LEAD DISCOVERY

OpenEye Machine Learning and Molecule Explainer

Build machine learning models, Assess generated models, Visualize and understand the results – all in one environment.

In a challenge for computer aided drug design, machine-learning techniques are typically opaque. They provide unknown-box algorithms for prediction or recommendation but do not explain those results.

Different from other machine learning methods, OpenEye lets you build models, assess quality, and understand your results in a chemically intuitive way.

OpenEye Machine Learning Molecule Explainer

With OpenEye’s Molecule Explainer, machine learning is no longer just a unknown-box system. Scientists can visualize areas of a molecule the algorithm considers important for the predicted property.

Features

Transparent. Explains predictions with molecular annotations
Confidence. Domain of applicability is provided with the predicted values
Performance. Extremely fast model building and computation
Turn-key. Guided workflows and pre-trained models (solubility) are provided
Control. Highly parameterizable for novice use and expert control
Modular. Integrate with other physics-based and cheminformatics methods and pipelines

OE ML Floe Results with Class Confidence

OpenEye’s machine learning results let you easily assess the quality of the prediction. For each prediction, a class confidence (low, medium, or high) is provided to help you determine trustworthiness of the predicted value.

OpenEye’s guided workflows (Orion® Floes) are designed to help you quickly build and assess your machine learning models. The built-in Molecule Explainer feature provides you with easy to understand visual explanation of the predicted physical properties for your small molecules.

: OpenEye uses fully connected and probabilistic neural network (2D Fingerprints) using TensorFlow, developed by the Google, that makes machine learning faster and easier.
: OpenEye’s created Molecule Explainer with our machine learning feature to provide explanations of predicted results. Molecule Explainer is an adaptation of the Local Interpretable Model agnostic Explanations (LIME) technique and OpenEye Toolkits, which maps machine learning predictions with interpretable and chemically-aware explanations of the prediction.
: OpenEye machine learning output report makes it easy for scientists to assess the quality of the predicted results. For each prediction, a class confidence (low, medium, or high) is assigned to the predicted value.
: Highly parameterizable for novice use and expert control. Visualization and statistics for each model to help you determine best models to select for your dataset.
: OpenEye’s Orion, a web-based modeling platform, lets you seamlessly integrate both physics-based (classical and QM) models and data-driven (machine learning) models into your computational drug-design projects.
: With the December 2022 release, users have the ability to add their custom feature vector for building machine learning models. Additionally, users have the options to build classification or regression models.

Learn More

OpenEye’s machine learning functionalities help you use data-driven decision making models, speed up your drug-design process, and save cost by reducing failure rates.

Orion Small Molecule Discovery Machine Learning

And, you can also WATCH OpenEye’s miniWebinar recording from September 8, 2022 on machine learning with one of our domain expert scientists, Sayan Mandal, Ph.D.