fixes bug

CLAUDE.md

@@ -0,0 +1,33 @@
+# Anton Microscopy Project Memory
+
+## VLM Integration Options
+
+### Current Implementation
+- Uses **Google Gemini 1.5 Flash** via `google-generativeai` library
+- Authentication: `GOOGLE_API_KEY` environment variable
+- Location: `/anton/vlm/interface.py:79-91`
+- Supports multimodal microscopy image analysis
+
+### Hugging Face VLM Alternatives
+
+#### Open Source Models (free, run locally):
+- `microsoft/kosmos-2-patch14-224` - Good for object detection
+- `Salesforce/blip2-opt-2.7b` - Image captioning and QA  
+- `llava-hf/llava-1.5-7b-hf` - Strong multimodal reasoning
+
+#### Hugging Face Inference API (hosted):
+- `meta-llama/Llama-3.2-11B-Vision-Instruct`
+- `microsoft/Phi-3.5-vision-instruct`
+- `Qwen/Qwen2-VL-7B-Instruct`
+
+#### Benefits of switching to HF VLMs:
+- No API costs for local models
+- Better privacy (data stays local)
+- More control over model behavior
+- Can fine-tune for microscopy-specific tasks
+
+### Integration Points
+- Main VLM interface: `/anton/vlm/interface.py`
+- Pipeline integration: `/anton/core/pipeline.py:23-28`
+- UI configuration: `/app.py:57-69`
+- Dependencies: `requirements.txt:8` (google-generativeai)

anton/cmpo/ontology.py

@@ -10,7 +10,13 @@ import logging
 class CMPOOntology:
     """Manage CMPO ontology data and provide lookup functionality"""
     
-    def __init__(self, data_path="data/cmpo.json", cache_path="data/cmpo_cache.pkl"):
+    def __init__(self, data_path=None, cache_path=None):
+        # Default to package-relative paths
+        if data_path is None:
+            data_path = Path(__file__).parent / "data" / "cmpo.json"
+        if cache_path is None:
+            cache_path = Path(__file__).parent / "data" / "cmpo_cache.pkl"
+        
         self.data_path = Path(data_path)
         self.cache_path = Path(cache_path)
         self.ontology = {}
@@ -20,6 +26,23 @@ class CMPOOntology:
         
         self._load_ontology()
     
+    def _save_ontology_data(self, ontology_data):
+        """Save ontology data with fallback to temp directory if permission denied"""
+        try:
+            self.data_path.parent.mkdir(parents=True, exist_ok=True)
+            with open(self.data_path, 'w') as f:
+                json.dump(ontology_data, f, indent=2)
+        except PermissionError:
+            # If we can't write to package directory, use temp directory
+            import tempfile
+            temp_dir = Path(tempfile.gettempdir()) / "anton_cmpo"
+            temp_dir.mkdir(exist_ok=True)
+            temp_file = temp_dir / "cmpo.json"
+            with open(temp_file, 'w') as f:
+                json.dump(ontology_data, f, indent=2)
+            logging.info(f"Saved CMPO data to temporary location: {temp_file}")
+            self.data_path = temp_file
+    
     def _load_ontology(self):
         """Load CMPO ontology from JSON file or download if needed"""
         if self.data_path.exists():
@@ -64,10 +87,7 @@ class CMPOOntology:
         ontology_data = self._parse_obo_content(response.text)
         
         # Save processed data
-        self.data_path.parent.mkdir(parents=True, exist_ok=True)
-        with open(self.data_path, 'w') as f:
-            json.dump(ontology_data, f, indent=2)
-        
+        self._save_ontology_data(ontology_data)
         self.ontology = ontology_data
         logging.info(f"Successfully loaded {len(ontology_data)} CMPO terms")
     
@@ -178,10 +198,7 @@ class CMPOOntology:
             page += 1
         
         # Save to file
-        self.data_path.parent.mkdir(parents=True, exist_ok=True)
-        with open(self.data_path, 'w') as f:
-            json.dump(ontology_data, f, indent=2)
-        
+        self._save_ontology_data(ontology_data)
         self.ontology = ontology_data
     
     def _download_owl_file(self):
@@ -219,10 +236,7 @@ class CMPOOntology:
             Path(temp_owl).unlink()
             
             # Save processed data
-            self.data_path.parent.mkdir(parents=True, exist_ok=True)
-            with open(self.data_path, 'w') as f:
-                json.dump(ontology_data, f, indent=2)
-            
+            self._save_ontology_data(ontology_data)
             self.ontology = ontology_data
             
         except ImportError:
@@ -267,10 +281,7 @@ class CMPOOntology:
         }
         
         # Save minimal ontology
-        self.data_path.parent.mkdir(parents=True, exist_ok=True)
-        with open(self.data_path, 'w') as f:
-            json.dump(minimal_ontology, f, indent=2)
-        
+        self._save_ontology_data(minimal_ontology)
         self.ontology = minimal_ontology
     
     def _build_indices(self):

prompts/cmpo_mapping.txt

@@ -0,0 +1,17 @@
+Given this microscopy description: "{FREEFORM_DESCRIPTION}"
+Map relevant phrases to CMPO ontology terms.
+
+Available CMPO terms: {CMPO_CONTEXT}
+
+Output format:
+{
+    "mappings": [
+        {
+            "phrase": "nuclear fragmentation",
+            "cmpo_id": "CMPO_0000094",
+            "confidence": 0.95,
+            "reasoning": "Clear indication of apoptotic phenotype"
+        }
+    ]
+} 
+ 

prompts/stage1_global.txt

@@ -0,0 +1,9 @@
+Analyze this fluorescence microscopy image for overall scene understanding.
+Provide:
+1. Image quality assessment
+2. Staining type identification
+3. General cellular/tissue characteristics
+4. Recommended analysis approach
+
+Focus on: [DYNAMIC_CONTEXT]
+Output format: Natural language description + structured assessment 

prompts/stage2_objects.txt

@@ -0,0 +1,7 @@
+Task: Identify major structures and suggest segmentation strategies for this fluorescence microscopy image.
+Input: [image, global context]
+Provide:
+1. List of detected objects/structures
+2. Segmentation guidance (e.g., nuclei, cytoplasm)
+3. Object count estimate
+Output format: Structured JSON with detected_objects, segmentation_guidance, object_count_estimate 

prompts/stage3_features.txt

@@ -0,0 +1,14 @@
+Task: Analyze segmented regions for complex CMPO features, focusing on texture-based patterns.
+Input:
+    - Region patches: [nuclei, cytoplasm patches]
+    - Config: {stain: "{STAIN}", channel: {CHANNEL}, phenotype_focus: "{PHENOTYPE}"}
+    - Target features: ["chromatin_condensation", "LC3_puncta", "nuclear_fragmentation"]
+Analyze:
+    1. Texture patterns (granular, smooth, fragmented)
+    2. Intensity distributions (bright spots, uniform, heterogeneous)
+    3. Morphological features (shape irregularities, size variations)
+Provide:
+    1. Feature descriptions with confidence scores
+    2. CMPO term mappings
+    3. Supporting visual evidence
+Output format: {features: [{name: str, confidence: float, evidence: str, cmpo_id: str}]} 

prompts/stage4_population.txt

@@ -0,0 +1,10 @@
+Task: Analyze population-level patterns in this fluorescence microscopy image.
+Input:
+    - Individual cell feature analyses (morphology, intensity, localization patterns)
+    - Experimental context and biological metadata
+Provide:
+    1. Population summary describing overall cellular characteristics and phenotype prevalence
+    2. Quantitative estimates (e.g., percentage of cells showing specific phenotypes)
+    3. Biological interpretation of patterns in experimental context
+    4. CMPO phenotype relevance assessment
+Output format: Natural language biological analysis with structured sections for population summary, quantitative insights, and biological interpretation 

requirements.txt

@@ -10,4 +10,5 @@ anthropic
 python-dotenv
 streamlit==1.30.0
 plotly
-networkx
+networkx
+owlready2