Added HF3 Dockerfile

dockerfiles/Dockerfile_nfcore-proteinfold_helixfold3

@@ -0,0 +1,34 @@
+FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04
+
+LABEL Author="j.caley@unsw.edu.au" \
+    title="nfcore/proteinfold_helixfold3" \
+    Version="0.9.0" \
+    description="Docker image containing all software requirements to run the RUN_HELIXFOLD3 module using the nf-core/proteinfold pipeline"
+
+ENV PYTHONPATH="/app/helixfold3:$PYTHONPATH" \
+    PATH="/conda/bin:/app/helixfold3:$PATH" \
+    PYTHON_BIN="/conda/envs/helixfold/bin/python3.9" \
+    ENV_BIN="/conda/envs/helixfold/bin" \
+    OBABEL_BIN="/conda/envs/helixfold/bin"
+
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y wget git && \
+    wget -q -P /tmp "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh" && \
+    bash /tmp/Miniforge3-$(uname)-$(uname -m).sh -b -p /conda && \
+    rm -rf /tmp/Miniforge3-$(uname)-$(uname -m).sh /var/lib/apt/lists/* && \
+    apt-get autoremove -y && apt-get clean -y
+
+RUN git clone --single-branch --branch dev --depth 1 --no-checkout https://github.com/PaddlePaddle/PaddleHelix.git /app/helixfold3 && \
+    cd /app/helixfold3 && \
+    git sparse-checkout init --cone && \
+    git sparse-checkout set apps/protein_folding/helixfold3 && \
+    git checkout dev && \
+    mv apps/protein_folding/helixfold3/* . && \
+    rm -rf apps
+
+COPY hf3_environment.yaml /app/helixfold3/
+RUN /conda/bin/mamba env create --file=/app/helixfold3/hf3_environment.yaml && \
+    /conda/bin/mamba install -y -c bioconda aria2 hmmer==3.3.2 kalign2==2.04 hhsuite==3.3.0 -n helixfold && \
+    /conda/bin/mamba install -y -c conda-forge openbabel -n helixfold && \
+    /conda/bin/mamba clean --all --force-pkgs-dirs -y && \
+    rm -rf /root/.cache && \
+    apt-get autoremove -y && apt-get remove --purge -y wget git && apt-get clean -y

dockerfiles/helixfold3.def

@@ -1,19 +1,19 @@
 Bootstrap: docker
-From: nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04
+From: nvidia/cuda:12.6.0-cudnn-devel-ubuntu24.04
 
 %labels
     Author j.caley@unsw.edu.au
-    Version 0.2.4
+    Version 0.2.1
 
 %files
-    hf3_environment.yaml .
+    environment.yaml .
 
 %post
-    apt update && DEBIAN_FRONTEND=noninteractive apt install --no-install-recommends -y wget git build-essential
+    apt update && DEBIAN_FRONTEND=noninteractive apt install --no-install-recommends -y wget git
 
-    wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
-    bash Miniforge3-$(uname)-$(uname -m).sh -b -p /opt/miniforge
-    rm Miniforge3-$(uname)-$(uname -m).sh
+    wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-Linux-x86_64.sh"
+    bash Miniforge3-Linux-x86_64.sh -b -p /opt/miniforge
+    rm Miniforge3-Linux-x86_64.sh
     export PATH="/opt/miniforge/bin:$PATH"
 
     git clone --single-branch --branch dev --depth 1 --no-checkout https://github.com/PaddlePaddle/PaddleHelix.git app/helixfold3
@@ -23,11 +23,18 @@ From: nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04
     git checkout dev
     mv apps/protein_folding/helixfold3/* .
     rm -rf apps
-    mv /hf3_environment.yaml .
-    CONDA_PKGS_DIRS=$(mktemp -d -p "${TMPDIR:-/tmp}") mamba env create --file=hf3_environment.yaml
+    mv /environment.yaml .
+    mamba env create -f environment.yaml
+
+    conda install -y -c bioconda aria2 hmmer==3.3.2 kalign2==2.04 hhsuite==3.3.0 -n helixfold
+    conda install -y -c conda-forge openbabel -n helixfold
+
+    mamba run -n helixfold \
+        'python3 -m pip install paddlepaddle-gpu==2.6.1 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html && \
+        python3 -m pip install -r requirements.txt'
 
     apt autoremove -y && apt remove --purge -y wget git && apt clean -y
-    rm -rf /var/lib/apt/lists/* /root/.cache $CONDA_PKGS_DIRS
+    rm -rf /var/lib/apt/lists/* /root/.cache *.tar.gz
     mamba clean --all --force-pkgs-dirs -y
 
 %environment

dockerfiles/hf3_environment.yaml

@@ -13,23 +13,3 @@ dependencies:
   - libgcc
   - libgomp
   - pip
-  - aria2
-  - hmmer==3.4
-  - kalign2==2.04
-  - hhsuite==3.3.0
-  - openbabel
-  - pip:
-      - paddlepaddle-gpu==2.6.1 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html
-      - absl-py==0.13.0
-      - biopython==1.79
-      - chex==0.0.7
-      - dm-haiku==0.0.4
-      - dm-tree==0.1.6
-      - docker==5.0.0
-      - immutabledict==2.0.0
-      - jax==0.2.14
-      - ml-collections==0.1.0
-      - pandas==1.3.4
-      - scipy==1.9.0
-      - rdkit-pypi==2022.9.5 
-      - posebusters

modules/local/run_helixfold3.nf

@@ -11,7 +11,7 @@ process RUN_HELIXFOLD3 {
         error("Local RUN_HELIXFOLD3 module does not support Conda. Please use Docker / Singularity / Podman / Apptainer instead.")
     }
 
-    container "/srv/scratch/sbf-pipelines/proteinfold/singularity/helixfold3.sif"
+    container "/srv/scratch/z5378336/apptainers/hf3_docker.sif"
 
     input:
     tuple val(meta), path(fasta)
@@ -43,19 +43,19 @@ process RUN_HELIXFOLD3 {
     """
     export MAXIT_SRC="./maxit_src"
     export RCSBROOT="\$MAXIT_SRC"
-    export PATH="\$MAXIT_SRC/bin:/opt/miniforge/envs/helixfold/bin:$PATH"
-    export OBABEL_BIN="/opt/miniforge/envs/helixfold/bin"
+    export PATH="\$MAXIT_SRC/bin:\$ENV_BIN:$PATH"
+    export OBABEL_BIN="\$ENV_BIN"
 
     ln -s /app/helixfold3/* .
 
-    /opt/miniforge/envs/helixfold/bin/python3.9 inference.py \
+    \$ENV_BIN/python3.9 inference.py \
         --maxit_binary "\$MAXIT_SRC/bin/maxit" \
-        --jackhmmer_binary_path "/opt/miniforge/envs/helixfold/bin/jackhmmer" \
-        --hhblits_binary_path "/opt/miniforge/envs/helixfold/bin/hhblits" \
-        --hhsearch_binary_path "/opt/miniforge/envs/helixfold/bin/hhsearch" \
-        --kalign_binary_path "/opt/miniforge/envs/helixfold/bin/kalign" \
-        --hmmsearch_binary_path "/opt/miniforge/envs/helixfold/bin/hmmsearch" \
-        --hmmbuild_binary_path "/opt/miniforge/envs/helixfold/bin/hmmbuild" \
+        --jackhmmer_binary_path "\$ENV_BIN/jackhmmer" \
+        --hhblits_binary_path "\$ENV_BIN/hhblits" \
+        --hhsearch_binary_path "\$ENV_BIN/hhsearch" \
+        --kalign_binary_path "\$ENV_BIN/kalign" \
+        --hmmsearch_binary_path "\$ENV_BIN/hmmsearch" \
+        --hmmbuild_binary_path "\$ENV_BIN/hmmbuild" \
         --preset='reduced_dbs' \
         --bfd_database_path="./bfd/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt" \
         --small_bfd_database_path="./small_bfd/bfd-first_non_consensus_sequences.fasta" \