Release for AlphaFold2 Multimer Parallel

.gitignore

@@ -9,3 +9,5 @@ tmp/
 .nextflow*
 stack-outputs.json
 test_data
+linter-rules-for-nextflow
+build/cloudformation/packaged.yaml

assets/containers/alphafold-data/Dockerfile

@@ -1,7 +1,7 @@
 # Copyright 2023 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-FROM public.ecr.aws/amazonlinux/amazonlinux:latest as build
+FROM public.ecr.aws/amazonlinux/amazonlinux:latest AS build
 
 RUN yum upgrade -y \
   && yum install -y \
@@ -19,26 +19,52 @@ RUN yum upgrade -y \
   wget \
   zstd \
   && yum clean all \
-  && rm -rf /var/cache/yum \
-  && pushd /tmp \
-  && git clone https://github.com/soedinglab/hh-suite.git \
-  && cd hh-suite && mkdir build && cd build \
-  && cmake -DCMAKE_INSTALL_PREFIX=/opt/hhsuite .. \
-  && make -j 4 && make install \
-  && popd \
-  && pushd /tmp \
-  && wget http://msa.sbc.su.se/downloads/kalign/current.tar.gz --no-check-certificate \
-  && mkdir -p /tmp/kalign2/build \
-  && tar -xvzf current.tar.gz -C /tmp/kalign2 \
-  && pushd /tmp/kalign2 \
-  && ./configure \
-  && make && make install \
-  && popd \
-  && rm -rf /tmp/kalign2 \
-  && popd \
-  && mkdir -p /tmp/hmmer && wget -O hmmer.tar.gz  http://eddylab.org/software/hmmer/hmmer-3.4.tar.gz \
-  && tar xvzf hmmer.tar.gz -C /tmp/hmmer \
-  && pushd /tmp/hmmer/hmmer-* \
+  && rm -rf /var/cache/yum
+
+# ADD hh-suite.tar.gz /tmp/hh-suite
+# RUN pushd /tmp/hh-suite \
+#   && cmake -DCMAKE_INSTALL_PREFIX=/opt/hhsuite . \
+#   && make && make install \
+#   && popd
+RUN pushd /tmp && \
+git clone https://github.com/soedinglab/hh-suite.git && \
+cd hh-suite && mkdir build && cd build && \
+cmake -DCMAKE_INSTALL_PREFIX=/opt/hhsuite .. && \
+make -j 4 && make install && \
+popd
+
+# ADD kalign.tar.gz /tmp/kalign-3.4.3
+# RUN pushd /tmp/kalign2 \
+#   && ./configure \
+#   && make && make install \
+#   && popd
+# RUN pushd /tmp && \
+# wget https://github.com/TimoLassmann/kalign/archive/refs/tags/v3.4.0.tar.gz && \
+# tar -xvzf v3.4.0.tar.gz && \
+# cd kalign-3.4.0 && \
+# mkdir build && \
+# cd build && \
+# cmake3 .. && \
+# make -j 4 && make test && \
+# make install && \
+# popd
+
+# Compile kalign2 from source
+RUN pushd /tmp && \
+wget http://msa.sbc.su.se/downloads/kalign/current.tar.gz --no-check-certificate \
+&& mkdir -p /tmp/kalign2/build \
+&& tar -xvzf current.tar.gz -C /tmp/kalign2 \
+&& pushd /tmp/kalign2 \
+&& ./configure \
+&& make && make install \
+&& popd \
+&& rm -rf /tmp/kalign2 && \
+popd
+
+# ADD hmmer.tar.gz /tmp/hmmer
+RUN mkdir -p /tmp/hmmer && wget -O hmmer.tar.gz  http://eddylab.org/software/hmmer/hmmer-3.4.tar.gz \
+&& tar xvzf hmmer.tar.gz -C /tmp/hmmer
+RUN pushd /tmp/hmmer/hmmer-* \
   && ./configure \
   && make && make install \
   && popd

assets/containers/alphafold-data/update_locations.py

@@ -8,22 +8,35 @@
 
 from alphafold.data.pipeline_multimer import int_id_to_str_id
 
-
+# Example file_lists:
+# 
+# [4ZQK.1_uniref90_hits.sto 4ZQK.2_uniref90_hits.sto]
+# [4ZQK.2_mgnify_hits.sto 4ZQK.1_mgnify_hits.sto]
+# [4ZQK.1_uniprot_hits.sto 4ZQK.2_uniprot_hits.sto]
+# [4ZQK.1_bfd_hits.a3m 4ZQK.2_bfd_hits.a3m]
+# [4ZQK.1_pdb_hits.sto 4ZQK.2_pdb_hits.sto]
+
+# target_dir = msa
 def update_locations(target_dir, file_list):
     for filename in file_list:
-        index, _null, outfile = filename.partition("_")
-        index = index.split(".")[1]
 
-        chain = int_id_to_str_id(int(index))
-        print(f'file: {filename} index: {index} chain: {chain} outfile:{outfile}')
-        chain = os.path.join(target_dir, chain)
-        path = pathlib.Path(chain)
+        # Indexed format: 5nl6.1_uniref90_hits.sto
+        # record_id = 5nl6.1
+        # outfile = uniref90_hits.sto
+        record_id, _null, outfile = filename.partition("_")
+        record_inx = int(record_id[-1])
+
+        chain = int_id_to_str_id(record_inx)
 
+        chain_dir_path = pathlib.Path(os.path.join(target_dir, chain))
 
-        if not path.exists():
-            path.mkdir(parents=True)
-        shutil.copy(filename, os.path.join(chain, outfile), follow_symlinks=True)
+        if not chain_dir_path.exists():
+            chain_dir_path.mkdir(parents=True)
 
+        target = os.path.join(chain_dir_path, outfile)
+        print(f"COPY {filename} -> {target}")
+        shutil.copy(filename, target, follow_symlinks=True)
+
 
 if __name__ == "__main__":
     update_locations(sys.argv[1], sys.argv[2:])

assets/containers/alphafold-predict/Dockerfile

@@ -3,10 +3,9 @@
 # SPDX-License-Identifier: Apache-2.0
 
 # ARG CUDA=11.1.1
-ARG CUDA=12.2.2
-# ARG ALPHAFOLD2_VERSION=v2.3.2
-ARG ALPHAFOLD2_VERSION=f251de6613cb478207c732bf9627b1e853c99c2f
-FROM nvcr.io/nvidia/cuda:${CUDA}-cudnn8-runtime-ubuntu20.04
+ARG CUDA=11.6.0
+ARG ALPHAFOLD2_VERSION=v2.3.2
+FROM nvcr.io/nvidia/cuda:${CUDA}-cudnn8-runtime-ubuntu18.04
 # FROM directive resets ARGS, so we specify again (the value is retained if
 # previously set).
 ARG CUDA
@@ -15,19 +14,18 @@ ARG ALPHAFOLD2_VERSION
 # Use bash to support string substitution.
 SHELL ["/bin/bash", "-o", "pipefail", "-c"]
 
-RUN apt-get update \
-  && DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y \
-  build-essential \
-  cmake \
-  cuda-command-line-tools-$(cut -f1,2 -d- <<< ${CUDA//./-}) \
-  git \
-  hmmer \
-  kalign \
-  tzdata \
-  wget \
-  awscli \
-  jq \
-  unzip \
+RUN apt-get update \ 
+    && DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y \
+    build-essential \
+    cmake \
+    cuda-command-line-tools-$(cut -f1,2 -d- <<< ${CUDA//./-}) \
+    git \
+    hmmer \
+    kalign \
+    tzdata \
+    wget \
+    awscli \
+    jq \
   && rm -rf /var/lib/apt/lists/* \
   && apt-get autoremove -y \
   && apt-get clean
@@ -36,7 +34,7 @@ RUN apt-get update \
 RUN git clone --branch v3.3.0 https://github.com/soedinglab/hh-suite.git /tmp/hh-suite \
   && mkdir /tmp/hh-suite/build \
   && pushd /tmp/hh-suite/build \
-  && cmake -DCMAKE_INSTALL_PREFIX=/opt/hhsuite .. \
+  && cmake -DHAVE_AVX2=1 -DCMAKE_INSTALL_PREFIX=/opt/hhsuite .. \
   && make -j 4 && make install \
   && ln -s /opt/hhsuite/bin/* /usr/bin \
   && popd \
@@ -50,18 +48,18 @@ RUN wget -q -P /tmp \
 
 # Install conda packages.
 ENV PATH="/opt/conda/bin:$PATH"
-ENV LD_LIBRARY_PATH="/opt/conda/lib:$LD_LIBRARY_PATH"
-RUN conda install -qy conda==24.5.0 pip python=3.11 \
-    && conda install -y -c nvidia/label/cuda-${CUDA} cuda \
-    && conda install -y -c conda-forge openmm=8.0.0 pdbfixer \
-    && conda clean --all --force-pkgs-dirs --yes
+# RUN conda install -qy conda==4.13.0 
+#   && conda install -y -c conda-forge
+RUN conda install -y -c conda-forge \
+    openmm=7.5.1 \    
+    cudatoolkit=${CUDA_VERSION} \
+    pdbfixer=1.7 \
+    pip \
+    python=3.9.16 \
+  && conda clean --all --force-pkgs-dirs --yes
 
-# Install AlphaFold
-RUN wget -q -P /tmp \
-    https://github.com/google-deepmind/alphafold/archive/${ALPHAFOLD2_VERSION}.zip \
-    && mkdir -p /app/alphafold \
-    && unzip /tmp/f251de6613cb478207c732bf9627b1e853c99c2f.zip -d /tmp \
-    && mv /tmp/alphafold-f251de6613cb478207c732bf9627b1e853c99c2f/* /app/alphafold
+
+RUN git clone --branch ${ALPHAFOLD2_VERSION} --depth 1 https://github.com/deepmind/alphafold.git /app/alphafold
 
 RUN wget -q -P /app/alphafold/alphafold/common/ \
     https://git.scicore.unibas.ch/schwede/openstructure/-/raw/7102c63615b64735c4941278d92b554ec94415f8/modules/mol/alg/src/stereo_chemical_props.txt
@@ -70,20 +68,33 @@ RUN wget -q -P /app/alphafold/alphafold/common/ \
 RUN pip3 install --upgrade pip --no-cache-dir \
     && pip3 install -r /app/alphafold/requirements.txt --no-cache-dir \
     && pip3 install --upgrade --no-cache-dir \
-      jax==0.4.26 \
-      jaxlib==0.4.26+cuda12.cudnn89 \
+      jax==0.3.25 \
+      jaxlib==0.3.25+cuda11.cudnn805 \
       -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html
 
 RUN pip3 install --upgrade --no-cache-dir \
-      matplotlib==3.9.2
+      matplotlib==3.6.3 \
+      numpy==1.24.3
+
+# Apply OpenMM patch.
+WORKDIR /opt/conda/lib/python3.9/site-packages
+RUN patch -p0 < /app/alphafold/docker/openmm.patch
 
 # Add SETUID bit to the ldconfig binary so that non-root users can run it.
 RUN chmod u+s /sbin/ldconfig.real
 
-# Currently needed to avoid undefined_symbol error.
-RUN ln -sf /usr/lib/x86_64-linux-gnu/libffi.so.7 /opt/conda/lib/libffi.so.7
-
+# We need to run `ldconfig` first to ensure GPUs are visible, due to some quirk
+# with Debian. See https://github.com/NVIDIA/nvidia-docker/issues/1399 for
+# details.
+# ENTRYPOINT does not support easily running multiple commands, so instead we
+# write a shell script to wrap them up.
 WORKDIR /app/alphafold
 COPY predict.py /app/alphafold/
+# COPY run.sh /app/alphafold/run.sh
+# RUN echo $'#!/bin/bash\n\
+# ldconfig\n\
+# python /app/alphafold/run_alphafold.py "$@"' > /app/run_alphafold.sh \
+#   && chmod +x /app/run_alphafold.sh /app/alphafold/run.sh
 
-ENTRYPOINT []
+# ENTRYPOINT ["bash", "/app/alphafold/run.sh"]
+ENTRYPOINT ["bash"]

assets/containers/protein-utils/Dockerfile

@@ -1,27 +1,25 @@
-FROM public.ecr.aws/amazonlinux/amazonlinux:2023 as build
+FROM public.ecr.aws/amazonlinux/amazonlinux:2 as build
 
-WORKDIR /home
-
-COPY code /home/putils
-COPY requirements.txt /home
+COPY code /tmp/putils
 
 # Install python and other dependencies
-RUN yum update \
+RUN amazon-linux-extras install python3.8 \
   && yum upgrade -y \
   && yum install -y \
-  python3.11 \
   unzip-6.0 \
-  wget-1.21.3 \
-  && python3.11 -m venv /opt/venv \
+  wget-1.14 \
+  && python3.8 -m venv /opt/venv \
   && source /opt/venv/bin/activate \
-  && pip install -U pip \
-  && pip install -q --no-cache-dir -r /home/requirements.txt \
-  && pip install -q --no-cache-dir /home/putils \
-  && yum autoremove -y \
+  && pip install -q --no-cache-dir \
+  pandas==2.0.0 \
+  numpy==1.24.2 \
+  biopython==1.81 \
+  /tmp/putils \
   && yum clean all \
-  && rm -rf /var/cache/yum
+  && rm -rf /var/cache/yum \
+  && rm -rf /tmp/putils
 
 ENV VIRTUAL_ENV="/opt/venv"
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 
-ENTRYPOINT []
+WORKDIR /home

assets/containers/protein-utils/code/resources.json

@@ -0,0 +1 @@
+{"id": "3D06", "seq_length": 200, "seq_count": 1, "template_search_resources": {"vcpu": 2, "memory": "4 GiB", "gpu": "False"}, "feature_gen_resources": {"vcpu": 2, "memory": "4 GiB", "gpu": "False"}, "predict_resources": {"vcpu": 8, "memory": "32 GiB", "gpu": "True"}, "uniref90_msa_resources": {"vcpu": 8, "memory": "16 GiB", "gpu": "False"}, "mgnify_msa_resources": {"vcpu": 8, "memory": "16 GiB", "gpu": "False"}, "bfd_msa_resources": {"vcpu": 16, "memory": "32 GiB", "gpu": "False"}}

assets/containers/protein-utils/code/seq_info.json

@@ -0,0 +1 @@
+{"id": "2022", "seq_length": "100", "seq_count": "1"}

assets/containers/protein-utils/code/setup.py

@@ -1,5 +1,5 @@
 # Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
-# SPDX-License-Identifier: MIT-0
+# SPDX-License-Identifier: Apache-2.0
 
 from setuptools import setup, find_packages