Deep learning and virtual drug screening

Abstract

Current drug development is still costly and slow given tremendous technological advancements in drug discovery and medicinal chemistry. Using machine learning (ML) to virtually screen compound libraries promises to fix this for generating drug leads more efficiently and accurately. Herein, we explain the broad basics and integration of both virtual screening (VS) and ML. We then discuss artificial neural networks (ANNs) and their usage for VS. The ANN is emerging as the dominant classifier for ML in general, and has proven its utility for both structure-based and ligand-based VS. Techniques such as dropout, multitask learning and convolution improve the performance of ANNs and enable them to take on chemical meaning when learning about the drug-target-binding activity of compounds.

Keywords: artificial intelligence; artificial neural networks; convolutional neural networks; deep learning; drug discovery; machine learning; multitask learning; virtual screening.

Figure 1.. Internal versus external validation.

This is a visual representation of the conceptual difference between internal and external validation. The arrow points from the data to be validated to the data used for validation.

Figure 2.. A block diagram of the optimal workflow for machine learning-based virtual screening.

Figure 3.. Representation of the hierarchy and relationship between different artificial-related concepts.

These concepts exist as subsets of each other.

Figure 4.. Stochastic gradient descent compared with gradient descent.

Figure 5.. Example architecture of a Convolutional Neural Network.

Dropout would involve dropping certain nodes that are illustrated within the layers.

Figure 6.. Visual representation of multitask learning.