Merge pull request #22 from MICS-Lab/dev

Dev
MICS-Lab · Sep 25, 2023 · 491ec29 · 491ec29
2 parents caefeb4 + b5cd347
commit 491ec29
Show file tree

Hide file tree

Showing 9 changed files with 185 additions and 62 deletions.
diff --git a/docs/api/tools.md b/docs/api/tools.md
@@ -2,14 +2,18 @@
     options:
       show_root_heading: true
 
-::: scyan.tools.palette_level
+::: scyan.tools.leiden
     options:
       show_root_heading: true
 
 ::: scyan.tools.subcluster
     options:
       show_root_heading: true
 
+::: scyan.tools.palette_level
+    options:
+      show_root_heading: true
+
 ::: scyan.tools.cell_type_ratios
     options:
       show_root_heading: true
@@ -25,3 +29,13 @@
         - __init__
         - select
         - save_selection
+        - extract_adata
+
+::: scyan.tools.PolygonGatingScatter
+    options:
+      show_root_heading: true
+      members:
+        - __init__
+        - select
+        - save_selection
+        - extract_adata
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "scyan"
-version = "1.5.0"
+version = "1.5.1"
 description = "Single-cell Cytometry Annotation Network"
 documentation = "https://mics-lab.github.io/scyan/"
 homepage = "https://mics-lab.github.io/scyan/"
@@ -14,11 +14,9 @@ classifiers = [
   "Operating System :: POSIX :: Linux",
   "Operating System :: Microsoft :: Windows",
   "Programming Language :: Python :: 3",
-  "Topic :: Scientific/Engineering"
-]
-packages = [
-    { include = "scyan" },
+  "Topic :: Scientific/Engineering",
 ]
+packages = [{ include = "scyan" }]
 
 [tool.poetry.dependencies]
 python = ">=3.8,<3.11"
@@ -32,25 +30,35 @@ FlowUtils = "^1.0.0"
 fcsparser = "^0.2.4"
 fcswrite = "^0.6.2"
 
-wandb = {version =  "0.13.7", optional = true}
-hydra-core = {version = "^1.2.0", optional = true}
-hydra-colorlog = {version = "^1.2.0", optional = true}
-hydra-optuna-sweeper = {version = "^1.2.0", optional = true}
+wandb = { version = "0.13.7", optional = true }
+hydra-core = { version = "^1.2.0", optional = true }
+hydra-colorlog = { version = "^1.2.0", optional = true }
+hydra-optuna-sweeper = { version = "^1.2.0", optional = true }
 
-pytest = {version = "^7.1.2", optional = true}
-ipykernel = {version = "^6.15.0", optional = true}
-ipywidgets = {version = "^7.7.1", optional = true}
-isort = {version = "^5.10.1", optional = true}
-black = {version = "^22.6.0", optional = true}
-mkdocs-material = {version = "^8.5.0", optional = true}
-mkdocstrings = {version = "^0.19.0", optional = true}
-mkdocstrings-python = {version = "^0.7.1", optional = true}
-mkdocs-jupyter = {version = "^0.21.0", optional = true}
+pytest = { version = "^7.1.2", optional = true }
+ipykernel = { version = "^6.15.0", optional = true }
+ipywidgets = { version = "^7.7.1", optional = true }
+isort = { version = "^5.10.1", optional = true }
+black = { version = "^22.6.0", optional = true }
+mkdocs-material = { version = "^8.5.0", optional = true }
+mkdocstrings = { version = "^0.19.0", optional = true }
+mkdocstrings-python = { version = "^0.7.1", optional = true }
+mkdocs-jupyter = { version = "^0.21.0", optional = true }
 
-leidenalg = {version = "^0.8.10", optional = true}
+leidenalg = { version = "^0.8.10", optional = true }
 
 [tool.poetry.extras]
-dev = ["pytest", "ipykernel", "ipywidgets", "isort", "black", "mkdocs-material", "mkdocstrings", "mkdocstrings-python", "mkdocs-jupyter"]
+dev = [
+  "pytest",
+  "ipykernel",
+  "ipywidgets",
+  "isort",
+  "black",
+  "mkdocs-material",
+  "mkdocstrings",
+  "mkdocstrings-python",
+  "mkdocs-jupyter",
+]
 hydra = ["wandb", "hydra-core", "hydra-colorlog", "hydra-optuna-sweeper"]
 discovery = ["leidenalg"]
 
@@ -65,7 +73,7 @@ python_files = "test_*.py"
 filterwarnings = [
   "ignore::DeprecationWarning",
   "ignore::UserWarning",
-  "ignore:::.*anndata*"
+  "ignore:::.*anndata*",
 ]
 
 [tool.black]
@@ -88,4 +96,4 @@ exclude = '''
 
 [tool.isort]
 profile = "black"
-skip_glob = ["*/__init__.py"]
+skip_glob = ["*/__init__.py"]
diff --git a/scyan/model.py b/scyan/model.py
@@ -203,8 +203,8 @@ def _prepare_data(self) -> None:
 
         self._n_samples = (
             min(self.hparams.max_samples or self.adata.n_obs, self.adata.n_obs)
-            // self.hparams.batch_size
-            * self.hparams.batch_size
+            // self._batch_size
+            * self._batch_size
         )
 
     @_requires_fit
@@ -410,13 +410,17 @@ def load(self, path: str) -> None:
         self.dataset = TensorDataset(self.x, self.covariates)
         self._is_fitted = True
 
+    @property
+    def _batch_size(self):
+        return min(self.hparams.batch_size, self.adata.n_obs)
+
     def train_dataloader(self):
         """PyTorch lightning `train_dataloader` implementation"""
         self.dataset = TensorDataset(self.x, self.covariates)
 
         return DataLoader(
             self.dataset,
-            batch_size=self.hparams.batch_size,
+            batch_size=self._batch_size,
             sampler=RandomSampler(self.adata.n_obs, self._n_samples),
             num_workers=self._num_workers,
         )
@@ -425,7 +429,7 @@ def predict_dataloader(self):
         """PyTorch lightning `predict_dataloader` implementation"""
         return DataLoader(
             self.dataset,
-            batch_size=self.hparams.batch_size,
+            batch_size=self._batch_size,
             num_workers=self._num_workers,
         )
 
@@ -449,7 +453,7 @@ def dataset_apply(self, func: Callable, data: Tuple[Tensor] = None) -> Tensor:
         else:
             loader = DataLoader(
                 TensorDataset(*data),
-                batch_size=self.hparams.batch_size,
+                batch_size=self._batch_size,
                 num_workers=self._num_workers,
             )
 
@@ -534,9 +538,7 @@ def fit(
                 check_on_train_epoch_end=True,
             )
 
-            log_every_n_steps = min(
-                log_every_n_steps, len(self.x) // self.hparams.batch_size
-            )
+            log_every_n_steps = min(log_every_n_steps, len(self.x) // self._batch_size)
             trainer = pl.Trainer(
                 max_epochs=max_epochs,
                 callbacks=[esc] + (callbacks or []),

diff --git a/scyan/plot/density.py b/scyan/plot/density.py
@@ -27,7 +27,7 @@ def kde(
     """Plot Kernel-Density-Estimation for each provided population and for multiple markers.
 
     Args:
-        adata: An `anndata` object.
+        adata: An `AnnData` object.
         population: One population, or a list of population to be analyzed, or `None`. If not `None`, the population name(s) has to be in `adata.obs[key]`.
         markers: List of markers to plot. If `None`, the list is chosen automatically.
         key: Key to look for populations in `adata.obs`. By default, uses the model predictions.
@@ -97,7 +97,7 @@ def log_prob_threshold(adata: AnnData, show: bool = True):
         To use this function, you first need to fit a `scyan.Scyan` model and use the `model.predict()` method.
 
     Args:
-        adata: The `anndata` object used during the model training.
+        adata: The `AnnData` object used during the model training.
         show: Whether or not to display the figure.
     """
     assert (

diff --git a/scyan/plot/dot.py b/scyan/plot/dot.py
@@ -27,7 +27,7 @@ def scatter(
     One scatter plot is displayed for each pair of markers.
 
     Args:
-        adata: An `anndata` object.
+        adata: An `AnnData` object.
         population: One population, or a list of population to be colored, or `None`. If not `None`, the population name(s) has to be in `adata.obs[key]`.
         markers: List of markers to plot. If `None`, the list is chosen automatically.
         n_markers: Number of markers to choose automatically if `markers is None`.
@@ -79,7 +79,7 @@ def umap(
         If you trained your UMAP with [scyan.tools.umap][] on a subset of cells, it will only display the desired subset of cells.
 
     Args:
-        adata: An `anndata` object.
+        adata: An `AnnData` object.
         color: Marker(s) or `obs` name(s) to color. It can be either just one string, or a list (it will plot one UMAP per element in the list).
         vmax: `scanpy.pl.umap` vmax argument.
         vmin: `scanpy.pl.umap` vmin argument.

diff --git a/scyan/preprocess.py b/scyan/preprocess.py
@@ -18,7 +18,7 @@ def auto_logicle_transform(
     We recommend it for flow cytometry or spectral flow cytometry data.
 
     Args:
-        adata: An `anndata` object.
+        adata: An `AnnData` object.
         q: See logicle article. Defaults to 0.05.
         m: See logicle article. Defaults to 4.5.
     """
@@ -73,7 +73,7 @@ def asinh_transform(adata: AnnData, translation: float = 0, cofactor: float = 5)
     """Asinh transformation for cell-expressions: $asinh((x - translation)/cofactor)$.
 
     Args:
-        adata: An `anndata` object.
+        adata: An `AnnData` object.
         translation: Constant substracted to the marker expression before division by the cofactor.
         cofactor: Scaling factor before computing the asinh.
     """
@@ -93,7 +93,7 @@ def inverse_transform(
         If you scaled your data, the complete inverse consists in running [scyan.preprocess.unscale][] first, and then this function.
 
     Args:
-        adata: An `anndata` object.
+        adata: An `AnnData` object.
         obsm: Name of the anndata obsm to consider. If `None`, use `adata.X`.
         obsm_names: Names of the ordered markers from obsm. It is required if obsm is not `None`, if there are less markers than in `adata.X`, and if the transformation to reverse is `logicle`. Usually, it corresponds to `model.var_names`.
         transformation: Name of the transformation to inverse: one of `['logicle', 'asinh', None]`. By default, it chooses automatically depending on which transformation was previously run.
@@ -148,7 +148,7 @@ def scale(adata: AnnData, max_value: float = 10, center: Optional[bool] = None)
     """Tranforms the data such as (i) `std=1`, and (ii) either `0` is sent to `-1` (for CyTOF data) or `means=0` (for flow or spectral flow data); except if `center` is set (which overwrites the default behavior).
 
     Args:
-        adata: An `anndata` object.
+        adata: An `AnnData` object.
         max_value: Clip to this value after scaling.
         center: If `None`, data is only centered for spectral or flow cytometry data (recommended), else, it is centered or not according to the value given.
     """
@@ -175,7 +175,7 @@ def unscale(
     """Reverse standardisation. It requires to have run [scyan.preprocess.scale][] before.
 
     Args:
-        adata: An `anndata` object.
+        adata: An `AnnData` object.
         obsm: Name of the adata obsm to consider. If `None`, use `adata.X`.
         obsm_names: Names of the ordered markers from obsm. It is required if obsm is not `None`, and if there are less markers than in `adata.X`. Usually, it corresponds to `model.var_names`.
 

diff --git a/scyan/tools/__init__.py b/scyan/tools/__init__.py
@@ -1,4 +1,4 @@
-from .representation import umap, subcluster
+from .representation import umap, subcluster, leiden
 from .biomarkers import cell_type_ratios, mean_intensities
-from .gating import PolygonGatingUMAP
+from .gating import PolygonGatingUMAP, PolygonGatingScatter
 from .colors import palette_level