Merge pull request #9 from MolecularAI/3.1.0_docs

Update docs for 3.1.0
MolecularAI · Jul 2, 2024 · 4298d58 · 4298d58
2 parents 330f907 + c059a9e
commit 4298d58
Show file tree

Hide file tree

Showing 84 changed files with 135 additions and 11,591 deletions.
diff --git a/docs/sphinx-builddir/doctrees/README.doctree b/docs/sphinx-builddir/doctrees/README.doctree
diff --git a/docs/sphinx-builddir/doctrees/algorithms.doctree b/docs/sphinx-builddir/doctrees/algorithms.doctree
diff --git a/docs/sphinx-builddir/doctrees/deduplicator.doctree b/docs/sphinx-builddir/doctrees/deduplicator.doctree
diff --git a/docs/sphinx-builddir/doctrees/descriptors.doctree b/docs/sphinx-builddir/doctrees/descriptors.doctree
diff --git a/docs/sphinx-builddir/doctrees/environment.pickle b/docs/sphinx-builddir/doctrees/environment.pickle
diff --git a/docs/sphinx-builddir/doctrees/index.doctree b/docs/sphinx-builddir/doctrees/index.doctree
diff --git a/docs/sphinx-builddir/doctrees/modules.doctree b/docs/sphinx-builddir/doctrees/modules.doctree
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks/QSARtuna_Tutorial.ipynb b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks/QSARtuna_Tutorial.ipynb
@@ -78,7 +78,7 @@
    "source": [
     "To use QSARtuna from Jupyter Notebook, install it with:\n",
     "```\n",
-    "python -m pip install http://pages.scp.astrazeneca.net/mai/qsartuna/releases/QSARtuna_latest.tar.gz\n",
+    "python -m pip install https://github.com/MolecularAI/QSARtuna/releases/download/3.1.0/qsartuna-3.1.0.tar.gz\n",
     "```"
    ]
   },

diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_101_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_101_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_110_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_110_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_119_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_119_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_123_1.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_123_1.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_125_1.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_125_1.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_133_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_133_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_135_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_135_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_137_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_137_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_148_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_148_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_153_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_153_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_160_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_160_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_162_2.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_162_2.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_170_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_170_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_172_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_172_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_174_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_174_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_176_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_176_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_177_1.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_177_1.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_200_1.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_200_1.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_208_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_208_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_21_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_21_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_237_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_237_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_23_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_23_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_244_1.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_244_1.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_35_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_35_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_56_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_56_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_67_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_67_0.png
diff --git a/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_71_0.png b/docs/sphinx-builddir/doctrees/nbsphinx/notebooks_QPTUNA_Tutorial_71_0.png
diff --git a/docs/sphinx-builddir/doctrees/notebooks/QSARtuna_Tutorial.doctree b/docs/sphinx-builddir/doctrees/notebooks/QSARtuna_Tutorial.doctree
diff --git a/docs/sphinx-builddir/doctrees/notebooks/preprocess_data.doctree b/docs/sphinx-builddir/doctrees/notebooks/preprocess_data.doctree
diff --git a/docs/sphinx-builddir/doctrees/optunaz.config.doctree b/docs/sphinx-builddir/doctrees/optunaz.config.doctree
diff --git a/docs/sphinx-builddir/doctrees/optunaz.doctree b/docs/sphinx-builddir/doctrees/optunaz.doctree
diff --git a/docs/sphinx-builddir/doctrees/optunaz.utils.doctree b/docs/sphinx-builddir/doctrees/optunaz.utils.doctree
diff --git a/docs/sphinx-builddir/doctrees/optunaz.utils.enums.doctree b/docs/sphinx-builddir/doctrees/optunaz.utils.enums.doctree
diff --git a/docs/sphinx-builddir/doctrees/optunaz.utils.preprocessing.doctree b/docs/sphinx-builddir/doctrees/optunaz.utils.preprocessing.doctree
diff --git a/docs/sphinx-builddir/doctrees/splitters.doctree b/docs/sphinx-builddir/doctrees/splitters.doctree
diff --git a/docs/sphinx-builddir/doctrees/transform.doctree b/docs/sphinx-builddir/doctrees/transform.doctree
diff --git a/docs/sphinx-builddir/html/.buildinfo b/docs/sphinx-builddir/html/.buildinfo
@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 9b1af61dfe8db8b73ea495bbe6736b6a
+config: 74e083516866086104039ea37495342c
 tags: 645f666f9bcd5a90fca523b33c5a78b7
diff --git a/docs/sphinx-builddir/html/README.html b/docs/sphinx-builddir/html/README.html
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_101_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_101_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_110_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_110_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_119_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_119_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_123_1.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_123_1.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_125_1.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_125_1.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_133_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_133_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_135_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_135_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_137_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_137_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_148_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_148_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_153_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_153_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_160_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_160_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_162_2.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_162_2.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_170_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_170_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_172_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_172_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_174_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_174_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_176_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_176_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_177_1.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_177_1.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_200_1.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_200_1.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_208_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_208_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_21_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_21_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_237_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_237_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_23_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_23_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_244_1.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_244_1.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_35_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_35_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_56_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_56_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_67_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_67_0.png
diff --git a/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_71_0.png b/docs/sphinx-builddir/html/_images/notebooks_QPTUNA_Tutorial_71_0.png
diff --git a/docs/sphinx-builddir/html/_sources/README.md.txt b/docs/sphinx-builddir/html/_sources/README.md.txt
@@ -1,15 +1,8 @@
-# QSARtuna: QSAR using Optimization for Hyperparameter Tuning (formerly Optuna AZ and known publically as QSARtuna)
+# QSARtuna 𓆛: QSAR using Optimization for Hyperparameter Tuning (formerly Optuna AZ and QPTUNA)
 
 Build predictive models for CompChem with hyperparameters optimized by [Optuna](https://optuna.org/).
 
-Internal AZ links: 
-[Docs](https://pages.scp.astrazeneca.net/mai/qsartuna),
-[Code](https://github.com/AZU-RDIT/optuna_az/),
-[Issues](https://jira.astrazeneca.com/projects/OPTUNA).
-
-External (QSARtuna) links:
-[Public](https://github.com/MolecularAI/QSARtuna/blob/master/README.md?_sm_nck=1),
-[Public docs](https://molecularai.github.io/QSARtuna/).
+Developed with Uncertainty Quantification and model explainability in mind.
 
 ## Background
 
@@ -21,6 +14,12 @@ for the given data.
 The search itself 
 is done using [Optuna](https://optuna.org/).
 
+Developed models employ
+the latest state-of-the-art
+uncertainty estimation and
+explainability python packages
+
+Further documentation in the GitHub pages [here](https://molecularai.github.io/QSARtuna/).
 
 ### The three-step process
 
@@ -41,7 +40,7 @@ QSARtuna is structured around three steps:
     but it has a big benefit that this final model is trained on the all available data.   
 
 
-## JSON-based Command-line interface on AZ SCP
+## JSON-based Command-line interface
 
 Let's look at a trivial example of modelling molecular weight
 using a training set of 50 molecules.
@@ -55,8 +54,7 @@ It contains four main sections:
 * **descriptors** - which molecular descriptors to use.
 * **algorithms** - which ML algorithms to use.
 
-Below is the example of such file 
-(it is also available in the [source code repository](https://github.com/AZU-RDIT/optuna_az/blob/master/examples/optimization/regression.json)):
+Below is the example of such a file 
 
 ```json
 {
@@ -120,8 +118,8 @@ Below is the example of such file
 ```
 
 Data section specifies location of the dataset file.
-In this example it specifies a relative path to the `tests/data` folder
-in the [source code repository](https://github.com/AZU-RDIT/optuna_az/tree/master/tests/data/DRD2/subset-50).
+In this example it specifies a relative path to the `tests/data` folder.
+
 
 Settings section specifies that:
 * we are building a regression model,
@@ -135,9 +133,9 @@ and optimization is free to pair any specified descriptor with any of the algori
 
 When we have our data and our configuration, it is time to start the optimization.
 
-### Running on SCP
+### Running via singulartity
 
-QSARtuna is deployed on SCP using [Singularity](https://sylabs.io/guides/3.7/user-guide/index.html) container.
+QSARtuna can be deployed using [Singularity](https://sylabs.io/guides/3.7/user-guide/index.html) container.
 
 To run commands inside the container, Singularity uses the following syntax:
 ```shell
@@ -177,12 +175,12 @@ We can submit our script to the queue by giving `sbatch` the following script:
 # The example we use is in examples/optimization/regression_drd2_50.json.
 
 # The example we chose uses relative paths to data files, change directory.
-cd /projects/cc/mai/OptunaAZ-versions/OptunaAZ_latest
+cd /{project_folder}/OptunaAZ-versions/OptunaAZ_latest
 
 singularity exec \
-  /projects/cc/mai/containers/QSARtuna_latest.sif \
+  /{project_folder}/containers/QSARtuna_latest.sif \
   /opt/qsartuna/.venv/bin/qsartuna-optimize \
-  --config examples/optimization/regression_drd2_50.json \
+  --config{project_folder}/examples/optimization/regression_drd2_50.json \
   --best-buildconfig-outpath ~/qsartuna-target/best.json \
   --best-model-outpath ~/qsartuna-target/best.pkl \
   --merged-model-outpath ~/qsartuna-target/merged.pkl
@@ -195,7 +193,7 @@ When the script is complete, it will create pickled model files inside your home
 
 When the model is built, run inference:
 ```shell
-singularity exec /projects/cc/mai/containers/QSARtuna_latest.sif \
+singularity exec /{project_folder}/containers/QSARtuna_latest.sif \
   /opt/qsartuna/.venv/bin/qsartuna-predict \
   --model-file target/merged.pkl \
   --input-smiles-csv-file tests/data/DRD2/subset-50/test.csv \
@@ -211,7 +209,7 @@ This can be specified by modifying the above command and supplying
 
 E.g:
 ```shell
-singularity exec /projects/cc/mai/containers/QSARtuna_2.5.1.sif \
+singularity exec /{project_folder}/containers/QSARtuna_2.5.1.sif \
   /opt/qsartuna/.venv/bin/qsartuna-predict \
   --model-file 2.5.1_model.pkl \
   --input-smiles-csv-file tests/data/DRD2/subset-50/test.csv \
@@ -221,6 +219,42 @@ singularity exec /projects/cc/mai/containers/QSARtuna_2.5.1.sif \
 
 would generate predictions for a model trained with QSARtuna 2.5.1.
 
+### Optional: inspect
+To inspect performance of different models tried during optimization,
+use [MLFlow Tracking UI](https://www.mlflow.org/docs/latest/tracking.html):
+```bash
+module load mlflow
+mlflow ui
+```
+
+Then open mlflow link your browser.
+
+![mlflow select experiment](docs/images/mlflow-select-experiment.png)
+
+If you run `mlflow ui` on SCP, 
+you can forward your mlflow port 
+with a separate SSH session started on your local ("non-SCP") machine:
+```bash
+ssh -N -L localhost:5000:localhost:5000 [email protected]
+```
+("-L" forwards ports, and "-N" just to not execute any commands).
+
+In the MLFlow Tracking UI, select experiment to the left, 
+it is named after the input file path.
+Then select all runs/trials in the experiment, and choose "Compare". 
+You will get a comparison page for selected runs/trials in the experiment.
+
+![mlflow inspecting trials](docs/images/mlflow-inspecting-trials.png)
+
+Comparison page will show MLFlow Runs (called Trials in Optuna), 
+as well as their Parameters and Metrics.
+At the bottom there are plots. 
+For X-axis, select "trial_number".
+For Y-axis, start with "optimization_objective_cvmean_r2".
+
+You can get more details by clicking individual runs. 
+There you can access run/trial build (training) configuration.
+
 
 ## Run from Python/Jupyter Notebook
 
@@ -232,7 +266,7 @@ conda create --name my_env_with_qsartuna python=3.10.10 jupyter pip
 conda activate my_env_with_qsartuna
 module purge  # Just in case.
 which python  # Check. Should output path that contains "my_env_with_qsartuna".
-python -m pip install http://pages.scp.astrazeneca.net/mai/qsartuna/releases/QSARtuna_latest.tar.gz
+python -m pip install https://github.com/MolecularAI/QSARtuna/files/14742594/qsartuna-3.0.0.1.tar.gz
 ```
 
 Then you can use QSARtuna inside your Notebook:
@@ -299,4 +333,4 @@ build_best(buildconfig, "target/best.pkl")
 ##
 # Build (Train) and save the model on the merged train+test data.
 build_merged(buildconfig, "target/merged.pkl")
-```
+```