GuacaMol: Benchmarking Models for de Novo Molecular Design

Multi-objective molecular generation via clustered Pareto-based reinforcement learning

De novo molecular design is the process of learning knowledge from existing data to propose new chemical structures that satisfy the desired properties. By using de novo design to generate compounds in a directed manner, better solutions can be obtained in large chemical libraries with less comparison cost. But drug design needs to take multiple factors into consideration. For example, in polypharmacology, molecules that activate or inhibit multiple target proteins produce multiple pharmacological activities and are less susceptible to drug resistance. However, most existing molecular generation methods either focus only on affinity for a single target or fail to effectively balance the relationship between multiple targets, resulting in insufficient validity and desirability of the generated molecules. To address the problems, an approach called clustered Pareto-based reinforcement learning (CPRL) is proposed. In CPRL, a pre-trained model is constructed to grasp existing molecular knowledge in a supervised learning manner. In addition, the clustered Pareto optimization algorithm is presented to find the best solution between different objectives. The algorithm first extracts an update set from the sampled molecules through the designed aggregation-based molecular clustering. Then, the final reward is computed by constructing the Pareto frontier ranking of the molecules from the updated set. To explore the vast chemical space, a reinforcement learning agent is designed in CPRL that can be updated under the guidance of the final reward to balance multiple properties. Furthermore, to increase the internal diversity of the molecules, a fixed-parameter exploration model is used for sampling in conjunction with the agent. The experimental results demonstrate that CPRL is capable of balancing multiple properties of the molecule and has higher desirability and validity, reaching 0.9551 and 0.9923, respectively.

Navigating Ultralarge Virtual Chemical Spaces with Product-of-Experts Chemical Language Models

Ultralarge virtual chemical spaces have emerged as a valuable resource for drug discovery, providing access to billions of make-on-demand compounds with high synthetic success rates. Chemical language models can potentially accelerate the exploration of these vast spaces through direct compound generation. However, existing models are not designed to navigate specific virtual chemical spaces and often overlook synthetic accessibility. To address this gap, we introduce product-of-experts (PoE) chemical language models, a modular and scalable approach to navigating ultralarge virtual chemical spaces. This method allows for controlled compound generation within a desired chemical space by combining a prior model pretrained on the target space with expert and anti-expert models fine-tuned using external property-specific data sets. We demonstrate that the PoE chemical language model can generate compounds with desirable properties, such as those that favorably dock to dopamine receptor D2 (DRD2) and are predicted to cross the blood-brain barrier (BBB), while ensuring that the majority of generated compounds are present within the target chemical space. Our results highlight the potential of chemical language models for navigating ultralarge virtual chemical spaces, and we anticipate that this study will motivate further research in this direction. The source code and data are freely available at https://github.com/shuyana/poeclm.

Current Status of Computational Approaches for Small Molecule Drug Discovery

2024 has been an exciting year for computational sciences, with the Nobel Prize in Physics awarded for "artificial neural network" and the Nobel Prize in Chemistry presented for "protein structure prediction and design". Given the rapid advancements in Computer-Aided Drug Design (CADD) and Artificial Intelligence in Drug Discovery (AIDD), a document summarizing their current standing and future directions would be timely and relevant to the readership of Journal of Medicinal Chemistry. This piece of commentary aims to highlight recent developments, key challenges, and potential synergies between these fields, contributing to ongoing discussions in the literature and scientific blogs.

Mothra: Multiobjective de novo Molecular Generation Using Monte Carlo Tree Search

In the field of drug discovery, identifying compounds that satisfy multiple criteria, such as target protein affinity, pharmacokinetics, and membrane permeability, is challenging because of the vast chemical space. Until now, multiobjective optimization via generative models has often involved linear combinations of different reward functions. Linear combinations solve multiobjective optimization problems by turning multiobjective optimization into a single-objective task and causing problems with weighting for each objective. Herein, we propose a scalable multiobjective molecular generative model developed using deep learning techniques. This model integrates the capabilities of recurrent neural networks for molecular generation and Pareto multiobjective Monte Carlo tree search to determine the optimal search direction. Through this integration, our model can generate compounds using enhanced evaluation functions that include important aspects like target protein affinity, drug similarity, and toxicity. The proposed model addresses the limitations of previous linear combination methods, and its effectiveness is demonstrated via extensive experimentation. The improvements achieved in the evaluation metrics underscore the potential utility of our approach toward drug discovery applications. In addition, we provide the source code for our model such that researchers can easily access and use our framework in their own investigations. The source code and pretrained model for Mothra, developed in this study, along with the Docker image for the Pareto front explorer and compound picker, designed to streamline the selection and visualization of optimal chemical compounds, are released under the GNU General Public License v3.0 and available at https://github.com/sekijima-lab/Mothra.

Diffusion Models in De Novo Drug Design

Diffusion models have emerged as powerful tools for molecular generation, particularly in the context of 3D molecular structures. Inspired by nonequilibrium statistical physics, these models can generate 3D molecular structures with specific properties or requirements crucial to drug discovery. Diffusion models were particularly successful at learning the complex probability distributions of 3D molecular geometries and their corresponding chemical and physical properties through forward and reverse diffusion processes. This review focuses on the technical implementation of diffusion models tailored for 3D molecular generation. It compares the performance, evaluation methods, and implementation details of various diffusion models used for molecular generation tasks. We cover strategies for atom and bond representation, architectures of reverse diffusion denoising networks, and challenges associated with generating stable 3D molecular structures. This review also explores the applications of diffusion models in de novo drug design and related areas of computational chemistry, such as structure-based drug design, including target-specific molecular generation, molecular docking, and molecular dynamics of protein-ligand complexes. We also cover conditional generation on physical properties, conformation generation, and fragment-based drug design. By summarizing the state-of-the-art diffusion models for 3D molecular generation, this review sheds light on their role in advancing drug discovery and their current limitations.

Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science

Machine learning has been pervasively touching many fields of science. Chemistry and materials science are no exception. While machine learning has been making a great impact, it is still not reaching its full potential or maturity. In this perspective, we first outline current applications across a diversity of problems in chemistry. Then, we discuss how machine learning researchers view and approach problems in the field. Finally, we provide our considerations for maximizing impact when researching machine learning for chemistry.

DrugSynthMC: An Atom-Based Generation of Drug-like Molecules with Monte Carlo Search

A growing number of deep learning (DL) methodologies have recently been developed to design novel compounds and expand the chemical space within virtual libraries. Most of these neural network approaches design molecules to specifically bind a target based on its structural information and/or knowledge of previously identified binders. Fewer attempts have been made to develop approaches for de novo design of virtual libraries, as synthesizability of generated molecules remains a challenge. In this work, we developed a new Monte Carlo Search (MCS) algorithm, DrugSynthMC (Drug Synthesis using Monte Carlo), in conjunction with DL and statistical-based priors to generate thousands of interpretable chemical structures and novel drug-like molecules per second. DrugSynthMC produces drug-like compounds using an atom-based search model that builds molecules as SMILES, character by character. Designed molecules follow Lipinski's "rule of 5″, show a high proportion of highly water-soluble nontoxic predicted-to-be synthesizable compounds, and efficiently expand the chemical space within the libraries, without reliance on training data sets, synthesizability metrics, or enforcing during SMILES generation. Our approach can function with or without an underlying neural network and is thus easily explainable and versatile. This ease in drug-like molecule generation allows for future integration of score functions aimed at different target- or job-oriented goals. Thus, DrugSynthMC is expected to enable the functional assessment of large compound libraries covering an extensive novel chemical space, overcoming the limitations of existing drug collections. The software is available at https://github.com/RoucairolMilo/DrugSynthMC.

Augmenting genetic algorithms with machine learning for inverse molecular design

Evolutionary and machine learning methods have been successfully applied to the generation of molecules and materials exhibiting desired properties. The combination of these two paradigms in inverse design tasks can yield powerful methods that explore massive chemical spaces more efficiently, improving the quality of the generated compounds. However, such synergistic approaches are still an incipient area of research and appear underexplored in the literature. This perspective covers different ways of incorporating machine learning approaches into evolutionary learning frameworks, with the overall goal of increasing the optimization efficiency of genetic algorithms. In particular, machine learning surrogate models for faster fitness function evaluation, discriminator models to control population diversity on-the-fly, machine learning based crossover operations, and evolution in latent space are discussed. The further potential of these synergistic approaches in generative tasks is also assessed, outlining promising directions for future developments.

Large Language Models as Molecular Design Engines

The design of small molecules is crucial for technological applications ranging from drug discovery to energy storage. Due to the vast design space available to modern synthetic chemistry, the community has increasingly sought to use data-driven and machine learning approaches to navigate this space. Although generative machine learning methods have recently shown potential for computational molecular design, their use is hindered by complex training procedures, and they often fail to generate valid and unique molecules. In this context, pretrained Large Language Models (LLMs) have emerged as potential tools for molecular design, as they appear to be capable of creating and modifying molecules based on simple instructions provided through natural language prompts. In this work, we show that the Claude 3 Opus LLM can read, write, and modify molecules according to prompts, with impressive 97% valid and unique molecules. By quantifying these modifications in a low-dimensional latent space, we systematically evaluate the model's behavior under different prompting conditions. Notably, the model is able to perform guided molecular generation when asked to manipulate the electronic structure of molecules using simple, natural-language prompts. Our findings highlight the potential of LLMs as powerful and versatile molecular design engines.

A Multi-view Molecular Pre-training with Generative Contrastive Learning

Molecular representation learning can preserve meaningful molecular structures as embedding vectors, which is a necessary prerequisite for molecular property prediction. Yet, learning how to accurately represent molecules remains challenging. Previous approaches to learning molecular representations in an end-to-end manner potentially suffered information loss while neglecting the utilization of molecular generative representations. To obtain rich molecular feature information, the pre-training molecular representation model utilized different molecular representations to reduce information loss caused by a single molecular representation. Therefore, we provide the MVGC, a unique multi-view generative contrastive learning pre-training model. Our pre-training framework specifically acquires knowledge of three fundamental feature representations of molecules and effectively integrates them to predict molecular properties on benchmark datasets. Comprehensive experiments on seven classification tasks and three regression tasks demonstrate that our proposed MVGC model surpasses the majority of state-of-the-art approaches. Moreover, we explore the potential of the MVGC model to learn the representation of molecules with chemical significance.

Navigating the frontier of drug-like chemical space with cutting-edge generative AI models

Deep generative models (GMs) have transformed the exploration of drug-like chemical space (CS) by generating novel molecules through complex, nontransparent processes, bypassing direct structural similarity. This review examines five key architectures for CS exploration: recurrent neural networks (RNNs), variational autoencoders (VAEs), generative adversarial networks (GANs), normalizing flows (NF), and Transformers. It discusses molecular representation choices, training strategies for focused CS exploration, evaluation criteria for CS coverage, and related challenges. Future directions include refining models, exploring new notations, improving benchmarks, and enhancing interpretability to better understand biologically relevant molecular properties.

Self-Driving Laboratories for Chemistry and Materials Science

Self-driving laboratories (SDLs) promise an accelerated application of the scientific method. Through the automation of experimental workflows, along with autonomous experimental planning, SDLs hold the potential to greatly accelerate research in chemistry and materials discovery. This review provides an in-depth analysis of the state-of-the-art in SDL technology, its applications across various scientific disciplines, and the potential implications for research and industry. This review additionally provides an overview of the enabling technologies for SDLs, including their hardware, software, and integration with laboratory infrastructure. Most importantly, this review explores the diverse range of scientific domains where SDLs have made significant contributions, from drug discovery and materials science to genomics and chemistry. We provide a comprehensive review of existing real-world examples of SDLs, their different levels of automation, and the challenges and limitations associated with each domain.

Diverse Hits in De Novo Molecule Design: Diversity-Based Comparison of Goal-Directed Generators

Since the rise of generative AI models, many goal-directed molecule generators have been proposed as tools for discovering novel drug candidates. However, molecule generators often produce highly similar molecules and tend to overemphasize conformity to an imperfect scoring function rather than capturing the true underlying properties sought. We rectify these two shortcomings by offering diversity-based evaluations using the #Circles metric and considering constraints on scoring function calls or computation time. Our findings highlight the superior performance of SMILES-based autoregressive models in generating diverse sets of desired molecules compared to graph-based models or genetic algorithms.

ACEGEN: Reinforcement Learning of Generative Chemical Agents for Drug Discovery

In recent years, reinforcement learning (RL) has emerged as a valuable tool in drug design, offering the potential to propose and optimize molecules with desired properties. However, striking a balance between capabilities, flexibility, reliability, and efficiency remains challenging due to the complexity of advanced RL algorithms and the significant reliance on specialized code. In this work, we introduce ACEGEN, a comprehensive and streamlined toolkit tailored for generative drug design, built using TorchRL, a modern RL library that offers thoroughly tested reusable components. We validate ACEGEN by benchmarking against other published generative modeling algorithms and show comparable or improved performance. We also show examples of ACEGEN applied in multiple drug discovery case studies. ACEGEN is accessible at https://github.com/acellera/acegen-open and available for use under the MIT license.

Hamiltonian diversity: effectively measuring molecular diversity by shortest Hamiltonian circuits

In recent years, significant advancements have been made in molecular generation algorithms aimed at facilitating drug development, and molecular diversity holds paramount importance within the realm of molecular generation. Nonetheless, the effective quantification of molecular diversity remains an elusive challenge, as extant metrics exemplified by Richness and Internal Diversity fall short in concurrently encapsulating the two main aspects of such diversity: quantity and dissimilarity. To address this quandary, we propose Hamiltonian diversity, a novel molecular diversity metric predicated upon the shortest Hamiltonian circuit. This metric embodies both aspects of molecular diversity in principle, and we implement its calculation with high efficiency and accuracy. Furthermore, through empirical experiments we demonstrate the high consistency of Hamiltonian diversity with real-world chemical diversity, and substantiate its effects in promoting diversity of molecular generation algorithms. Our implementation of Hamiltonian diversity in Python is available at: https://github.com/HXYfighter/HamDiv .Scientific contributionWe propose a more rational molecular diversity metric for the community of cheminformatics and drug development. This metric can be applied to evaluation of existing molecular generation methods and enhancing drug design algorithms.

Application progress of deep generative models in de novo drug design

The deep molecular generative model has recently become a research hotspot in pharmacy. This paper analyzes a large number of recent reports and reviews these models. In the central part of this paper, four compound databases and two molecular representation methods are compared. Five model architectures and applications for deep molecular generative models are emphatically introduced. Three evaluation metrics for model evaluation are listed. Finally, the limitations and challenges in this field are discussed to provide a reference and basis for developing and researching new models published in future.

Artificial intelligence and cheminformatics tools: a contribution to the drug development and chemical science

In the ever-evolving field of drug discovery, the integration of Artificial Intelligence (AI) and Machine Learning (ML) with cheminformatics has proven to be a powerful combination. Cheminformatics, which combines the principles of computer science and chemistry, is used to extract chemical information and search compound databases, while the application of AI and ML allows for the identification of potential hit compounds, optimization of synthesis routes, and prediction of drug efficacy and toxicity. This collaborative approach has led to the discovery, preclinical evaluations and approval of over 70 drugs in recent years. To aid researchers in the pursuit of new drugs, this article presents a comprehensive list of databases, datasets, predictive and generative models, scoring functions and web platforms that have been launched between 2021 and 2022. These resources provide a wealth of information and tools for computer-assisted drug development, and are a valuable asset for those working in the field of cheminformatics. Overall, the integration of AI, ML and cheminformatics has greatly advanced the drug discovery process and continues to hold great potential for the future. As new resources and technologies become available, we can expect to see even more groundbreaking discoveries and advancements in these fields.Communicated by Ramaswamy H. Sarma.

Reinforcement learning-driven exploration of peptide space: accelerating generation of drug-like peptides

Using amino acid residues in peptide generation has solved several key problems, including precise control of amino acid sequence order, customized peptides for property modification, and large-scale peptide synthesis. Proteins contain unknown amino acid residues. Extracting them for the synthesis of drug-like peptides can create novel structures with unique properties, driving drug development. Computer-aided design of novel peptide drug molecules can solve the high-cost and low-efficiency problems in the traditional drug discovery process. Previous studies faced limitations in enhancing the bioactivity and drug-likeness of polypeptide drugs due to less emphasis on the connection relationships in amino acid structures. Thus, we proposed a reinforcement learning-driven generation model based on graph attention mechanisms for peptide generation. By harnessing the advantages of graph attention mechanisms, this model effectively captured the connectivity structures between amino acid residues in peptides. Simultaneously, leveraging reinforcement learning's strength in guiding optimal sequence searches provided a novel approach to peptide design and optimization. This model introduces an actor-critic framework with real-time feedback loops to achieve dynamic balance between attributes, which can customize the generation of multiple peptides for specific targets and enhance the affinity between peptides and targets. Experimental results demonstrate that the generated drug-like peptides meet specified absorption, distribution, metabolism, excretion, and toxicity properties and bioactivity with a success rate of over 90$\%$, thereby significantly accelerating the process of drug-like peptide generation.

Estimating the synthetic accessibility of molecules with building block and reaction-aware SAScore

Synthetic accessibility prediction is a task to estimate how easily a given molecule might be synthesizable in the laboratory, playing a crucial role in computer-aided molecular design. Although synthesis planning programs can determine synthesis routes, their slow processing times make them impractical for large-scale molecule screening. On the other hand, existing rapid synthesis accessibility estimation methods offer speed but typically lack integration with actual synthesis routes and building block information. In this work, we introduce BR-SAScore, an enhanced version of SAScore that integrates the available building block information (B) and reaction knowledge (R) from synthesis planning programs into the scoring process. In particular, we differentiate fragments inherent in building blocks and fragments to be derived from synthesis (reactions) when scoring synthetic accessibility. Compared to existing methods, our experimental findings demonstrate that BR-SAScore offers more accurate and precise identification of a molecule's synthetic accessibility by the synthesis planning program with a fast calculation time. Moreover, we illustrate how BR-SAScore provides chemically interpretable results, aligning with the capability of the synthesis planning program embedded with the same reaction knowledge and available building blocks.Scientific contributionWe introduce BR-SAScore, an extension of SAScore, to estimate the synthetic accessibility of molecules by leveraging known building-block and reactivity information. In our experiments, BR-SAScore shows superior prediction performance on predicting molecule synthetic accessibility compared to previous methods, including SAScore and deep-learning models, while requiring significantly less computation time. In addition, we show that BR-SAScore is able to precisely identify the chemical fragment contributing to the synthetic infeasibility, holding great potential for future molecule synthesizability optimization.

Chemical language modeling with structured state space sequence models

Generative deep learning is reshaping drug design. Chemical language models (CLMs) - which generate molecules in the form of molecular strings - bear particular promise for this endeavor. Here, we introduce a recent deep learning architecture, termed Structured State Space Sequence (S4) model, into de novo drug design. In addition to its unprecedented performance in various fields, S4 has shown remarkable capabilities to learn the global properties of sequences. This aspect is intriguing in chemical language modeling, where complex molecular properties like bioactivity can 'emerge' from separated portions in the molecular string. This observation gives rise to the following question: Can S4 advance chemical language modeling for de novo design? To provide an answer, we systematically benchmark S4 with state-of-the-art CLMs on an array of drug discovery tasks, such as the identification of bioactive compounds, and the design of drug-like molecules and natural products. S4 shows a superior capacity to learn complex molecular properties, while at the same time exploring diverse scaffolds. Finally, when applied prospectively to kinase inhibition, S4 designs eight of out ten molecules that are predicted as highly active by molecular dynamics simulations. Taken together, these findings advocate for the introduction of S4 into chemical language modeling - uncovering its untapped potential in the molecular sciences.

Machine learning in preclinical drug discovery

Drug-discovery and drug-development endeavors are laborious, costly and time consuming. These programs can take upward of 12 years and cost US $2.5 billion, with a failure rate of more than 90%. Machine learning (ML) presents an opportunity to improve the drug-discovery process. Indeed, with the growing abundance of public and private large-scale biological and chemical datasets, ML techniques are becoming well positioned as useful tools that can augment the traditional drug-development process. In this Perspective, we discuss the integration of algorithmic methods throughout the preclinical phases of drug discovery. Specifically, we highlight an array of ML-based efforts, across diverse disease areas, to accelerate initial hit discovery, mechanism-of-action (MOA) elucidation and chemical property optimization. With advances in the application of ML across diverse therapeutic areas, we posit that fully ML-integrated drug-discovery pipelines will define the future of drug-development programs.

Evolutionary Multiobjective Molecule Optimization in an Implicit Chemical Space

Optimization techniques play a pivotal role in advancing drug development, serving as the foundation of numerous generative methods tailored to efficiently design optimized molecules derived from existing lead compounds. However, existing methods often encounter difficulties in generating diverse, novel, and high-property molecules that simultaneously optimize multiple drug properties. To overcome this bottleneck, we propose a multiobjective molecule optimization framework (MOMO). MOMO employs a specially designed Pareto-based multiproperty evaluation strategy at the molecular sequence level to guide the evolutionary search in an implicit chemical space. A comparative analysis of MOMO with five state-of-the-art methods across two benchmark multiproperty molecule optimization tasks reveals that MOMO markedly outperforms them in terms of diversity, novelty, and optimized properties. The practical applicability of MOMO in drug discovery has also been validated on four challenging tasks in the real-world discovery problem. These results suggest that MOMO can provide a useful tool to facilitate molecule optimization problems with multiple properties.

PromptSMILES: prompting for scaffold decoration and fragment linking in chemical language models

SMILES-based generative models are amongst the most robust and successful recent methods used to augment drug design. They are typically used for complete de novo generation, however, scaffold decoration and fragment linking applications are sometimes desirable which requires a different grammar, architecture, training dataset and therefore, re-training of a new model. In this work, we describe a simple procedure to conduct constrained molecule generation with a SMILES-based generative model to extend applicability to scaffold decoration and fragment linking by providing SMILES prompts, without the need for re-training. In combination with reinforcement learning, we show that pre-trained, decoder-only models adapt to these applications quickly and can further optimize molecule generation towards a specified objective. We compare the performance of this approach to a variety of orthogonal approaches and show that performance is comparable or better. For convenience, we provide an easy-to-use python package to facilitate model sampling which can be found on GitHub and the Python Package Index.Scientific contributionThis novel method extends an autoregressive chemical language model to scaffold decoration and fragment linking scenarios. This doesn't require re-training, the use of a bespoke grammar, or curation of a custom dataset, as commonly required by other approaches.

The application of artificial intelligence to accelerate G protein-coupled receptor drug discovery

The application of artificial intelligence (AI) approaches to drug discovery for G protein-coupled receptors (GPCRs) is a rapidly expanding area. Artificial intelligence can be used at multiple stages during the drug discovery process, from aiding our understanding of the fundamental actions of GPCRs to the discovery of new ligand-GPCR interactions or the prediction of clinical responses. Here, we provide an overview of the concepts behind artificial intelligence, including the subfields of machine learning and deep learning. We summarise the published applications of artificial intelligence to different stages of the GPCR drug discovery process. Finally, we reflect on the benefits and limitations of artificial intelligence and share our vision for the exciting potential for further development of applications to aid GPCR drug discovery. In addition to making the drug discovery process "faster, smarter and cheaper," we anticipate that the application of artificial intelligence will create exciting new opportunities for GPCR drug discovery. LINKED ARTICLES: This article is part of a themed issue Therapeutic Targeting of G Protein-Coupled Receptors: hot topics from the Australasian Society of Clinical and Experimental Pharmacologists and Toxicologists 2021 Virtual Annual Scientific Meeting. To view the other articles in this section visit http://onlinelibrary.wiley.com/doi/10.1111/bph.v181.14/issuetoc.

Prediction and Interpretation Microglia Cytotoxicity by Machine Learning

Ameliorating microglia-mediated neuroinflammation is a crucial strategy in developing new drugs for neurodegenerative diseases. Plant compounds are an important screening target for the discovery of drugs for the treatment of neurodegenerative diseases. However, due to the spatial complexity of phytochemicals, it becomes particularly important to evaluate the effectiveness of compounds while avoiding the mixing of cytotoxic substances in the early stages of compound screening. Traditional high-throughput screening methods suffer from high cost and low efficiency. A computational model based on machine learning provides a novel avenue for cytotoxicity determination. In this study, a microglia cytotoxicity classifier was developed using a machine learning approach. First, we proposed a data splitting strategy based on the molecule murcko generic scaffold, under this condition, three machine learning approaches were coupled with three kinds of molecular representation methods to construct microglia cytotoxicity classifier, which were then compared and assessed by the predictive accuracy, balanced accuracy, F1-score, and Matthews Correlation Coefficient. Then, the recursive feature elimination integrated with support vector machine (RFE-SVC) dimension reduction method was introduced to molecular fingerprints with high dimensions to further improve the model performance. Among all the microglial cytotoxicity classifiers, the SVM coupled with ECFP4 fingerprint after feature selection (ECFP4-RFE-SVM) obtained the most accurate classification for the test set (ACC of 0.99, BA of 0.99, F1-score of 0.99, MCC of 0.97). Finally, the Shapley additive explanations (SHAP) method was used in interpreting the microglia cytotoxicity classifier and key substructure smart identified as structural alerts. Experimental results show that ECFP4-RFE-SVM have reliable classification capability for microglia cytotoxicity, and SHAP can not only provide a rational explanation for microglia cytotoxicity predictions, but also offer a guideline for subsequent molecular cytotoxicity modifications.

Augmented Memory: Sample-Efficient Generative Molecular Design with Reinforcement Learning

Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal calls to oracles (computational property predictors). This problem becomes more apparent when using oracles that can provide increased predictive accuracy but impose significant computational cost. Consequently, designing molecules that are optimized for such oracles cannot be achieved under a practical computational budget. Molecular generative models based on simplified molecular-input line-entry system (SMILES) have shown remarkable sample efficiency when coupled with reinforcement learning, as demonstrated in the practical molecular optimization (PMO) benchmark. Here, we first show that experience replay drastically improves the performance of multiple previously proposed algorithms. Next, we propose a novel algorithm called Augmented Memory that combines data augmentation with experience replay. We show that scores obtained from oracle calls can be reused to update the model multiple times. We compare Augmented Memory to previously proposed algorithms and show significantly enhanced sample efficiency in an exploitation task, a drug discovery case study requiring both exploration and exploitation, and a materials design case study optimizing explicitly for quantum-mechanical properties. Our method achieves a new state-of-the-art in sample-efficient de novo molecular design, outperforming all of the previously reported methods. The code is available at https://github.com/schwallergroup/augmented_memory.

Llamol: a dynamic multi-conditional generative transformer for de novo molecular design

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.

t-SMILES: a fragment-based molecular representation framework for de novo ligand design

Effective representation of molecules is a crucial factor affecting the performance of artificial intelligence models. This study introduces a flexible, fragment-based, multiscale molecular representation framework called t-SMILES (tree-based SMILES) with three code algorithms: TSSA (t-SMILES with shared atom), TSDY (t-SMILES with dummy atom but without ID) and TSID (t-SMILES with ID and dummy atom). It describes molecules using SMILES-type strings obtained by performing a breadth-first search on a full binary tree formed from a fragmented molecular graph. Systematic evaluations using JTVAE, BRICS, MMPA, and Scaffold show the feasibility of constructing a multi-code molecular description system, where various descriptions complement each other, enhancing the overall performance. In addition, it can avoid overfitting and achieve higher novelty scores while maintaining reasonable similarity on labeled low-resource datasets, regardless of whether the model is original, data-augmented, or pre-trained then fine-tuned. Furthermore, it significantly outperforms classical SMILES, DeepSMILES, SELFIES and baseline models in goal-directed tasks. And it surpasses state-of-the-art fragment, graph and SMILES based approaches on ChEMBL, Zinc, and QM9.

Unleashing the power of generative AI in drug discovery

Artificial intelligence (AI) is revolutionizing drug discovery by enhancing precision, reducing timelines and costs, and enabling AI-driven computer-aided drug design. This review focuses on recent advancements in deep generative models (DGMs) for de novo drug design, exploring diverse algorithms and their profound impact. It critically analyses the challenges that are intricately interwoven into these technologies, proposing strategies to unlock their full potential. It features case studies of both successes and failures in advancing drugs to clinical trials with AI assistance. Last, it outlines a forward-looking plan for optimizing DGMs in de novo drug design, thereby fostering faster and more cost-effective drug development.

DeLA-DrugSelf: Empowering multi-objective de novo design through SELFIES molecular representation

In this paper, we introduce DeLA-DrugSelf, an upgraded version of DeLA-Drug [J. Chem. Inf. Model. 62 (2022) 1411-1424], which incorporates essential advancements for automated multi-objective de novo design. Unlike its predecessor, which relies on SMILES notation for molecular representation, DeLA-DrugSelf employs a novel and robust molecular representation string named SELFIES (SELF-referencing Embedded String). The generation process in DeLA-DrugSelf not only involves substitutions to the initial string representing the starting query molecule but also incorporates insertions and deletions. This enhancement makes DeLA-DrugSelf significantly more adept at executing data-driven scaffold decoration and lead optimization strategies. Remarkably, DeLA-DrugSelf explicitly addresses the SELFIES-related collapse issue, considering only collapse-free compounds during generation. These compounds undergo a rigorous quality metrics evaluation, highlighting substantial advancements in terms of drug-likeness, uniqueness, and novelty compared to the molecules generated by the previous version of the algorithm. To evaluate the potential of DeLA-DrugSelf as a mutational operator within a genetic algorithm framework for multi-objective optimization, we employed a fitness function based on Pareto dominance. Our objectives focused on target-oriented properties aimed at optimizing known cannabinoid receptor 2 (CB2R) ligands. The results obtained indicate that DeLA-DrugSelf, available as a user-friendly web platform (https://www.ba.ic.cnr.it/softwareic/delaself/), can effectively contribute to the data-driven optimization of starting bioactive molecules based on user-defined parameters.

MolScore: a scoring, evaluation and benchmarking framework for generative models in de novo drug design

Generative models are undergoing rapid research and application to de novo drug design. To facilitate their application and evaluation, we present MolScore. MolScore already contains many drug-design-relevant scoring functions commonly used in benchmarks such as, molecular similarity, molecular docking, predictive models, synthesizability, and more. In addition, providing performance metrics to evaluate generative model performance based on the chemistry generated. With this unification of functionality, MolScore re-implements commonly used benchmarks in the field (such as GuacaMol, MOSES, and MolOpt). Moreover, new benchmarks can be created trivially. We demonstrate this by testing a chemical language model with reinforcement learning on three new tasks of increasing complexity related to the design of 5-HT2a ligands that utilise either molecular descriptors, 266 pre-trained QSAR models, or dual molecular docking. Lastly, MolScore can be integrated into an existing Python script with just three lines of code. This framework is a step towards unifying generative model application and evaluation as applied to drug design for both practitioners and researchers. The framework can be found on GitHub and downloaded directly from the Python Package Index.Scientific ContributionMolScore is an open-source platform to facilitate generative molecular design and evaluation thereof for application in drug design. This platform takes important steps towards unifying existing benchmarks, providing a platform to share new benchmarks, and improves customisation, flexibility and usability for practitioners over existing solutions.

Development of scoring-assisted generative exploration (SAGE) and its application to dual inhibitor design for acetylcholinesterase and monoamine oxidase B

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.

Complementary multi-modality molecular self-supervised learning via non-overlapping masking for property prediction

Self-supervised learning plays an important role in molecular representation learning because labeled molecular data are usually limited in many tasks, such as chemical property prediction and virtual screening. However, most existing molecular pre-training methods focus on one modality of molecular data, and the complementary information of two important modalities, SMILES and graph, is not fully explored. In this study, we propose an effective multi-modality self-supervised learning framework for molecular SMILES and graph. Specifically, SMILES data and graph data are first tokenized so that they can be processed by a unified Transformer-based backbone network, which is trained by a masked reconstruction strategy. In addition, we introduce a specialized non-overlapping masking strategy to encourage fine-grained interaction between these two modalities. Experimental results show that our framework achieves state-of-the-art performance in a series of molecular property prediction tasks, and a detailed ablation study demonstrates efficacy of the multi-modality framework and the masking strategy.

Streamlining Computational Fragment-Based Drug Discovery through Evolutionary Optimization Informed by Ligand-Based Virtual Prescreening

Recent advances in computational methods provide the promise of dramatically accelerating drug discovery. While mathematical modeling and machine learning have become vital in predicting drug-target interactions and properties, there is untapped potential in computational drug discovery due to the vast and complex chemical space. This paper builds on our recently published computational fragment-based drug discovery (FBDD) method called fragment databases from screened ligand drug discovery (FDSL-DD). FDSL-DD uses in silico screening to identify ligands from a vast library, fragmenting them while attaching specific attributes based on predicted binding affinity and interaction with the target subdomain. In this paper, we further propose a two-stage optimization method that utilizes the information from prescreening to optimize computational ligand synthesis. We hypothesize that using prescreening information for optimization shrinks the search space and focuses on promising regions, thereby improving the optimization for candidate ligands. The first optimization stage assembles these fragments into larger compounds using genetic algorithms, followed by a second stage of iterative refinement to produce compounds with enhanced bioactivity. To demonstrate broad applicability, the methodology is demonstrated on three diverse protein targets found in human solid cancers, bacterial antimicrobial resistance, and the SARS-CoV-2 virus. Combined, the proposed FDSL-DD and a two-stage optimization approach yield high-affinity ligand candidates more efficiently than other state-of-the-art computational FBDD methods. We further show that a multiobjective optimization method accounting for drug-likeness can still produce potential candidate ligands with a high binding affinity. Overall, the results demonstrate that integrating detailed chemical information with a constrained search framework can markedly optimize the initial drug discovery process, offering a more precise and efficient route to developing new therapeutics.

De novo generation of multi-target compounds using deep generative chemistry

Polypharmacology drugs-compounds that inhibit multiple proteins-have many applications but are difficult to design. To address this challenge we have developed POLYGON, an approach to polypharmacology based on generative reinforcement learning. POLYGON embeds chemical space and iteratively samples it to generate new molecular structures; these are rewarded by the predicted ability to inhibit each of two protein targets and by drug-likeness and ease-of-synthesis. In binding data for >100,000 compounds, POLYGON correctly recognizes polypharmacology interactions with 82.5% accuracy. We subsequently generate de-novo compounds targeting ten pairs of proteins with documented co-dependency. Docking analysis indicates that top structures bind their two targets with low free energies and similar 3D orientations to canonical single-protein inhibitors. We synthesize 32 compounds targeting MEK1 and mTOR, with most yielding >50% reduction in each protein activity and in cell viability when dosed at 1-10 μM. These results support the potential of generative modeling for polypharmacology.

AlvaBuilder: A Software for De Novo Molecular Design

AlvaBuilder is a software tool for de novo molecular design and can be used to generate novel molecules having desirable characteristics. Such characteristics can be defined using a simple step by step graphical interface, and they can be based on molecular descriptors, on predictions of QSAR/QSPR models, and on matching molecular fragments or used to design compounds similar to a given one. The molecules generated are always syntactically valid since they are composed by combining fragments of molecules taken from a training data set chosen by the user. In this paper, we demonstrate how the software can be used to design new compounds for a defined case study. AlvaBuilder is available at https://www.alvascience.com/alvabuilder/.

Deep Generative Models in De Novo Drug Molecule Generation

The discovery of new drugs has important implications for human health. Traditional methods for drug discovery rely on experiments to optimize the structure of lead molecules, which are time-consuming and high-cost. Recently, artificial intelligence has exhibited promising and efficient performance for drug-like molecule generation. In particular, deep generative models achieve great success in de novo generation of drug-like molecules with desired properties, showing massive potential for novel drug discovery. In this study, we review the recent progress of molecule generation using deep generative models, mainly focusing on molecule representations, public databases, data processing tools, and advanced artificial intelligence based molecule generation frameworks. In particular, we present a comprehensive comparison of state-of-the-art deep generative models for molecule generation and a summary of commonly used molecular design strategies. We identify research gaps and challenges of molecule generation such as the need for better databases, missing 3D information in molecular representation, and the lack of high-precision evaluation metrics. We suggest future directions for molecular generation and drug discovery.

Directional multiobjective optimization of metal complexes at the billion-system scale

The discovery of transition metal complexes (TMCs) with optimal properties requires large ligand libraries and efficient multiobjective optimization algorithms. Here we provide the tmQMg-L library, containing 30k diverse and synthesizable ligands with robustly assigned charges and metal coordination modes. tmQMg-L enabled the generation of 1.37 million palladium TMCs, which were used to develop and benchmark the Pareto-Lighthouse multiobjective genetic algorithm (PL-MOGA). With fine control over aim and scope, this algorithm maximized both the polarizability and highest occupied molecular orbital-lowest unoccupied molecular orbital gap of the TMCs within selected regions of the Pareto front, without requiring prior knowledge on the objective limits. Instead of genetic operations on small ligand fragments, the PL-MOGA did whole-ligand mutation and crossover operations, which in chemical spaces containing billions of systems, yielded thousands of highly diverse TMCs in an interpretable manner.

Chemoinformatic approaches for navigating large chemical spaces

INTRODUCTION

Large chemical spaces (CSs) include traditional large compound collections, combinatorial libraries covering billions to trillions of molecules, DNA-encoded chemical libraries comprising complete combinatorial CSs in a single mixture, and virtual CSs explored by generative models. The diverse nature of these types of CSs require different chemoinformatic approaches for navigation.

AREAS COVERED

An overview of different types of large CSs is provided. Molecular representations and similarity metrics suitable for large CS exploration are discussed. A summary of navigation of CSs in generative models is provided. Methods for characterizing and comparing CSs are discussed.

EXPERT OPINION

The size of large CSs might restrict navigation to specialized algorithms and limit it to considering neighborhoods of structurally similar molecules. Efficient navigation of large CSs not only requires methods that scale with size but also requires smart approaches that focus on better but not necessarily larger molecule selections. Deep generative models aim to provide such approaches by implicitly learning features relevant for targeted biological properties. It is unclear whether these models can fulfill this ideal as validation is difficult as long as the covered CSs remain mainly virtual without experimental verification.

GLDM: hit molecule generation with constrained graph latent diffusion model

Discovering hit molecules with desired biological activity in a directed manner is a promising but profound task in computer-aided drug discovery. Inspired by recent generative AI approaches, particularly Diffusion Models (DM), we propose Graph Latent Diffusion Model (GLDM)-a latent DM that preserves both the effectiveness of autoencoders of compressing complex chemical data and the DM's capabilities of generating novel molecules. Specifically, we first develop an autoencoder to encode the molecular data into low-dimensional latent representations and then train the DM on the latent space to generate molecules inducing targeted biological activity defined by gene expression profiles. Manipulating DM in the latent space rather than the input space avoids complicated operations to map molecule decomposition and reconstruction to diffusion processes, and thus improves training efficiency. Experiments show that GLDM not only achieves outstanding performances on molecular generation benchmarks, but also generates samples with optimal chemical properties and potentials to induce desired biological activity.

The AI-driven Drug Design (AIDD) platform: an interactive multi-parameter optimization system integrating molecular evolution with physiologically based pharmacokinetic simulations

Computer-aided drug design has advanced rapidly in recent years, and multiple instances of in silico designed molecules advancing to the clinic have demonstrated the contribution of this field to medicine. Properly designed and implemented platforms can drastically reduce drug development timelines and costs. While such efforts were initially focused primarily on target affinity/activity, it is now appreciated that other parameters are equally important in the successful development of a drug and its progression to the clinic, including pharmacokinetic properties as well as absorption, distribution, metabolic, excretion and toxicological (ADMET) properties. In the last decade, several programs have been developed that incorporate these properties into the drug design and optimization process and to varying degrees, allowing for multi-parameter optimization. Here, we introduce the Artificial Intelligence-driven Drug Design (AIDD) platform, which automates the drug design process by integrating high-throughput physiologically-based pharmacokinetic simulations (powered by GastroPlus) and ADMET predictions (powered by ADMET Predictor) with an advanced evolutionary algorithm that is quite different than current generative models. AIDD uses these and other estimates in iteratively performing multi-objective optimizations to produce novel molecules that are active and lead-like. Here we describe the AIDD workflow and details of the methodologies involved therein. We use a dataset of triazolopyrimidine inhibitors of the dihydroorotate dehydrogenase from Plasmodium falciparum to illustrate how AIDD generates novel sets of molecules.

Gaussian Process Regression-Based Near-Infrared d-Luciferin Analogue Design Using Mutation-Controlled Graph-Based Genetic Algorithm

Molecular discovery is central to the field of chemical informatics. Although optimization approaches have been developed that target-specific molecular properties in combination with machine learning techniques, optimization using databases of limited size is challenging for efficient molecular design. We present a molecular design method with a Gaussian process regression model and a graph-based genetic algorithm (GB-GA) from a data set comprising a small number of compounds by introducing mutation probability control in the genetic algorithm to enhance the optimization capability and speed up the convergence to the optimal solution. In addition, we propose reducing the number of parameters in the conventional GB-GA focusing on efficient molecular design from a small database. We generated a target-specific database by combining active learning and iterative design in the evolutionary methodologies and chose Gaussian process regression as the prediction model for molecular properties. We show that the proposed scheme is more efficient for optimization toward the target properties from goal-directed benchmarks with several drug-like molecules compared to the conventional GB-GA method. Finally, we provide a demonstration whereby we designed D-luciferin analogues with near-infrared fluorescence for bioimaging, which is desirable for effective in vivo light sources, from a small-size data set.

PoseBusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences

The last few years have seen the development of numerous deep learning-based protein-ligand docking methods. They offer huge promise in terms of speed and accuracy. However, despite claims of state-of-the-art performance in terms of crystallographic root-mean-square deviation (RMSD), upon closer inspection, it has become apparent that they often produce physically implausible molecular structures. It is therefore not sufficient to evaluate these methods solely by RMSD to a native binding mode. It is vital, particularly for deep learning-based methods, that they are also evaluated on steric and energetic criteria. We present PoseBusters, a Python package that performs a series of standard quality checks using the well-established cheminformatics toolkit RDKit. The PoseBusters test suite validates chemical and geometric consistency of a ligand including its stereochemistry, and the physical plausibility of intra- and intermolecular measurements such as the planarity of aromatic rings, standard bond lengths, and protein-ligand clashes. Only methods that both pass these checks and predict native-like binding modes should be classed as having "state-of-the-art" performance. We use PoseBusters to compare five deep learning-based docking methods (DeepDock, DiffDock, EquiBind, TankBind, and Uni-Mol) and two well-established standard docking methods (AutoDock Vina and CCDC Gold) with and without an additional post-prediction energy minimisation step using a molecular mechanics force field. We show that both in terms of physical plausibility and the ability to generalise to examples that are distinct from the training data, no deep learning-based method yet outperforms classical docking tools. In addition, we find that molecular mechanics force fields contain docking-relevant physics missing from deep-learning methods. PoseBusters allows practitioners to assess docking and molecular generation methods and may inspire new inductive biases still required to improve deep learning-based methods, which will help drive the development of more accurate and more realistic predictions.

Genetic Algorithm-Based Receptor Ligand: A Genetic Algorithm-Guided Generative Model to Boost the Novelty and Drug-Likeness of Molecules in a Sampling Chemical Space

Deep learning-based de novo molecular design has recently gained significant attention. While numerous DL-based generative models have been successfully developed for designing novel compounds, the majority of the generated molecules lack sufficiently novel scaffolds or high drug-like profiles. The aforementioned issues may not be fully captured by commonly used metrics for the assessment of molecular generative models, such as novelty, diversity, and quantitative estimation of the drug-likeness score. To address these limitations, we proposed a genetic algorithm-guided generative model called GARel (genetic algorithm-based receptor-ligand interaction generator), a novel framework for training a DL-based generative model to produce drug-like molecules with novel scaffolds. To efficiently train the GARel model, we utilized dense net to update the parameters based on molecules with novel scaffolds and drug-like features. To demonstrate the capability of the GARel model, we used it to design inhibitors for three targets: AA2AR, EGFR, and SARS-Cov2. The results indicate that GARel-generated molecules feature more diverse and novel scaffolds and possess more desirable physicochemical properties and favorable docking scores. Compared with other generative models, GARel makes significant progress in balancing novelty and drug-likeness, providing a promising direction for the further development of DL-based de novo design methodology with potential impacts on drug discovery.

Reinvent 4: Modern AI-driven generative molecule design

REINVENT 4 is a modern open-source generative AI framework for the design of small molecules. The software utilizes recurrent neural networks and transformer architectures to drive molecule generation. These generators are seamlessly embedded within the general machine learning optimization algorithms, transfer learning, reinforcement learning and curriculum learning. REINVENT 4 enables and facilitates de novo design, R-group replacement, library design, linker design, scaffold hopping and molecule optimization. This contribution gives an overview of the software and describes its design. Algorithms and their applications are discussed in detail. REINVENT 4 is a command line tool which reads a user configuration in either TOML or JSON format. The aim of this release is to provide reference implementations for some of the most common algorithms in AI based molecule generation. An additional goal with the release is to create a framework for education and future innovation in AI based molecular design. The software is available from https://github.com/MolecularAI/REINVENT4 and released under the permissive Apache 2.0 license. Scientific contribution. The software provides an open-source reference implementation for generative molecular design where the software is also being used in production to support in-house drug discovery projects. The publication of the most common machine learning algorithms in one code and full documentation thereof will increase transparency of AI and foster innovation, collaboration and education.

Molecule auto-correction to facilitate molecular design

Ensuring that computationally designed molecules are chemically reasonable is at best cumbersome. We present a molecule correction algorithm that morphs invalid molecular graphs into structurally related valid analogs. The algorithm is implemented as a tree search, guided by a set of policies to minimize its cost. We showcase how the algorithm can be applied to molecular design, either as a post-processing step or as an integral part of molecule generators.

ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generation

The incredible capabilities of generative artificial intelligence models have inevitably led to their application in the domain of drug discovery. Within this domain, the vastness of chemical space motivates the development of more efficient methods for identifying regions with molecules that exhibit desired characteristics. In this work, we present a computationally efficient active learning methodology and demonstrate its applicability to targeted molecular generation. When applied to c-Abl kinase, a protein with FDA-approved small-molecule inhibitors, the model learns to generate molecules similar to the inhibitors without prior knowledge of their existence and even reproduces two of them exactly. We also show that the methodology is effective for a protein without any commercially available small-molecule inhibitors, the HNH domain of the CRISPR-associated protein 9 (Cas9) enzyme. To facilitate implementation and reproducibility, we made all of our software available through the open-source ChemSpaceAL Python package.

Generative artificial intelligence in drug discovery: basic framework, recent advances, challenges, and opportunities

There are two main ways to discover or design small drug molecules. The first involves fine-tuning existing molecules or commercially successful drugs through quantitative structure-activity relationships and virtual screening. The second approach involves generating new molecules through de novo drug design or inverse quantitative structure-activity relationship. Both methods aim to get a drug molecule with the best pharmacokinetic and pharmacodynamic profiles. However, bringing a new drug to market is an expensive and time-consuming endeavor, with the average cost being estimated at around $2.5 billion. One of the biggest challenges is screening the vast number of potential drug candidates to find one that is both safe and effective. The development of artificial intelligence in recent years has been phenomenal, ushering in a revolution in many fields. The field of pharmaceutical sciences has also significantly benefited from multiple applications of artificial intelligence, especially drug discovery projects. Artificial intelligence models are finding use in molecular property prediction, molecule generation, virtual screening, synthesis planning, repurposing, among others. Lately, generative artificial intelligence has gained popularity across domains for its ability to generate entirely new data, such as images, sentences, audios, videos, novel chemical molecules, etc. Generative artificial intelligence has also delivered promising results in drug discovery and development. This review article delves into the fundamentals and framework of various generative artificial intelligence models in the context of drug discovery via de novo drug design approach. Various basic and advanced models have been discussed, along with their recent applications. The review also explores recent examples and advances in the generative artificial intelligence approach, as well as the challenges and ongoing efforts to fully harness the potential of generative artificial intelligence in generating novel drug molecules in a faster and more affordable manner. Some clinical-level assets generated form generative artificial intelligence have also been discussed in this review to show the ever-increasing application of artificial intelligence in drug discovery through commercial partnerships.

De Novo Drug Design Using Transformer-Based Machine Translation and Reinforcement Learning of an Adaptive Monte Carlo Tree Search

The discovery of novel therapeutic compounds through de novo drug design represents a critical challenge in the field of pharmaceutical research. Traditional drug discovery approaches are often resource intensive and time consuming, leading researchers to explore innovative methods that harness the power of deep learning and reinforcement learning techniques. Here, we introduce a novel drug design approach called drugAI that leverages the Encoder-Decoder Transformer architecture in tandem with Reinforcement Learning via a Monte Carlo Tree Search (RL-MCTS) to expedite the process of drug discovery while ensuring the production of valid small molecules with drug-like characteristics and strong binding affinities towards their targets. We successfully integrated the Encoder-Decoder Transformer architecture, which generates molecular structures (drugs) from scratch with the RL-MCTS, serving as a reinforcement learning framework. The RL-MCTS combines the exploitation and exploration capabilities of a Monte Carlo Tree Search with the machine translation of a transformer-based Encoder-Decoder model. This dynamic approach allows the model to iteratively refine its drug candidate generation process, ensuring that the generated molecules adhere to essential physicochemical and biological constraints and effectively bind to their targets. The results from drugAI showcase the effectiveness of the proposed approach across various benchmark datasets, demonstrating a significant improvement in both the validity and drug-likeness of the generated compounds, compared to two existing benchmark methods. Moreover, drugAI ensures that the generated molecules exhibit strong binding affinities to their respective targets. In summary, this research highlights the real-world applications of drugAI in drug discovery pipelines, potentially accelerating the identification of promising drug candidates for a wide range of diseases.

RediscMol: Benchmarking Molecular Generation Models in Biological Properties

Deep learning-based molecular generative models have garnered emerging attention for their capability to generate molecules with novel structures and desired physicochemical properties. However, the evaluation of these models, particularly in a biological context, remains insufficient. To address the limitations of existing metrics and emulate practical application scenarios, we construct the RediscMol benchmark that comprises active molecules extracted from 5 kinase and 3 GPCR data sets. A set of rediscovery- and similarity-related metrics are introduced to assess the performance of 8 representative generative models (CharRNN, VAE, Reinvent, AAE, ORGAN, RNNAttn, TransVAE, and GraphAF). Our findings based on the RediscMol benchmark differ from those of previous evaluations. CharRNN, VAE, and Reinvent exhibit a greater ability to reproduce known active molecules, while RNNAttn, TransVAE, and GraphAF struggle in this aspect despite their notable performance on commonly used distribution-learning metrics. Our evaluation framework may provide valuable guidance for advancing generative models in real-world drug design scenarios.