🤖 AI Summary
To address the challenge of efficiently generating drug-like molecules targeting oncogenic proteins such as AKT1, this paper introduces DrugGEN—a novel end-to-end generative model that uniquely integrates a graph Transformer with generative adversarial networks (GANs) for target-specific de novo molecular design. Methodologically, DrugGEN conditions generation on the 3D structure of the target protein, employs graph neural networks to encode molecular topology, and leverages attention mechanisms to enhance interpretability; generated molecules are rigorously validated via molecular docking and molecular dynamics simulations to assess binding stability. Key contributions include: (1) support for cross-target transfer learning and interpretable structure–activity analysis; (2) generated compounds exhibiting AKT1 binding affinity comparable to native ligands; and (3) an open-source framework enabling rapid adaptation to other druggable targets. This work establishes a new paradigm for AI-driven, precision-targeted drug discovery.
📝 Abstract
Discovering novel drug candidate molecules is one of the most fundamental and critical steps in drug development. Generative deep learning models, which create synthetic data given a probability distribution, offer a high potential for designing de novo molecules. However, for them to be useful in real-life drug development pipelines, these models should be able to design drug-like and target-centric molecules. In this study, we propose an end-to-end generative system, DrugGEN, for the de novo design of drug candidate molecules that interact with intended target proteins. The proposed method represents molecules as graphs and processes them via a generative adversarial network comprising graph transformer layers. The system is trained using a large dataset of drug-like compounds and target-specific bioactive molecules to design effective inhibitory molecules against the AKT1 protein, which is critically important in developing treatments for various types of cancer. We conducted molecular docking and dynamics to assess the target-centric generation performance of the model, as well as attention score visualisation to examine model interpretability. Results indicate that our de novo molecules have a high potential for interacting with the AKT1 protein at the level of its native ligands. Using the open-access DrugGEN codebase, it is possible to easily train models for other druggable proteins, given a dataset of experimentally known bioactive molecules.
