zmap-tools 0.2.2.2__tar.gz → 0.2.2.5__tar.gz

{zmap_tools-0.2.2.2 → zmap_tools-0.2.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: zmap-tools
-Version: 0.2.2.2
+Version: 0.2.2.5
 Summary: API for working with ZMAP (Zebrafish Multi-Atlas Project)
 Author-email: Daniel Wagner <Daniel.Wagner@ucsf.edu>
 License: BSD 3-Clause License
@@ -44,26 +44,30 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: anndata==0.12.18
-Requires-Dist: scanpy==1.12.1
-Requires-Dist: numpy==2.0.2
-Requires-Dist: numba==0.60.0
-Requires-Dist: llvmlite==0.43.0
-Requires-Dist: pandas<3.0,>=2.0
-Requires-Dist: matplotlib<4.0,>=3.7
+Requires-Dist: anndata<0.14,>=0.12.18
+Requires-Dist: scanpy<1.13,>=1.12.1
+Requires-Dist: numpy<3,>=2.1
+Requires-Dist: numba>=0.64
+Requires-Dist: pandas<3,>=2.2
+Requires-Dist: matplotlib<4,>=3.7
 Requires-Dist: requests>=2.31
-Requires-Dist: scipy==1.16.3
-Requires-Dist: scikit-learn==1.6.1
-Requires-Dist: faiss-cpu==1.14.3
-Requires-Dist: seaborn==0.13.2
+Requires-Dist: scipy<2,>=1.15
+Requires-Dist: scikit-learn<2,>=1.6
+Requires-Dist: faiss-cpu<2,>=1.14.3
+Requires-Dist: seaborn<0.14,>=0.13.2
 Requires-Dist: tqdm>=4.66
 Requires-Dist: adjustText>=0.8
-Requires-Dist: symphonypy==0.2.4
-Requires-Dist: igraph==1.0.0
-Requires-Dist: leidenalg==0.12.0
+Requires-Dist: symphonypy<0.3,>=0.2.4
+Requires-Dist: igraph<2,>=1.0
+Requires-Dist: leidenalg<0.13,>=0.12
+Requires-Dist: joblib>=1.3
+Requires-Dist: h5py>=3.0
+Requires-Dist: torch>=2.0
+Requires-Dist: lightgbm>=4.0
 Dynamic: license-file
 
 # zmap-tools

{zmap_tools-0.2.2.2 → zmap_tools-0.2.2.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "zmap-tools"
-version = "0.2.2.2"
+version = "0.2.2.5"
 description = "API for working with ZMAP (Zebrafish Multi-Atlas Project)"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -24,28 +24,32 @@ classifiers = [
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
 ]
 
 dependencies = [
-  "anndata==0.12.18",
-  "scanpy==1.12.1",
+  "anndata>=0.12.18,<0.14",
+  "scanpy>=1.12.1,<1.13",
 
-  "numpy==2.0.2",
-  "numba==0.60.0",
-  "llvmlite==0.43.0",
+  "numpy>=2.1,<3",
+  "numba>=0.64",
 
-  "pandas>=2.0,<3.0",
-  "matplotlib>=3.7,<4.0",
+  "pandas>=2.2,<3",
+  "matplotlib>=3.7,<4",
   "requests>=2.31",
-  "scipy==1.16.3",
-  "scikit-learn==1.6.1",
-  "faiss-cpu==1.14.3",
-  "seaborn==0.13.2",
+  "scipy>=1.15,<2",
+  "scikit-learn>=1.6,<2",
+  "faiss-cpu>=1.14.3,<2",
+  "seaborn>=0.13.2,<0.14",
   "tqdm>=4.66",
   "adjustText>=0.8",
-  "symphonypy==0.2.4",
-  "igraph==1.0.0",
-  "leidenalg==0.12.0",
+  "symphonypy>=0.2.4,<0.3",
+  "igraph>=1.0,<2",
+  "leidenalg>=0.12,<0.13",
+  "joblib>=1.3",
+  "h5py>=3.0",
+  "torch>=2.0",
+  "lightgbm>=4.0",
 ]
 
 [project.urls]
@@ -55,6 +59,12 @@ Issues = "https://github.com/WagnerLabUCSF/zmap-tools/issues"
 
 [tool.setuptools]
 package-dir = {"" = "src"}
+include-package-data = true
 
 [tool.setuptools.packages.find]
 where = ["src"]
+
+[tool.setuptools.package-data]
+zmap = [
+  "predict/baseline2_file/**/*",
+]

zmap_tools-0.2.2.5/src/zmap/__init__.py

@@ -0,0 +1,76 @@
+from __future__ import annotations
+
+"""
+zmap-tools — Python API for the Zebrafish Multi-Atlas Project (ZMAP).
+
+A curated single-cell RNA-seq reference atlas for zebrafish development,
+with tools for reference loading, label transfer, and visualization.
+
+Submodules
+----------
+reference (aliased as ref)
+    Download, cache, and load ZMAP reference H5ADs and consensus markers.
+predict
+    kNN-based label transfer from the ZMAP reference to query datasets.
+dotplot
+    Publication-ready dotplot visualization of gene expression patterns.
+"""
+
+from importlib.metadata import PackageNotFoundError, version as _version
+
+# Package version (from the PyPI/dist name)
+try:
+    __version__ = _version("zmap-tools")
+except PackageNotFoundError:
+    __version__ = "0.0.0"
+
+# Import subpackages as attributes 
+from . import reference    # zmap.reference
+from . import dotplot      # zmap.dotplot
+from . import predict      # zmap.predict
+
+# Scanpy-style aliases: 
+ref = reference
+
+# Top-level convenience APIs for biological module / baseline2 workflows.
+apply_encoder = predict.apply_encoder
+zmap_projection = predict.zmap_projection
+predict_pseudo_tissue = predict.predict_pseudo_tissue
+knn_config = predict.knn_config
+time_prediction_KNN = predict.time_prediction_KNN
+time_prediction_MLP = predict.time_prediction_MLP
+predict_labels_MLP = predict.predict_labels_MLP
+predict_labels_mlp = predict.predict_labels_mlp
+predict_labels_baseline2 = predict.predict_labels_baseline2
+predict_labels_baseline_tissue = predict.predict_labels_baseline_tissue
+baseline2 = predict.baseline2
+baseline_tissue = predict.baseline_tissue
+plot_conf_entropy_margin = predict.plot_conf_entropy_margin
+plot_pseudo_tissue_conf_entropy_margin = predict.plot_pseudo_tissue_conf_entropy_margin
+plot_confusion_matrix = predict.plot_confusion_matrix
+report_leiden_celltype_topk = predict.report_leiden_celltype_topk
+plot_leiden_celltype = predict.plot_leiden_celltype
+plot_projection_celltype_overlay = predict.plot_projection_celltype_overlay
+
+__all__ = ["__version__", "ref", "dotplot", "predict"]
+
+__all__ += [
+    "apply_encoder",
+    "zmap_projection",
+    "predict_pseudo_tissue",
+    "knn_config",
+    "time_prediction_KNN",
+    "time_prediction_MLP",
+    "predict_labels_MLP",
+    "predict_labels_mlp",
+    "predict_labels_baseline2",
+    "predict_labels_baseline_tissue",
+    "baseline2",
+    "baseline_tissue",
+    "plot_conf_entropy_margin",
+    "plot_pseudo_tissue_conf_entropy_margin",
+    "plot_confusion_matrix",
+    "report_leiden_celltype_topk",
+    "plot_leiden_celltype",
+    "plot_projection_celltype_overlay",
+]

{zmap_tools-0.2.2.2 → zmap_tools-0.2.2.5}/src/zmap/dotplot/dotplot_gene.py

@@ -39,6 +39,29 @@ DEFAULT_ROW_COLOR_GROUPS_ZMAP_CellType = {
 
 DEFAULT_ROW_DIVIDERS_ZMAP_CellType = [1, 11, 18, 24, 31, 35, 49, 63, 68, 73, 76]
 
+DEFAULT_CLUSTER_ORDER_ZMAP_Tissue = [
+    'blastomeres',
+    'ectoderm_early', 'epidermis', 'ionocyte_epithelium', 'placodes',
+    'endoderm_early', 'pharyngeal', 'intestine', 'liver', 'pancreas',
+    'neural_crest',
+    'neural_early', 'eye', 'forebrain', 'midbrain', 'hindbrain', 'spinal_cord', 'neurons',
+    'mesoderm_early', 'axial_meso', 'somitic_meso', 'muscle', 'lateral_plate', 'endothelial', 'fin_bud', 'heart', 'hematopoietic', 'intermediate_meso',
+    'primordial_germ_cell',
+    ]
+
+DEFAULT_ROW_COLOR_GROUPS_ZMAP_Tissue = {
+    "black":      ["blastomeres"],
+    "green":      ['ectoderm_early', 'epidermis', 'ionocyte_epithelium', 'placodes'],
+    "darkorange": ['endoderm_early', 'pharyngeal', 'intestine', 'liver', 'pancreas'],
+    "steelblue":  ['neural_crest'],
+    "blue":       ['neural_early', 'eye', 'forebrain', 'midbrain', 'hindbrain', 'spinal_cord', 'neurons'],
+    "darkblue":   ['optic_cup', 'retinal_pigment_epithelium', 'retina', 'photoreceptors'],
+    "red":        ['mesoderm_early', 'axial_meso', 'somitic_meso', 'muscle', 'lateral_plate', 'endothelial', 'fin_bud', 'heart', 'hematopoietic', 'intermediate_meso'],
+    "purple":     ["primordial_germ_cell"],
+}
+
+DEFAULT_ROW_DIVIDERS_ZMAP_Tissue = [1, 5, 12, 13, 18, 28]
+
 DEFAULT_STUDY_ORDER = ["Kamimoto2023", "Farrell2018", "Kukreja2024", "Wagner2018",
 "Farnsworth2020", "Lange2023", "Sur2023", "Spanjaard2018"]
 
@@ -484,7 +507,7 @@ def gene_groups_vs_time(
     size_legend_title: str | None = None,
     size_legend_facecolor: str = "black",
     # ===== ordering & filtering =====
-    cluster_order: list[str] | None = DEFAULT_CLUSTER_ORDER_ZMAP_CellType,
+    cluster_order: list[str] | None = None,
     time_order: list[str] | None = None,
     omit_groups: list[str] | None = ['nan', 'unknown'],
     # ===== cosmetics =====
@@ -497,10 +520,10 @@ def gene_groups_vs_time(
     tick_grid_alpha: float = 0.15,
     tick_grid_lw: float = 0.6,
     # ===== Row color group mapping & legend =====
-    row_color_groups: dict[str, list[str]] | None = DEFAULT_ROW_COLOR_GROUPS_ZMAP_CellType,
+    row_color_groups: dict[str, list[str]] | None = None,
     show_row_color_legend: bool = False,
     # ===== Horizontal split lines between rows =====
-    row_dividers: list[int] | None = DEFAULT_ROW_DIVIDERS_ZMAP_CellType,
+    row_dividers: list[int] | None = None,
     row_divider_color: str = "black",
     row_divider_lw: float = 0.5,
     row_divider_alpha: float = 1,
@@ -571,6 +594,20 @@ def gene_groups_vs_time(
     """
     color = str(color)
 
+    # Select defaults based on grouping
+    if groupby not in ("ZMAP_CellType", "ZMAP_Tissue"):
+        raise ValueError("groupby must be 'ZMAP_CellType' or 'ZMAP_Tissue'")
+
+    if cluster_order is None:
+        cluster_order = globals()[f"DEFAULT_CLUSTER_ORDER_{groupby}"]
+    if row_color_groups is None:
+        row_color_groups = globals()[f"DEFAULT_ROW_COLOR_GROUPS_{groupby}"]
+    if row_dividers is None:
+        row_dividers = globals()[f"DEFAULT_ROW_DIVIDERS_{groupby}"]
+
+    if figsize is None and groupby == "ZMAP_Tissue":
+        figsize = (4, 5)
+
     # ------------------------ color vector ------------------------
     x, color_source = _extract_color_vector(adata, color, layer, use_raw)
 
@@ -785,9 +822,9 @@ def gene_groups_vs_time(
             size_legend_title=size_legend_title,
             size_legend_facecolor=size_legend_facecolor,
             left=1.0 - gutter_pad - 0.18,
-            bottom=0.55,
+            bottom=0.40 if groupby == "ZMAP_Tissue" else 0.55,
             width=0.22,
-            height=0.10,
+            height=0.20 if groupby == "ZMAP_Tissue" else 0.10,
             background=background,
         )
 
@@ -878,7 +915,7 @@ def gene_groups_vs_studies(
     size_legend_title: str | None = None,
     size_legend_facecolor: str = "black",
     # ===== ordering & filtering =====
-    cluster_order: list[str] | None = DEFAULT_CLUSTER_ORDER_ZMAP_CellType,
+    cluster_order: list[str] | None = None,
     study_order: list[str] | None = DEFAULT_STUDY_ORDER,
     omit_groups: list[str] | None = ['nan', 'unknown'],     # omits clusters
     # ===== cosmetics =====
@@ -891,10 +928,10 @@ def gene_groups_vs_studies(
     tick_grid_alpha: float = 0.15,
     tick_grid_lw: float = 0.6,
     # ===== Row color group mapping & legend =====
-    row_color_groups: dict[str, list[str]] | None = DEFAULT_ROW_COLOR_GROUPS_ZMAP_CellType,
+    row_color_groups: dict[str, list[str]] | None = None,
     show_row_color_legend: bool = False,
     # ===== Horizontal split lines between rows =====
-    row_dividers: list[int] | None = DEFAULT_ROW_DIVIDERS_ZMAP_CellType,
+    row_dividers: list[int] | None = None,
     row_divider_color: str = "black",
     row_divider_lw: float = 0.5,
     row_divider_alpha: float = 1,
@@ -964,6 +1001,20 @@ def gene_groups_vs_studies(
     """
     color = str(color)
 
+    # Select defaults based on grouping
+    if groupby not in ("ZMAP_CellType", "ZMAP_Tissue"):
+        raise ValueError("groupby must be 'ZMAP_CellType' or 'ZMAP_Tissue'")
+
+    if cluster_order is None:
+        cluster_order = globals()[f"DEFAULT_CLUSTER_ORDER_{groupby}"]
+    if row_color_groups is None:
+        row_color_groups = globals()[f"DEFAULT_ROW_COLOR_GROUPS_{groupby}"]
+    if row_dividers is None:
+        row_dividers = globals()[f"DEFAULT_ROW_DIVIDERS_{groupby}"]
+
+    if figsize is None and groupby == "ZMAP_Tissue":
+        figsize = (4, 5)
+
     # ------------------------ color vector ------------------------
     x, color_source = _extract_color_vector(adata, color, layer, use_raw)
 
@@ -1179,9 +1230,9 @@ def gene_groups_vs_studies(
             size_legend_title=size_legend_title,
             size_legend_facecolor=size_legend_facecolor,
             left=1.0 - gutter_pad - 0.18,
-            bottom=0.55,
+            bottom=0.40 if groupby == "ZMAP_Tissue" else 0.55,
             width=0.22,
-            height=0.10,
+            height=0.20 if groupby == "ZMAP_Tissue" else 0.10,
             background=background,
         )
 
@@ -1274,7 +1325,7 @@ def gene_groups_vs_time_and_studies(
     size_legend_title: str | None = None,
     size_legend_facecolor: str = "black",
     # ===== ordering & filtering =====
-    cluster_order: list[str] | None = DEFAULT_CLUSTER_ORDER_ZMAP_CellType,
+    cluster_order: list[str] | None = None,
     time_order: list[str] | None = None,
     study_order: list[str] | None = DEFAULT_STUDY_ORDER,
     omit_groups: list[str] | None = ['nan', 'unknown'],
@@ -1289,10 +1340,10 @@ def gene_groups_vs_time_and_studies(
     tick_grid_alpha: float = 0.15,
     tick_grid_lw: float = 0.6,
     # ===== Row color group mapping & legend =====
-    row_color_groups: dict[str, list[str]] | None = DEFAULT_ROW_COLOR_GROUPS_ZMAP_CellType,
+    row_color_groups: dict[str, list[str]] | None = None,
     show_row_color_legend: bool = False,
     # ===== Horizontal split lines between rows =====
-    row_dividers: list[int] | None = DEFAULT_ROW_DIVIDERS_ZMAP_CellType,
+    row_dividers: list[int] | None = None,
     row_divider_color: str = "black",
     row_divider_lw: float = 0.5,
     row_divider_alpha: float = 1.0,
@@ -1394,6 +1445,20 @@ def gene_groups_vs_time_and_studies(
     """
     color = str(color)
 
+    # Select defaults based on grouping
+    if groupby not in ("ZMAP_CellType", "ZMAP_Tissue"):
+        raise ValueError("groupby must be 'ZMAP_CellType' or 'ZMAP_Tissue'")
+
+    if cluster_order is None:
+        cluster_order = globals()[f"DEFAULT_CLUSTER_ORDER_{groupby}"]
+    if row_color_groups is None:
+        row_color_groups = globals()[f"DEFAULT_ROW_COLOR_GROUPS_{groupby}"]
+    if row_dividers is None:
+        row_dividers = globals()[f"DEFAULT_ROW_DIVIDERS_{groupby}"]
+    
+    if figsize is None and groupby == "ZMAP_Tissue":
+        figsize = (4, 5)
+
     # ------------------------ color vector ------------------------
     x_full, color_source = _extract_color_vector(adata, color, layer, use_raw)
 
@@ -1664,7 +1729,7 @@ def gene_groups_vs_time_and_studies(
 
     # ------------------------ SHARED colorbar in gutter + rotated label -----
     if add_colorbar:
-        left_cb = 1.0 - gutter_pad - 0.12
+        left_cb = 1.0 - gutter_pad - 0.06
         bottom_cb = 0.70
         width_cb = 0.02
         height_cb = 0.15
@@ -1702,9 +1767,9 @@ def gene_groups_vs_time_and_studies(
             size_legend_title=size_legend_title,
             size_legend_facecolor=size_legend_facecolor,
             left=1.0 - gutter_pad - 0.14,
-            bottom=0.55,
-            width=0.12,
-            height=0.10,
+            bottom=0.40 if groupby == "ZMAP_Tissue" else 0.55,
+            width=0.22,
+            height=0.20 if groupby == "ZMAP_Tissue" else 0.10,
             background=background,
         )
 

{zmap_tools-0.2.2.2 → zmap_tools-0.2.2.5}/src/zmap/predict/__init__.py

@@ -33,6 +33,31 @@ from .predict import (
     validate_markers,
     plot_marker_comparison,
 )
+from .encoder_pipeline import (
+    apply_encoder,
+    zmap_projection,
+    predict_pseudo_tissue,
+    knn_config,
+    build_module_faiss,
+    build_module_concat_reference,
+    apply_module_concat_query,
+    time_prediction_KNN,
+    plot_conf_entropy_margin,
+    plot_pseudo_tissue_conf_entropy_margin,
+    plot_confusion_matrix,
+    report_leiden_celltype_topk,
+    plot_leiden_celltype,
+    plot_projection_celltype_overlay,
+)
+from .baseline2 import (
+    predict_labels_MLP,
+    predict_labels_mlp,
+    predict_labels_baseline2,
+    predict_labels_baseline_tissue,
+    time_prediction_MLP,
+    baseline2,
+    baseline_tissue,
+)
 
 __all__ = [
     "preprocess_adata_query",
@@ -55,3 +80,27 @@ __all__ = [
     "validate_markers",
     "plot_marker_comparison",
 ]
+
+__all__ += [
+    "apply_encoder",
+    "zmap_projection",
+    "predict_pseudo_tissue",
+    "knn_config",
+    "build_module_faiss",
+    "build_module_concat_reference",
+    "apply_module_concat_query",
+    "time_prediction_KNN",
+    "plot_conf_entropy_margin",
+    "plot_pseudo_tissue_conf_entropy_margin",
+    "plot_confusion_matrix",
+    "report_leiden_celltype_topk",
+    "plot_leiden_celltype",
+    "plot_projection_celltype_overlay",
+    "predict_labels_MLP",
+    "predict_labels_mlp",
+    "predict_labels_baseline2",
+    "predict_labels_baseline_tissue",
+    "time_prediction_MLP",
+    "baseline2",
+    "baseline_tissue",
+]