created dockerfile and dockerignore

.dockerignore

@@ -0,0 +1 @@
+# Nothing here yet

data/create_pfam_data.ipynb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d66a3b8c2ba7fe8750182a735b30f7411ddf3868d879b0360999bc5b7d435bb2
+oid sha256:f3a501ca1d972d4e54cc335e10da2bbf637f5be700553a06d35754ae76c23f85
 size 60030

dockerfile

@@ -0,0 +1,46 @@
+# 1. Base image: Ubuntu 22.04
+FROM ubuntu:22.04
+
+# 2. Prevent interactive prompts during apt installs
+ENV DEBIAN_FRONTEND=noninteractive
+
+# 3. System dependencies
+RUN apt-get update && apt-get install -y \
+      wget bzip2 ca-certificates git \
+      libglib2.0-0 libxext6 libsm6 libxrender1 \
+    && rm -rf /var/lib/apt/lists/*
+
+# 4. Install Miniconda
+RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh \
+ && bash Miniconda3-latest-Linux-x86_64.sh -b -p /opt/conda \
+ && rm Miniconda3-latest-Linux-x86_64.sh
+
+ENV PATH=/opt/conda/bin:$PATH
+
+# 5. Create a working dir and copy only environment spec
+WORKDIR /workspace
+COPY environment.yml /workspace/
+
+# Pre-accept Anaconda channel Terms of Service
+RUN conda tos accept \
+      --override-channels \
+      --channel https://repo.anaconda.com/pkgs/main && \
+    conda tos accept \
+      --override-channels \
+      --channel https://repo.anaconda.com/pkgs/r
+
+# Create the env and clean up
+RUN conda env create -f environment.yml && \
+    conda clean -afy
+
+# 7. Copy the rest of your code
+COPY . /workspace/
+
+# 8. Activate env by default
+SHELL ["conda", "run", "-n", "protein-conformal", "/bin/bash", "-c"]
+
+# 9. Expose Gradio port
+EXPOSE 7860
+
+# 10. Default command: start your Gradio app
+CMD ["python", "-m", "protein_conformal.gradio_app"]

environment.yml

@@ -0,0 +1,69 @@
+name: protein-conformal
+channels:
+  - pytorch
+  - conda-forge
+  - huggingface
+  - defaults
+
+dependencies:
+  # Python version
+  - python=3.10
+
+  # Core scientific computing
+  - numpy>=1.24.0
+  - pandas>=2.0.0
+  - scipy>=1.10.0
+  - scikit-learn>=1.0.0
+
+  # Machine Learning & Deep Learning
+  - pytorch>=2.0.0
+  - cpuonly  # CPU-only PyTorch for Windows compatibility
+  - transformers>=4.30.0
+
+  # FAISS for similarity search
+  - faiss-cpu>=1.7.4  # Use faiss-gpu if you have GPU support
+
+  # Bioinformatics
+  - biopython>=1.81
+
+  # Web frameworks and APIs
+  - gradio>=3.50.0
+  - fastapi>=0.90.0
+  - uvicorn>=0.18.0
+  - jinja2>=3.1.0
+  - pydantic>=1.10.0
+  - python-multipart>=0.0.5
+
+  # Visualization and plotting
+  - matplotlib>=3.5.0
+  - seaborn>=0.12.0
+  - plotly>=5.9.0
+  - networkx>=2.8.0
+
+  # Development and debugging tools
+  - tqdm
+  - ipdb
+  - jupyter
+  - notebook
+  - jupyterlab
+
+  # Utilities
+  - requests>=2.27.1
+
+  # Pip dependencies (packages not available via conda)
+  - pip
+  - pip:
+    - py3Dmol>=1.8.0  # 3D molecular visualization for Gradio
+
+# Installation instructions:
+# conda env update -f environment.yaml --prune  # Update existing 'cpr' environment
+# conda activate cpr
+# 
+# Alternative: Create new environment
+# conda env create -f environment.yaml
+# conda activate protein-conformal
+#
+# For GPU support on Linux/properly configured CUDA systems:
+# 1. Replace 'cpuonly' with 'pytorch-cuda=11.8' 
+# 2. Change 'faiss-cpu' to 'faiss-gpu'
+# 3. Add nvidia channel: conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia

pfam/analyze_protein_vec_results.ipynb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e612e3e900789cbb6789c7ba6e56e71f446e5a75d9713785631373929acc4294
-size 529367
+oid sha256:b8d2f7b45d20e8454f32382094c420d90d143b272f0593e6f5e5cfb2e5a0a4f4
+size 1033684

pfam/genes_unknown.ipynb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3eeb0f63505548713fd7d511a1c96282bc98e37f524d807c85d9f6a6dda069e
-size 192542
+oid sha256:651874d343ab2bc89588a928ec485ecff2ef898a1b4cb8444064d30aaace8e58
+size 225341

scripts/precompute_fnr_thresholds.sh

@@ -13,53 +13,6 @@ OUTPUT_DIR="../results"
 TEMP_DIR="./temp_fnr_results"
 CSV_OUTPUT="$OUTPUT_DIR/fnr_thresholds.csv"
 
-# Parse command line arguments
-while [[ $# -gt 0 ]]; do
-    case $1 in
-        --min-alpha)
-            MIN_ALPHA="$2"
-            shift 2
-            ;;
-        --max-alpha)
-            MAX_ALPHA="$2"
-            shift 2
-            ;;
-        --num-values)
-            NUM_ALPHA_VALUES="$2"
-            shift 2
-            ;;
-        --num-trials)
-            NUM_TRIALS="$2"
-            shift 2
-            ;;
-        --n-calib)
-            N_CALIB="$2"
-            shift 2
-            ;;
-        --output)
-            CSV_OUTPUT="$2"
-            shift 2
-            ;;
-        -h|--help)
-            echo "Usage: $0 [OPTIONS]"
-            echo "Options:"
-            echo "  --min-alpha FLOAT      Minimum alpha value (default: $MIN_ALPHA)"
-            echo "  --max-alpha FLOAT      Maximum alpha value (default: $MAX_ALPHA)"
-            echo "  --num-values INT       Number of alpha values to test (default: $NUM_ALPHA_VALUES)"
-            echo "  --num-trials INT       Number of trials per alpha (default: $NUM_TRIALS)"
-            echo "  --n-calib INT          Calibration set size (default: $N_CALIB)"
-            echo "  --output PATH          Output CSV file (default: $CSV_OUTPUT)"
-            echo "  -h, --help             Show this help message"
-            exit 0
-            ;;
-        *)
-            echo "Unknown option: $1"
-            exit 1
-            ;;
-    esac
-done
-
-# Create necessary directories
 mkdir -p "$OUTPUT_DIR"
 mkdir -p "$TEMP_DIR"
 
@@ -75,7 +28,7 @@ echo "Output file: $CSV_OUTPUT"
 echo ""
 
 # Generate alpha values using Python
-ALPHA_VALUES=$(python3 -c "
+ALPHA_VALUES=$(python -c "
 import numpy as np
 alphas = np.linspace($MIN_ALPHA, $MAX_ALPHA, $NUM_ALPHA_VALUES)
 print(' '.join([str(a) for a in alphas]))
@@ -92,7 +45,7 @@ for alpha in $ALPHA_VALUES; do
     
     # Run FNR generation for exact matches
     echo "  Running exact matches..."
-    python3 ../pfam/generate_fnr.py \
+    python ../pfam/generate_fnr.py \
         --alpha "$alpha" \
         --partial false \
         --num_trials "$NUM_TRIALS" \
@@ -102,7 +55,7 @@ for alpha in $ALPHA_VALUES; do
     
     # Run FNR generation for partial matches
     echo "  Running partial matches..."
-    python3 ../pfam/generate_fnr.py \
+    python ../pfam/generate_fnr.py \
         --alpha "$alpha" \
         --partial true \
         --num_trials "$NUM_TRIALS" \
@@ -111,7 +64,7 @@ for alpha in $ALPHA_VALUES; do
         --add_date false
     
     # Extract results and append to CSV using Python
-    python3 -c "
+    python -c "
 import numpy as np
 import sys