1. Double-click the Materials Science icon
   • (No icon? See Starting Maestro)

Figure 2-1. Change Working Directory option.

2. Go to File > Change Working Directory
3. Find your directory, and click Choose
4. Pre-generated files are included for running jobs or examining output. Download the zip file here: schrodinger.com/sites/default/files/s3/release/current/Tutorials/zip/ml_formulations.zip
5. After downloading the zip file, unzip the contents in your Working Directorythe location where files are saved for ease of access throughout the tutorial

Figure 2-2. Save Project panel.

6. Go to File > Save Project As
7. Change the File name to ml_formulations_tutorial, click Save
   • The project is now named ml_formulations_tutorial.prj

Figure 3-1. The Formulation Machine Learning panel after opening.

The provided .csv file is loaded directly into the Formulation Machine Learning panel (not into MS Maestro):

1. Go to Tasks > Materials > Informatics > Formulations Machine Learning
   • The Formulation Machine Learning panel opens

 

Figure 3-2. Loading the training data into the panel.

2. Keep Formulation type as Simple
3. Click Load Training Data …
4. Navigate to the provided files, presumably in your working directorythe location where files are saved, choose train.csv and click Open
   • The panel is populated with the training data

Figure 3-3. Viewing the training data in the panel.

Take a moment to view the data in the panel. Scrolling down, we can see examples with the number of components varying from 1 to 5, as well as the density and other imported data columns.

Note that the data is editable within the panel. To alter any molecules, click on the corresponding SMILES string to open the 2D Sketcher. Click on the row to edit the values. Importantly, editing the data in the panel will not edit the imported .csv file (though the Export Data button can be used to create a new file). For this example, we will not edit the data.

Figure 3-4. Plotting the distribution of the training data.

The panel offers a useful way to visualize the distribution of the data set prior to model construction.

5. On the right side of the panel, for Properties, choose num_components and then density
   • The plot updates to show the distribution of densities in the data set with respect to the number of components
   • Statistical parameters such as R², root-mean-squared error (RMSE) and Pearson’s r correlation coefficient are printed, and can be toggled on and off with the checkboxes above the plot

Figure 3-5. Setting the parameters on the Build tab.

6. Go to the Build tab
7. Maintain the Featurizers as 4 items
   • Clicking the dropdown enables specific selection of features. In this case, we maintain the default of generating all of the available features
8. Change the Machine learning models to all
   • We include all of the available machine learning models
9. Change the Target property to density
   • The target property is that which we wish to predict with the machine learning model
10. Maintain Descriptors as None
    • If you had additional descriptors available with your dataset, you could refer to them here
11. Change the Hyperparameter tuning steps to 20

Figure 3-6. Naming and running the training calculation.

12. Change the Job name to formulation_ml_train_density
13. Adjust the job settings () as needed
    • This job requires a CPU host. The job will be completed in about 10 minutes on a CPU host
14. If you would like to perform the calculation, click Run. Otherwise, we will import pre-generated results in the next step.

By default, the panel will automatically perform a random 90:10 train:test split on your dataset. The panel will use the training set for model training and testing set to evaluate whether the model can generalize to unseen formulations. Performance on the train and test sets are reported after building a model.

Figure 3-7. Loading the model file.

If you performed the calculation, the results will automatically be incorporated into the panel when the job is complete. Here, we will assume that you are proceeding with the provided files:

15. Go to the Performance tab
16. Click Load Model …
17. In the provided files, go to the Section_03 > formulation_ml_train_density directory, choose the formulation_ml_train_density.mlform file and click Open
    • If you get a warning saying that the uploaded ML model was trained on an older version, feel free to click okay and proceed. If you wish to retrain the model, you can use the ML Model Manager panel.

Figure 3-8. Viewing the model.

The performance tab is populated with the corresponding scatterplot.

Above the plot, the Featurizers and Machine learning models used in building the model are listed.

The plot contains predicted versus actual values from the train and test set, with corresponding R² and RMSE values in a table below.

In this case, we can clearly see that the model generalized well on the test set.

Note: If you performed the calculations yourself, you should expect slight variance in the results.

Figure 4-1. The Predict tab. 

1. In the Formulation Machine Learning panel, go to the Predict tab
2. Ensure that next to Load Model, the .mlform file associated with Section 3 is shown. If not, load the formulation_ml_train_density.mlform file

Figure 4-2. Loading the prediction input data. 

We can load new formulation data into the panel and use our model to predict density values.

3. Make sure the dropdown shows Prediction Input and click Load …
4. Navigate to the provided tutorial files and choose the test.csv file. Click Open

Figure 4-3. Viewing the prediction input data. 

The panel is updated with the data in the test.csv file. Note that the densities are provided only to compare the quality of the predictions; the machine learning model will be able to predict the density of these formulations with only SMILES and composition information.

Similar to the “Training Data” tab,  the data is editable within the “Predict” tab. To alter any molecules, click on the corresponding SMILES string to open the 2D Sketcher. To edit any values, click on the row to enable editing. For this example, we will not edit the data.

Figure 4-4. Naming and running the job. 

With the trained model and input data loaded, we can run the job to predict density for each formulation.

5. Change the Job name to formulation_ml_test_density
6. Adjust the job settings () as needed
   • This job requires a CPU host. The job will be completed in about 1 minute on a CPU host
7. If you would like to perform the calculation, click Run. Otherwise, we will import pre-generated results in the next step.

Figure 4-5. Loading the prediction output.

If you performed the calculation, the results will automatically be incorporated into the panel when the job is complete. We will assume that you are proceeding with the provided files:

8. Change the dropdown from Predict Input Data to Prediction Output
9. Click Load …
10. Navigate to the formulation_ml_test_density_predict.csv file in the Section_04 > formulation_ml_test_density > formulation_ml_test_density_predict.csv
11. Click Open

Figure 4-6. Viewing the prediction output.

The second data column contains the provided density. The fourth and fifth columns contain the outputs from the machine learning model, specifically the predicted density and associated uncertainty

 

Note: If you performed the calculations yourself, you should expect slight variance in the results..

Figure 4-7. Plotting a scatter plot of the data.

The panel enables quick generation of a scatter plot to assess the performance of the model.

12. Click on the density_predict column header to pull up the plotter tool
13. Set the Properties from the dropdowns to density and density_predict

A scatterplot of predicted density versus provided density is shown. Statistical parameters such as R², RMSE and Pearson’s r are printed, and can be toggled on and off with the checkboxes above the plot.