Navigating Chemical Space by Interfacing Generative Artificial Intelligence and Molecular Docking

HIt Discovery using docking ENriched by GEnerative Modeling (HIDDEN GEM): A novel computational workflow for accelerated virtual screening of ultra-large chemical libraries

Recent rapid expansion of make-on-demand, purchasable, chemical libraries comprising dozens of billions or even trillions of molecules has challenged the efficient application of traditional structure-based virtual screening methods that rely on molecular docking. We present a novel computational methodology termed HIDDEN GEM (HIt Discovery using Docking ENriched by GEnerative Modeling) that greatly accelerates virtual screening. This workflow uniquely integrates machine learning, generative chemistry, massive chemical similarity searching and molecular docking of small, selected libraries in the beginning and the end of the workflow. For each target, HIDDEN GEM nominates a small number of top-scoring virtual hits prioritized from ultra-large chemical libraries. We have benchmarked HIDDEN GEM by conducting virtual screening campaigns for 16 diverse protein targets using Enamine REAL Space library comprising 37 billion molecules. We show that HIDDEN GEM yields the highest enrichment factors as compared to state of the art accelerated virtual screening methods, while requiring the least computational resources. HIDDEN GEM can be executed with any docking software and employed by users with limited computational resources.

Low-Data Drug Design with Few-Shot Generative Domain Adaptation

Developing new drugs for emerging diseases, such as COVID-19, is crucial for promoting public health. In recent years, the application of artificial intelligence (AI) has significantly advanced drug discovery pipelines. Generative models, such as generative adversarial networks (GANs), exhibit the potential for discovering novel drug molecules by relying on a vast number of training samples. However, for new diseases, only a few samples are typically available, posing a significant challenge to learning a generative model that produces both high-quality and diverse molecules under limited supervision. To address this low-data drug generation issue, we propose a novel molecule generative domain adaptation paradigm (Mol-GenDA), which transfers a pre-trained GAN on a large-scale drug molecule dataset to a new disease domain using only a few references. Specifically, we introduce a molecule adaptor into the GAN generator during the fine tuning, allowing the generator to reuse prior knowledge learned in pre-training to the greatest extent and maintain the quality and diversity of the generated molecules. Comprehensive downstream experiments demonstrate that Mol-GenDA can produce high-quality and diverse drug candidates. In summary, the proposed approach offers a promising solution to expedite drug discovery for new diseases, which could lead to the timely development of effective drugs to combat emerging outbreaks.

Integrating structure-based approaches in generative molecular design

Generative molecular design for drug discovery and development has seen a recent resurgence promising to improve the efficiency of the design-make-test-analyse cycle; by computationally exploring much larger chemical spaces than traditional virtual screening techniques. However, most generative models thus far have only utilized small-molecule information to train and condition de novo molecule generators. Here, we instead focus on recent approaches that incorporate protein structure into de novo molecule optimization in an attempt to maximize the predicted on-target binding affinity of generated molecules. We summarize these structure integration principles into either distribution learning or goal-directed optimization and for each case whether the approach is protein structure-explicit or implicit with respect to the generative model. We discuss recent approaches in the context of this categorization and provide our perspective on the future direction of the field.

Docking-based generative approaches in the search for new drug candidates

Despite the popularity of virtual screening (VS) of existing compound libraries, the search for new potential drug candidates also takes advantage of generative protocols, where new compound suggestions are enumerated using various algorithms. To increase the activity potency of generative approaches, they have recently been coupled with molecular docking, a leading methodology of structure-based drug design (SBDD). In this review, we summarize progress since docking-based generative models emerged. We propose a new taxonomy for these methods and discuss their importance for the field of computer-aided drug design (CADD). In addition, we discuss the most promising directions for the further development of generative protocols coupled with docking.

PETrans: De Novo Drug Design with Protein-Specific Encoding Based on Transfer Learning

Recent years have seen tremendous success in the design of novel drug molecules through deep generative models. Nevertheless, existing methods only generate drug-like molecules, which require additional structural optimization to be developed into actual drugs. In this study, a deep learning method for generating target-specific ligands was proposed. This method is useful when the dataset for target-specific ligands is limited. Deep learning methods can extract and learn features (representations) in a data-driven way with little or no human participation. Generative pretraining (GPT) was used to extract the contextual features of the molecule. Three different protein-encoding methods were used to extract the physicochemical properties and amino acid information of the target protein. Protein-encoding and molecular sequence information are combined to guide molecule generation. Transfer learning was used to fine-tune the pretrained model to generate molecules with better binding ability to the target protein. The model was validated using three different targets. The docking results show that our model is capable of generating new molecules with higher docking scores for the target proteins.

Beyond sequence: Structure-based machine learning

Recent breakthroughs in protein structure prediction demarcate the start of a new era in structural bioinformatics. Combined with various advances in experimental structure determination and the uninterrupted pace at which new structures are published, this promises an age in which protein structure information is as prevalent and ubiquitous as sequence. Machine learning in protein bioinformatics has been dominated by sequence-based methods, but this is now changing to make use of the deluge of rich structural information as input. Machine learning methods making use of structures are scattered across literature and cover a number of different applications and scopes; while some try to address questions and tasks within a single protein family, others aim to capture characteristics across all available proteins. In this review, we look at the variety of structure-based machine learning approaches, how structures can be used as input, and typical applications of these approaches in protein biology. We also discuss current challenges and opportunities in this all-important and increasingly popular field.

Optimizing interactions to protein binding sites by integrating docking-scoring strategies into generative AI methods

The identification and optimization of promising lead molecules is essential for drug discovery. Recently, artificial intelligence (AI) based generative methods provided complementary approaches for generating molecules under specific design constraints of relevance in drug design. The goal of our study is to incorporate protein 3D information directly into generative design by flexible docking plus an adapted protein-ligand scoring function, thereby moving towards automated structure-based design. First, the protein-ligand scoring function RFXscore integrating individual scoring terms, ligand descriptors, and combined terms was derived using the PDBbind database and internal data. Next, design results for different workflows are compared to solely ligand-based reward schemes. Our newly proposed, optimal workflow for structure-based generative design is shown to produce promising results, especially for those exploration scenarios, where diverse structures fitting to a protein binding site are requested. Best results are obtained using docking followed by RFXscore, while, depending on the exact application scenario, it was also found useful to combine this approach with other metrics that bias structure generation into "drug-like" chemical space, such as target-activity machine learning models, respectively.

Augmented Hill-Climb increases reinforcement learning efficiency for language-based de novo molecule generation

A plethora of AI-based techniques now exists to conduct de novo molecule generation that can devise molecules conditioned towards a particular endpoint in the context of drug design. One popular approach is using reinforcement learning to update a recurrent neural network or language-based de novo molecule generator. However, reinforcement learning can be inefficient, sometimes requiring up to 105 molecules to be sampled to optimize more complex objectives, which poses a limitation when using computationally expensive scoring functions like docking or computer-aided synthesis planning models. In this work, we propose a reinforcement learning strategy called Augmented Hill-Climb based on a simple, hypothesis-driven hybrid between REINVENT and Hill-Climb that improves sample-efficiency by addressing the limitations of both currently used strategies. We compare its ability to optimize several docking tasks with REINVENT and benchmark this strategy against other commonly used reinforcement learning strategies including REINFORCE, REINVENT (version 1 and 2), Hill-Climb and best agent reminder. We find that optimization ability is improved ~ 1.5-fold and sample-efficiency is improved ~ 45-fold compared to REINVENT while still delivering appealing chemistry as output. Diversity filters were used, and their parameters were tuned to overcome observed failure modes that take advantage of certain diversity filter configurations. We find that Augmented Hill-Climb outperforms the other reinforcement learning strategies used on six tasks, especially in the early stages of training or for more difficult objectives. Lastly, we show improved performance not only on recurrent neural networks but also on a reinforcement learning stabilized transformer architecture. Overall, we show that Augmented Hill-Climb improves sample-efficiency for language-based de novo molecule generation conditioning via reinforcement learning, compared to the current state-of-the-art. This makes more computationally expensive scoring functions, such as docking, more accessible on a relevant timescale.

Machine learning, artificial intelligence, and chemistry: how smart algorithms are reshaping simulation and the laboratory

Machine learning and artificial intelligence are increasingly gaining in prominence through image analysis, language processing, and automation, to name a few applications. Machine learning is also making profound changes in chemistry. From revisiting decades-old analytical techniques for the purpose of creating better calibration curves, to assisting and accelerating traditional in silico simulations, to automating entire scientific workflows, to being used as an approach to deduce underlying physics of unexplained chemical phenomena, machine learning and artificial intelligence are reshaping chemistry, accelerating scientific discovery, and yielding new insights. This review provides an overview of machine learning and artificial intelligence from a chemist’s perspective and focuses on a number of examples of the use of these approaches in computational chemistry and in the laboratory.

Molecular Screening and Toxicity Estimation of 260,000 Perfluoroalkyl and Polyfluoroalkyl Substances (PFASs) through Machine Learning

Perfluoroalkyl and polyfluoroalkyl substances (PFASs) are a class of chemicals widely used in industrial applications due to their exceptional properties and stability. However, they do not readily degrade in the environment and are linked to contamination and adverse health effects in humans and wildlife. To find alternatives for the most commonly used PFAS molecules that maintain their desirable chemical properties but are not adverse to biological lifeforms, a novel approach based upon machine learning is utilized. The machine learning model is trained on an existing set of PFAS molecules to generate over 260,000 novel PFAS molecules, which we dub PFAS-AI-Gen. Using molecular descriptors with known relationships to toxicity and industrial suitability followed by molecular docking and molecular dynamics simulations, this set of molecules is screened. In this manner, increasingly complex calculations are performed only for candidate molecules that are most likely to yield the desired properties of low binding affinity toward two selected protein receptors, the human pregnane x receptor (hPXR) and peroxisome proliferator-activated receptor γ (PPAR-γ), and high industrial suitability, defined by critical micelle concentration (CMC). The selection criteria of low binding affinity and high industrial suitability are relative to the popular PFAS alternative GenX. hPXR and PPAR-γ are selected as they are PFAS targets and facilitate a variety of functions, such as drug metabolism and glucose regulation, respectively. Through this approach, 22 promising new PFAS substitutes that may warrant experimental investigation are identified. This integrated approach of molecular screening and toxicity estimation may be applicable to other chemical classes.

Collaborative Approach between Explainable Artificial Intelligence and Simplified Chemical Interactions to Explore Active Ligands for Cyclin-Dependent Kinase 2

To improve virtual screening for drug discovery, we present a collaborative approach between explainable artificial intelligence (AI) and simplified chemical interaction scores to efficiently search for active ligands bound to the target receptor. In particular, we focus on cyclin-dependent kinase 2 (CDK2), which is well known as a cancer target protein. Docking simulation alone is insufficient to distinguish active ligands from decoy molecules. To identify active ligands, in this paper, machine learning is employed together with scoring functions that simplify the screened Coulomb and Lennard-Jones interactions between the ligands and residues of the target receptor. We demonstrate that these simplified interaction scores can significantly improve the classification ability of machine learning models. We also demonstrate that explainable AI together with the simplified scoring method can highlight the important residues of CDK2 for recognizing active ligands.