De Novo Molecular Design of Caspase-6 Inhibitors by a GRU-Based Recurrent Neural Network Combined with a Transfer Learning Approach

Due to their potential in the treatment of neurodegenerative diseases, caspase-6 inhibitors have attracted widespread attention. However, the existing caspase-6 inhibitors showed more or less inevitable deficiencies that restrict their clinical development and applications. Therefore, there is an urgent need to develop novel caspase-6 candidate inhibitors. Herein, a gated recurrent unit (GRU)-based recurrent neural network (RNN) combined with transfer learning was used to build a molecular generative model of caspase-6 inhibitors. The results showed that the GRU-based RNN model can accurately learn the SMILES grammars of about 2.4 million chemical molecules including ionic and isomeric compounds and can generate potential caspase-6 inhibitors after transfer learning of the known 433 caspase-6 inhibitors. Based on the novel molecules derived from the molecular generative model, an optimal logistic regression model and Surflex-dock were employed for predicting and ranking the inhibitory activities. According to the prediction results, three potential caspase-6 inhibitors with different scaffolds were selected as the promising candidates for further research. In general, this paper provides an efficient combinational strategy for de novo molecular design of caspase-6 inhibitors.

DockStream: a docking wrapper to enhance de novo molecular design

Recently, we have released the de novo design platform REINVENT in version 2.0. This improved and extended iteration supports far more features and scoring function components, which allows bespoke and tailor-made protocols to maximize impact in small molecule drug discovery projects. A major obstacle of generative models is producing active compounds, in which predictive (QSAR) models have been applied to enrich target activity. However, QSAR models are inherently limited by their applicability domains. To overcome these limitations, we introduce a structure-based scoring component for REINVENT. DockStream is a flexible, stand-alone molecular docking wrapper that provides access to a collection of ligand embedders and docking backends. Using the benchmarking and analysis workflow provided in DockStream, execution and subsequent analysis of a variety of docking configurations can be automated. Docking algorithms vary greatly in performance depending on the target and the benchmarking and analysis workflow provides a streamlined solution to identifying productive docking configurations. We show that an informative docking configuration can inform the REINVENT agent to optimize towards improving docking scores using public data. With docking activated, REINVENT is able to retain key interactions in the binding site, discard molecules which do not fit the binding cavity, harness unused (sub-)pockets, and improve overall performance in the scaffold-hopping scenario. The code is freely available at https://github.com/MolecularAI/DockStream.

Improving De Novo Molecular Design with Curriculum Learning

Reinforcement learning (RL) is a powerful paradigm that has gained popularity across multiple domains. However, applying RL may come at a cost of multiple interactions between the agent and the environment. This cost can be especially pronounced when the single feedback from the environment is slow or computationally expensive, causing extensive periods of nonproductivity. Curriculum learning (CL) provides a suitable alternative by arranging a sequence of tasks of increasing complexity with the aim of reducing the overall cost of learning. Here, we demonstrate the application of CL for drug discovery. We implement CL in the de novo design platform, REINVENT, and apply it on illustrative de novo molecular design problems of different complexity. The results show both accelerated learning and a positive impact on the quality of the output when compared to standard policy based RL. To our knowledge, this is the first application of CL for the purposes of de novo molecular design. The code is freely available at https://github.com/MolecularAI/Reinvent.

Improving De Novo Molecular Design with Curriculum Learning

Reinforcement learning (RL) is a powerful paradigm that has gained popularity across multiple domains. However, applying RL may come at a cost of multiple interactions between the agent and the environment. This cost can be especially pronounced when the single feedback from the environment is slow or computationally expensive, causing extensive periods of nonproductivity. Curriculum learning (CL) provides a suitable alternative by arranging a sequence of tasks of increasing complexity with the aim of reducing the overall cost of learning. Here, we demonstrate the application of CL for drug discovery. We implement CL in the de novo design platform, REINVENT, and apply it on illustrative de novo molecular design problems of different complexity. The results show both accelerated learning and a positive impact on the quality of the output when compared to standard policy based RL. To our knowledge, this is the first application of CL for the purposes of de novo molecular design. The code is freely available at https://github.com/MolecularAI/Reinvent.

InFrag: Using Attribution-based Explainability to Guide Deep Molecular Optimization

The recently proposed Genetic expert guided learning (GEGL) framework has demonstrated impressive performances on several \textit{de novo} molecular design tasks. Despite the displayed state-of-the art results, the proposed system relies on an expert-designed Genetic expert. Although hand-crafted experts allow to navigate the chemical space efficiently, designing such experts requires a significant amount of effort and might contain inherent biases which can potentially slow down convergence or even lead to sub-optimal solutions. In this research, we propose a novel genetic expert named \textit{InFrag} which is free of design rules and can generate new molecules by combining promising molecular fragments. Fragments are obtained by using an additional graph convolutional neural network which computes attributions for each atom for a given molecule. Molecular substructures which contribute positively to the task score are kept and combined to propose novel molecules. We experimentally demonstrate that, within the GEGL framework, our proposed attribution-based genetic expert is either competitive or outperforms the original expert-designed genetic expert on goal-directed optimization tasks. When limiting the number of optimization rounds to one and three rounds, a performance increase of approximately 43% and 20% respectively is observed compared to the baseline genetic expert. Furthermore, we empirically show that combining several experts that share a fixed sampling budget at each optimization round generally improves or maintains the overall performance of the framework.

Molecular Generators and Optimizers Failure Modes

In recent years, there has been an uptick in interest in generative models for molecules in drug development. In the field of de novo molecular design, these models are used to make molecules with desired properties from scratch. This is occasionally used instead of virtual screening, which is limited by the size of the libraries that can be searched in practice. Rather than screening existing libraries, generative models can be used to build custom libraries from scratch. Using generative models, which may optimize molecules straight towards the desired profile, this time-consuming approach can be sped up. The purpose of this work is to show how current shortcomings in evaluating generative models for molecules can be avoided. We cover both distribution-learning and goal-directed generation with a focus on the latter. Three well-known targets were downloaded from ChEMBL: Janus kinase 2 (JAK2), epidermal growth factor receptor (EGFR), and dopamine receptor D2 (DRD2) (Bento et al. 2014). We preprocessed the data to get binary classification jobs. Before calculating a scoring function, the data is split into two halves, which we shall refer to as split 1/2. The ratio of active to inactive users. Our goal is to train three bioactivity models with equal prediction performance, one to be used as a scoring function for chemical optimization and the other two to be used as performance evaluation models. Our findings suggest that distribution-learning can attain near-perfect scores on many existing criteria even with the most basic and completely useless models. According to benchmark studies, likelihood-based models account for many of the best technologies, and we propose that test set likelihoods be included in future comparisons.