Update setup.py -> pyinstaller files

- Included missing 'llm/prosst_structure/static/*' static model binaries
- Added Dockerfile

Author: niklases

.vscode/launch.json

@@ -231,6 +231,26 @@
             ]
         },
 
+        { // Test on test set: Hybrid DCA-LLM ProSST
+            "name": "Python: PyPEF hybrid/only-TS-zero-shot GREMLIN-DCA-ProSST avGFP",
+            "type": "debugpy",
+            "request": "launch",
+            "env": {"PYTHONPATH": "${workspaceFolder}"},
+            "program": "${workspaceFolder}/pypef/main.py",
+            "console": "integratedTerminal",
+            "justMyCode": true,
+            "cwd": "${workspaceFolder}/datasets/AVGFP/",
+            "args": [
+                "hybrid", 
+                //"-m", "GREMLIN",   // optional, not required  
+                "--ts", "TS.fasl", 
+                "--params", "GREMLIN",
+                "--llm", "prosst",
+                "--wt", "P42212_F64L.fasta",
+                "--pdb", "GFP_AEQVI.pdb"
+            ]
+        },
+
         {
             "name": "Python: PyPEF hybrid/only-PS-zero-shot GREMLIN-DCA avGFP",
             "type": "debugpy",

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+RUN mkdir -p pypef
+
+COPY requirements.txt run.py /app/
+COPY pypef/ /app/pypef/
+
+RUN pip install --upgrade pip
+RUN pip install --no-cache-dir -r requirements.txt
+RUN ["python", "-c", "import torch;print(torch.__version__)"]
+
+EXPOSE 5000
+
+# Not defining entrypoint herein for eased chaining of multiple commands 
+# with /bin/bash -c "command1 && command2..."
+#ENTRYPOINT ["python", "/app/run.py"]

README.md

@@ -67,6 +67,22 @@ pypef --help
 The detailed routine for setting up a new virtual environment with Anaconda, installing the necessary Python packages for that environment, and running the Jupyter notebook tutorial can be found below in the Tutorial section.
 A quick file setup and run test can be performed running files in [scripts/Setup](scripts/Setup) containing a Batch script for Windows and a Bash script for Linux (the latter requires conda, i.e. Miniconda3 or Anaconda3, already being installed).
 
+### Setup and Run Docker Image 
+
+Build the image using the stored [Dockerfile](./Dockerfile)
+```bash
+docker build -t pypef . # --progress=plain --no-cache
+```
+
+A chained container command using the built Docker image can be run with e.g.:
+```
+docker run --gpus=all -v ./datasets/:/datasets --workdir /datasets/AVGFP pypef /bin/bash -c \
+    "python /app/run.py mklsts --wt P42212_F64L.fasta --input avGFP.csv --ls_proportion 0.01 &&  \
+     python /app/run.py hybrid --ls LS.fasl --ts TS.fasl --params GREMLIN --llm prosst --wt P42212_F64L.fasta --pdb GFP_AEQVI.pdb"
+
+```
+
+
 <a name="gui-installation"></a>
 ### GUI Installation
 

build_with_pyinstaller.bat

@@ -1,21 +1,24 @@
 REM Up to now pastes DLLs from local Python environment bin's to _internal...
-REM alternative?: set PATH=%PATH%;%USERPROFILE%\miniconda3\envs\py312\Library\bin\;
+REM alternative?: set PATH=%PATH%;%USERPROFILE%\miniconda3\envs\pypef\Library\bin\;
 pip install -r requirements.txt
 pip install -U pyinstaller pyside6
 pip install -e .
+set PATH=%PATH%;%USERPROFILE%\miniconda3\Scripts
 pyinstaller^
   --console^
   --noconfirm^
+  --collect-data pypef^
+  --collect-all pypef^
   --collect-data torch^
   --collect-data biotite^
   --collect-all biotite^
   --collect-data torch_geometric^
   --collect-all torch_geometric^
   --hidden-import torch_geometric^
-  --add-binary=%USERPROFILE%\miniconda3\envs\py312\Library\bin\onedal_thread.3.dll:.^
-  --add-binary=%USERPROFILE%\miniconda3\envs\py312\Library\bin\tbbbind.dll:.^
-  --add-binary=%USERPROFILE%\miniconda3\envs\py312\Library\bin\tbbbind_2_0.dll:.^
-  --add-binary=%USERPROFILE%\miniconda3\envs\py312\Library\bin\tbbbind_2_5.dll:.^
-  --add-binary=%USERPROFILE%\miniconda3\envs\py312\Library\bin\tbbmalloc.dll:.^
-  --add-binary=%USERPROFILE%\miniconda3\envs\py312\Library\bin\tbbmalloc_proxy.dll:.^
+  --add-binary=%USERPROFILE%\miniconda3\envs\pypef\Library\bin\onedal_thread.3.dll:.^
+  --add-binary=%USERPROFILE%\miniconda3\envs\pypef\Library\bin\tbbbind.dll:.^
+  --add-binary=%USERPROFILE%\miniconda3\envs\pypef\Library\bin\tbbbind_2_0.dll:.^
+  --add-binary=%USERPROFILE%\miniconda3\envs\pypef\Library\bin\tbbbind_2_5.dll:.^
+  --add-binary=%USERPROFILE%\miniconda3\envs\pypef\Library\bin\tbbmalloc.dll:.^
+  --add-binary=%USERPROFILE%\miniconda3\envs\pypef\Library\bin\tbbmalloc_proxy.dll:.^
   gui\PyPEFGUIQtWindow.py

build_with_pyinstaller.sh

@@ -5,6 +5,8 @@ pip install -e .
 pyinstaller \
   --console \
   --noconfirm \
+  --collect-data pypef \
+  --collect-all pypef \
   --collect-data torch \
   --collect-data biotite \
   --collect-all biotite \

pypef/__init__.py

@@ -12,4 +12,4 @@
 # Journal of Chemical Information and Modeling, 2021, 61, 3463-3476
 # https://doi.org/10.1021/acs.jcim.1c00099
 
-__version__ = '0.4.1'
+__version__ = '0.4.2'

setup.py

@@ -39,7 +39,11 @@
     url='https://github.com/niklases/PyPEF',
     py_modules=['pypef'],
     packages=find_packages(include=['pypef', 'pypef.*']),
-    package_data={'pypef': ['ml/AAindex/*', 'ml/AAindex/Refined_cluster_indices_r0.93_r0.97/*']},
+    package_data={'pypef': [
+        'ml/AAindex/*', 
+        'ml/AAindex/Refined_cluster_indices_r0.93_r0.97/*',
+        'llm/prosst_structure/static/*'
+        ]},
     include_package_data=True,
     install_requires=[cleaned_requirements],
     python_requires='>= 3.10, < 3.13',