Merge pull request #11 from colbyford/main

Update Dockerfile to run the bio-diffusion model(s)

Author: amorehead

Dockerfile

@@ -1,18 +1,41 @@
-FROM nvcr.io/nvidia/pytorch:21.06-py3
+# FROM nvcr.io/nvidia/pytorch:21.06-py3
+FROM pytorch/pytorch:1.12.1-cuda11.3-cudnn8-runtime
 
-####################################################################
+LABEL authors="Colby T. Ford <[email protected]>"
 
-# install system requirements
-RUN apt update && apt install -y vim libgl-dev libgl1
-RUN apt-get install -y --reinstall ca-certificates  # note: for git
-RUN apt install -y git
+## Install system requirements
+RUN apt update && \
+    apt-get install -y --reinstall \
+        ca-certificates && \
+    apt install -y \
+        git \
+        vim \
+        wget \
+        libxml2 \
+        libgl-dev \
+        libgl1
 
-# set environment variables
+## Set environment variables
 ENV MPLCONFIGDIR /data/MPL_Config
 ENV TORCH_HOME /data/Torch_Home
 ENV TORCH_EXTENSIONS_DIR /data/Torch_Extensions
+ENV DEBIAN_FRONTEND noninteractive
 
-####################################################################
+## Make directories
+RUN mkdir -p /software/
+WORKDIR /software/
+
+## Install dependencies from Conda/Mamba
+COPY environment.yaml /software/environment.yaml
+RUN conda env create -f environment.yaml
+RUN conda init bash && \
+    echo "conda activate bio-diffusion" >> ~/.bashrc
+SHELL ["/bin/bash", "--login", "-c"]
+
+## Install bio-diffusion
+RUN git clone https://github.com/BioinfoMachineLearning/bio-diffusion && \
+    cd bio-diffusion && \
+    pip install -e .
+WORKDIR /software/bio-diffusion/
 
-# set the entrypoint
 CMD /bin/bash

README.md

@@ -298,6 +298,20 @@ python3 src/mol_gen_eval_optimization_qm9.py datamodule=edm_qm9 model=qm9_mol_ge
 
 Please refer to the following dedicated GitHub repository for further details: https://github.com/BioinfoMachineLearning/GCDM-SBDD.
 
+## Docker
+
+To run this project in a Docker container, you can use the following commands:
+
+```bash
+## Build the image
+docker build -t bio-diffusion .
+
+## Run the container (with GPUs and mounting the current directory)
+docker run -it --gpus all -v .:/mnt --name bio-diffusion bio-diffusion
+```
+__Note:__ You will still need to download the checkpoints and data as described in the installation guide. Then, update the Python commands to point to the desired local location of your files (e.g., `/mnt/checkpoints` and `/mnt/outputs`) once in the container.
+
+
 ## Acknowledgements
 
 Bio-Diffusion builds upon the source code and data from the following projects:

environment.yaml

@@ -70,7 +70,7 @@ dependencies:
   - glm=0.9.9.4=h924138e_2
   - gmp=6.2.1=h58526e2_0
   - gnutls=3.6.13=h85f3911_1
-  - graphite2=1.3.13=h58526e2_1001
+  # - graphite2=1.3.13=h58526e2_1001
   - gst-plugins-base=1.21.3=h4243ec0_1
   - gstreamer=1.21.3=h25f0c4b_1
   - gstreamer-orc=0.4.33=h166bdaf_0
@@ -274,10 +274,10 @@ dependencies:
   - xorg-renderproto=0.11.1=h7f98852_1002
   - xorg-xextproto=7.3.0=h7f98852_1002
   - xorg-xproto=7.0.31=h7f98852_1007
-  - xtb=6.5.1=h97a9613_0
+  # - xtb=6.5.1=h97a9613_0
   - xz=5.2.6=h5eee18b_0
-  - yaml=0.2.5=h7f98852_2
-  - yaml-cpp=0.7.0=h27087fc_2
+  # - yaml=0.2.5=h7f98852_2
+  # - yaml-cpp=0.7.0=h27087fc_2
   - zlib=1.2.13=h166bdaf_4
   - zstandard=0.19.0=py39h29414ee_1
   - zstd=1.5.2=h8a70e8d_1
@@ -337,7 +337,7 @@ dependencies:
       - identify==2.5.6
       - imageio==2.22.2
       - importlib-metadata==5.0.0
-      - iniconfig==1.1.1
+      # - iniconfig==1.1.1
       - ipython==8.8.0
       - jedi==0.18.2
       - jupyter-client==7.4.8
@@ -434,4 +434,4 @@ dependencies:
       - werkzeug==2.2.2
       - wrapt==1.14.1
       - yarl==1.8.1
-      - zipp==3.9.0
+      - zipp==3.9.0