Improve installation by providing replicable conda/mamba environment & Add option for batch screaning

.gitignore

@@ -151,3 +151,6 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+# Ignore apptainers
+*.sif

README.md

@@ -20,8 +20,9 @@ You can find the environment file under `env` folder.
 
 ### Apptainer
 
+Run this from this root directory:
 ```
-apptainer build -s --nv ${CONTAINER_PATH} ./env/Apptainer
+apptainer build --nv SpatialPPIv2.sif ./env/Apptainer
 ```
 
 ### Docker
@@ -33,25 +34,12 @@ docker build -t ${IMAGE_NAME} ./env
 ### Conda
 
 ```
-conda create -n pytorch221 python=3.11
-conda activate pytorch221
-conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia
-pip install numpy pandas seaborn tensorboard
-pip install torch_geometric==2.5.1
-pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.2.0+cu118.html
-conda install lightning -c conda-forge
-pip install lightning[extra]
-pip install matplotlib==3.8.3
-pip install biopandas==0.5.1
-pip install biopython==1.83
-pip install transformers==4.40.2
-pip install sentencepiece==0.2.0
-pip install torchsummary==1.5.1
-pip install scipy==1.12.0
-pip install torch_cluster -f https://data.pyg.org/whl/torch-2.2.0+cu118.html
-pip install git+https://github.com/yusuf1759/prodigy-cryst.git
-pip install pinder[all]
-pip install fair-esm
+conda env create -f env/environment.yaml
+```
+
+or if you have mamba (should be faster)
+```
+mamba env create -f env/environment.yaml
 ```
 
 ## Inference protein interactions
@@ -79,6 +67,31 @@ When there is no suitable protein structure file, `fasta` files can be used to m
 python inference.py --A demo/D3INY1.fasta --B demo/P62593.fasta
 ```
 
+### Batch inference: one query protein vs a folder
+
+You can screen one query protein against all supported files in a folder and save interaction probabilities to a CSV file:
+
+```
+python inference_batch.py --query demo/P33895.pdb --targets demo --output results.csv
+```
+
+Options:
+
+- `--query`: Query protein file (`.pdb`/`.cif` or `.fasta`/`.fa`/`.faa`/`.fna`)
+- `--targets`: Folder containing target protein files
+- `--output`: Output CSV path. Default is `inference_batch.csv`
+- `--chain_query`: Chain ID for query structure files. Default is `first`
+- `--chain_targets`: Chain ID for target structure files. Default is `first`
+- `--model`: Model for structure inputs (`ProtT5` or `ESM-2+ac`). For FASTA query, `ESM-2+ac` is forced
+- `--device`: Either `cuda` or `cpu`
+
+Notes:
+
+- Query and target files must be the same modality:
+  - FASTA query requires all FASTA targets
+  - Structure query (`pdb`/`cif`) requires all structure targets
+- The output CSV contains columns: `query`, `target`, `probability`, `status`, `error`
+
 ### Visualization of inference process
 
 Please check the [notebook](https://github.com/ohuelab/SpatialPPIv2/blob/main/demo/example_visualize.ipynb).

env/Apptainer

@@ -1,23 +1,41 @@
 Bootstrap: docker
-From: pytorch/pytorch:2.2.1-cuda11.8-cudnn8-devel
+From: nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04
+
+%files
+    env/environment.yaml environment.yaml
 
 %post
-    apt-get update && apt-get install -y git
-
-    pip install -U pip
-    pip install numpy pandas seaborn tensorboard
-    pip install torch_geometric==2.5.1
-    pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.2.0+cu118.html
-    conda install lightning -c conda-forge
-    pip install lightning[extra]
-    pip install matplotlib==3.8.3
-    pip install biopandas==0.5.1
-    pip install biopython==1.83
-    pip install transformers==4.40.2
-    pip install sentencepiece==0.2.0
-    pip install torchsummary==1.5.1
-    pip install scipy==1.12.0
-    pip install torch_cluster -f https://data.pyg.org/whl/torch-2.2.0+cu118.html
-    pip install git+https://github.com/yusuf1759/prodigy-cryst.git
-    pip install pinder[all]
-    pip install fair-esm
+    set -e
+    export DEBIAN_FRONTEND=noninteractive
+
+    apt-get update
+    apt-get install -y --no-install-recommends \
+        bzip2 \
+        ca-certificates \
+        curl \
+        git
+    rm -rf /var/lib/apt/lists/*
+
+    curl -Ls https://micro.mamba.pm/api/micromamba/linux-64/latest \
+      | tar -xvj -C /usr/local/bin --strip-components=1 bin/micromamba
+
+    export MAMBA_ROOT_PREFIX=/opt/conda
+    mkdir -p "${MAMBA_ROOT_PREFIX}"
+
+    micromamba create -y -n SpatialPPIv2 -f environment.yaml
+    micromamba clean -a -y
+
+%environment
+    export MAMBA_ROOT_PREFIX=/opt/conda
+    export MAMBA_EXE=/usr/local/bin/micromamba
+    export CONDA_DEFAULT_ENV=SpatialPPIv2
+    export PATH=/opt/conda/envs/SpatialPPIv2/bin:/opt/conda/bin:$PATH
+    export CUDA_HOME=/usr/local/cuda
+    export LD_LIBRARY_PATH=/usr/local/cuda/lib64:${LD_LIBRARY_PATH}
+
+%runscript
+    if [ "$#" -eq 0 ]; then
+        exec /bin/bash
+    else
+        exec micromamba run -n SpatialPPIv2 "$@"
+    fi

env/Dockerfile

@@ -1,20 +1,41 @@
-FROM pytorch/pytorch:2.2.1-cuda11.8-cudnn8-devel
-RUN apt-get update && apt-get install -y git
-# Install dependency.
-RUN pip install -U pip
-RUN pip install numpy pandas seaborn tensorboard
-RUN pip install torch_geometric==2.5.1
-RUN pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.2.0+cu118.html
-RUN conda install lightning -c conda-forge
-RUN pip install lightning[extra]
-RUN pip install matplotlib==3.8.3
-RUN pip install biopandas==0.5.1
-RUN pip install biopython==1.83
-RUN pip install transformers==4.40.2
-RUN pip install sentencepiece==0.2.0
-RUN pip install torchsummary==1.5.1
-RUN pip install scipy==1.12.0
-RUN pip install torch_cluster -f https://data.pyg.org/whl/torch-2.2.0+cu118.html
-RUN pip install git+https://github.com/yusuf1759/prodigy-cryst.git
-RUN pip install pinder[all]
-RUN pip install fair-esm
+FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV MAMBA_ROOT_PREFIX=/opt/conda
+ENV MAMBA_EXE=/usr/local/bin/micromamba
+ENV CONDA_DEFAULT_ENV=SpatialPPIv2
+ENV CUDA_HOME=/usr/local/cuda
+ENV PATH=/opt/conda/envs/SpatialPPIv2/bin:/opt/conda/bin:${PATH}
+ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:${LD_LIBRARY_PATH}
+
+WORKDIR /workspace
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    bzip2 \
+    ca-certificates \
+    curl \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN curl -Ls https://micro.mamba.pm/api/micromamba/linux-64/latest \
+    | tar -xvj -C /usr/local/bin --strip-components=1 bin/micromamba
+
+COPY env/environment.yaml /tmp/environment.yaml
+
+RUN mkdir -p "${MAMBA_ROOT_PREFIX}" \
+    && micromamba create -y -n SpatialPPIv2 -f /tmp/environment.yaml \
+    && micromamba clean -a -y \
+    && rm -f /tmp/environment.yaml
+
+RUN printf '%s\n' \
+    '#!/usr/bin/env bash' \
+    'set -e' \
+    'if [ "$#" -eq 0 ]; then' \
+    '  exec /bin/bash' \
+    'else' \
+    '  exec micromamba run -n SpatialPPIv2 "$@"' \
+    'fi' \
+    > /usr/local/bin/docker-entrypoint.sh \
+    && chmod +x /usr/local/bin/docker-entrypoint.sh
+
+ENTRYPOINT ["/usr/local/bin/docker-entrypoint.sh"]