openms-insight 0.1.9__py3-none-any.whl → 0.1.11__py3-none-any.whl

openms_insight/preprocessing/compression.py

@@ -238,9 +238,10 @@ def downsample_2d_simple(
     data: Union[pl.LazyFrame, pl.DataFrame],
     max_points: int = 20000,
     intensity_column: str = "intensity",
+    descending: bool = True,
 ) -> pl.LazyFrame:
     """
-    Simple downsampling by keeping highest-intensity points.
+    Simple downsampling by keeping top-priority points.
 
     A simpler alternative to downsample_2d that doesn't require scipy.
     Less spatially aware but still preserves important peaks.
@@ -249,6 +250,7 @@ def downsample_2d_simple(
         data: Input data as Polars LazyFrame or DataFrame
         max_points: Maximum number of points to keep
         intensity_column: Name of intensity column for ranking
+        descending: If True (default), keep highest values. If False, keep lowest.
 
     Returns:
         Downsampled data as Polars LazyFrame
@@ -256,7 +258,7 @@ def downsample_2d_simple(
     if isinstance(data, pl.DataFrame):
         data = data.lazy()
 
-    return data.sort(intensity_column, descending=True).head(max_points)
+    return data.sort(intensity_column, descending=descending).head(max_points)
 
 
 def downsample_2d_streaming(
@@ -269,6 +271,7 @@ def downsample_2d_streaming(
     y_bins: int = 50,
     x_range: Optional[tuple] = None,
     y_range: Optional[tuple] = None,
+    descending: bool = True,
 ) -> pl.LazyFrame:
     """
     Streaming 2D downsampling using pure Polars operations.
@@ -287,6 +290,8 @@ def downsample_2d_streaming(
         y_bins: Number of bins along y-axis
         x_range: Optional (min, max) tuple for x-axis. If None, computed from data.
         y_range: Optional (min, max) tuple for y-axis. If None, computed from data.
+        descending: If True (default), keep highest intensity per bin.
+            If False, keep lowest intensity per bin.
 
     Returns:
         Downsampled data as Polars LazyFrame (fully lazy, no collection)
@@ -319,7 +324,7 @@ def downsample_2d_streaming(
 
         result = (
             data.with_columns([x_bin_expr, y_bin_expr])
-            .sort(intensity_column, descending=True)
+            .sort(intensity_column, descending=descending)
             .group_by(["_x_bin", "_y_bin"])
             .head(points_per_bin)
             .drop(["_x_bin", "_y_bin"])
@@ -349,7 +354,7 @@ def downsample_2d_streaming(
                     .alias("_y_bin"),
                 ]
             )
-            .sort(intensity_column, descending=True)
+            .sort(intensity_column, descending=descending)
             .group_by(["_x_bin", "_y_bin"])
             .head(points_per_bin)
             .drop(["_x_bin", "_y_bin"])

openms_insight/rendering/bridge.py

@@ -16,6 +16,20 @@ _DEBUG_HASH_TRACKING = os.environ.get("SVC_DEBUG_HASH", "").lower() == "true"
 _DEBUG_STATE_SYNC = os.environ.get("SVC_DEBUG_STATE", "").lower() == "true"
 _logger = logging.getLogger(__name__)
 
+# Numeric data types for type conversion during selection validation
+NUMERIC_DTYPES = (
+    pl.Int8,
+    pl.Int16,
+    pl.Int32,
+    pl.Int64,
+    pl.UInt8,
+    pl.UInt16,
+    pl.UInt32,
+    pl.UInt64,
+    pl.Float32,
+    pl.Float64,
+)
+
 
 def _make_hashable(value: Any) -> Any:
     """
@@ -237,9 +251,7 @@ def _prepare_vue_data_cached(
 
     if _DEBUG_HASH_TRACKING:
         cache_hit = cached is not None
-        _logger.warning(
-            f"[CacheDebug] {component._cache_id}: cache_hit={cache_hit}"
-        )
+        _logger.warning(f"[CacheDebug] {component._cache_id}: cache_hit={cache_hit}")
 
     if cached is not None:
         cached_data, cached_hash, _ = cached  # Ignore cached annotation hash here
@@ -259,7 +271,16 @@ def _prepare_vue_data_cached(
                 data_hash = _hash_data(vue_data)
                 return vue_data, data_hash
         else:
-            # No dynamic annotations - return cached as-is
+            # No dynamic annotations - ensure _plotConfig is present
+            # When annotations are cleared, Vue needs _plotConfig with null columns
+            # to stop showing stale annotations (Vue merge only updates keys present)
+            if hasattr(component, "_build_plot_config"):
+                vue_data = dict(cached_data)
+                vue_data["_plotConfig"] = component._build_plot_config(
+                    getattr(component, "_highlight_column", None),
+                    getattr(component, "_annotation_column", None),
+                )
+                return vue_data, cached_hash
             return cached_data, cached_hash
 
     # Cache miss - compute data
@@ -276,7 +297,9 @@ def _prepare_vue_data_cached(
             # Fallback: store without _plotConfig (may have stale column refs)
             base_data = {k: v for k, v in vue_data.items() if k != "_plotConfig"}
         base_hash = _hash_data(base_data)
-        _set_cached_vue_data(component_id, filter_state_hashable, base_data, base_hash, ann_hash)
+        _set_cached_vue_data(
+            component_id, filter_state_hashable, base_data, base_hash, ann_hash
+        )
 
         # Return full data with annotations
         data_hash = _hash_data(vue_data)
@@ -284,7 +307,9 @@ def _prepare_vue_data_cached(
     else:
         # Store complete data in cache
         data_hash = _hash_data(vue_data)
-        _set_cached_vue_data(component_id, filter_state_hashable, vue_data, data_hash, ann_hash)
+        _set_cached_vue_data(
+            component_id, filter_state_hashable, vue_data, data_hash, ann_hash
+        )
         return vue_data, data_hash
 
 
@@ -330,6 +355,113 @@ def get_vue_component_function():
     return _vue_component_func
 
 
+def _validate_interactivity_selections(
+    component: "BaseComponent",
+    state_manager: "StateManager",
+    state: Dict[str, Any],
+) -> bool:
+    """
+    Validate that interactivity selections still exist in filtered data.
+
+    When an external filter changes, the currently selected value may no longer
+    exist in the filtered dataset. This function checks each interactivity
+    selection and clears it if invalid.
+
+    Args:
+        component: The component to validate selections for
+        state_manager: StateManager to clear invalid selections
+        state: Current state dict (already has filter values)
+
+    Returns:
+        True if any selection was cleared (state changed), False otherwise
+    """
+    interactivity = getattr(component, "_interactivity", None)
+    if not interactivity:
+        return False
+
+    filters = getattr(component, "_filters", None) or {}
+    filter_defaults = getattr(component, "_filter_defaults", None) or {}
+
+    # Get the preprocessed data
+    preprocessed = getattr(component, "_preprocessed_data", None)
+    if preprocessed is not None:
+        data = preprocessed.get("data")
+    else:
+        data = None
+    if data is None:
+        data = getattr(component, "_raw_data", None)
+    if data is None:
+        # Component doesn't have data we can validate against
+        return False
+
+    # Ensure LazyFrame
+    if isinstance(data, pl.DataFrame):
+        data = data.lazy()
+
+    # Apply filters to get the filtered dataset
+    for identifier, column in filters.items():
+        selected_value = state.get(identifier)
+        if selected_value is None and identifier in filter_defaults:
+            selected_value = filter_defaults[identifier]
+
+        if selected_value is None:
+            # Awaiting filter - no data to validate against
+            return False
+
+        # Convert float to int for integer columns (type mismatch handling)
+        if isinstance(selected_value, float) and selected_value.is_integer():
+            selected_value = int(selected_value)
+
+        data = data.filter(pl.col(column) == selected_value)
+
+    # Collect all checks to validate
+    state_changed = False
+    schema = data.collect_schema()
+    checks_to_validate: list[tuple[str, str, Any]] = []
+
+    for identifier, column in interactivity.items():
+        selected_value = state.get(identifier)
+        if selected_value is None:
+            continue  # No selection to validate
+
+        if column not in schema.names():
+            continue  # Column doesn't exist
+
+        # Type conversion for numeric columns
+        col_dtype = schema[column]
+        if col_dtype in NUMERIC_DTYPES:
+            if isinstance(selected_value, float) and selected_value.is_integer():
+                selected_value = int(selected_value)
+
+        checks_to_validate.append((identifier, column, selected_value))
+
+    # Early return if nothing to validate
+    if not checks_to_validate:
+        return False
+
+    # Build single query with all existence checks
+    existence_exprs = [
+        (pl.col(column) == value).any().alias(identifier)
+        for identifier, column, value in checks_to_validate
+    ]
+
+    # Execute ONE query instead of N
+    results = data.select(existence_exprs).collect().row(0, named=True)
+
+    # Process results and clear invalid selections
+    for identifier, _column, value in checks_to_validate:
+        if not results[identifier]:
+            state_manager.set_selection(identifier, None)
+            state_changed = True
+            if _DEBUG_STATE_SYNC:
+                _logger.warning(
+                    f"[Bridge:{component._cache_id}] Cleared invalid selection: "
+                    f"{identifier}={value} not in filtered data"
+                )
+
+    return state_changed
+
+
 def render_component(
     component: "BaseComponent",
     state_manager: "StateManager",
@@ -418,8 +550,8 @@ def render_component(
             cached_ann_hash = None
 
         # Cache valid only if BOTH filter state AND annotation state match
-        filter_state_matches = (cached_state == current_filter_state)
-        ann_state_matches = (cached_ann_hash == current_ann_hash)
+        filter_state_matches = cached_state == current_filter_state
+        ann_state_matches = cached_ann_hash == current_ann_hash
         cache_valid = filter_state_matches and ann_state_matches
 
         if _DEBUG_STATE_SYNC:
@@ -522,6 +654,15 @@ def render_component(
             awaiting_filter = True
             break
 
+    # === Validate interactivity selections BEFORE preparing data ===
+    # When filter changes, the current selection may no longer exist
+    # in the filtered data. Clear it so auto-selection can kick in.
+    if not awaiting_filter:
+        if _validate_interactivity_selections(component, state_manager, state):
+            state_changed = True
+            # Refresh state after clearing invalid selections
+            state = state_manager.get_state_for_vue()
+
     if not awaiting_filter:
         # Extract state keys that affect this component's data
         state_keys = set(component.get_state_dependencies())
@@ -548,6 +689,14 @@ def render_component(
             component, component_id, filter_state_hashable, relevant_state
         )
 
+        # Apply auto-selection from first row (for tables with interactivity)
+        # This ensures downstream components receive data when a filter changes
+        auto_selection = vue_data.pop("_auto_selection", {})
+        for identifier, value in auto_selection.items():
+            if state_manager.get_selection(identifier) is None:
+                state_manager.set_selection(identifier, value)
+                state_changed = True
+
         # Check if Python overrode state during _prepare_vue_data
         # (e.g., table.py sets page to last page after sort)
         final_state = state_manager.get_state_for_vue()
@@ -562,7 +711,9 @@ def render_component(
         data_hash = "awaiting_filter"
         filter_state_hashable = ()
 
-    _logger.info(f"[bridge] Phase4: {component._cache_id} prepared data, hash={data_hash[:8] if data_hash else 'None'}")
+    _logger.info(
+        f"[bridge] Phase4: {component._cache_id} prepared data, hash={data_hash[:8] if data_hash else 'None'}"
+    )
 
     # === PHASE 5: Cache data for next render ===
     if vue_data:
@@ -579,7 +730,12 @@ def render_component(
                 converted_data[data_key] = value
 
         # Store in cache for next render (include annotation hash for validity check)
-        cache[component_id] = (filter_state_hashable, converted_data, data_hash, current_ann_hash)
+        cache[component_id] = (
+            filter_state_hashable,
+            converted_data,
+            data_hash,
+            current_ann_hash,
+        )
 
         # If cache was invalid at Phase 1, we didn't send data to Vue (dataChanged=False).
         # Trigger a rerun so the newly cached data gets sent on the next render.
@@ -595,9 +751,13 @@ def render_component(
 
         if _DEBUG_STATE_SYNC:
             # Log what we're caching for debugging
-            pagination_key = next((k for k, v in filter_state_hashable if "page" in k.lower()), None)
+            pagination_key = next(
+                (k for k, v in filter_state_hashable if "page" in k.lower()), None
+            )
             if pagination_key:
-                pagination_val = next((v for k, v in filter_state_hashable if k == pagination_key), None)
+                pagination_val = next(
+                    (v for k, v in filter_state_hashable if k == pagination_key), None
+                )
                 _logger.warning(
                     f"[Bridge:{component._cache_id}] Phase5: Cached data with hash={data_hash[:8]}, "
                     f"filter_state includes {pagination_key}={pagination_val}"
@@ -625,6 +785,7 @@ def render_component(
             if st.session_state.get(ann_hash_key) is not None:
                 annotations_changed = True
                 st.session_state[ann_hash_key] = None
+            _store_component_annotations(key, None)
 
         if annotations_changed:
             state_changed = True
@@ -664,7 +825,11 @@ def _hash_data(data: Dict[str, Any]) -> str:
     hash_parts = []
     for key, value in sorted(data.items()):
         # Skip internal metadata but NOT dynamic annotation columns or pagination
-        if key.startswith("_") and not key.startswith("_dynamic") and not key.startswith("_pagination"):
+        if (
+            key.startswith("_")
+            and not key.startswith("_dynamic")
+            and not key.startswith("_pagination")
+        ):
             continue
         if isinstance(value, pd.DataFrame):
             # Efficient hash for DataFrames

{openms_insight-0.1.9.dist-info → openms_insight-0.1.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openms-insight
-Version: 0.1.9
+Version: 0.1.11
 Summary: Interactive visualization components for mass spectrometry data in Streamlit
 Project-URL: Homepage, https://github.com/t0mdavid-m/OpenMS-Insight
 Project-URL: Documentation, https://github.com/t0mdavid-m/OpenMS-Insight#readme
@@ -243,7 +243,9 @@ Heatmap(
 - `min_points`: Target size for downsampling (default: 20000)
 - `x_bins`, `y_bins`: Grid resolution for spatial binning
 - `colorscale`: Plotly colorscale name (default: 'Portland')
+- `reversescale`: Invert colorscale direction (default: False)
 - `log_scale`: Use log10 color mapping (default: True). Set to False for linear.
+- `low_values_on_top`: Prioritize low values during downsampling and display them on top (default: False). Use for scores where lower = better (e.g., e-values, PEP, q-values).
 - `intensity_label`: Custom colorbar label (default: 'Intensity')
 
 **Linear scale example:**
@@ -260,6 +262,24 @@ Heatmap(
 )
 ```
 
+**Low values on top (PSM scores):**
+For identification results where lower scores indicate better matches (e.g., e-values, PEP, q-values), use `low_values_on_top=True` to preserve low-scoring points during downsampling and display them on top of high-scoring points:
+
+```python
+Heatmap(
+    cache_id="psm_evalue",
+    data_path="psm_data.parquet",
+    x_column='rt',
+    y_column='mz',
+    intensity_column='e_value',
+    log_scale=True,               # Log scale for e-values
+    low_values_on_top=True,       # Keep/show low e-values (best hits)
+    reversescale=True,            # Bright color = low value = best
+    intensity_label='E-value',
+    colorscale='Portland',
+)
+```
+
 **Categorical mode:**
 Use `category_column` for discrete coloring by category instead of continuous intensity colorscale:
 

{openms_insight-0.1.9.dist-info → openms_insight-0.1.11.dist-info}/RECORD

@@ -1,9 +1,9 @@
-openms_insight/__init__.py,sha256=b4H9k0fPVZ6jCiJ4QVSwzlUQnyElF6ZwAlDI8fdPMJE,1111
+openms_insight/__init__.py,sha256=tmst1YCzXuVLQAs7Hzit5idMPmJsAqn3djpV8fVduYU,1112
 openms_insight/components/__init__.py,sha256=Lcg-D0FILta-YVgMJBlWMKLKC5G5kXOqdy9hBOENABw,233
-openms_insight/components/heatmap.py,sha256=psrdW4gNzZR1jAIox9YS9EHaZaTRrDHFR0t2_0APU9Y,47214
+openms_insight/components/heatmap.py,sha256=Yek06-TCDformcR42VeUCu0d7WDtRQPCpNQ5kOnfv5w,48372
 openms_insight/components/lineplot.py,sha256=I-JPvDzCr3Nu8Boc1V4D8QQ1bHgTqvM6CbeoIe7zJ-s,30896
-openms_insight/components/sequenceview.py,sha256=0pDOE0xeoc1-85QZNGdNwwoBwXi-5MFfeb9pCcOi6rc,30274
-openms_insight/components/table.py,sha256=6r0SiWTDSJS6AHNCy4jTxByY9aCt4ussCQFKKrEg77U,36955
+openms_insight/components/sequenceview.py,sha256=ufvtzuU9zaAybsT3pqfqIR0ZHCl7dKJ-jk3kwJALr54,31241
+openms_insight/components/table.py,sha256=gmgWlsd5GXV2NRkYoDmhi4asaS0pzwoW0C4yf5jI_cI,42740
 openms_insight/components/volcanoplot.py,sha256=F-cmYxJMKXVK-aYJpifp8be7nB8hkQd2kLi9DrBElD8,15155
 openms_insight/core/__init__.py,sha256=EPjKX_FFQRgO8mWHs59I-o0BiuzEMzEU1Pfu9YOfLC4,338
 openms_insight/core/base.py,sha256=h0OaubHLky8mk7Yfy3HTIimsz-DfuNRgLfotJu3pZVw,20517
@@ -12,19 +12,19 @@ openms_insight/core/registry.py,sha256=Hak80Jqhx0qa4gbd1YolNZnM6xBrS8I4U_X7zC0bQ
 openms_insight/core/state.py,sha256=CMToxxNyGnqxMccwOcn7FwABNTzjjTsgsMrJCZOZc2o,12438
 openms_insight/core/subprocess_preprocess.py,sha256=m9FbAAFy9Do1Exlh-m4Wo-LDwv6yHlEI4klz5OVwemc,3133
 openms_insight/preprocessing/__init__.py,sha256=xoGdhNVrX8Ty3ywmyaCcWAO3a6QlKceO1xxsy1C8ZTI,596
-openms_insight/preprocessing/compression.py,sha256=T4YbX9PUlfTfPit_kpuLZn8hYpqLYu3xtTme_CG2ymc,12241
+openms_insight/preprocessing/compression.py,sha256=jHcZqjcFCKb4rRns4PY2DglQecbO0cSThB523bUvUtM,12519
 openms_insight/preprocessing/filtering.py,sha256=fkmaIXfR5hfjyWfaMYqaeybMHaZjvUZYaKCqvxPOWMQ,14152
 openms_insight/preprocessing/scatter.py,sha256=2ifCNTUKHEW9UVpv4z9c5GaLnz5zw9o1119IenzAe9s,4703
 openms_insight/rendering/__init__.py,sha256=ApHvKeh87yY4GTIEai-tCeIXpNbwOXWlmcmIwMMRZYc,198
-openms_insight/rendering/bridge.py,sha256=a_6lq3jR9tDFxdSxMjeJhyV_Tgw7ALcm-UFEvl_TE_M,25615
+openms_insight/rendering/bridge.py,sha256=xFM74gbyzQHFmKt61-hk2ouYZ7KAG7HHosvwmKNBY_M,31311
 openms_insight/js-component/dist/index.html,sha256=LSJ3B_YmGUrCCdZ1UaZO2p6Wqsih6nTH62Z_0uZxpD8,430
-openms_insight/js-component/dist/assets/index.css,sha256=wFvo7FbG132LL7uw0slXfrL_oSQ8u2RKL1DW9hD9-kk,884264
-openms_insight/js-component/dist/assets/index.js,sha256=aqGc3g7XLTRr7ptEgoA3XDu5oMS47yxxjUBXgansIo0,6091480
+openms_insight/js-component/dist/assets/index.css,sha256=s0J7lg0ben8EwwtgSI5tDqNPmPlTI4xOy0XoKsum46Y,884264
+openms_insight/js-component/dist/assets/index.js,sha256=TjpKz5QuvUcdM5-iXP4cHh49m0U4z618yJMHRpS0gEc,6092354
 openms_insight/js-component/dist/assets/materialdesignicons-webfont.eot,sha256=CxgxBNL8XyYZbnc8d72vLgVQn9QlnS0V7O3Kebh-hPk,1307880
 openms_insight/js-component/dist/assets/materialdesignicons-webfont.ttf,sha256=YeirpaTpgf4iz3yOi82-oAR251xiw38Bv37jM2HWhCg,1307660
 openms_insight/js-component/dist/assets/materialdesignicons-webfont.woff,sha256=pZKKDVwvYk5G-Y2bFcL2AEU3f3xZTdeKF1kTLqO0Y-s,587984
 openms_insight/js-component/dist/assets/materialdesignicons-webfont.woff2,sha256=Zi_vqPL4qVwYWI0hd0eJwQfGTnccvmWmmvRikcQxGvw,403216
-openms_insight-0.1.9.dist-info/METADATA,sha256=--VBuRN6Co39E_BZYFk6OwYkOyWEE9uOq_OBK21PdWE,16787
-openms_insight-0.1.9.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-openms_insight-0.1.9.dist-info/licenses/LICENSE,sha256=INFF4rOMmpah7Oi14hLqu7NTOsx56KRRNChAAUcfh2E,1823
-openms_insight-0.1.9.dist-info/RECORD,,
+openms_insight-0.1.11.dist-info/METADATA,sha256=J4jpnQDVfM73lukRzb5JLGZjqeUt-lzbfdtsnMIm8x8,17708
+openms_insight-0.1.11.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+openms_insight-0.1.11.dist-info/licenses/LICENSE,sha256=INFF4rOMmpah7Oi14hLqu7NTOsx56KRRNChAAUcfh2E,1823
+openms_insight-0.1.11.dist-info/RECORD,,