,91
+xspect-0.4.1.dist-info/entry_points.txt,sha256=L7qliX3pIuwupQxpuOSsrBJCSHYPOPNEzH8KZKQGGUw,43
+xspect-0.4.1.dist-info/top_level.txt,sha256=hdoa4cnBv6OVzpyhMmyxpJxEydH5n2lDciy8urc1paE,7
+xspect-0.4.1.dist-info/RECORD,,