sclab 0.2.2__tar.gz → 0.3.4__tar.gz

{sclab-0.2.2 → sclab-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sclab
-Version: 0.2.2
+Version: 0.3.4
 Summary: sclab
 Author-email: Argenis Arriojas <ArriojasMaldonado001@umb.edu>
 Requires-Python: >=3.10,<3.13
@@ -14,15 +14,20 @@ License-File: LICENSE
 Requires-Dist: anndata
 Requires-Dist: anywidget
 Requires-Dist: ipywidgets
-Requires-Dist: itables
+Requires-Dist: itables<2.4
+Requires-Dist: matplotlib
 Requires-Dist: numpy<2.2
 Requires-Dist: pandas
 Requires-Dist: plotly<6.0
-Requires-Dist: requests>=2.32.3
+Requires-Dist: requests
+Requires-Dist: ripser>=0.6.12
 Requires-Dist: scikit-learn
+Requires-Dist: scipy<1.16
 Requires-Dist: svgpathtools
-Requires-Dist: tqdm>=4.67.1
+Requires-Dist: tqdm
 Requires-Dist: jupyterlab>=4.3.6 ; extra == "jupyter"
+Requires-Dist: anndata2ri>=1.3 ; extra == "r"
+Requires-Dist: rpy2>=3.5 ; extra == "r"
 Requires-Dist: scanpy[leiden, skmisc]>=1.10 ; extra == "scanpy"
 Requires-Dist: pytest>=8.3.4 ; extra == "test"
 Project-URL: Bug Tracker, https://github.com/umbibio/sclab/issues
@@ -31,6 +36,7 @@ Project-URL: Documentation, https://github.com/umbibio/sclab/docs
 Project-URL: Homepage, https://github.com/umbibio/sclab
 Project-URL: Repository, https://github.com/umbibio/sclab.git
 Provides-Extra: jupyter
+Provides-Extra: r
 Provides-Extra: scanpy
 Provides-Extra: test
 
@@ -60,7 +66,6 @@ Open a Jupyter Notebook and run the following:
 ```python
 from IPython.display import display
 from sclab import SCLabDashboard
-from sclab.examples.processor_steps import QC, Preprocess, PCA, Neighbors, UMAP, Cluster
 import scanpy as sc
 
 # Load your data
@@ -68,8 +73,6 @@ adata = sc.read_10x_h5("your_data.h5")
 
 # Create dashboard
 dashboard = SCLabDashboard(adata, name="My Analysis")
-# Add desired processing steps to the interface
-dashboard.pr.add_steps({"Processing": [QC, Preprocess, PCA, Neighbors, UMAP, Cluster]})
 
 # Display dashboard
 display(dashboard)
@@ -79,8 +82,10 @@ display(dashboard)
 # dashboard.pl  # Plotter
 # dashboard.pr  # Processor
 
-# the resulting AnnData object is found within the dataset object:
+# the active AnnData object is found within the dataset object:
 # dashboard.ds.adata
+
+# by default, the dashboard will update the loaded AnnData object in-place
 ```
 
 ## Components
@@ -89,6 +94,7 @@ display(dashboard)
 
 The main interface that integrates all components with a tabbed layout:
 - Main graph for visualizations
+- Results panel
 - Observations table
 - Genes table
 - Event logs

{sclab-0.2.2 → sclab-0.3.4}/README.md

@@ -24,7 +24,6 @@ Open a Jupyter Notebook and run the following:
 ```python
 from IPython.display import display
 from sclab import SCLabDashboard
-from sclab.examples.processor_steps import QC, Preprocess, PCA, Neighbors, UMAP, Cluster
 import scanpy as sc
 
 # Load your data
@@ -32,8 +31,6 @@ adata = sc.read_10x_h5("your_data.h5")
 
 # Create dashboard
 dashboard = SCLabDashboard(adata, name="My Analysis")
-# Add desired processing steps to the interface
-dashboard.pr.add_steps({"Processing": [QC, Preprocess, PCA, Neighbors, UMAP, Cluster]})
 
 # Display dashboard
 display(dashboard)
@@ -43,8 +40,10 @@ display(dashboard)
 # dashboard.pl  # Plotter
 # dashboard.pr  # Processor
 
-# the resulting AnnData object is found within the dataset object:
+# the active AnnData object is found within the dataset object:
 # dashboard.ds.adata
+
+# by default, the dashboard will update the loaded AnnData object in-place
 ```
 
 ## Components
@@ -53,6 +52,7 @@ display(dashboard)
 
 The main interface that integrates all components with a tabbed layout:
 - Main graph for visualizations
+- Results panel
 - Observations table
 - Genes table
 - Event logs

{sclab-0.2.2 → sclab-0.3.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "sclab"
-version = "0.2.2"
+version = "0.3.4"
 description = "sclab"
 readme = "README.md"
 authors = [
@@ -18,14 +18,17 @@ dependencies = [
     "anndata",
     "anywidget",
     "ipywidgets",
-    "itables",
+    "itables<2.4",
+    "matplotlib",
     "numpy<2.2",
     "pandas",
     "plotly<6.0",
-    "requests>=2.32.3",
+    "requests",
+    "ripser>=0.6.12",
     "scikit-learn",
+    "scipy<1.16",
     "svgpathtools",
-    "tqdm>=4.67.1",
+    "tqdm",
 ]
 
 [project.urls]
@@ -36,9 +39,10 @@ dependencies = [
 "Changelog" = "https://github.com/umbibio/sclab/blob/main/CHANGELOG.md"
 
 [project.optional-dependencies]
-test = ["pytest>=8.3.4"]
-scanpy = ["scanpy[leiden,skmisc]>=1.10"]
 jupyter = ["jupyterlab>=4.3.6"]
+r = ["anndata2ri>=1.3", "rpy2>=3.5"]
+scanpy = ["scanpy[leiden,skmisc]>=1.10"]
+test = ["pytest>=8.3.4"]
 
 [build-system]
 requires = ["flit_core>=3.2,<4"]
@@ -48,6 +52,9 @@ build-backend = "flit_core.buildapi"
 name = "sclab"
 source = "src/sclab"
 
+[tool.uv.sources]
+sclab-tools = { path = "../sclab-tools" }
+
 [dependency-groups]
 dev = [
     "bump-my-version>=0.31.1",
@@ -58,6 +65,8 @@ dev = [
     "mkdocs>=1.6.1",
     "mkdocs-material>=9.6.3",
     "mkdocs-jupyter>=0.25.1",
-    "scanpy[leiden]>=1.10.4",
+    "scanpy[harmony,leiden,scrublet,skmisc]>=1.10.4",
     "jupyterlab>=4.3.6",
+    "sclab-tools",
+    "scrublet>=0.2.3",
 ]

{sclab-0.2.2 → sclab-0.3.4}/src/sclab/__init__.py

@@ -6,4 +6,4 @@ __all__ = [
     "SCLabDashboard",
 ]
 
-__version__ = "0.2.2"
+__version__ = "0.3.4"

{sclab-0.2.2 → sclab-0.3.4}/src/sclab/_io.py

@@ -58,12 +58,6 @@ def load_adata_from_url(
     assert is_valid_url(url), "URL is not valid"
     url_path = Path(urlparse(url).path)
 
-    if url_path.suffix == ".h5":
-        try:
-            import scanpy as sc
-        except ImportError:
-            raise ImportError("Please install scanpy: `pip install scanpy`")
-
     file_content = fetch_file(url, progress=progress)
     match url_path.suffix:
         case ".h5":

{sclab-0.2.2 → sclab-0.3.4}/src/sclab/_sclab.py

@@ -170,7 +170,11 @@ class DataLoader(VBox):
         self.upload = FileUpload(layout=Layout(width="200px"))
         self.upload_info = Output(layout=Layout(width="95%"))
         self.upload_row = HBox(
-            [self.upload_row_label, self.upload, self.upload_info],
+            [
+                self.upload_row_label,
+                self.upload,
+                self.upload_info,
+            ],
             layout=Layout(width="100%"),
         )
         self.upload.observe(self.on_upload, "value")
@@ -187,7 +191,7 @@ class DataLoader(VBox):
         user_f_locals = inspect.stack()[2].frame.f_locals
         self.defined_adatas_dict = {}
         for name, variable_type in [(k, type(v)) for k, v in user_f_locals.items()]:
-            if variable_type is AnnData:
+            if variable_type is AnnData and not name.startswith("_"):
                 self.defined_adatas_dict[name] = user_f_locals[name]
 
         self.defined_adatas_label = Label(
@@ -213,8 +217,8 @@ class DataLoader(VBox):
         VBox.__init__(
             self,
             [
-                self.url_row,
-                self.upload_row,
+                # self.url_row,
+                # self.upload_row,
                 self.defined_adatas_row,
                 self.progress_output,
             ],
@@ -233,6 +237,8 @@ class DataLoader(VBox):
         self.adata = adata
 
     def on_upload(self, *args, **kwargs):
+        import tempfile
+
         from .scanpy.readwrite import read_10x_h5, read_h5ad
 
         files = self.upload.value
@@ -256,14 +262,20 @@ class DataLoader(VBox):
 
         match path.suffix:
             case ".h5":
-                adata = read_10x_h5(contents)
+                with tempfile.NamedTemporaryFile(suffix=".h5") as tmp:
+                    tmp.write(contents.getbuffer())
+                    tmp.flush()
+                    adata = read_10x_h5(tmp.name)
             case ".h5ad":
-                adata = read_h5ad(contents)
+                with tempfile.NamedTemporaryFile(suffix=".h5ad") as tmp:
+                    tmp.write(contents.getbuffer())
+                    tmp.flush()
+                    adata = read_h5ad(tmp.name)
             case _:
                 self.upload_info.clear_output()
                 with self.upload_info:
                     print(f"`{filename}` is not valid")
-                    print("Please upload a 10x h5 or h5ad file")
+                    print("Please upload a 10x .h5 or .h5ad file")
                 return
 
         if var_names in adata.var:

{sclab-0.2.2 → sclab-0.3.4}/src/sclab/dataset/_dataset.py

@@ -365,7 +365,7 @@ class SCLabDataset(EventClient):
         if not index.isin(self.metadata.index).all():
             raise InvalidRowSubset("index contains invalid values")
 
-        self.adata = self.adata[index].copy()
+        self.adata._inplace_subset_obs(index)
 
         self.broker.publish("dset_total_rows_change", self.metadata)
 

{sclab-0.2.2 → sclab-0.3.4}/src/sclab/dataset/processor/_processor.py

@@ -1025,22 +1025,37 @@ class Processor(EventClient):
                 else:
                     control.value = current_value
 
-    def dset_anndata_layers_change_callback(self, layers):
-        options = {layer: layer for layer in layers}
+    def dset_anndata_layers_change_callback(self, *args, **kwargs):
+        layer_options = {key: key for key in self.dataset.adata.layers.keys()}
+        obsm_options = {key: key for key in self.dataset.adata.obsm.keys()}
+
         for control in self.all_controls_list:
             if not isinstance(control, Dropdown):
                 continue
             description: str = control.description
+
             if description.lower().strip(" :.") == "layer":
                 current_value = control.value
-                control.options = options
+                control.options = layer_options
+                if current_value not in control.options:
+                    control.value = None
+                else:
+                    control.value = current_value
+
+            if description.lower().strip(" :.") == "use rep":
+                current_value = control.value
+                control.options = {**layer_options, **obsm_options}
                 if current_value not in control.options:
                     control.value = None
                 else:
                     control.value = current_value
 
     def dset_data_dict_change_callback(self, *args, **kwargs):
-        options = {v: v for v in self.dataset.adata.obsm.keys()}
+        options = [
+            *self.dataset.adata.layers.keys(),
+            *self.dataset.adata.obsm.keys(),
+        ]
+        options = {v: v for v in options}
         for control in self.all_controls_list:
             if not isinstance(control, Dropdown):
                 continue

{sclab-0.2.2 → sclab-0.3.4}/src/sclab/dataset/processor/_results_panel.py

@@ -1,14 +1,24 @@
-from ipywidgets import GridBox, Layout, Stack, ToggleButtons, link
+from ipywidgets import Box, Dropdown, Layout, Stack, VBox, link
 
 from sclab.event import EventBroker, EventClient
 
+# Create a layout with a bottom border to act as the horizontal line
+hr_layout = Layout(
+    border="1px solid black",  # 1px width, solid style, black color
+    margin="10px 0",  # Add margin for spacing above and below
+    width="100%",  # Extend the line across the full width
+)
+
+# Create a Box widget with the styled layout
+hr = Box(layout=hr_layout)
+
 
 class _Results:
     namespace: str
 
 
-class ResultsPanel(GridBox, EventClient):
-    available_results: ToggleButtons
+class ResultsPanel(VBox, EventClient):
+    available_results: Dropdown
     results_stack: Stack
 
     events: list[str] = [
@@ -22,7 +32,7 @@ class ResultsPanel(GridBox, EventClient):
     ):
         EventClient.__init__(self, broker)
 
-        self.available_results = ToggleButtons(options={})
+        self.available_results = Dropdown(options={}, description="Category")
         self.results_stack = Stack([])
 
         link(
@@ -30,15 +40,19 @@ class ResultsPanel(GridBox, EventClient):
             (self.results_stack, "selected_index"),
         )
 
-        GridBox.__init__(
+        VBox.__init__(
             self,
-            [self.available_results, self.results_stack],
-            layout=Layout(
-                width="100%",
-                grid_template_columns="150px auto",
-                grid_template_areas=""" "available-results selected-results_stack" """,
-                border="0px solid black",
-            ),
+            [
+                self.available_results,
+                hr,
+                self.results_stack,
+            ],
+            # layout=Layout(
+            #     width="100%",
+            #     grid_template_columns="150px auto",
+            #     grid_template_areas=""" "available-results selected-results_stack" """,
+            #     border="0px solid black",
+            # ),
         )
 
     def add_result(self, results: _Results):

{sclab-0.2.2 → sclab-0.3.4}/src/sclab/examples/processor_steps/__init__.py

@@ -1,5 +1,8 @@
 from ._cluster import Cluster
 from ._differential_expression import DifferentialExpression
+from ._doublet_detection import DoubletDetection
+from ._gene_expression import GeneExpression
+from ._integration import Integration
 from ._neighbors import Neighbors
 from ._pca import PCA
 from ._preprocess import Preprocess
@@ -10,8 +13,11 @@ __all__ = [
     "QC",
     "Preprocess",
     "PCA",
+    "Integration",
     "Neighbors",
     "UMAP",
     "Cluster",
+    "DoubletDetection",
+    "GeneExpression",
     "DifferentialExpression",
 ]

{sclab-0.2.2 → sclab-0.3.4}/src/sclab/examples/processor_steps/_differential_expression.py

@@ -25,7 +25,7 @@ class DifferentialExpressionResults(VBox):
 
     def __init__(self, dataset: SCLabDataset):
         self.dataset = dataset
-        self.result_selector = Dropdown()
+        self.result_selector = Dropdown(description="Analysis Name")
         self.group_selector = ToggleButtons()
         self.table_output = Output()
 
@@ -198,6 +198,7 @@ class DifferentialExpression(ProcessorStepBase):
             reference=reference,
             layer=layer,
             key_added=key_added,
+            pts=True,
         )
 
         self.results.sync_results_list(focus_result=key_added)

sclab-0.3.4/src/sclab/examples/processor_steps/_doublet_detection.py

@@ -0,0 +1,68 @@
+from ipywidgets import Dropdown
+
+from sclab.dataset.processor import Processor
+from sclab.dataset.processor.step import ProcessorStepBase
+from sclab.tools.doublet_detection import scrublet
+
+# from sclab.tools.doublet_detection import doubletdetection
+# from sclab.tools.doublet_detection import scdblfinder
+
+
+class DoubletDetection(ProcessorStepBase):
+    parent: Processor
+    name: str = "doublet_detection"
+    description: str = "Doublet Detection"
+
+    def __init__(self, parent: Processor) -> None:
+        variable_controls = dict(
+            layer=Dropdown(
+                options=tuple(parent.dataset.adata.layers.keys()),
+                value=None,
+                description="Layer",
+            ),
+            flavor=Dropdown(
+                options=[
+                    "scrublet",
+                    # "doubletdetection",
+                    # "scDblFinder",
+                ],
+                description="Flavor",
+            ),
+        )
+
+        super().__init__(
+            parent=parent,
+            fixed_params={},
+            variable_controls=variable_controls,
+        )
+
+    def function(self, layer: str, flavor: str):
+        adata = self.parent.dataset.adata
+
+        kvargs = {"adata": adata, "layer": layer, "key_added": flavor}
+
+        self.broker.std_output.clear_output(wait=False)
+        with self.broker.std_output:
+            match flavor:
+                # case "scDblFinder":
+                #     scdblfinder(**kvargs, clusters_col="leiden")
+
+                # case "doubletdetection":
+                #     doubletdetection(
+                #         **kvargs,
+                #         pseudocount=1,
+                #         clustering_algorithm="leiden",
+                #         clustering_kwargs=dict(resolution=5.0),
+                #     )
+
+                case "scrublet":
+                    scrublet(**kvargs)
+
+                case _:
+                    raise ValueError(f"Unknown flavor: {flavor}")
+
+        self.broker.publish(
+            "dset_metadata_change",
+            self.parent.dataset.metadata,
+            f"{flavor}_label",
+        )

sclab-0.3.4/src/sclab/examples/processor_steps/_gene_expression.py

@@ -0,0 +1,125 @@
+import numpy as np
+import pandas as pd
+import plotly.colors as pc
+import plotly.express as px
+from ipywidgets import Combobox, Dropdown
+
+from sclab.dataset.processor import Processor
+from sclab.dataset.processor.step import ProcessorStepBase
+
+colorscales = list(
+    filter(lambda s: "swatch" not in s and not s.startswith("_"), dir(pc.sequential))
+)
+
+
+class GeneExpression(ProcessorStepBase):
+    parent: Processor
+    name: str = "gene_expression"
+    description: str = "Gene Expression"
+
+    run_button_description = "Plot Expression"
+
+    def __init__(self, parent: Processor) -> None:
+        df = parent.dataset.metadata.select_dtypes("number")
+        df = parent.dataset.metadata
+        axis_key_options = {"": None, **{c: c for c in df.columns}}
+
+        gene_input_options = parent.dataset.adata.var_names
+        genes_df = parent.dataset.adata.var
+        info_cols = ["name", "symbol", "description"]
+        for col in [
+            c for c in genes_df.columns if any([s.lower() in c for s in info_cols])
+        ]:
+            new_info = genes_df[col].astype(str).str.replace("nan", "")
+            gene_input_options = gene_input_options + " - " + new_info
+
+        variable_controls = dict(
+            gene_input=Combobox(
+                placeholder="Type gene name",
+                options=gene_input_options.to_list(),
+                description="Gene",
+                ensure_option=True,
+            ),
+            layer=Dropdown(
+                options=tuple(parent.dataset.adata.layers.keys()),
+                value=None,
+                description="Layer",
+            ),
+            time_key=Dropdown(
+                options=axis_key_options,
+                value=None,
+                description="Horiz. axis",
+            ),
+            colorscale=Dropdown(
+                options=colorscales, value="Oryel", description="Col. scale"
+            ),
+        )
+
+        super().__init__(
+            parent=parent,
+            fixed_params={},
+            variable_controls=variable_controls,
+        )
+
+        self.variable_controls["gene_input"].observe(self.send_plot, names="value")
+        self.variable_controls["layer"].observe(self.send_plot, names="value")
+        self.variable_controls["time_key"].observe(self.send_plot, names="value")
+        self.variable_controls["colorscale"].observe(self.send_plot, names="value")
+
+    def function(self, *pargs, **kwargs):
+        self.send_plot({})
+
+    def send_plot(self, change: dict):
+        adata = self.parent.dataset.adata
+        metadata = self.parent.dataset.metadata
+        selected_cells = self.parent.dataset.selected_rows
+
+        gene_input: str = self.variable_controls["gene_input"].value
+        layer: str = self.variable_controls["layer"].value
+        time_key: str = self.variable_controls["time_key"].value
+        colorscale: str = self.variable_controls["colorscale"].value
+
+        if gene_input is None or gene_input == "":
+            self.update_output("")
+            return
+
+        if layer is None or layer == "":
+            self.update_output("")
+            return
+
+        gene_id = gene_input.split(" ")[0]
+
+        if layer == "X":
+            X = adata[:, gene_id].X
+        else:
+            X = adata[:, gene_id].layers[layer]
+
+        E = np.asarray(X.sum(axis=1)).flatten()
+
+        self.update_output(f"Showing gene: {gene_id}")
+        # self.variable_controls["gene_input"].value = ""
+
+        df = pd.DataFrame({gene_id: E}, index=adata.obs.index)
+        metadata = metadata.join(df)
+        if selected_cells.size > 0:
+            metadata = metadata.loc[selected_cells]
+
+        if time_key is None:
+            self.broker.publish(
+                "dplt_plot_figure_request",
+                metadata=metadata,
+                colorby=gene_id,
+                color_continuous_scale=colorscale,
+            )
+            return
+
+        fig = px.scatter(
+            metadata,
+            x=time_key,
+            y=gene_id,
+            color=gene_id,
+            color_continuous_scale=colorscale,
+            hover_name=adata.obs.index,
+            title=f"Gene: {gene_id}, Layer: {layer}",
+        )
+        self.broker.publish("dplt_plot_figure_request", figure=fig)