Remove batch annotation functionality and related tests

Eliminated the batch_annotate_clusters function and its prompt generator from the codebase, as well as all references and tests related to batch annotation. Updated the tutorial and README to remove batch annotation examples and documentation.

Author: cafferychen777

notebooks/mLLMCelltype_Tutorial.ipynb

@@ -548,99 +548,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# 1. Batch processing multiple datasets\n",
-    "print(\"🔄 Batch Processing Example:\")\n",
-    "print(\"\"\"\n",
-    "from mllmcelltype import batch_annotate_clusters\n",
-    "\n",
-    "# Process multiple datasets\n",
-    "datasets = {\n",
-    "    'sample1': marker_genes_1,\n",
-    "    'sample2': marker_genes_2,\n",
-    "    'sample3': marker_genes_3\n",
-    "}\n",
-    "\n",
-    "batch_results = batch_annotate_clusters(\n",
-    "    datasets=datasets,\n",
-    "    species='human',\n",
-    "    models=selected_models,\n",
-    "    api_keys=api_keys\n",
-    ")\n",
-    "\"\"\")\n",
-    "\n",
-    "# 2. Custom prompts for specialized contexts\n",
-    "print(\"\\n🎨 Custom Prompt Example:\")\n",
-    "print(\"\"\"\n",
-    "# For specialized tissues or conditions\n",
-    "custom_prompt = '''You are analyzing {species} {tissue} from a patient with autoimmune disease.\n",
-    "Focus on immune cell subtypes and activation states.'''\n",
-    "\n",
-    "results = annotate_clusters(\n",
-    "    marker_genes=marker_genes,\n",
-    "    custom_prompt=custom_prompt,\n",
-    "    species='human',\n",
-    "    tissue='synovial fluid',\n",
-    "    model=model,\n",
-    "    api_key=api_key\n",
-    ")\n",
-    "\"\"\")\n",
-    "\n",
-    "# 3. Hierarchical annotation\n",
-    "print(\"\\n🌳 Hierarchical Annotation Example:\")\n",
-    "print(\"\"\"\n",
-    "# First level: broad cell types\n",
-    "level1_results = annotate_clusters(\n",
-    "    marker_genes, \n",
-    "    species=species,\n",
-    "    model=model,\n",
-    "    api_key=api_key\n",
-    ")\n",
-    "\n",
-    "# Second level: detailed subtypes for immune cells\n",
-    "immune_clusters = [c for c, ct in level1_results.items() \n",
-    "                  if any(term in ct.lower() for term in ['immune', 't cell', 'b cell'])]\n",
-    "immune_markers = {k: marker_genes[k] for k in immune_clusters}\n",
-    "\n",
-    "level2_results = annotate_clusters(\n",
-    "    immune_markers,\n",
-    "    species=species,\n",
-    "    tissue=tissue,\n",
-    "    custom_prompt='Focus on detailed immune cell subtypes and activation states.',\n",
-    "    model=model,\n",
-    "    api_key=api_key\n",
-    ")\n",
-    "\"\"\")\n",
-    "\n",
-    "# 4. Cost estimation\n",
-    "print(\"\\n💰 Cost Estimation:\")\n",
-    "total_clusters = len(marker_genes)\n",
-    "models_used = len(selected_models)\n",
-    "avg_tokens_per_annotation = 500  # Approximate\n",
-    "\n",
-    "print(f\"Clusters to annotate: {total_clusters}\")\n",
-    "print(f\"Models used: {models_used}\")\n",
-    "print(f\"Total API calls: ~{total_clusters * models_used}\")\n",
-    "print(\"\\nEstimated costs vary by provider:\")\n",
-    "print(\"- OpenRouter free models: $0\")\n",
-    "print(\"- GPT-4: ~$0.01-0.02 per cluster\")\n",
-    "print(\"- Claude: ~$0.01-0.015 per cluster\")\n",
-    "print(\"- Gemini: ~$0.001-0.005 per cluster\")\n",
-    "\n",
-    "# 5. Cache management\n",
-    "print(\"\\n🗄️ Cache Management:\")\n",
-    "print(\"\"\"\n",
-    "from mllmcelltype import get_cache_stats, clear_cache\n",
-    "\n",
-    "# Check cache statistics\n",
-    "stats = get_cache_stats()\n",
-    "print(f\"Cache size: {stats['total_size_mb']:.2f} MB\")\n",
-    "print(f\"Cached results: {stats['total_entries']}\")\n",
-    "\n",
-    "# Clear cache if needed\n",
-    "# clear_cache()  # Uncomment to clear\n",
-    "\"\"\")"
-   ]
+   "source": "# 1. Processing multiple datasets\nprint(\"🔄 Processing Multiple Datasets:\")\nprint(\"\"\"\n# Process multiple datasets with a simple loop\ndatasets = {\n    'sample1': marker_genes_1,\n    'sample2': marker_genes_2,\n    'sample3': marker_genes_3\n}\n\nresults = {}\nfor name, markers in datasets.items():\n    results[name] = annotate_clusters(\n        marker_genes=markers,\n        species='human',\n        provider='openai',\n        model='gpt-4-turbo'\n    )\n\"\"\")\n\n# 2. Custom prompts for specialized contexts\nprint(\"\\n🎨 Custom Prompt Example:\")\nprint(\"\"\"\n# For specialized tissues or conditions\ncustom_prompt = '''You are analyzing {species} {tissue} from a patient with autoimmune disease.\nFocus on immune cell subtypes and activation states.'''\n\nresults = annotate_clusters(\n    marker_genes=marker_genes,\n    custom_prompt=custom_prompt,\n    species='human',\n    tissue='synovial fluid',\n    model=model,\n    api_key=api_key\n)\n\"\"\")\n\n# 3. Hierarchical annotation\nprint(\"\\n🌳 Hierarchical Annotation Example:\")\nprint(\"\"\"\n# First level: broad cell types\nlevel1_results = annotate_clusters(\n    marker_genes, \n    species=species,\n    model=model,\n    api_key=api_key\n)\n\n# Second level: detailed subtypes for immune cells\nimmune_clusters = [c for c, ct in level1_results.items() \n                  if any(term in ct.lower() for term in ['immune', 't cell', 'b cell'])]\nimmune_markers = {k: marker_genes[k] for k in immune_clusters}\n\nlevel2_results = annotate_clusters(\n    immune_markers,\n    species=species,\n    tissue=tissue,\n    custom_prompt='Focus on detailed immune cell subtypes and activation states.',\n    model=model,\n    api_key=api_key\n)\n\"\"\")\n\n# 4. Cost estimation\nprint(\"\\n💰 Cost Estimation:\")\ntotal_clusters = len(marker_genes)\nmodels_used = len(selected_models)\navg_tokens_per_annotation = 500  # Approximate\n\nprint(f\"Clusters to annotate: {total_clusters}\")\nprint(f\"Models used: {models_used}\")\nprint(f\"Total API calls: ~{total_clusters * models_used}\")\nprint(\"\\nEstimated costs vary by provider:\")\nprint(\"- OpenRouter free models: $0\")\nprint(\"- GPT-4: ~$0.01-0.02 per cluster\")\nprint(\"- Claude: ~$0.01-0.015 per cluster\")\nprint(\"- Gemini: ~$0.001-0.005 per cluster\")\n\n# 5. Cache management\nprint(\"\\n🗄️ Cache Management:\")\nprint(\"\"\"\nfrom mllmcelltype import get_cache_stats, clear_cache\n\n# Check cache statistics\nstats = get_cache_stats()\nprint(f\"Cache size: {stats['total_size_mb']:.2f} MB\")\nprint(f\"Cached results: {stats['total_entries']}\")\n\n# Clear cache if needed\n# clear_cache()  # Uncomment to clear\n\"\"\")"
   },
   {
    "cell_type": "markdown",

python/README.md

@@ -241,30 +241,6 @@ consensus_results = interactive_consensus_annotation(
 
 ## Advanced Usage
 
-### Batch Annotation
-
-```python
-from mllmcelltype import batch_annotate_clusters
-
-# Prepare multiple sets of marker genes (e.g., from different samples)
-marker_genes_list = [marker_genes_df1, marker_genes_df2, marker_genes_df3]
-
-# Batch annotate multiple datasets efficiently
-batch_annotations = batch_annotate_clusters(
-    marker_genes_list=marker_genes_list,
-    species='mouse',                      # Organism species
-    provider='anthropic',                 # LLM provider
-    model='claude-sonnet-4-5-20250929',  # Latest Sonnet model (recommended)
-    tissue='brain'                       # Optional tissue context
-)
-
-# Process and utilize results
-for i, annotations in enumerate(batch_annotations):
-    print(f"Dataset {i+1} annotations:")
-    for cluster, annotation in annotations.items():
-        print(f"  Cluster {cluster}: {annotation}")
-```
-
 ### Targeted Analysis: New Enhanced Parameters
 
 mLLMCelltype v1.3.0+ introduces two powerful parameters for more precise control over cell type annotation:

python/mllmcelltype/__init__.py

@@ -1,6 +1,6 @@
 """mLLMCelltype: A Python module for cell type annotation using various LLMs."""
 
-from .annotate import annotate_clusters, batch_annotate_clusters, get_model_response
+from .annotate import annotate_clusters, get_model_response
 from .cache_manager import get_cache_info
 from .consensus import (
     check_consensus,
@@ -11,7 +11,6 @@
 from .functions import get_provider
 from .logger import setup_logging, write_log
 from .prompts import (
-    create_batch_prompt,
     create_consensus_check_prompt,
     create_discussion_prompt,
     create_prompt,
@@ -37,7 +36,6 @@
 __all__ = [
     # Core annotation
     "annotate_clusters",
-    "batch_annotate_clusters",
     "get_model_response",
     # Functions
     "get_provider",
@@ -56,7 +54,6 @@
     "format_results",
     # Prompts
     "create_prompt",
-    "create_batch_prompt",
     "create_discussion_prompt",
     "create_consensus_check_prompt",
     # Consensus