Lean-Docking: Exploiting Ligands' Predicted Docking Scores to Accelerate Molecular Docking

Emerging structure-based computational methods to screen the exploding accessible chemical space

Structure-based virtual screening can be a valuable approach to computationally select hit candidates based on their predicted interaction with a protein of interest. The recent explosion in the size of chemical libraries increases the chances of hitting high-quality compounds during virtual screening exercises but also poses new challenges as the number of chemically accessible molecules grows faster than the computing power necessary to screen them. We review here two novel approaches rapidly gaining in popularity to address this problem: machine learning-accelerated and synthon-based library screening. We summarize the results from seminal proof-of-concept studies, highlight the latest developments, and discuss limitations and future directions.

Accelerating Molecular Docking using Machine Learning Methods

Virtual screening (VS) is one of the well-established approaches in drug discovery which speeds up the search for a bioactive molecule and, reduces costs and efforts associated with experiments. VS helps to narrow down the search space of chemical space and allows selecting fewer and more probable candidate compounds for experimental testing. Docking calculations are one of the commonly used and highly appreciated structure-based drug discovery methods. Databases for chemical structures of small molecules have been growing rapidly. However, at the moment virtual screening of large libraries via docking is not very common. In this work, we aim to accelerate docking studies by predicting docking scores without explicitly performing docking calculations. We experimented with an attention based long short-term memory (LSTM) neural network for an efficient prediction of docking scores as well as other machine learning models such as XGBoost. By using docking scores of a small number of ligands we trained our models and predicted docking scores of a few million molecules. Specifically, we tested our approaches on 11 datasets that were produced from in-house drug discovery studies. On average, by training models using only 7000 molecules we predicted docking scores of approximately 3.8 million molecules with R2 (coefficient of determination) of 0.77 and Spearman rank correlation coefficient of 0.85. We designed the system with ease of use in mind. All the user needs to provide is a csv file containing SMILES and their respective docking scores, the system then outputs a model that the user can use for the prediction of docking score for a new molecule.

Regression-Based Active Learning for Accessible Acceleration of Ultra-Large Library Docking

Structure-based drug discovery is a process for both hit finding and optimization that relies on a validated three-dimensional model of a target biomolecule, used to rationalize the structure-function relationship for this particular target. An ultralarge virtual screening approach has emerged recently for rapid discovery of high-affinity hit compounds, but it requires substantial computational resources. This study shows that active learning with simple linear regression models can accelerate virtual screening, retrieving up to 90% of the top-1% of the docking hit list after docking just 10% of the ligands. The results demonstrate that it is unnecessary to use complex models, such as deep learning approaches, to predict the imprecise results of ligand docking with a low sampling depth. Furthermore, we explore active learning meta-parameters and find that constant batch size models with a simple ensembling method provide the best ligand retrieval rate. Finally, our approach is validated on the ultralarge size virtual screening data set, retrieving 70% of the top-0.05% of ligands after screening only 2% of the library. Altogether, this work provides a computationally accessible approach for accelerated virtual screening that can serve as a blueprint for the future design of low-compute agents for exploration of the chemical space via large-scale accelerated docking. With recent breakthroughs in protein structure prediction, this method can significantly increase accessibility for the academic community and aid in the rapid discovery of high-affinity hit compounds for various targets.

Protein Structure-Based Organic Chemistry-Driven Ligand Design from Ultralarge Chemical Spaces

Ultralarge chemical spaces describing several billion compounds are revolutionizing hit identification in early drug discovery. Because of their size, such chemical spaces cannot be fully enumerated and require ad-hoc computational tools to navigate them and pick potentially interesting hits. We here propose a structure-based approach to ultralarge chemical space screening in which commercial chemical reagents are first docked to the target of interest and then directly connected according to organic chemistry and topological rules, to enumerate drug-like compounds under three-dimensional constraints of the target. When applied to bespoke chemical spaces of different sizes and chemical complexity targeting two receptors of pharmaceutical interest (estrogen β receptor, dopamine D3 receptor), the computational method was able to quickly enumerate hits that were either known ligands (or very close analogs) of targeted receptors as well as chemically novel candidates that could be experimentally confirmed by in vitro binding assays. The proposed approach is generic, can be applied to any docking algorithm, and requires few computational resources to prioritize easily synthesizable hits from billion-sized chemical spaces.

Benchmarking Active Learning Protocols for Ligand-Binding Affinity Prediction

Active learning (AL) has become a powerful tool in computational drug discovery, enabling the identification of top binders from vast molecular libraries. To design a robust AL protocol, it is important to understand the influence of AL parameters, as well as the features of the data sets on the outcomes. We use four affinity data sets for different targets (TYK2, USP7, D2R, Mpro) to systematically evaluate the performance of machine learning models [Gaussian process (GP) model and Chemprop model], sample selection protocols, and the batch size based on metrics describing the overall predictive power of the model (R2, Spearman rank, root-mean-square error) as well as the accurate identification of top 2%/5% binders (Recall, F1 score). Both models have a comparable Recall of top binders on large data sets, but the GP model surpasses the Chemprop model when training data are sparse. A larger initial batch size, especially on diverse data sets, increased the Recall of both models as well as overall correlation metrics. However, for subsequent cycles, smaller batch sizes of 20 or 30 compounds proved to be desirable. Furthermore, adding artificial Gaussian noise to the data up to a certain threshold still allowed the model to identify clusters with top-scoring compounds. However, excessive noise (<1σ) did impact the model's predictive and exploitative capabilities.

Large-Scale Pretraining Improves Sample Efficiency of Active Learning-Based Virtual Screening

Virtual screening of large compound libraries to identify potential hit candidates is one of the earliest steps in drug discovery. As the size of commercially available compound collections grows exponentially to the scale of billions, active learning and Bayesian optimization have recently been proven as effective methods of narrowing down the search space. An essential component of those methods is a surrogate machine learning model that predicts the desired properties of compounds. An accurate model can achieve high sample efficiency by finding hits with only a fraction of the entire library being virtually screened. In this study, we examined the performance of a pretrained transformer-based language model and graph neural network in a Bayesian optimization active learning framework. The best pretrained model identifies 58.97% of the top-50,000 compounds after screening only 0.6% of an ultralarge library containing 99.5 million compounds, improving 8% over the previous state-of-the-art baseline. Through extensive benchmarks, we show that the superior performance of pretrained models persists in both structure-based and ligand-based drug discovery. Pretrained models can serve as a boost to the accuracy and sample efficiency of active learning-based virtual screening.

Banxia-Shengjiang drug pair inhibits gastric cancer development and progression by improving body immunity

To investigate the mechanism of action of Banxia-Shengjiang drug pair on the inhibition of gastric cancer (GC) using network pharmacology and bioinformatics techniques. The action targets of the Banxia (Pinellia ternata (Thunb.) Makino) -Shengjiang (Zingiber officinale Roscoe) drug pair obtained from the TCMSP database were intersected with differentially expressed genes (DEGs) and GC-related genes, and the intersected genes were analyzed for pathway enrichment to identify the signaling pathways and core target genes. Subsequently, the core target genes were analyzed for clinical relevance gene mutation analysis, methylation analysis, immune infiltration analysis and immune cell analysis. Finally, by constructing the PPI network of hub genes and corresponding active ingredients, the key active ingredients of the Banxia-Shengjiang drug pair were screened for molecular docking with the hub genes. In this study, a total of 557 target genes of Banxia-Shengjiang pairs, 7754 GC-related genes and 1799 DEGs in GC were screened. Five hub genes were screened, which were PTGS2, MMP9, PPARG, MMP2, and CXCR4. The pathway enrichment analyses showed that the intersecting genes were associated with RAS/MAPK signaling pathway. In addition, the clinical correlation analysis showed that hub genes were differentially expressed in GC and was closely associated with immune infiltration and immunotherapy. The results of single nucleotide variation (SNV) and copy number variation (CNV) indicated that mutations in the hub genes were associated with the survival of gastric cancer patients. Finally, the PPI network and molecular docking results showed that PTGS2 and MMP9 were potentially important targets for the inhibition of GC by Banxia-Shengjiang drug pair, while cavidine was an important active ingredient for the inhibition of GC by Banxia-Shengjiang drug pair. Banxia-Shengjiang drug pair may regulate the immune function and inhibit GC by modulating the expression of core target genes such as RAS/MAPK signaling pathway, PTGS2 and MMP9.

Thompson Sampling─An Efficient Method for Searching Ultralarge Synthesis on Demand Databases

Over the last five years, virtual screening of ultralarge synthesis on-demand libraries has emerged as a powerful tool for hit identification in drug discovery programs. As these libraries have grown to tens of billions of molecules, we have reached a point where it is no longer cost-effective to screen every molecule virtually. To address these challenges, several groups have developed heuristic search methods to rapidly identify the best molecules on a virtual screen. This article describes the application of Thompson sampling (TS), an active learning approach that streamlines the virtual screening of large combinatorial libraries by performing a probabilistic search in the reagent space, thereby never requiring the full enumeration of the library. TS is a general technique that can be applied to various virtual screening modalities, including 2D and 3D similarity search, docking, and application of machine-learning models. In an illustrative example, we show that TS can identify more than half of the top 100 molecules from a docking-based virtual screen of 335 million molecules by evaluating 1% of the data set.

Integrating QSAR modelling and deep learning in drug discovery: the emergence of deep QSAR

Quantitative structure-activity relationship (QSAR) modelling, an approach that was introduced 60 years ago, is widely used in computer-aided drug design. In recent years, progress in artificial intelligence techniques, such as deep learning, the rapid growth of databases of molecules for virtual screening and dramatic improvements in computational power have supported the emergence of a new field of QSAR applications that we term 'deep QSAR'. Marking a decade from the pioneering applications of deep QSAR to tasks involved in small-molecule drug discovery, we herein describe key advances in the field, including deep generative and reinforcement learning approaches in molecular design, deep learning models for synthetic planning and the application of deep QSAR models in structure-based virtual screening. We also reflect on the emergence of quantum computing, which promises to further accelerate deep QSAR applications and the need for open-source and democratized resources to support computer-aided drug design.

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.

Molecular docking and dynamics of a dextranase derived from Penicillium cyclopium CICC-4022

This study aimed to investigate the recognition mechanism of dextranase (PC-Edex) produced by Penicillium cyclopium CICC-4022 on dextran. Whole genome information of P. cyclopium CICC-4022 was obtained through genome sequencing technology. The coding information of PC-Edex was determined based on the annotation of the protein-coding genes using protein databases. The three-dimensional structure of PC-Edex was obtained via homology modelling. The active site and binding free energy between PC-Edex and dextran were calculated by molecular docking and molecular dynamics techniques. The results showed that the total sequence length and GC content of P. cyclopium CICC-4022 were 29,710,801 bp and 47.02 %, respectively. The annotation of protein-encoding genes showed that P. cyclopium CICC-4022 is highly active and has many carbohydrate transport and metabolic functions, and most of its proteases are glycolytic anhydrases. Furthermore, the gene encoding PC-Edex was successfully annotated. Molecular dynamics simulations indicated that van der Waals interaction was the main driving force of interaction. Residues Ile114, Asp115, Tyr332, Lys344, and Gln403 significantly promoted the binding between dextran and PC-Edex. In summary, this study explored the active site catalyzed by PC-Edex based on the binding pattern of PC-Edex and dextran. Therefore, this study provides genomic information on dextranase and data supporting the rational modification and enhancement of PC-Edex.

Biodegradation mechanisms of polycyclic aromatic hydrocarbons: Combination of instrumental analysis and theoretical calculation

Polycyclic aromatic hydrocarbons (PAHs) are a common class of petroleum hydrocarbons, widely encountered in both environment and industrial pollution sources. Owing to their toxicity, environmental persistence, and potential bioaccumulation properties, a mounting interest has been kindled in addressing the remediation of PAHs. Biodegradation is widely employed for the removal and remediation of PAHs due to its low cost, lack of second-contamination and ease of operation. This paper reviews the degradation efficiency of degradation and the underlying mechanisms exhibited by algae, bacteria, and fungi in remediation. Additionally, it delved into the application of modern instrumental analysis techniques and theoretical investigations in the realm of PAH degradation. Advanced instrumental analysis methods such as mass spectrometry provide a powerful tool for identifying intermediates and metabolites throughout the degradation process. Meanwhile, theoretical calculations could guide the optimization of degradation processes by revealing the reaction mechanisms and energy changes in PAH degradation. The combined use of instrumental analysis and theoretical calculations allows for a comprehensive understanding of the degradation mechanisms of PAHs and provides new insights and approaches for the development of environmental remediation technologies.

Improving drug discovery with a hybrid deep generative model using reinforcement learning trained on a Bayesian docking approximation

Generative approaches to molecular design are an area of intense study in recent years as a method to generate new pharmaceuticals with desired properties. Often though, these types of efforts are constrained by limited experimental activity data, resulting in either models that generate molecules with poor performance or models that are overfit and produce close analogs of known molecules. In this paper, we reduce this data dependency for the generation of new chemotypes by incorporating docking scores of known and de novo molecules to expand the applicability domain of the reward function and diversify the compounds generated during reinforcement learning. Our approach employs a deep generative model initially trained using a combination of limited known drug activity and an approximate docking score provided by a second machine learned Bayes regression model, with final evaluation of high scoring compounds by a full docking simulation. This strategy results in molecules with docking scores improved by 10-20% compared to molecules of similar size, while being 130 × faster than a docking only approach on a typical GPU workstation. We also show that the increased docking scores correlate with (1) docking poses with interactions similar to known inhibitors and (2) result in higher MM-GBSA binding energies comparable to the energies of known DDR1 inhibitors, demonstrating that the Bayesian model contains sufficient information for the network to learn to efficiently interact with the binding pocket during reinforcement learning. This outcome shows that the combination of the learned latent molecular representation along with the feature-based docking regression is sufficient for reinforcement learning to infer the relationship between the molecules and the receptor binding site, which suggest that our method can be a powerful tool for the discovery of new chemotypes with potential therapeutic applications.

Engineering All-Round Cellulase for Bioethanol Production

One strategy to decrease both the consumption of crude oil and environmental damage is through the production of bioethanol from biomass. Cellulolytic enzyme stability and enzymatic hydrolysis play important roles in the bioethanol process. However, the gradually increased ethanol concentration often reduces enzyme activity and leads to inactivation, thereby limiting the final ethanol yield. Herein, we employed an optimized Two-Gene Recombination Process (2GenReP) approach to evolve the exemplary cellulase CBHI for practical bioethanol fermentation. Two all-round CBHI variants (named as R2 and R4) were obtained with simultaneously improved ethanol resistance, organic solvent inhibitor tolerance, and enzymolysis stability in simultaneous saccharification and fermentation (SSF). Notably, CBHI R4 had a 7.0- to 34.5-fold enhanced catalytic efficiency (kcat/KM) in the presence/absence of ethanol. Employing the evolved CBHI R2 and R4 in the 1G bioethanol process resulted in up to 10.27% (6.7 g/L) improved ethanol yield (ethanol concentration) than non-cellulase, which was far more beyond than other optimization strategies. Besides bioenergy fields, this transferable protein engineering routine holds the potential to generate all-round enzymes that meet the requirement in biotransformation and bioenergy fields.

The Impact of Supervised Learning Methods in Ultralarge High-Throughput Docking

Structure-based virtual screening methods are, nowadays, one of the key pillars of computational drug discovery. In recent years, a series of studies have reported docking-based virtual screening campaigns of large databases ranging from hundreds to thousands of millions compounds, further identifying novel hits after experimental validation. As these larg-scale efforts are not generally accessible, machine learning-based protocols have emerged to accelerate the identification of virtual hits within an ultralarge chemical space, reaching impressive reductions in computational time. Herein, we illustrate the motivation and the problem behind the screening of large databases, providing an overview of key concepts and essential applications of machine learning-accelerated protocols, specifically concerning supervised learning methods. We also discuss where the field stands with these novel developments, highlighting possible insights for future studies.

Application of Molecular Simulation Methods in Food Science: Status and Prospects

Molecular simulation methods, such as molecular docking, molecular dynamic (MD) simulation, and quantum chemical (QC) calculation, have become popular as characterization and/or virtual screening tools because they can visually display interaction details that in vitro experiments can not capture and quickly screen bioactive compounds from large databases with millions of molecules. Currently, interdisciplinary research has expanded molecular simulation technology from computer aided drug design (CADD) to food science. More food scientists are supporting their hypotheses/results with this technology. To understand better the use of molecular simulation methods, it is necessary to systematically summarize the latest applications and usage trends of molecular simulation methods in the research field of food science. However, this type of review article is rare. To bridge this gap, we have comprehensively summarized the principle, combination usage, and application of molecular simulation methods in food science. We also analyzed the limitations and future trends and offered valuable strategies with the latest technologies to help food scientists use molecular simulation methods.

AI-accelerated protein-ligand docking for SARS-CoV-2 is 100-fold faster with no significant change in detection

Protein-ligand docking is a computational method for identifying drug leads. The method is capable of narrowing a vast library of compounds down to a tractable size for downstream simulation or experimental testing and is widely used in drug discovery. While there has been progress in accelerating scoring of compounds with artificial intelligence, few works have bridged these successes back to the virtual screening community in terms of utility and forward-looking development. We demonstrate the power of high-speed ML models by scoring 1 billion molecules in under a day (50 k predictions per GPU seconds). We showcase a workflow for docking utilizing surrogate AI-based models as a pre-filter to a standard docking workflow. Our workflow is ten times faster at screening a library of compounds than the standard technique, with an error rate less than 0.01% of detecting the underlying best scoring 0.1% of compounds. Our analysis of the speedup explains that another order of magnitude speedup must come from model accuracy rather than computing speed. In order to drive another order of magnitude of acceleration, we share a benchmark dataset consisting of 200 million 3D complex structures and 2D structure scores across a consistent set of 13 million "in-stock" molecules over 15 receptors, or binding sites, across the SARS-CoV-2 proteome. We believe this is strong evidence for the community to begin focusing on improving the accuracy of surrogate models to improve the ability to screen massive compound libraries 100 × or even 1000 × faster than current techniques and reduce missing top hits. The technique outlined aims to be a fast drop-in replacement for docking for screening billion-scale molecular libraries.

A fully differentiable ligand pose optimization framework guided by deep learning and a traditional scoring function

The recently reported machine learning- or deep learning-based scoring functions (SFs) have shown exciting performance in predicting protein-ligand binding affinities with fruitful application prospects. However, the differentiation between highly similar ligand conformations, including the native binding pose (the global energy minimum state), remains challenging that could greatly enhance the docking. In this work, we propose a fully differentiable, end-to-end framework for ligand pose optimization based on a hybrid SF called DeepRMSD+Vina combined with a multi-layer perceptron (DeepRMSD) and the traditional AutoDock Vina SF. The DeepRMSD+Vina, which combines (1) the root mean square deviation (RMSD) of the docking pose with respect to the native pose and (2) the AutoDock Vina score, is fully differentiable; thus is capable of optimizing the ligand binding pose to the energy-lowest conformation. Evaluated by the CASF-2016 docking power dataset, the DeepRMSD+Vina reaches a success rate of 94.4%, which outperforms most reported SFs to date. We evaluated the ligand conformation optimization framework in practical molecular docking scenarios (redocking and cross-docking tasks), revealing the high potentialities of this framework in drug design and discovery. Structural analysis shows that this framework has the ability to identify key physical interactions in protein-ligand binding, such as hydrogen-bonding. Our work provides a paradigm for optimizing ligand conformations based on deep learning algorithms. The DeepRMSD+Vina model and the optimization framework are available at GitHub repository https://github.com/zchwang/DeepRMSD-Vina_Optimization.

Analyzing network pharmacology and molecular docking to clarify Duhuo Jisheng decoction potential mechanism of osteoarthritis mitigation

As a classic remedy for treating Osteoarthritis (OA), Duhuo Jisheng decoction has successfully treated countless patients. Nevertheless, its specific mechanism is unknown. This study explored the active constituents of Duhuo Jisheng decoction and the potential molecular mechanisms for treating OA using a Network Pharmacology approaches. Screening active components and corresponding targets of Duhuo parasite decoction by traditional Chinese medicine systems pharmacology database and analysis platform database. Combining the following databases yielded OA disease targets: GeneCards, DrugBank, PharmGkb, Online Mendelian Inheritance in Man, and therapeutic target database. The interaction analysis of the herb-active ingredient-core target network and protein-protein interaction protein network was constructed by STRING platform and Cytoscape software. Gene ontology functional enrichment analysis and Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis were carried out. PyMOL and other software were used to verify the molecular docking between the essential active components and the core target. 262 active ingredients were screened, and their main components were quercetin, kaempferol, wogonin, baicalein, and beta-carotene. 108 intersection targets of disease and drug were identified, and their main components were RELA, FOS, STAT3, MAPK14, MAPK1, JUN, and ESR1. Gene ontology analysis showed that the key targets were mainly involved in biological processes such as response to lipopolysaccharide, response to xenobiotic stimulus, and response to nutrient levels. The results of Kyoto Encyclopedia of Genes and Genomes analysis show that the signal pathways include the AGE - RAGE signaling pathway, IL - 17 signaling pathway, TNF signaling pathway, and Toll - like receptor signaling pathway. Molecular docking showed that the main active components of Duhuo parasitic decoction had a good bonding activity with the key targets in treating OA. Duhuo Jisheng decoction can reduce the immune-inflammatory reaction, inhibit apoptosis of chondrocytes, strengthen proliferation and repair of chondrocytes and reduce the inflammatory response in a multi-component-multi-target-multi-pathway way to play a role in the treatment of OA.

MILCDock: Machine Learning Enhanced Consensus Docking for Virtual Screening in Drug Discovery

Molecular docking tools are regularly used to computationally identify new molecules in virtual screening for drug discovery. However, docking tools suffer from inaccurate scoring functions with widely varying performance on different proteins. To enable more accurate ranking of active over inactive ligands in virtual screening, we created a machine learning consensus docking tool, MILCDock, that uses predictions from five traditional molecular docking tools to predict the probability a ligand binds to a protein. MILCDock was trained and tested on data from both the DUD-E and LIT-PCBA docking datasets and shows improved performance over traditional molecular docking tools and other consensus docking methods on the DUD-E dataset. LIT-PCBA targets proved to be difficult for all methods tested. We also find that DUD-E data, although biased, can be effective in training machine learning tools if care is taken to avoid DUD-E's biases during training.

A novel anti-atherosclerotic mechanism of quercetin: Competitive binding to KEAP1 via Arg483 to inhibit macrophage pyroptosis

Natural antioxidants represented by quercetin have been documented to be effective against atherosclerosis. However, the related mechanisms remain largely unclear. In this study, we identified a novel anti-atherosclerotic mechanism of quercetin inhibiting macrophage pyroptosis by activating NRF2 through binding to the Arg483 site of KEAP1 competitively. In ApoE-/- mice fed with high fat diet, quercetin administration attenuated atherosclerosis progression by reducing oxidative stress level and suppressing macrophage pyroptosis. At the cellular level, quercetin suppressed THP-1 macrophage pyroptosis induced by ox-LDL, demonstrated by inhibiting NLRP3 inflammasome activation and reducing ROS level, while these effects were reversed by the specific NRF2 inhibitor (ML385). Mechanistically, quercetin promoted NRF2 to dissociate from KEAP1, enhanced NRF2 nuclear translocation as well as transcription of downstream antioxidant protein. Molecular docking results suggested that quercetin could bind with KEAP1 at Arg415 and Arg483. In order to verify the binding sites, KEAP1 mutated at Arg415 and Arg483 to Ser (R415S and R483S) was transfected into THP-1 macrophages, and the anti-pyroptotic effect of quercetin was abrogated by Arg483 mutation, but not Arg415 mutation. Furthermore, after administration of adeno associated viral vector (AAV) with AAV-KEAP1-R483S, the anti-atherosclerotic effects of quercetin were almost abolished in ApoE-/- mice. These findings proved quercetins suppressed macrophage pyroptosis by targeting KEAP1/NRF2 interaction, and provided reliable data on the underlying mechanism of natural antioxidants to protect against atherosclerosis.

Artificial intelligence-enabled virtual screening of ultra-large chemical libraries with deep docking

With the recent explosion of chemical libraries beyond a billion molecules, more efficient virtual screening approaches are needed. The Deep Docking (DD) platform enables up to 100-fold acceleration of structure-based virtual screening by docking only a subset of a chemical library, iteratively synchronized with a ligand-based prediction of the remaining docking scores. This method results in hundreds- to thousands-fold virtual hit enrichment (without significant loss of potential drug candidates) and hence enables the screening of billion molecule-sized chemical libraries without using extraordinary computational resources. Herein, we present and discuss the generalized DD protocol that has been proven successful in various computer-aided drug discovery (CADD) campaigns and can be applied in conjunction with any conventional docking program. The protocol encompasses eight consecutive stages: molecular library preparation, receptor preparation, random sampling of a library, ligand preparation, molecular docking, model training, model inference and the residual docking. The standard DD workflow enables iterative application of stages 3-7 with continuous augmentation of the training set, and the number of such iterations can be adjusted by the user. A predefined recall value allows for control of the percentage of top-scoring molecules that are retained by DD and can be adjusted to control the library size reduction. The procedure takes 1-2 weeks (depending on the available resources) and can be completely automated on computing clusters managed by job schedulers. This open-source protocol, at https://github.com/jamesgleave/DD_protocol , can be readily deployed by CADD researchers and can significantly accelerate the effective exploration of ultra-large portions of a chemical space.

Automated discovery of noncovalent inhibitors of SARS-CoV-2 main protease by consensus Deep Docking of 40 billion small molecules

Recent explosive growth of 'make-on-demand' chemical libraries brought unprecedented opportunities but also significant challenges to the field of computer-aided drug discovery. To address this expansion of the accessible chemical universe, molecular docking needs to accurately rank billions of chemical structures, calling for the development of automated hit-selecting protocols to minimize human intervention and error. Herein, we report the development of an artificial intelligence-driven virtual screening pipeline that utilizes Deep Docking with Autodock GPU, Glide SP, FRED, ICM and QuickVina2 programs to screen 40 billion molecules against SARS-CoV-2 main protease (Mpro). This campaign returned a significant number of experimentally confirmed inhibitors of Mpro enzyme, and also enabled to benchmark the performance of twenty-eight hit-selecting strategies of various degrees of stringency and automation. These findings provide new starting scaffolds for hit-to-lead optimization campaigns against Mpro and encourage the development of fully automated end-to-end drug discovery protocols integrating machine learning and human expertise.

Navigating Chemical Space by Interfacing Generative Artificial Intelligence and Molecular Docking

Here, we report the implementation and application of a simple, structure-aware framework to generate target-specific screening libraries. Our approach combines advances in generative artificial intelligence (AI) with conventional molecular docking to explore chemical space conditioned on the unique physicochemical properties of the active site of a biomolecular target. As a demonstration, we used our framework, which we refer to as sample-and-dock, to construct focused libraries for cyclin-dependent kinase type-2 (CDK2) and the active site of the main protease (M^pro) of the SARS-CoV-2 virus. We envision that the sample-and-dock framework could be used to generate theoretical maps of the chemical space specific to a given target and so provide information about its molecular recognition characteristics.

Efficient Exploration of Chemical Space with Docking and Deep Learning

With the advent of make-on-demand commercial libraries, the number of purchasable compounds available for virtual screening and assay has grown explosively in recent years, with several libraries eclipsing one billion compounds. Today's screening libraries are larger and more diverse, enabling the discovery of more-potent hit compounds and unlocking new areas of chemical space, represented by new core scaffolds. Applying physics-based in silico screening methods in an exhaustive manner, where every molecule in the library must be enumerated and evaluated independently, is increasingly cost-prohibitive. Here, we introduce a protocol for machine learning-enhanced molecular docking based on active learning to dramatically increase throughput over traditional docking. We leverage a novel selection protocol that strikes a balance between two objectives: (1) identifying the best scoring compounds and (2) exploring a large region of chemical space, demonstrating superior performance compared to a purely greedy approach. Together with automated redocking of the top compounds, this method captures almost all the high scoring scaffolds in the library found by exhaustive docking. This protocol is applied to our recent virtual screening campaigns against the D4 and AMPC targets that produced dozens of highly potent, novel inhibitors, and a blind test against the MT1 target. Our protocol recovers more than 80% of the experimentally confirmed hits with a 14-fold reduction in compute cost, and more than 90% of the hit scaffolds in the top 5% of model predictions, preserving the diversity of the experimentally confirmed hit compounds.

V-Dock: Fast Generation of Novel Drug-like Molecules Using Machine-Learning-Based Docking Score and Molecular Optimization

We propose a computational workflow to design novel drug-like molecules by combining the global optimization of molecular properties and protein-ligand docking with machine learning. However, most existing methods depend heavily on experimental data, and many targets do not have sufficient data to train reliable activity prediction models. To overcome this limitation, protein-ligand docking calculations must be performed using the limited data available. Such docking calculations during molecular generation require considerable computational time, preventing extensive exploration of the chemical space. To address this problem, we trained a machine-learning-based model that predicted the docking energy using SMILES to accelerate the molecular generation process. Docking scores could be accurately predicted using only a SMILES string. We combined this docking score prediction model with the global molecular property optimization approach, MolFinder, to find novel molecules exhibiting the desired properties with high values of predicted docking scores. We named this design approach V-dock. Using V-dock, we efficiently generated many novel molecules with high docking scores for a target protein, a similarity to the reference molecule, and desirable drug-like and bespoke properties, such as QED. The predicted docking scores of the generated molecules were verified by correlating them with the actual docking scores.

Identification of an AXL kinase inhibitor in triple-negative breast cancer by structure-based virtual screening and bioactivity test

Breast cancer is a malignant tumor that occurs in the glandular epithelium of the breast, and more than 15% of the patients are triple-negative breast cancer (TNBC). Therefore, finding new targets and targeted therapeutic drugs for TNBC is urgent. Overexpression of the AXL is associated with motility and invasiveness of the TNBC cells, which is a potential target for breast cancer therapy. A compound Y041-5921 (IC₅₀  = 6.069 μm for AXL kinase and IC₅₀  = 4.1 μm for MDA-MB-231 cell line) was identified through structure-based virtual screening and bioassay test for the first time. The compound Y041-5921 could significantly inhibit the proliferation and invasion of the TNBC cells and the toxicity of Y041-5921 to normal immortalized breast epithelial cells was far lower than that of commonly used clinical chemotherapy drugs. Besides, it also had well inhibitory effect on the proliferation of many other malignant tumor cell lines (the IC₅₀  value are 10.0 m, 7.1 m, 10.3 m, 11.4 m and 5.8 m for U251 cell, COLO cell, PC-9 cell, CAKI-1 cell and MG63 cell, respectively). The interaction mechanism between Y041-5921 and AXL was studied by molecular dynamics (MD) simulations and binding free energy calculation, and the key residues whose energy contribution mainly comes from non-polar solvation interaction (such as Ala565, Lys567, Met598, Leu620, Pro621, Met623, Lys624, Arg676, Asn677 and Met679) were identified. The small molecule inhibitors Y041-5921 targeting AXL reported in this work will lay a foundation and provide a theoretical basis for the development of the TNBC.

Machine Learning-Enabled Pipeline for Large-Scale Virtual Drug Screening

Virtual screening is receiving renewed attention in drug discovery, but progress is hampered by challenges on two fronts: handling the ever-increasing sizes of libraries of drug-like compounds and separating true positives from false positives. Here, we developed a machine learning-enabled pipeline for large-scale virtual screening that promises breakthroughs on both fronts. By clustering compounds according to molecular properties and limited docking against a drug target, the full library was trimmed by 10-fold; the remaining compounds were then screened individually by docking; and finally, a dense neural network was trained to classify the hits into true and false positives. As illustration, we screened for inhibitors against RPN11, the deubiquitinase subunit of the proteasome, and a drug target for breast cancer.