Merge branch 'feature/merge-v2.2.0' of HPC-OpenFold/openfold-mirror into fugaku_v2

Author: hakama2

.github/dependabot.yml

@@ -0,0 +1,7 @@
+version: 2
+updates:
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"

.github/workflows/docker-image.yml

@@ -10,6 +10,8 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
+    - name: Cleanup  # https://github.com/actions/virtual-environments/issues/2840
+      run: sudo rm -rf /usr/share/dotnet && sudo rm -rf /opt/ghc && sudo rm -rf "/usr/local/share/boost" && sudo rm -rf "$AGENT_TOOLSDIRECTORY"
     - name: Build the Docker image
-      run: docker build . --file Dockerfile --tag openfold:$(date +%s)
+      run: docker build . --file Dockerfile --tag openfold:$(date +%s)

.github/workflows/undefined_names.yml

@@ -4,8 +4,8 @@ jobs:
   undefined_names:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-python@v2
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
       - run: pip install --upgrade pip
       - run: pip install flake8
       - run: flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics

.gitignore

@@ -5,6 +5,13 @@ dist/
 preproc/log/
 train/log/
 inference/log/
-openfold/resources/stereo_chemical_props.txt
 *.out
 *.stats
+.vscode/
+.idea/
+
+# files from script downloads
+data
+openfold/resources/
+tests/test_data/
+cutlass/

.readthedocs.yaml

@@ -0,0 +1,14 @@
+version: 2
+
+# Set the OS, Python version and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "mambaforge-4.10" 
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+  configuration: docs/source/conf.py
+
+conda:
+  environment: docs/environment.yml

CITATION.cff

@@ -1,22 +1,91 @@
 cff-version: 1.2.0
-message: "For now, cite OpenFold with its DOI."
-authors:
-- family-names: "Ahdritz"
-  given-names: "Gustaf"
-  orcid: https://orcid.org/0000-0001-8283-5324
-- family-names: "Bouatta"
-  given-names: "Nazim"
-  orcid: https://orcid.org/0000-0002-6524-874X
-- family-names: "Kadyan"
-  given-names: "Sachin"
-- family-names: "Xia"
-  given-names: "Qinghui"
-- family-names: "Gerecke"
-  given-names: "William"
-- family-names: "AlQuraishi"
-  given-names: "Mohammed"
-  orcid: https://orcid.org/0000-0001-6817-1322
-title: "OpenFold"
-doi: 10.5281/zenodo.5709539
+preferred-citation:
+    authors:
+    - family-names: "Ahdritz"
+      given-names: "Gustaf"
+      orcid: https://orcid.org/0000-0001-8283-5324
+    - family-names: "Bouatta"
+      given-names: "Nazim"
+      orcid: https://orcid.org/0000-0002-6524-874X
+    - family-names: "Kadyan"
+      given-names: "Sachin"
+      orcid: https://orcid.org/0000-0002-6079-7627
+    - family-names: "Xia"
+      given-names: "Qinghui"
+    - family-names: "Gerecke"
+      given-names: "William"
+      orcid: https://orcid.org/0000-0002-9777-6192
+    - family-names: "O'Donnell"
+      given-names: "Timothy J"
+      orcid: https://orcid.org/0000-0002-9949-069X
+    - family-names: "Berenberg"
+      given-names: "Daniel"
+      orcid: https://orcid.org/0000-0003-4631-0947
+    - family-names: "Fisk"
+      given-names: "Ian"
+    - family-names: "Zanichelli"
+      given-names: "Niccolò"
+      orcid: https://orcid.org/0000-0002-3093-3587
+    - family-names: "Zhang"
+      given-names: "Bo"
+      orcid: https://orcid.org/0000-0002-9714-2827
+    - family-names: "Nowaczynski"
+      given-names: "Arkadiusz"
+      orcid: https://orcid.org/0000-0002-3351-9584
+    - family-names: "Wang"
+      given-names: "Bei"
+      orcid: https://orcid.org/0000-0003-4942-9652
+    - family-names: "Stepniewska-Dziubinska"
+      given-names: "Marta M"
+      orcid: https://orcid.org/0000-0003-4942-9652
+    - family-names: "Zhang"
+      given-names: "Shang"
+      orcid: https://orcid.org/0000-0003-0759-2080
+    - family-names: "Ojewole"
+      given-names: "Adegoke"
+      orcid: https://orcid.org/0000-0003-2661-4388
+    - family-names: "Guney"
+      given-names: "Murat Efe"
+    - family-names: "Biderman"
+      given-names: "Stella"
+      orcid: https://orcid.org/0000-0001-8228-1042
+    - family-names: "Watkins"
+      given-names: "Andrew M"
+      orcid: https://orcid.org/0000-0003-1617-1720
+    - family-names: "Ra"
+      given-names: "Stephen"
+      orcid: https://orcid.org/0000-0002-2820-0050
+    - family-names: "Lorenzo"
+      given-names: "Pablo Ribalta"
+      orcid: https://orcid.org/0000-0002-3657-8053
+    - family-names: "Nivon"
+      given-names: "Lucas"
+    - family-names: "Weitzner"
+      given-names: "Brian"
+      orcid: https://orcid.org/0000-0002-1909-0961
+    - family-names: "Ban"
+      given-names: "Yih-En"
+      orcid: https://orcid.org/0000-0003-3698-3574
+    - family-names: "Ban"
+      given-names: "Yih-En Andrew"
+      orcid: https://orcid.org/0000-0003-3698-3574
+    - family-names: "Sorger"
+      given-names: "Peter K"
+      orcid: https://orcid.org/0000-0002-3364-1838
+    - family-names: "Mostaque"
+      given-names: "Emad"
+    - family-names: "Zhang"
+      given-names: "Zhao"
+      orcid: https://orcid.org/0000-0001-5921-0035
+    - family-names: "Bonneau"
+      given-names: "Richard"
+      orcid: https://orcid.org/0000-0003-4354-7906
+    - family-names: "AlQuraishi"
+      given-names: "Mohammed"
+      orcid: https://orcid.org/0000-0001-6817-1322
+    title: "OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization"
+    type: article
+    doi: 10.1101/2022.11.20.517210
+doi: 10.1101/2022.11.20.517210
 date-released: 2021-11-12
-url: "https://github.com/aqlaboratory/openfold"
+url: "https://doi.org/10.1101/2022.11.20.517210"

Dockerfile

@@ -1,29 +1,38 @@
-FROM nvidia/cuda:10.2-cudnn8-runtime-ubuntu18.04
+FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04
+
+# metainformation
+LABEL org.opencontainers.image.version = "2.0.0"
+LABEL org.opencontainers.image.authors = "OpenFold Team"
+LABEL org.opencontainers.image.source = "https://github.com/aqlaboratory/openfold"
+LABEL org.opencontainers.image.licenses = "Apache License 2.0"
+LABEL org.opencontainers.image.base.name="docker.io/nvidia/cuda:12.4.1-devel-ubuntu22.04"
+
+RUN apt-get update && apt-get install -y wget
 
 RUN apt-key del 7fa2af80
-RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/7fa2af80.pub
-RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub
+RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb
+RUN dpkg -i cuda-keyring_1.0-1_all.deb
+
+RUN apt-get install -y libxml2 cuda-minimal-build-12-1 libcusparse-dev-12-1 libcublas-dev-12-1 libcusolver-dev-12-1 git
 
-RUN apt-get update && apt-get install -y wget cuda-minimal-build-10-2 git
 RUN wget -P /tmp \
-    "https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh" \
-    && bash /tmp/Miniconda3-latest-Linux-x86_64.sh -b -p /opt/conda \
-    && rm /tmp/Miniconda3-latest-Linux-x86_64.sh
+    "https://github.com/conda-forge/miniforge/releases/download/23.3.1-1/Miniforge3-Linux-x86_64.sh" \
+    && bash /tmp/Miniforge3-Linux-x86_64.sh -b -p /opt/conda \
+    && rm /tmp/Miniforge3-Linux-x86_64.sh
 ENV PATH /opt/conda/bin:$PATH
 
 COPY environment.yml /opt/openfold/environment.yml
 
 # installing into the base environment since the docker container wont do anything other than run openfold
-RUN conda env update -n base --file /opt/openfold/environment.yml && conda clean --all
+RUN mamba env update -n base --file /opt/openfold/environment.yml && mamba clean --all
+RUN export LD_LIBRARY_PATH=${CONDA_PREFIX}/lib:${LD_LIBRARY_PATH}
 
 COPY openfold /opt/openfold/openfold
 COPY scripts /opt/openfold/scripts
 COPY run_pretrained_openfold.py /opt/openfold/run_pretrained_openfold.py
 COPY train_openfold.py /opt/openfold/train_openfold.py
 COPY setup.py /opt/openfold/setup.py
-COPY lib/openmm.patch /opt/openfold/lib/openmm.patch
 RUN wget -q -P /opt/openfold/openfold/resources \
     https://git.scicore.unibas.ch/schwede/openstructure/-/raw/7102c63615b64735c4941278d92b554ec94415f8/modules/mol/alg/src/stereo_chemical_props.txt
-RUN patch -p0 -d /opt/conda/lib/python3.7/site-packages/ < /opt/openfold/lib/openmm.patch
 WORKDIR /opt/openfold
 RUN python3 setup.py install

LICENSE

@@ -187,7 +187,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright [yyyy] [name of copyright owner]
+   Copyright 2024 AlQuraishi Laboratory 
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

README.md

@@ -4,8 +4,8 @@
 
 「富岳」実装版OpenFoldのソースコードをクローンする
 ```shell
-git clone https://github.com/RIKEN-RCCS/OpenFold-for-Fugaku.git
-cd OpenFold-for-Fugaku
+git clone https://github.com/RIKEN-RCCS/openfold.git
+cd openfold
 ```
 
 `openfold/resources/`ディレクトリに`stereo_chemical_props.txt`をダウンロードする
@@ -67,3 +67,4 @@ However, DeepMind's pretrained parameters fall under the CC BY 4.0 license, a co
 - Port the memory-efficient attention module to CPUs
 - Improve processing efficiency of batch matrix multiplications (BMMs) by making the input tensors to BMMs contiguous
 - Speed up reading of mmcif data by pickling and lz4 compression beforehand
+