ML Build: Regression Model using Feature Input

This Floe trains multiple ML(machine learning) Neural Network Regression models on physical properties of small molecules.

Every molecule in the input dataset needs to have a type Float physical property column to train on. In addition, every molecule needs a set of user input features as float vector to train the models on. The models train on these User provided Feature Vectors which are normalized pre-training. The molecule provided as input provides a basis for depiction against features.

It builds machine learning models on user input feature for all possible combinations of neural network hyperparameters provided in the Advanced sections. Read the documentation to learn more about these parameters and how they should be set for a given training data set.

Generates a Floe report containing details of the best models built. User can pick any model and use it to predict properties of other molecules in the Floe ML Regression using Feature Input. The Floe report presents detailed statistics on the hyperparameters, adjust them and rerun the Floe to build better models (See documentation).

In addition to prediction, the built models provide an explanation of predictions, a confidence interval, and the domain of application. The explainer picks the strongest features towards and against the prediction and reports as a histogram.

Warning: This Floe by default, builds about 1,000 machine learning models. On a large dataset, this may be expensive. Since multiple parameters lead to this cost, refer to documentation on how to build a cheaper version for practice. The dataset size to build decent models needs to be at least a ~200 molecules (barring exceptions). We have stress tested up to 50,000 molecules. It is recommended to increase the Memory and Disk Space requirements of the cubes to run on larger datasets.

Inputs

Name	Description	Type
Input Small Molecules to train machine learning models on.	Input dataset file with each record containing molecule and response value(float) to train on	Molecule Dataset

Options

Name	Description	Type
Response Value Field	Name of the field containing the primary data being trained on and predicted.	Float
Custom Feature	Field containing feature vector to train model on. Must be a float vector	FloatVec
Number of Models to show in Floe report	How many best models to provide in FloeReport. By default, keeps best 20 models (based on r2 score) such that it meet memory requirement	Int
Preprocess Molecule	For every molecule, stores only largest component, adjusts ionization to Neutral Ph	Bool
Apply Blockbuster filter	Apply blockbuster filter	Bool
Negative Log	Transform Learning Value to Negative Log. Only for Regression. False: Build Tensorflow Neural Network Model for prediction and explanation (Deterministic Model)	Bool
Number of Top features to explain	Number of top features to provide LIME votes results for. These are the most important features that determine property prediction based on trained ML Model	List

Advaced: Neural Network Hyperparameter Options

Name	Description	Type
Dropouts	List of dropout hyperparameters.	FloatVec
Sets of Hidden Layers	list(s) of hidden layers separated by -1. Input and output layer will be determined by data. Eg: 150,100,50 will create NN with 3 hidden layers of size 150, 100, 50.	IntVec
Sets of Regularisation Layers	list(s) of regularisation layers separated by -1. No regularisation on Input and output layer.	FloatVec
Learning Rates	List of all the learning rate hyperparameters to train model.	FloatVec
Max Epochs	Maximum number of epochs to train model.	Int
Activation	Activation Functions: ReLU, LeakyReLU, PReLU, tanh, SELU, ELU	List
Batch Size	Batch size for training regressor	Int

Outputs

Name	Description	Type
Models Built	Output of Generated Models	Dataset
Failure Output	Output of Failure	Dataset