senoquant 1.0.0b3__py3-none-any.whl → 1.0.0b4__py3-none-any.whl

senoquant/tabs/visualization/plots/umap.py

@@ -0,0 +1,140 @@
+"""UMAP plot handler for visualization."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Iterable
+
+from .base import PlotData, SenoQuantPlot
+
+
+class UMAPData(PlotData):
+    """Configuration data for UMAP plot."""
+
+    pass
+
+
+class UMAPPlot(SenoQuantPlot):
+    """UMAP dimensionality reduction plot handler."""
+
+    feature_type = "UMAP"
+    order = 1
+
+    def build(self) -> None:
+        """Build the UI for UMAP plot configuration."""
+        # Minimal UI for now; can add controls for n_components, metric, etc. later
+        pass
+
+    def plot(
+        self, 
+        temp_dir: Path, 
+        input_path: Path, 
+        export_format: str,
+        markers: list[str] | None = None,
+        thresholds: dict[str, float] | None = None,
+    ) -> Iterable[Path]:
+        """Generate UMAP plot from input CSV.
+
+        Parameters
+        ----------
+        temp_dir : Path
+            Temporary directory to write plot output.
+        input_path : Path
+            Path to input CSV file or folder containing CSV files.
+        export_format : str
+            Output format ("png", "svg", or "pdf").
+        markers : list of str, optional
+            List of selected markers to include.
+        thresholds : dict, optional
+            Dictionary of {marker_name: threshold_value} for filtering.
+
+        Returns
+        -------
+        iterable of Path
+            Paths to generated plot files.
+        """
+        try:
+            try:
+                import pandas as pd
+            except ImportError:
+                print("[UMAPPlot] pandas is not installed; skipping plot generation.")
+                return []
+            try:
+                import matplotlib.pyplot as plt
+            except ImportError:
+                print("[UMAPPlot] matplotlib is not installed; skipping plot generation.")
+                return []
+            try:
+                from umap import UMAP as UMAPReducer
+            except ImportError:
+                print("[UMAPPlot] umap-learn is not installed; skipping plot generation.")
+                return []
+
+            print(f"[UMAPPlot] Starting with input_path={input_path}")
+            # Find the first data file (CSV or Excel) in the input folder
+            data_files = list(input_path.glob("*.csv")) + list(input_path.glob("*.xlsx")) + list(input_path.glob("*.xls"))
+            print(f"[UMAPPlot] Found {len(data_files)} data files")
+            if not data_files:
+                print(f"[UMAPPlot] No CSV/Excel files found in {input_path}")
+                return []
+            
+            data_file = data_files[0]
+            print(f"[UMAPPlot] Reading {data_file}")
+            if data_file.suffix.lower() in ('.xlsx', '.xls'):
+                df = pd.read_excel(data_file)
+            else:
+                df = pd.read_csv(data_file)
+            print(f"[UMAPPlot] Loaded dataframe with shape {df.shape}")
+            if df.empty:
+                print(f"[UMAPPlot] DataFrame is empty")
+                return []
+
+            # Apply thresholds if provided
+            if thresholds:
+                for marker, thresh in thresholds.items():
+                    col_name = f"{marker}_mean_intensity"
+                    if col_name in df.columns:
+                        # Clip values below threshold to 0
+                        df.loc[df[col_name] < thresh, col_name] = 0
+
+            # Select numeric columns for UMAP
+            if markers:
+                numeric_cols = [f"{m}_mean_intensity" for m in markers if f"{m}_mean_intensity" in df.columns]
+                print(f"[UMAPPlot] Using {len(numeric_cols)} selected markers for UMAP")
+            else:
+                numeric_cols = df.select_dtypes(include=["number"]).columns
+                print(f"[UMAPPlot] Found {len(numeric_cols)} numeric columns (default)")
+            
+            if len(numeric_cols) < 2:
+                print(f"[UMAPPlot] Need at least 2 numeric columns for UMAP, found {len(numeric_cols)}")
+                return []
+
+            X = df[numeric_cols].values
+
+            # Fit UMAP
+            print(f"[UMAPPlot] Fitting UMAP with {len(X)} samples")
+            reducer = UMAPReducer(n_components=2, random_state=42)
+            embedding = reducer.fit_transform(X)
+            print(f"[UMAPPlot] UMAP embedding created with shape {embedding.shape}")
+
+            # Create plot
+            fig, ax = plt.subplots(figsize=(8, 6))
+            ax.scatter(embedding[:, 0], embedding[:, 1], alpha=0.6, s=20)
+            ax.set_xlabel("UMAP 1")
+            ax.set_ylabel("UMAP 2")
+            ax.set_title("UMAP Plot")
+
+            # Save plot
+            output_file = temp_dir / f"umap_plot.{export_format}"
+            print(f"[UMAPPlot] Saving to {output_file}")
+            fig.savefig(str(output_file), dpi=150, bbox_inches="tight")
+            plt.close(fig)
+            print(f"[UMAPPlot] Plot saved successfully")
+
+            return [output_file]
+
+        except Exception as e:
+            import traceback
+            print(f"[UMAPPlot] ERROR generating UMAP plot: {e}")
+            print(traceback.format_exc())
+            return []

{senoquant-1.0.0b3.dist-info → senoquant-1.0.0b4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: senoquant
-Version: 1.0.0b3
+Version: 1.0.0b4
 Summary: napari plugin for spatial quantification of senescence markers in tissue imaging
 Author: SenoQuant Contributors
 Maintainer: SenoQuant Contributors
@@ -43,13 +43,13 @@ Requires-Dist: onnxruntime-gpu>=1.21.0; platform_system != "Darwin"
 Requires-Dist: openpyxl>=3.1
 Requires-Dist: huggingface_hub>=0.23.0
 Requires-Dist: scikit-image<0.25,>=0.22
+Requires-Dist: PyWavelets>=1.5
 Requires-Dist: scipy>=1.8
 Requires-Dist: senoquant-stardist-ext>=0.1.1
 Requires-Dist: dask[array]>=2024.4
 Requires-Dist: dask[distributed]>=2024.4
-Provides-Extra: gpu
-Requires-Dist: cupy-cuda12x>=12.0; extra == "gpu"
-Requires-Dist: cucim>=23.4; extra == "gpu"
+Requires-Dist: matplotlib>=3.8
+Requires-Dist: umap-learn>=0.5
 Provides-Extra: all
 Requires-Dist: napari[all]; extra == "all"
 Requires-Dist: bioio>=3.2.0; extra == "all"
@@ -72,12 +72,13 @@ Requires-Dist: onnxruntime-gpu>=1.21.0; platform_system != "Darwin" and extra ==
 Requires-Dist: openpyxl>=3.1; extra == "all"
 Requires-Dist: huggingface_hub>=0.23.0; extra == "all"
 Requires-Dist: scikit-image<0.25,>=0.22; extra == "all"
+Requires-Dist: PyWavelets>=1.5; extra == "all"
 Requires-Dist: scipy>=1.8; extra == "all"
 Requires-Dist: senoquant-stardist-ext>=0.1.1; extra == "all"
 Requires-Dist: dask[array]>=2024.4; extra == "all"
 Requires-Dist: dask[distributed]>=2024.4; extra == "all"
-Requires-Dist: cupy-cuda12x>=12.0; extra == "all"
-Requires-Dist: cucim>=23.4; extra == "all"
+Requires-Dist: matplotlib>=3.8; extra == "all"
+Requires-Dist: umap-learn>=0.5; extra == "all"
 Dynamic: license-file
 
 # SenoQuant

{senoquant-1.0.0b3.dist-info → senoquant-1.0.0b4.dist-info}/RECORD

@@ -1,15 +1,15 @@
-senoquant/__init__.py,sha256=mNRYmhG-SXPlokw7tiuHYRGLzqtfECSRH-QIpZiEJbk,269
+senoquant/__init__.py,sha256=UbZDFUGVkGaxQFqjwIfVZt0x2mckTYJpbFUXQBGg5FA,269
 senoquant/_reader.py,sha256=HVGhwQTuuDbvNM9tEkUpE6js_Lzh7vTHXdYfDCqvvXk,154
-senoquant/_widget.py,sha256=nuNaKvWAx7aKXORAipOUf7sUI5I3DvZazXnwrJcBqcw,1102
+senoquant/_widget.py,sha256=83J186GFmImr_lY3wo3bZKouW_AHR_xannIlJZwtv1M,1233
 senoquant/napari.yaml,sha256=2r1EpZcV1B3mLv0z3FwjS8e1T-yIMzoWvNj2SBqmftI,1664
 senoquant/utils.py,sha256=XpvJjaoN_9DMD-cxURCStFccBYNccttdJtGnFO6PD2E,641
 senoquant/reader/__init__.py,sha256=3lDuOpQC8TGUdfXdpLrr7MaszOVCqKMYM9YaTdq3DVQ,92
 senoquant/reader/core.py,sha256=GGEU_FVFohhWR0KkbuTl50wdS04WzroBBC67gbwfLtA,15809
-senoquant/tabs/__init__.py,sha256=DnIT3E7XRSw2CmlZ-Ma4aYpoUFSFjF-66kMDNPaZEmU,371
+senoquant/tabs/__init__.py,sha256=YvagQQzYgZNMsquHD8gvNwJJv6TfdKoycWORSLOjrLk,448
 senoquant/tabs/batch/__init__.py,sha256=0-xDYyAEEch9Yq7OhGeTkgoXus52Y_SQjqvtIbI-I20,291
-senoquant/tabs/batch/backend.py,sha256=R8cSMkPL8sf49-vNc7PnvWrLA3FQ_1KJ9KQHSUnd0Os,24727
+senoquant/tabs/batch/backend.py,sha256=0npTLVEHP_ZWrAhCy3vyQiH59j7lwD1KoYLqBZABhwo,26683
 senoquant/tabs/batch/config.py,sha256=w6DR0Nw6BL0hrFacQPIAHb-wCirYnogYJgmAPy2j9zo,8639
-senoquant/tabs/batch/frontend.py,sha256=_zhv2H7UneeMtB8jZ6YZhFGaqu6DhuAB6Q7BtHS3fxA,51987
+senoquant/tabs/batch/frontend.py,sha256=4nT8_4YrTKIHPL0IfV-RQVMVG8U5FBGZWHFkQ71Dgec,56289
 senoquant/tabs/batch/io.py,sha256=mggktbDDsGr4hQvpu4oj1eJcxG-xiPwfquO7QBesdDk,8382
 senoquant/tabs/batch/layers.py,sha256=JjWS6WVZ3YOd-KZ4AjqstRF0qTPwOxOgGHd5FXrer08,2078
 senoquant/tabs/quantification/__init__.py,sha256=iCqW7cg9QFfUdnYF7JSwOEus_tm66IZXdxSShy7RxwA,34
@@ -134,14 +134,24 @@ senoquant/tabs/settings/backend.py,sha256=ZVtmrUYNsox7DiVMlcS666XRyLG7GksgC818oo
 senoquant/tabs/settings/frontend.py,sha256=_hTWJHZeEtU6n6qke31R6Es63knKeHhWZYUZj0ep79s,721
 senoquant/tabs/spots/__init__.py,sha256=dYrAIzX3A5w4TOLRRadxL2agOte_Z0ennuEIOCbJD5w,25
 senoquant/tabs/spots/backend.py,sha256=LZdkNzw-bpK0NClbeLttpg4C_8AqnIFg1W4NaxepTSs,4547
-senoquant/tabs/spots/frontend.py,sha256=IGyT-rWbX_vVgaIiDkxkijt6EoAPdnkW2dKOvL2Ziwg,28151
+senoquant/tabs/spots/frontend.py,sha256=2uRrhWXT8q_8MySYVDoGQyETq8RDHLua5haCwnXehi4,30262
 senoquant/tabs/spots/models/__init__.py,sha256=OKnBIi-aaBsuXmwQNeg4EKeV66gSscedXyZ1-O3cJhY,123
 senoquant/tabs/spots/models/base.py,sha256=VABmb2E7xvWOW8J60ZZkog0ZEG4XyW96qeXJMZVuKT8,2786
-senoquant/tabs/spots/models/ufish/details.json,sha256=126sbAoU1SMCLCCphUKcTqh4HtKbPYDdgm41cNifMmA,312
-senoquant/tabs/spots/models/ufish/model.py,sha256=iOxdQizYmQ8Fj-CvFjMkAEjFBKpwqC5gjxmHc9jfGBI,4236
+senoquant/tabs/spots/models/rmp/details.json,sha256=FIuLJmA0HPvhUkLd04IPY47Hg2duV7dlwpl9BcN4G9w,1128
+senoquant/tabs/spots/models/rmp/model.py,sha256=pdeYaXbQ1lQK1D_ZUhn0Chf9XSDV4dG2Nn4Jht3v3mI,19181
+senoquant/tabs/spots/models/ufish/details.json,sha256=TW1pagjfQI2CYFAIRJ6pB14_bI1nU7EsoW5PLZtMcJg,602
+senoquant/tabs/spots/models/ufish/model.py,sha256=YxCH5k2R3E9gk7H8CAbxrIQ2qa5yPOEYv7uj-hM8N-g,11074
 senoquant/tabs/spots/ufish_utils/__init__.py,sha256=QH8ReVcWtg2_Mgx2Oxg6OZbcQ8ntp42lOMlaJoT3ZSE,394
-senoquant/tabs/spots/ufish_utils/core.py,sha256=ZuJU8tkY3KJ9N-jMqMeYjsCcfhaZon44e1CcjxLR51Q,10649
-senoquant-1.0.0b3.dist-info/licenses/LICENSE,sha256=wJjNEZJA6A7m6ozqNeq3tXi4X5gzbEGraFm2jw5ahG0,1509
+senoquant/tabs/spots/ufish_utils/core.py,sha256=agSR6KD7potqvKrUQlcGTcOuhQTykPkTcgwYI6JwHBw,11764
+senoquant/tabs/visualization/__init__.py,sha256=RV8qmD1xqR5i2PlAk_1Dx-6XRig9q7D7H2kwcFPGruc,33
+senoquant/tabs/visualization/backend.py,sha256=z0_mHft-fnzqSE_qv0JTX5UgWhCJ7vf11Cpa210NQDo,10877
+senoquant/tabs/visualization/frontend.py,sha256=E4h7jBmyF7ZBnKUH1Hhvfj9YDzrbnJljp6h1k6PYLRg,42580
+senoquant/tabs/visualization/plots/__init__.py,sha256=fyic7xGD_h4CNoDI9Ui1UrZZwgPwqJPwJ16YFRW6aXE,1965
+senoquant/tabs/visualization/plots/base.py,sha256=hUsX7Oz2TlQb-g3eAKZL82URyoB2pbyQPCPNvGQdCzg,4297
+senoquant/tabs/visualization/plots/double_expression.py,sha256=jcYEDt_taHtm4uSUx7viv3J2BW4MP7cGax33guwo1bc,6637
+senoquant/tabs/visualization/plots/spatialplot.py,sha256=4GR4w8ChBFZ_hsh03_kRo3yKCfkCEbfqIeJvC3IxQ_M,5673
+senoquant/tabs/visualization/plots/umap.py,sha256=fQuwtmsuMyWmUMcmmcuMOVqKrON0aBi-xMQ0W_vxyeA,5134
+senoquant-1.0.0b4.dist-info/licenses/LICENSE,sha256=wJjNEZJA6A7m6ozqNeq3tXi4X5gzbEGraFm2jw5ahG0,1509
 ufish/__init__.py,sha256=ls1camlIoMxEZz9gSkZ1OJo-MXqHWwKPtdPbZJmwp7E,22
 ufish/api.py,sha256=Nezcny6yTGMwdmB8qZv5dyCAeDq1RCSvMcAiZmGcn1s,29658
 ufish/model/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -154,8 +164,8 @@ ufish/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 ufish/utils/img.py,sha256=8CkEZyWCKriCFuSq_qPphwmj-WPUrFMDyMGnRPQCA3k,12904
 ufish/utils/log.py,sha256=_nF9sJJAMFqQJvvIUYI5o2ffAMTHmQhDVkp2EI3rsvc,280
 ufish/utils/spot_calling.py,sha256=y7lSWOuxG7ca1nFz2uKC7x7aSzocqQu2p3tCijvvLSI,3970
-senoquant-1.0.0b3.dist-info/METADATA,sha256=pY9mFrZO9gi6IBl4MGxM7y9XWrSN9pueFvzfh0nc6us,7269
-senoquant-1.0.0b3.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-senoquant-1.0.0b3.dist-info/entry_points.txt,sha256=_HUyyJcDeBQVdUKjY3ZW9fqvHLWFn2mPXS_9KBPIzuU,52
-senoquant-1.0.0b3.dist-info/top_level.txt,sha256=n-FXEO-BsEDOq-ur29UIHcQLD-PgvSbN2eV1onngiSU,16
-senoquant-1.0.0b3.dist-info/RECORD,,
+senoquant-1.0.0b4.dist-info/METADATA,sha256=23gWiyLwY3INGiBy-N5-heQUVt0xirsQPguswkV8XQE,7297
+senoquant-1.0.0b4.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+senoquant-1.0.0b4.dist-info/entry_points.txt,sha256=_HUyyJcDeBQVdUKjY3ZW9fqvHLWFn2mPXS_9KBPIzuU,52
+senoquant-1.0.0b4.dist-info/top_level.txt,sha256=n-FXEO-BsEDOq-ur29UIHcQLD-PgvSbN2eV1onngiSU,16
+senoquant-1.0.0b4.dist-info/RECORD,,