Introduction and Layout of Machine Learning Model Building package¶
OpenEye Model Building is a tool to build machine learning models that predict properties of small molecules.
In this introductory article, we present the overview and structure of the package. This tutorial walks through how to use the package to execute specific tasks.
Broadly, the floes can be categorized into three categories: 1 Data-preprocessing 2 Machine Learning Model Building 3 Molecule Property Prediction using built models
1 Data-preprocessing Floe¶
The first operation should be to run the data pre-processing floe (reference here). It cleans the data and preps it for any machine learning (and general prep usecase) operations.
2 Machine Learning Model Building¶
To build Machine Learning models, we need to choose among floes that is prefaced by **ML Build*. These floes build several ML models in parallel on the training data provided and provide a detailed statistical report on the best models built. The floes differ in the type of models built that may depend on the factors mentioned in the table.
Input Type |
Type of Model Built |
Architecture of Model Built |
|---|---|---|
Fingerprint
|
Regression
|
TensorFlow
|
Custom User Input
|
Classification
|
Tensorflow Probability
|