Search

Abstract Generative models have demonstrated substantial promise in Natural Language Processing (NLP) and have found application in designing molecules, as seen in General Pretrained Transformer (GPT) models. In our efforts to develop such a tool for exploring the organic chemical space in search of potentially electro-active compounds, we present Llamol, a single novel generative transformer model based on the Llama 2 architecture, which was trained on a 12.5M superset of organic compounds drawn from diverse public sources. To allow for a maximum flexibility in usage and robustness in view of potentially incomplete data, we introduce Stochastic Context Learning (SCL) as a new training procedure. We demonstrate that the resulting model adeptly handles single- and multi-conditional organic molecule generation with up to four conditions, yet more are possible. The model generates valid molecular structures in SMILES notation while flexibly incorporating three numerical and/or one token sequence into the generative process, just as requested. The generated compounds are very satisfactory in all scenarios tested. In detail, we showcase the model’s capability to utilize token sequences for conditioning, either individually or in combination with numerical properties, making Llamol a potent tool for de novo molecule design, easily expandable with new properties. Scientific contribution We developed a novel generative transformer model, Llamol, based on the Llama 2 architecture that was trained on a diverse set of 12.5 M organic compounds. It introduces Stochastic Context Learning (SCL) as a new training procedure, allowing for flexible and robust generation of valid organic molecules with up to multiple conditions that can be combined in various ways, making it a potent tool for de novo molecular design.

Abstract De novo molecular design is the process of searching chemical space for drug-like molecules with desired properties, and deep learning has been recognized as a promising solution. In this study, I developed an effective computational method called Scoring-Assisted Generative Exploration (SAGE) to enhance chemical diversity and property optimization through virtual synthesis simulation, the generation of bridged bicyclic rings, and multiple scoring models for drug-likeness. In six protein targets, SAGE generated molecules with high scores within reasonable numbers of steps by optimizing target specificity without a constraint and even with multiple constraints such as synthetic accessibility, solubility, and metabolic stability. Furthermore, I suggested a top-ranked molecule with SAGE as dual inhibitors of acetylcholinesterase and monoamine oxidase B through multiple desired property optimization. Therefore, SAGE can generate molecules with desired properties by optimizing multiple properties simultaneously, indicating the importance of de novo design strategies in the future of drug discovery and development. Scientific contribution The scientific contribution of this study lies in the development of the Scoring-Assisted Generative Exploration (SAGE) method, a novel computational approach that significantly enhances de novo molecular design. SAGE uniquely integrates virtual synthesis simulation, the generation of complex bridged bicyclic rings, and multiple scoring models to optimize drug-like properties comprehensively. By efficiently generating molecules that meet a broad spectrum of pharmacological criteria—including target specificity, synthetic accessibility, solubility, and metabolic stability—within a reasonable number of steps, SAGE represents a substantial advancement over traditional methods. Additionally, the application of SAGE to discover dual inhibitors for acetylcholinesterase and monoamine oxidase B not only demonstrates its potential to streamline and enhance the drug development process but also highlights its capacity to create more effective and precisely targeted therapies. This study emphasizes the critical and evolving role of de novo design strategies in reshaping the future of drug discovery and development, providing promising avenues for innovative therapeutic discoveries.

De novo molecular design is the process of searching chemical space for drug-like molecules with desired properties, and deep learning has been recognized as a promising solution. In this study, I developed an effective computational method called Scoring-Assisted Generative Exploration (SAGE) to enhance chemical diversity and property optimization through virtual synthesis simulation, the generation of bridged bicyclic rings, and multiple scoring models for drug-likeness. In six protein targets, SAGE generated molecules with high scores within reasonable numbers of steps by optimizing target specificity without a constraint and even with multiple constraints such as synthetic accessibility, solubility, and metabolic stability. Furthermore, I suggested a top-ranked molecule with SAGE as dual inhibitors of acetylcholinesterase and monoamine oxidase B through multiple desired property optimization. Therefore, SAGE can generate molecules with desired properties by optimizing multiple properties simultaneously, indicating the importance of de novo design strategies in the future of drug discovery and development. Scientific contribution: The scientific contribution of this study lies in the development of the Scoring-Assisted Generative Exploration (SAGE) method, a novel computational approach that significantly enhances de novo molecular design. SAGE uniquely integrates virtual synthesis simulation, the generation of complex bridged bicyclic rings, and multiple scoring models to optimize drug-like properties comprehensively. By efficiently generating molecules that meet a broad spectrum of pharmacological criteria—including target specificity, synthetic accessibility, solubility, and metabolic stability—within a reasonable number of steps, SAGE represents a substantial advancement over traditional methods. Additionally, the application of SAGE to discover dual inhibitors for acetylcholinesterase and monoamine oxidase B not only demonstrates its potential to streamline and enhance the drug development process but also highlights its capacity to create more effective and precisely targeted therapies. This study emphasizes the critical and evolving role of de novo design strategies in reshaping the future of drug discovery and development, providing promising avenues for innovative therapeutic discoveries. [ABSTRACT FROM AUTHOR]

Using generative deep learning models and reinforcement learning together can effectively generate new molecules with desired properties. By employing a multi-objective scoring function, thousands of high-scoring molecules can be generated, making this approach useful for drug discovery and material science. However, the application of these methods can be hindered by computationally expensive or time-consuming scoring procedures, particularly when a large number of function calls are required as feedback in the reinforcement learning optimization. Here, we propose the use of double-loop reinforcement learning with simplified molecular line entry system (SMILES) augmentation to improve the efficiency and speed of the optimization. By adding an inner loop that augments the generated SMILES strings to non-canonical SMILES for use in additional reinforcement learning rounds, we can both reuse the scoring calculations on the molecular level, thereby speeding up the learning process, as well as offer additional protection against mode collapse. We find that employing between 5 and 10 augmentation repetitions is optimal for the scoring functions tested and is further associated with an increased diversity in the generated compounds, improved reproducibility of the sampling runs and the generation of molecules of higher similarity to known ligands. [ABSTRACT FROM AUTHOR]

Abstract A de novo molecular design workflow can be used together with technologies such as reinforcement learning to navigate the chemical space. A bottleneck in the workflow that remains to be solved is how to integrate human feedback in the exploration of the chemical space to optimize molecules. A human drug designer still needs to design the goal, expressed as a scoring function for the molecules that captures the designer’s implicit knowledge about the optimization task. Little support for this task exists and, consequently, a chemist usually resorts to iteratively building the objective function of multi-parameter optimization (MPO) in de novo design. We propose a principled approach to use human-in-the-loop machine learning to help the chemist to adapt the MPO scoring function to better match their goal. An advantage is that the method can learn the scoring function directly from the user’s feedback while they browse the output of the molecule generator, instead of the current manual tuning of the scoring function with trial and error. The proposed method uses a probabilistic model that captures the user’s idea and uncertainty about the scoring function, and it uses active learning to interact with the user. We present two case studies for this: In the first use-case, the parameters of an MPO are learned, and in the second use-case a non-parametric component of the scoring function to capture human domain knowledge is developed. The results show the effectiveness of the methods in two simulated example cases with an oracle, achieving significant improvement in less than 200 feedback queries, for the goals of a high QED score and identifying potent molecules for the DRD2 receptor, respectively. We further demonstrate the performance gains with a medicinal chemist interacting with the system. Graphical Abstract

A de novo molecular design workflow can be used together with technologies such as reinforcement learning to navigate the chemical space. A bottleneck in the workflow that remains to be solved is how to integrate human feedback in the exploration of the chemical space to optimize molecules. A human drug designer still needs to design the goal, expressed as a scoring function for the molecules that captures the designer's implicit knowledge about the optimization task. Little support for this task exists and, consequently, a chemist usually resorts to iteratively building the objective function of multi-parameter optimization (MPO) in de novo design. We propose a principled approach to use human-in-the-loop machine learning to help the chemist to adapt the MPO scoring function to better match their goal. An advantage is that the method can learn the scoring function directly from the user's feedback while they browse the output of the molecule generator, instead of the current manual tuning of the scoring function with trial and error. The proposed method uses a probabilistic model that captures the user's idea and uncertainty about the scoring function, and it uses active learning to interact with the user. We present two case studies for this: In the first use-case, the parameters of an MPO are learned, and in the second use-case a non-parametric component of the scoring function to capture human domain knowledge is developed. The results show the effectiveness of the methods in two simulated example cases with an oracle, achieving significant improvement in less than 200 feedback queries, for the goals of a high QED score and identifying potent molecules for the DRD2 receptor, respectively. We further demonstrate the performance gains with a medicinal chemist interacting with the system. [ABSTRACT FROM AUTHOR]

In today's era of rapid development of large models, the traditional drug development process is undergoing a profound transformation. The vast demand for data and consumption of computational resources are making independent drug discovery increasingly difficult. By integrating federated learning technology into the drug discovery field, we have found a solution that both protects privacy and shares computational power. However, the differences in data held by various pharmaceutical institutions and the diversity in drug design objectives have exacerbated the issue of data heterogeneity, making traditional federated learning consensus models unable to meet the personalized needs of all parties. In this study, we introduce and evaluate an innovative drug discovery framework, MolCFL, which utilizes a multi-layer perceptron (MLP) as the generator and a graph convolutional network (GCN) as the discriminator in a generative adversarial network (GAN). By learning the graph structure of molecules, it generates new molecules in a highly personalized manner and then optimizes the learning process by clustering federated learning, grouping compound data with high similarity. MolCFL not only enhances the model's ability to protect privacy but also significantly improves the efficiency and personalization of molecular design. MolCFL exhibits superior performance when handling non-independently and identically distributed data compared to traditional models. Experimental results show that the framework demonstrates outstanding performance on two benchmark datasets, with the generated new molecules achieving over 90% in Uniqueness and close to 100% in Novelty. MolCFL not only improves the quality and efficiency of drug molecule design but also, through its highly customized clustered federated learning environment, promotes collaboration and specialization in the drug discovery process while ensuring data privacy. These features make MolCFL a powerful tool suitable for addressing the various challenges faced in the modern drug research and development field. [Display omitted] • Propose a new clustered federated learning approach (MolCFL) for drug discovery. • Demonstrate MolCFL's capability to generate molecules under non-IID conditions. • Validate the effectiveness of MolCFL through ablation and comparative experiments. [ABSTRACT FROM AUTHOR]

In the chemical industry, the generation of novel molecular structures with beneficial pharmacological and physicochemical properties in de novo molecular design is a critical problem. The advent of deep learning and neural generative models has recently enabled significant achievements in constructing molecular design models in de novo design. Consequently, studies on new generative models continue to generate molecules that exhibit more useful chemical properties. In this study, we propose a method for de novo design that utilizes generative adversarial networks based on reinforcement learning for realistic molecule generation. This method learns to reproduce the training data distribution of simplified molecular‐input line‐entry system strings. The proposed method is demonstrated to effectively generate novel molecular structures from five benchmark results using a real‐world public dataset, ChEMBL. The code is available at https://github.com/dudwojae/SMILES‐MaskGAN. [ABSTRACT FROM AUTHOR]

Abstract: A major challenge in computational chemistry is the generation of novel molecular structures with desirable pharmacological and physiochemical properties. In this work, we investigate the potential use of autoencoder, a deep learning methodology, for de novo molecular design. Various generative autoencoders were used to map molecule structures into a continuous latent space and vice versa and their performance as structure generator was assessed. Our results show that the latent space preserves chemical similarity principle and thus can be used for the generation of analogue structures. Furthermore, the latent space created by autoencoders were searched systematically to generate novel compounds with predicted activity against dopamine receptor type 2 and compounds similar to known active compounds not included in the trainings set were identified. [ABSTRACT FROM AUTHOR]

Abstract: The Van enzymes are ATP-dependant ligases responsible for resistance to vancomycin in Staphylococcus aureus and Enteroccoccus species. The de novo molecular design programme SPROUT was used in conjunction with the X-ray crystal structure of Enterococcus faecium d-alanyl-d-lactate ligase (VanA) to design new putative inhibitors based on a hydroxyethylamine template. The two best ranked structures were selected and efficient syntheses developed. The inhibitory activities of these molecules were determined on E. faecium VanA, and due to structural similarity and a common reaction mechanism, also on d-Ala-d-Ala ligase (DdlB) from Escherichia coli. The phosphate group attached to the hydroxyl moiety of the hydroxyethylamine isostere within these systems is essential for their inhibitory activity against both VanA and DdlB. [Copyright &y& Elsevier]

This paper tests the performance of a simple empirical scoring function on a set of candidate designs produced by a de novo design package. The scoring function calculates approximate ligand-receptor binding affinities given a putative binding geometry. To our knowledge this is the first substantial test of an empirical scoring function of this type on a set of molecular designs which were then subsequently synthesised and assayed. The performance illustrates that the methods used to construct the scoring function and the reliance on plausible, yet potentially false, binding modes can lead to significant over-prediction of binding affinity in bad cases. This is anticipated on theoretical grounds and provides caveats on the reliance which can be placed when using the scoring function as a screen in the choice of molecular designs. To improve the predictability of the scoring function and to understand experimental results, it is important to perform subsequent Quantitative Structure-Activity Relationship (QSAR) studies. In this paper, Bayesian regression is performed to improve the predictability of the scoring function in the light of the assay results. Bayesian regression provides a rigorous mathematical framework for the incorporation of prior information, in this case information from the original training set, into a regression on the assay results of the candidate molecular designs. The results indicate that Bayesian regression is a useful and practical technique when relevant prior knowledge is available and that the constraints embodied in the prior information can be used to improve the robustness and accuracy of regression models. We believe this to be the first application of Bayesian regression to QSAR analysis in chemistry. [ABSTRACT FROM AUTHOR]

This paper describes the development of a simple empirical scoringfunction designed to estimate the free energy of binding for aprotein–ligand complex when the 3D structure of the complex is knownor can be approximated. The function uses simple contact terms to estimatelipophilic and metal–ligand binding contributions, a simple explicitform for hydrogen bonds and a term which penalises flexibility. Thecoefficients of each term are obtained using a regression based on 82ligand–receptor complexes for which the binding affinity is known. Thefunction reproduces the binding affinity of the complexes with across-validated error of 8.68 kJ/mol. Tests on internal consistency indicatethat the coefficients obtained are stable to changes in the composition ofthe training set. The function is also tested on two test sets containing afurther 20 and 10 complexes, respectively. The deficiencies of this type offunction are discussed and it is compared to approaches by other workers. [ABSTRACT FROM AUTHOR]

This paper describes a novel methodology, PRO_SELECT, which combines elements of structure-based drug design and combinatorial chemistry to create a new paradigm for accelerated lead discovery. Starting with a synthetically accessible template positioned in the active site of the target of interest, PRO_SELECT employs database searching to generate lists of potential substituents for each substituent position on the template. These substituents are selected on the basis of their being able to couple to the template using known synthetic routes and their possession of the correct functionality to interact with specified residues in the active site. The lists of potential substituents are then screened computationally against the active site using rapid algorithms. An empirical scoring function, correlated to binding free energy, is used to rank the substituents at each position. The highest scoring substituents at each position can then be examined using a variety of techniques and a final selection is made. Combinatorial enumeration of the final lists generates a library of synthetically accessible molecules, which may then be prioritised for synthesis and assay. The results obtained using PRO_SELECT to design thrombin inhibitors are briefly discussed. [ABSTRACT FROM AUTHOR]

In the past few years, de novo molecular design has increasingly been using generative models from the emergent field of Deep Learning, proposing novel compounds that are likely to possess desired properties or activities. De novo molecular design finds applications in different fields ranging from drug discovery and materials sciences to biotechnology. A panoply of deep generative models, including architectures as Recurrent Neural Networks, Autoencoders, and Generative Adversarial Networks, can be trained on existing data sets and provide for the generation of novel compounds. Typically, the new compounds follow the same underlying statistical distributions of properties exhibited on the training data set Additionally, different optimization strategies, including transfer learning, Bayesian optimization, reinforcement learning, and conditional generation, can direct the generation process toward desired aims, regarding their biological activities, synthesis processes or chemical features. Given the recent emergence of these technologies and their relevance, this work presents a systematic and critical review on deep generative models and related optimization methods for targeted compound design, and their applications.

A major challenge in computational chemistry is the generation of novel molecular structures with desirable pharmacological and physiochemical properties. In this work, we investigate the potential use of autoencoder, a deep learning methodology, for de novo molecular design. Various generative autoencoders were used to map molecule structures into a continuous latent space and vice versa and their performance as structure generator was assessed. Our results show that the latent space preserves chemical similarity principle and thus can be used for the generation of analogue structures. Furthermore, the latent space created by autoencoders were searched systematically to generate novel compounds with predicted activity against dopamine receptor type 2 and compounds similar to known active compounds not included in the trainings set were identified., (© 2018 The Authors. Published by Wiley-VCH Verlag GmbH & Co. KGaA.)