zmap-tools 0.2.1__tar.gz → 0.2.2.2__tar.gz

{zmap_tools-0.2.1 → zmap_tools-0.2.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: zmap-tools
-Version: 0.2.1
+Version: 0.2.2.2
 Summary: API for working with ZMAP (Zebrafish Multi-Atlas Project)
 Author-email: Daniel Wagner <Daniel.Wagner@ucsf.edu>
 License: BSD 3-Clause License
@@ -47,19 +47,23 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: anndata>=0.10
-Requires-Dist: scanpy>=1.9
-Requires-Dist: numpy>=1.24
-Requires-Dist: pandas>=2.0
-Requires-Dist: matplotlib>=3.7
+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: requests>=2.31
-Requires-Dist: scipy>=1.10
-Requires-Dist: scikit-learn>=1.3
-Requires-Dist: faiss-cpu>=1.8
-Requires-Dist: seaborn>=0.12
+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: tqdm>=4.66
 Requires-Dist: adjustText>=0.8
-Requires-Dist: symphonypy>=0.2
+Requires-Dist: symphonypy==0.2.4
+Requires-Dist: igraph==1.0.0
+Requires-Dist: leidenalg==0.12.0
 Dynamic: license-file
 
 # zmap-tools

{zmap_tools-0.2.1 → zmap_tools-0.2.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "zmap-tools"
-version = "0.2.1"
+version = "0.2.2.2"
 description = "API for working with ZMAP (Zebrafish Multi-Atlas Project)"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -27,19 +27,25 @@ classifiers = [
 ]
 
 dependencies = [
-  "anndata>=0.10",
-  "scanpy>=1.9",
-  "numpy>=1.24",
-  "pandas>=2.0",
-  "matplotlib>=3.7",
+  "anndata==0.12.18",
+  "scanpy==1.12.1",
+
+  "numpy==2.0.2",
+  "numba==0.60.0",
+  "llvmlite==0.43.0",
+
+  "pandas>=2.0,<3.0",
+  "matplotlib>=3.7,<4.0",
   "requests>=2.31",
-  "scipy>=1.10",
-  "scikit-learn>=1.3",
-  "faiss-cpu>=1.8",
-  "seaborn>=0.12",
+  "scipy==1.16.3",
+  "scikit-learn==1.6.1",
+  "faiss-cpu==1.14.3",
+  "seaborn==0.13.2",
   "tqdm>=4.66",
   "adjustText>=0.8",
-  "symphonypy>=0.2",
+  "symphonypy==0.2.4",
+  "igraph==1.0.0",
+  "leidenalg==0.12.0",
 ]
 
 [project.urls]

{zmap_tools-0.2.1 → zmap_tools-0.2.2.2}/src/zmap/predict/knn_backend.py

@@ -18,10 +18,12 @@ _FAISS_INDEX_CACHE_ORDER: list[tuple[str, str, int, int]] = []
 
 
 def _as_float32_c(x: np.ndarray) -> np.ndarray:
+    """Cast array to float32 and ensure C-contiguous memory layout (required by FAISS)."""
     return np.ascontiguousarray(np.asarray(x, dtype=np.float32))
 
 
 def _l2_normalize(x: np.ndarray) -> np.ndarray:
+    """Row-wise L2-normalize an array to unit vectors (used for cosine similarity via inner product)."""
     x = _as_float32_c(x)
     norms = np.linalg.norm(x, axis=1, keepdims=True)
     norms = np.where(norms == 0, 1.0, norms)
@@ -29,6 +31,7 @@ def _l2_normalize(x: np.ndarray) -> np.ndarray:
 
 
 def _parse_cuda_device(device: str) -> int:
+    """Parse a device string like 'cuda:1' into an integer GPU index. Returns 0 on failure."""
     d = str(device).strip().lower()
     if ":" in d:
         try:
@@ -44,6 +47,17 @@ def _search_sklearn(
     n_neighbors: int,
     metric: str,
 ) -> tuple[np.ndarray, np.ndarray]:
+    """
+    kNN search using scikit-learn's NearestNeighbors.
+
+    Used as the fallback when FAISS is unavailable or fails. Slower than FAISS
+    on large references but supports any sklearn-compatible metric.
+
+    Returns
+    -------
+    neighbor_indices : np.ndarray, shape (n_query, n_neighbors)
+    distances : np.ndarray, shape (n_query, n_neighbors)
+    """
     nn = NearestNeighbors(n_neighbors=n_neighbors, metric=metric)
     nn.fit(ref)
     distances, neighbor_indices = nn.kneighbors(query, return_distance=True)
@@ -59,6 +73,44 @@ def _search_faiss(
     nprobe: int | None = None,
     cache_key: str | None = None,
 ) -> tuple[np.ndarray, np.ndarray, dict[str, Any]]:
+    """
+    kNN search using FAISS with optional GPU acceleration and index caching.
+
+    Builds an IVF-Flat index by default for fast approximate search on large references.
+    Falls back to an exact Flat index if IVF training fails. Cosine similarity is
+    implemented as inner product after L2-normalization; euclidean uses L2 distance.
+
+    Parameters
+    ----------
+    ref : np.ndarray, shape (n_ref, d)
+        Reference embedding matrix.
+    query : np.ndarray, shape (n_query, d)
+        Query embedding matrix.
+    n_neighbors : int
+        Number of nearest neighbors to return.
+    metric : {'euclidean', 'cosine'}
+        Distance metric.
+    device : str
+        Target device — 'cpu', 'auto', 'cuda', or 'cuda:<id>'.
+    nprobe : int, optional
+        Number of IVF cells to probe during search. Higher values increase recall
+        at the cost of speed. Defaults to DEFAULT_FAISS_NPROBE (16).
+    cache_key : str, optional
+        If provided, the built FAISS index is cached in-memory under this key and
+        reused on subsequent calls with matching (key, metric, n_ref, d). Up to
+        MAX_FAISS_INDEX_CACHE (16) indices are retained (LRU eviction).
+
+    Returns
+    -------
+    indices : np.ndarray, shape (n_query, n_neighbors), dtype int64
+        Indices into ref for each neighbor. Entries are -1 (set to NaN in distances)
+        when FAISS cannot fill all k neighbors (rare with Flat indices).
+    distances : np.ndarray, shape (n_query, n_neighbors), dtype float32
+        Euclidean distances or cosine-distance proxies (1 - cosine_similarity).
+    meta : dict
+        Diagnostic info: backend_used, device_used, index_type, nlist, nprobe,
+        cache_key_used, cache_hit.
+    """
     try:
         import faiss  # type: ignore
     except Exception as e:
@@ -233,21 +285,47 @@ def knn_search(
     cache_key: str | None = None,
 ) -> tuple[np.ndarray, np.ndarray, dict[str, Any]]:
     """
-    Unified kNN search for ZMAP API.
-
-    backend:
-      - auto: try faiss first, fallback to sklearn
-      - faiss: require faiss, fallback to sklearn with warning
-      - sklearn: force sklearn
-    device:
-      - auto | cpu | cuda | cuda:<id>
-      - used only by faiss backend
-    nprobe:
-      - IVF probe count for FAISS (None -> default)
-      - used only by faiss backend
-    cache_key:
-      - optional key to reuse FAISS index build across repeated calls
-      - used only by faiss backend
+    Unified kNN search supporting FAISS and scikit-learn backends.
+
+    Tries FAISS first (fast, approximate) and falls back to sklearn (exact) if
+    FAISS is unavailable or raises. Both backends return consistent output shapes
+    and distance semantics.
+
+    Parameters
+    ----------
+    ref : np.ndarray, shape (n_ref, d)
+        Reference embedding matrix.
+    query : np.ndarray, shape (n_query, d)
+        Query embedding matrix.
+    n_neighbors : int
+        Number of nearest neighbors to return per query point.
+    metric : {'cosine', 'euclidean'}, default 'cosine'
+        Distance metric. Cosine is computed as 1 - cosine_similarity.
+    backend : {'auto', 'faiss', 'sklearn'}, default 'auto'
+        Search backend. 'auto' tries FAISS first and falls back to sklearn.
+        'faiss' also falls back to sklearn with a warning if FAISS fails.
+        'sklearn' skips FAISS entirely.
+    device : {'auto', 'cpu', 'cuda', 'cuda:<id>'}, default 'auto'
+        Device for FAISS index. Ignored by the sklearn backend. 'auto' uses
+        GPU if FAISS GPU support is available, otherwise CPU.
+    nprobe : int, optional
+        Number of IVF partitions to probe during FAISS search. Higher values
+        improve recall at the cost of speed. Defaults to DEFAULT_FAISS_NPROBE.
+        Ignored by the sklearn backend and FAISS Flat indices.
+    cache_key : str, optional
+        If provided, the FAISS index built for `ref` is cached in-memory under
+        this key and reused on subsequent calls with the same (key, metric,
+        n_ref, d). Useful when the same reference is queried repeatedly.
+
+    Returns
+    -------
+    indices : np.ndarray, shape (n_query, n_neighbors), dtype int64
+        Row indices into `ref` for each neighbor, ordered by ascending distance.
+    distances : np.ndarray, shape (n_query, n_neighbors), dtype float32
+        Corresponding distances. NaN where FAISS returns invalid indices (-1).
+    meta : dict
+        Diagnostic info including backend_used, device_used, index_type, and
+        cache_hit. Useful for verifying which backend and device were actually used.
     """
     metric = str(metric).lower()
     backend_req = str(backend).lower()

{zmap_tools-0.2.1 → zmap_tools-0.2.2.2}/src/zmap/predict/predict.py

@@ -232,6 +232,7 @@ def preprocess_adata_query(
         adata.X = np.log1p(X_tpm)
 
     # ---- 5. bookkeeping ----
+    adata.uns["log1p"] = {"base": None}
     adata.uns.setdefault("ZMAP_preprocessing", {})
     adata.uns["ZMAP_preprocessing"]["query"] = {
         "counts_source": counts_source,
@@ -991,7 +992,7 @@ def predict_labels_kNN(
             cache.get('query_basis') == query_basis and
             cache.get('metric') == metric and
             cache.get('n_neighbors') == n_neighbors and
-            cache.get('mask_digest') == _mask_digest and
+            list(cache.get('mask_digest', [])) == list(_mask_digest) and
             cache.get('tissue_mode', 'none') == expected_cache_mode and
             cache.get('knn_backend_requested', 'auto') == knn_backend and
             cache.get('knn_device_requested', 'auto') == knn_device and
@@ -2229,6 +2230,17 @@ def aggregate_by_cluster(
 
     df = pd.DataFrame(records)
 
+    # Ensure object columns are h5ad-serializable in uns:
+    # - numeric columns demoted to object by pd.NA → coerce back to float (pd.NA → np.nan)
+    # - string columns with pd.NA → fillna("") and cast to str
+    _numeric_cols = {"top_fraction", "mean_prob", "margin", "second_fraction"}
+    for col in df.columns:
+        if df[col].dtype == object:
+            if col in _numeric_cols:
+                df[col] = pd.to_numeric(df[col], errors="coerce")
+            else:
+                df[col] = df[col].fillna("").astype(str)
+
     if save_csv:
         os.makedirs(output_dir, exist_ok=True)
         out_path = os.path.join(output_dir, f"{label_space}_cluster_summary.csv")
@@ -2564,6 +2576,7 @@ def plot_embedding_with_ondata_labels(
     # ---- data/keys ----
     color_key: str = "ZMAP_Tissue_predicted",
     basis: str = "X_umap",
+    ref_basis: str | None = None,
     filter_na: bool = True,
 
     # ---- palette handling ----
@@ -2579,12 +2592,14 @@ def plot_embedding_with_ondata_labels(
     # ---- figure style ----
     figsize: tuple[float, float] = (6, 6),
     dpi: int = 200,
+    title_fontsize: float = 10,
 
     # ---- point style ----
     ref_size: float = 2,
     ref_alpha: float = 0.3,
     test_size: float = 2,
     test_alpha: float = 1.0,
+    show_ref: bool = True,
     cmap: str = "jet",
     frameon: bool = False,
     sort_order: bool = True,
@@ -2625,9 +2640,10 @@ def plot_embedding_with_ondata_labels(
     Plot a query dataset overlaid on the reference embedding, with on-data labels
     and an optional vertical time distribution strip.
 
-    Renders two layers: (1) the full reference embedding as a faint grey
-    background for spatial context, and (2) the query cells colored by a
-    predicted label column. Labels are drawn directly on the embedding using
+    Renders up to two layers: (1) optionally, the full reference embedding
+    as a faint grey background for spatial context (controlled by
+    ``show_ref``), and (2) the query cells colored by a predicted label
+    column. Labels are drawn directly on the embedding using
     ``adjustText`` to minimize overlap. A vertical colorbar histogram of
     predicted developmental time (``ZMAP_time_id``) can optionally be added
     as a strip on the right side of the figure.
@@ -2642,7 +2658,12 @@ def plot_embedding_with_ondata_labels(
         Column in ``adata_test.obs`` containing the categorical labels to color
         and annotate. Typically a ``_predicted`` column from ``predict_labels_kNN``.
     basis : str, default ``"X_umap"``
-        ``obsm`` key used for the 2D embedding coordinates in both datasets.
+        ``obsm`` key used for the 2D embedding coordinates in the query dataset.
+    ref_basis : str or None, default ``None``
+        ``obsm`` key for the reference background embedding. When ``None``,
+        falls back to ``basis``. Useful when the query embedding lives in a
+        different key than the reference (e.g. ``basis="X_umap_zmap"`` for
+        the query while the reference uses ``"X_umap"``).
     filter_na : bool, default ``True``
         Drop query cells with ``NaN`` in ``color_key`` before plotting.
     palette : dict or None, default ``None``
@@ -2674,6 +2695,11 @@ def plot_embedding_with_ondata_labels(
         Scatter point size for query (projected) cells.
     test_alpha : float, default ``1.0``
         Opacity of query overlay points.
+    show_ref : bool, default ``True``
+        If ``True``, draw the reference embedding as a faint grey background
+        for spatial context. If ``False``, only the query cells are plotted
+        (useful when ``do_ingest=False``). When ``False``, ``adata_ref``
+        may be ``None``.
     cmap : str, default ``"jet"``
         Colormap used for the reference background scatter.
     legend_loc : str, default ``"on data"``
@@ -2730,7 +2756,7 @@ def plot_embedding_with_ondata_labels(
     # Only attempt sync if there's no _color_map dict already available
     # (annotate_with_zmap populates _color_map from reference colormaps)
     cmap_dict_key = f"{base_obs}_color_map"
-    if cmap_dict_key not in adata_test_plot.uns:
+    if cmap_dict_key not in adata_test_plot.uns and adata_ref is not None:
         try:
             sync_zmap_colors(adata_ref, obs_key=base_obs)
             sync_zmap_colors(adata_test_plot, obs_key=color_key, ref_adata=adata_ref, ref_obs_key=base_obs)
@@ -2795,6 +2821,9 @@ def plot_embedding_with_ondata_labels(
     ax_umap = None
     ax_strip = None
 
+    # ---- Resolve ref_basis: defaults to basis if not provided ----
+    ref_basis_use = ref_basis if ref_basis is not None else basis
+
     # ---- figure + axes layout ----
     with plt.rc_context({'figure.figsize': figsize, 'figure.dpi': dpi}):
         if has_time:
@@ -2812,15 +2841,18 @@ def plot_embedding_with_ondata_labels(
             fig, ax_umap = plt.subplots()
             ax_strip = None
 
-        # ---- reference embedding in UMAP axis ----
-        ax = sc.pl.embedding(
-            adata_ref,
-            basis=basis,
-            show=False,
-            s=ref_size,
-            ax=ax_umap,
-            **ref_kwargs,
-        )
+        # ---- reference embedding in UMAP axis (optional) ----
+        if show_ref:
+            ax = sc.pl.embedding(
+                adata_ref,
+                basis=ref_basis_use,
+                show=False,
+                s=ref_size,
+                ax=ax_umap,
+                **ref_kwargs,
+            )
+        else:
+            ax = ax_umap
 
         # ---- query overlay in UMAP axis ----
         ax = sc.pl.embedding(
@@ -2840,6 +2872,7 @@ def plot_embedding_with_ondata_labels(
             palette=palette,
             **test_kwargs,
         )
+        ax.title.set_fontsize(title_fontsize)
 
         # --- on-data label styling (only when show_labels=True) ---
         if show_labels:
@@ -3117,20 +3150,26 @@ def map_query_labels(
     fig = None
     if show_plot or save_plots:
         plt.rcParams["axes.grid"] = False
-        fig, ax = plt.subplots(figsize=(figsize, figsize))
+        n_rows, n_cols = plot_table.shape
+        tick_fontsize = 8
+        cell_size = 0.25          # inches per cell — fits 8pt labels without crowding
+        fig_w = min(28, max(figsize, n_cols * cell_size))
+        fig_h = min(28, max(figsize, n_rows * cell_size))
+        cb_shrink = min(0.8, 3.0 / fig_h)   # keep colorbar ~3 inches tall
+        fig, ax = plt.subplots(figsize=(fig_w, fig_h))
 
         im = ax.imshow(plot_table.to_numpy(), cmap=cmap, vmin=vmin, vmax=vmax)
 
         ax.set_aspect("equal")
         ax.set_xticks(np.arange(plot_table.shape[1]))
         ax.set_yticks(np.arange(plot_table.shape[0]))
-        ax.set_xticklabels(plot_table.columns, rotation=90)
-        ax.set_yticklabels(plot_table.index)
+        ax.set_xticklabels(plot_table.columns, rotation=90, fontsize=tick_fontsize)
+        ax.set_yticklabels(plot_table.index, fontsize=tick_fontsize)
         ax.set_title(title)
         ax.set_xlabel(obs_A)
         ax.set_ylabel(obs_B)
 
-        cb = fig.colorbar(im, ax=ax, shrink=0.5)
+        cb = fig.colorbar(im, ax=ax, shrink=cb_shrink)
         cb.ax.set_ylabel(colorbar_label)
 
         if overlay_values:
@@ -3228,7 +3267,7 @@ def annotate_with_zmap(
     predict_kwargs: Mapping[str, Any] | None = None,
 
     # --- output controls ---
-    verbosity: int = 2,               # 0=silent, 1=progress, 2=summary+UMAP+QC, 3=full
+    verbosity: int = 3,               # 0=silent, 1=progress, 2=summary+UMAP+QC, 3=full
     debug: bool = False,              # if True, re-raise exceptions instead of catching
     print_summary: bool | None = None,   # deprecated → use verbosity
     show_plots: bool | None = None,      # deprecated → use verbosity
@@ -3324,7 +3363,7 @@ def annotate_with_zmap(
         Extra keyword arguments forwarded to ``predict_labels_kNN``.
         For common options, prefer the top-level ``tissue_aware`` and
         ``evaluate`` parameters instead of passing dicts manually.
-    verbosity : int, default ``2``
+    verbosity : int, default ``3``
         Controls how much output is printed and displayed inline:
 
         - ``0`` — silent (no print, no inline plots).
@@ -3354,7 +3393,7 @@ def annotate_with_zmap(
         - ``.obs[f"{label_space}_predicted"]``                       — transferred cell labels.
         - ``.obs[f"{label_space}_prob"]``                            — label confidence (0–1).
         - ``.obs["ZMAP_time_id_predicted"]``                         — predicted time (hpf).
-        - ``.obsm["X_umap"]``                                        — UMAP coordinates (if ingested).
+        - ``.obsm["X_umap_zmap"]``                                   — projected UMAP coordinates (if ingested).
         - ``.uns['zmap_labels']['_last_space']``                     — most recent label_space.
         - ``.uns['zmap_labels'][label_space]['_run_config']``        — stored run parameters
           for zero-arg on-demand plot accessors.
@@ -3517,9 +3556,29 @@ def annotate_with_zmap(
         if do_ingest:
             if v >= 1:
                 _zlog("Ingesting query into reference UMAP...")
+
+            # Stash pre-existing X_umap so symphony doesn't clobber it
+            _had_existing_umap = "X_umap" in adata_query.obsm
+            if _had_existing_umap:
+                _existing_umap = adata_query.obsm["X_umap"].copy()
+
             with warnings.catch_warnings():
                 warnings.simplefilter("ignore", FutureWarning)
                 sp.tl.ingest(adata_query=adata_query, adata_ref=adata_ref)
+
+            # Move ingested coords to X_umap_zmap (non-destructive)
+            adata_query.obsm["X_umap_zmap"] = adata_query.obsm["X_umap"].copy()
+
+            # Restore original X_umap if one existed, otherwise remove
+            if _had_existing_umap:
+                adata_query.obsm["X_umap"] = _existing_umap
+                if v >= 1:
+                    _zlog("Restored pre-existing X_umap; ingested coords in X_umap_zmap.")
+            else:
+                del adata_query.obsm["X_umap"]
+                if v >= 1:
+                    _zlog("Ingested coords stored in X_umap_zmap.")
+
             if v >= 1:
                 _zlog("Ingestion complete.")
 
@@ -3593,15 +3652,26 @@ def annotate_with_zmap(
     adata_query.uns.setdefault("zmap_labels", {})
     adata_query.uns["zmap_labels"]["_last_space"] = space
     adata_query.uns["zmap_labels"].setdefault(space, {})
+    # Determine embedding basis and whether to show reference background
+    if do_ingest:
+        _plot_basis = "X_umap_zmap"
+        _show_ref = True
+    else:
+        # No ingest → query lives in its own UMAP space
+        _plot_basis = "X_umap" if "X_umap" in adata_query.obsm else None
+        _show_ref = False
+
     adata_query.uns["zmap_labels"][space]["_run_config"] = {
         "label_space": space,
         "ref_label_col": ref_label_col,
         "query_label_col": query_label_col,
         "time_col": time_col_actual,
         "output_dir": space_dir,
+        "basis": _plot_basis,
+        "show_ref": _show_ref,
     }
-    # Store reference UMAP for on-demand plot_embedding (avoids needing adata_ref)
-    if "X_umap" in adata_ref.obsm:
+    # Store reference UMAP for on-demand plot_embedding (only when ingested)
+    if do_ingest and "X_umap" in adata_ref.obsm:
         adata_query.uns["zmap_labels"][space]["_ref_umap"] = (
             np.asarray(adata_ref.obsm["X_umap"]).copy()
         )
@@ -3668,6 +3738,7 @@ def annotate_with_zmap(
 
     # ------------------------------------------------------------------
     # 8. Copy colormap dict from reference → query (order-independent)
+    # Also copy reference color palettes and order lists
     # ------------------------------------------------------------------
     cmap_src_key = _COLORMAP_UNS_KEY.get(ref_label_col)
     if cmap_src_key and cmap_src_key in adata_ref.uns:
@@ -3687,19 +3758,35 @@ def annotate_with_zmap(
             "arrays — palette may be incorrect if query categories differ from reference.",
             stacklevel=2,
         )
+    
+    # Standard palettes
+    keys = ["ZMAP_CellType_order","ZMAP_Tissue_order","ZMAP_colormap_C12","ZMAP_colormap_C79",
+        "ZMAP_colormap_G7","ZMAP_colormap_T28","ZMAP_colormap_T7"]
+    for k in keys:
+        if k in adata_ref.uns:
+            adata_query.uns[k] = adata_ref.uns[k]
 
     # ------------------------------------------------------------------
     # 9. UMAP overlay figure (v >= 2)
     # ------------------------------------------------------------------
-    if v >= 2:
+    if _plot_basis is None:
+        if v >= 1:
+            _zlog(
+                "Skipping UMAP overlay: no embedding found "
+                "(do_ingest=False and no pre-existing X_umap)."
+            )
+    elif v >= 2:
         try:
             if v >= 1:
                 _zlog("Plotting UMAP overlay with predicted labels...")
             plot_embedding_with_ondata_labels(
-                adata_ref,
+                adata_ref if _show_ref else None,
                 adata_query,
                 color_key=f"{space}_predicted",
                 time_key=time_col_actual,
+                basis=_plot_basis,
+                ref_basis="X_umap",
+                show_ref=_show_ref,
                 show=True,
                 save=save_outputs,
                 output_dir=space_dir,
@@ -3714,10 +3801,13 @@ def annotate_with_zmap(
         # Still save the figure even if not showing it
         try:
             plot_embedding_with_ondata_labels(
-                adata_ref,
+                adata_ref if _show_ref else None,
                 adata_query,
                 color_key=f"{space}_predicted",
                 time_key=time_col_actual,
+                basis=_plot_basis,
+                ref_basis="X_umap",
+                show_ref=_show_ref,
                 show=False,
                 save=True,
                 output_dir=space_dir,
@@ -3985,6 +4075,7 @@ def validate_markers(
             groupby=groupby,
             method=method,
             corr_method=corr_method,
+            use_raw=False,
         )
 
     # ---- Extract and filter DE results per group ----
@@ -4271,19 +4362,30 @@ def plot_embedding(
     label_space, config = _resolve_config(adata_query, label_space)
     space_store = adata_query.uns.get("zmap_labels", {}).get(label_space, {})
 
-    ref_umap = space_store.get("_ref_umap")
-    if ref_umap is None:
+    # Resolve basis and show_ref from stored config
+    plot_basis = config.get("basis", "X_umap_zmap")
+    show_ref = config.get("show_ref", True)
+
+    if plot_basis is None:
         raise KeyError(
-            f"No stored reference UMAP found at "
-            f"adata.uns['zmap_labels']['{label_space}']['_ref_umap']. "
-            "Run annotate_with_zmap first."
+            f"No embedding basis stored for label_space='{label_space}'. "
+            "The original run had do_ingest=False and no pre-existing X_umap."
         )
 
-    # Build a minimal AnnData shell with just the reference UMAP
-    adata_ref_mini = ad.AnnData(
-        obs=pd.DataFrame(index=[f"ref_{i}" for i in range(ref_umap.shape[0])]),
-    )
-    adata_ref_mini.obsm["X_umap"] = ref_umap
+    # Build reference shell only when needed
+    adata_ref_mini = None
+    if show_ref:
+        ref_umap = space_store.get("_ref_umap")
+        if ref_umap is None:
+            raise KeyError(
+                f"No stored reference UMAP found at "
+                f"adata.uns['zmap_labels']['{label_space}']['_ref_umap']. "
+                "Run annotate_with_zmap first."
+            )
+        adata_ref_mini = ad.AnnData(
+            obs=pd.DataFrame(index=[f"ref_{i}" for i in range(ref_umap.shape[0])]),
+        )
+        adata_ref_mini.obsm["X_umap"] = ref_umap
 
     color_key = f"{label_space}_predicted"
     time_key = config.get("time_col", "ZMAP_time_id_predicted")
@@ -4294,6 +4396,9 @@ def plot_embedding(
         adata_query,
         color_key=color_key,
         time_key=time_key,
+        basis=plot_basis,
+        ref_basis="X_umap",
+        show_ref=show_ref,
         show=True,
         save=save,
         show_labels=show_labels,

{zmap_tools-0.2.1 → zmap_tools-0.2.2.2}/src/zmap_tools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: zmap-tools
-Version: 0.2.1
+Version: 0.2.2.2
 Summary: API for working with ZMAP (Zebrafish Multi-Atlas Project)
 Author-email: Daniel Wagner <Daniel.Wagner@ucsf.edu>
 License: BSD 3-Clause License
@@ -47,19 +47,23 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: anndata>=0.10
-Requires-Dist: scanpy>=1.9
-Requires-Dist: numpy>=1.24
-Requires-Dist: pandas>=2.0
-Requires-Dist: matplotlib>=3.7
+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: requests>=2.31
-Requires-Dist: scipy>=1.10
-Requires-Dist: scikit-learn>=1.3
-Requires-Dist: faiss-cpu>=1.8
-Requires-Dist: seaborn>=0.12
+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: tqdm>=4.66
 Requires-Dist: adjustText>=0.8
-Requires-Dist: symphonypy>=0.2
+Requires-Dist: symphonypy==0.2.4
+Requires-Dist: igraph==1.0.0
+Requires-Dist: leidenalg==0.12.0
 Dynamic: license-file
 
 # zmap-tools

zmap_tools-0.2.2.2/src/zmap_tools.egg-info/requires.txt

@@ -0,0 +1,17 @@
+anndata==0.12.18
+scanpy==1.12.1
+numpy==2.0.2
+numba==0.60.0
+llvmlite==0.43.0
+pandas<3.0,>=2.0
+matplotlib<4.0,>=3.7
+requests>=2.31
+scipy==1.16.3
+scikit-learn==1.6.1
+faiss-cpu==1.14.3
+seaborn==0.13.2
+tqdm>=4.66
+adjustText>=0.8
+symphonypy==0.2.4
+igraph==1.0.0
+leidenalg==0.12.0

zmap_tools-0.2.1/src/zmap_tools.egg-info/requires.txt

@@ -1,13 +0,0 @@
-anndata>=0.10
-scanpy>=1.9
-numpy>=1.24
-pandas>=2.0
-matplotlib>=3.7
-requests>=2.31
-scipy>=1.10
-scikit-learn>=1.3
-faiss-cpu>=1.8
-seaborn>=0.12
-tqdm>=4.66
-adjustText>=0.8
-symphonypy>=0.2