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

In silico discovery of novel compounds for FAK activation using virtual screening, AI-based prediction, and molecular dynamics

Focal Adhesion Kinase (FAK) is a non-receptor tyrosine kinase that plays a crucial role in cell proliferation, migration, and signal transduction. FAK is overexpressed in metastatic and advanced-stage cancers, where it is considered a key kinase in cancer growth and metastasis. However, recent research has revealed that FAK activity decreases in various diseases. we aimed to identify compounds that could enhance FAK activity using structure-based virtual screening and artificial intelligence models from a vast chemical database. We began with an extensive chemical database containing over 10 million compounds and used our newly developed pipeline to screen candidate molecules. To select compounds structurally similar to ZINC40099027 (ZN27), a known FAK activator, we calculated Tanimoto Similarity scores and chose compounds with a score of at least 0.8. Clustering was performed using K-means based on the molecular properties. Subsequently, we utilized docking simulation, deep learning and SAScorer to evaluate and predict the protein-ligand docking affinity and physicochemical properties of the candidate compounds. The deep learning models were selected as state-of-the-art models: GLAM predicts the blood-brain barrier permeability of FAK, and elEmBERT predicts the potential toxicity of compound. The combined results were used to create an evaluation matrix. We selected 10 promising candidate compounds from the initial dataset of 10 million. To evaluate the stability of these top 10 candidate compounds in interaction with the FAK protein, we conducted Molecular Dynamics (MD) simulations. We performed a molecular dynamics simulation for a total of 50 ns and identified the top three promising candidate compounds.

Design and synthesis of thiolutin derived PSMD14/HDAC dual-target inhibitors against esophageal squamous cell carcinoma

Esophageal cancer is one of the most migratory, invasive, and lethal malignancies and has a poor prognosis, highlighting the urgent need to develop more effective drugs for its treatment. Given that PSMD14 and HDAC play an important role in the treatment of esophageal cancer, thiolutin is used as a lead compound to design and synthesize a series of dual-target PSMD14/HDAC small molecule inhibitors, aiming to discover more effective anti-esophageal cancer drugs. Through the in vitro screening of PSMD14/HDAC enzyme inhibitory activities of a series of thiolutin derivatives, it was found that compound 8b, with a linker length of 8 and a Zn2+-chelating group of 1,2-phenylenediamine, exhibited the most balanced inhibitory activity against PSMD14/HDAC.The impact of 8b on PSMD14/HDAC at the cellular level was evaluated, and its drug-like properties were further assessed in vivo. Compound 8b demonstrates balanced dual-target activity (PSMD14 IC50 = 238.7 ± 27 nM, HDAC1 IC50 = 141.2 ± 10.3 nM) and excellent cytotoxicity against esophageal cancer cells (IC50 = 30-250 nM), effectively reversing epithelial-mesenchymal transition in cancer cells. Moreover, 8b exhibited excellent pharmacokinetic characteristics. More importantly, in a nude mouse xenograft model with subcutaneous transplantation of KYSE 30 cells, compound 8b (0.8 mg/kg, BID, PO, TGI = 81 %; 0.8 mg/kg, Q3D, SC, TGI = 77 %) significantly inhibited tumor growth, outperforming single-agent or combination treatments, thereby highlighting the therapeutic advantages of dual-target inhibition. These findings highlight the potential of dual-target PSMD14/HDAC inhibitors as a promising strategy for developing anti-esophageal cancer drugs.

Transcriptomic and Molecular Docking Analysis Reveal Virulence Gene Regulation-Mediated Antibacterial Effects of Benzyl Isothiocyanate Against Staphylococcus aureus

Staphylococcus aureus (S. aureus) is a common pathogen that can cause many serious infections. Thus, efficient and practical techniques to fight S. aureus are required. In this study, transcriptomics was used to evaluate changes in S. aureus following treatment with benzyl isothiocyanate (BITC) to determine its antibacterial action. The results revealed that the BITC at subinhibitory concentrations (1/8th MIC) treated group had 94 differentially expressed genes compared to the control group, with 52 downregulated genes. Moreover, STRING analyses were used to reveal the protein interactions encoded by 36 genes. Then, we verified three significant virulence genes by qRT-PCR, including capsular polysaccharide synthesis enzyme (cp8F), capsular polysaccharide biosynthesis protein (cp5D), and thermonuclease (nuc). Furthermore, molecular docking analysis was performed to investigate the action site of BITC with the encoded proteins of cp8F, cp5D, and nuc. The results showed that the docking fraction of BITC with selected proteins ranged from - 6.00 to - 6.60 kcal/mol, predicting the stability of these complexes. BITC forms hydrophobic, hydrogen-bonded, π-π conjugated interactions with amino acids TRP (130), GLY (10), ILE (406), LYS (368), TYR (192), and ARG (114) of these proteins. These findings will aid future research into the antibacterial effects of BITC against S. aureus.

How exascale computing can shape drug design: A perspective from multiscale QM/MM molecular dynamics simulations and machine learning-aided enhanced sampling algorithms

Molecular simulations are an essential asset in the first steps of drug design campaigns. However, the requirement of high-throughput limits applications mainly to qualitative approaches with low computational cost, but also low accuracy. Unlocking the potential of more rigorous quantum mechanical/molecular mechanics (QM/MM) models combined with molecular dynamics-based free energy techniques could have a tremendous impact. Indeed, these two relatively old techniques are emerging as promising methods in the field. This has been favored by the exponential growth of computer power and the proliferation of powerful data-driven methods. Here, we briefly review recent advances and applications, and give our perspective on the impact that QM/MM and free-energy methods combined with machine learning-aided algorithms can have on drug design.

Computational Chemistry in Structure-Based Solute Carrier Transporter Drug Design: Recent Advances and Future Perspectives

Solute carrier transporters (SLCs) are a class of important transmembrane proteins that are involved in the transportation of diverse solute ions and small molecules into cells. There are approximately 450 SLCs within the human body, and more than a quarter of them are emerging as attractive therapeutic targets for multiple complex diseases, e.g., depression, cancer, and diabetes. However, only 44 unique transporters (∼9.8% of the SLC superfamily) with 3D structures and specific binding sites have been reported. To design innovative and effective drugs targeting diverse SLCs, there are a number of obstacles that need to be overcome. However, computational chemistry, including physics-based molecular modeling and machine learning- and deep learning-based artificial intelligence (AI), provides an alternative and complementary way to the classical drug discovery approach. Here, we present a comprehensive overview on recent advances and existing challenges of the computational techniques in structure-based drug design of SLCs from three main aspects: (i) characterizing multiple conformations of the proteins during the functional process of transportation, (ii) identifying druggability sites especially the cryptic allosteric ones on the transporters for substrates and drugs binding, and (iii) discovering diverse small molecules or synthetic protein binders targeting the binding sites. This work is expected to provide guidelines for a deep understanding of the structure and function of the SLC superfamily to facilitate rational design of novel modulators of the transporters with the aid of state-of-the-art computational chemistry technologies including artificial intelligence.

Shape-Aware Synthon Search (SASS) for Virtual Screening of Synthon-Based Chemical Spaces

Virtual screening of large-scale chemical libraries has become increasingly useful for identifying high-quality candidates for drug discovery. While it is possible to exhaustively screen chemical spaces that number on the order of billions, indirect combinatorial approaches are needed to efficiently navigate larger, synthon-based virtual spaces. We describe Shape-Aware Synthon Search (SASS), a synthon-based virtual screening method that carries out shape similarity searches in the synthon space instead of the enumerated product space. SASS can replicate results from exhaustive searches in ultralarge, combinatorial spaces with high recall on a variety of query molecules while only scoring a small subspace of possible enumerated products, thereby significantly accelerating large-scale, shape-based virtual screening.

Molecular Gas-Phase Conformational Ensembles

Accurately determining the global minima of a molecular structure is important in diverse scientific fields, including drug design, materials science, and chemical synthesis. Conformational search engines serve as valuable tools for exploring the extensive conformational space of molecules and for identifying energetically favorable conformations. In this study, we present a comparison of Auto3D, CREST, Balloon, and ETKDG (from RDKit), which are freely available conformational search engines, to evaluate their effectiveness in locating global minima. These engines employ distinct methodologies, including machine learning (ML) potential-based, semiempirical, and force field-based approaches. To validate these methods, we propose the use of collisional cross-section (CCS) values obtained from ion mobility-mass spectrometry studies. We hypothesize that experimental gas-phase CCS values can provide experimental evidence that we likely have the global minimum for a given molecule. To facilitate this effort, we used our gas-phase conformation library (GPCL) which currently consists of the full ensembles of 20 small molecules and can be used by the community to validate any conformational search engine. Further members of the GPCL can be readily created for any molecule of interest using our standard workflow used to compute CCS values, expanding the ability of the GPCL in validation exercises. These innovative validation techniques enhance our understanding of the conformational landscape and provide valuable insights into the performance of conformational generation engines. Our findings shed light on the strengths and limitations of each search engine, enabling informed decisions for their utilization in various scientific fields, where accurate molecular structure determination is crucial for understanding biological activity and designing targeted interventions. By facilitating the identification of reliable conformations, this study significantly contributes to enhancing the efficiency and accuracy of molecular structure determination, with particular focus on metabolite structure elucidation. The findings of this research also provide valuable insights for developing effective workflows for predicting the structures of unknown compounds with high precision.

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.

ChatGPT in Drug Discovery: A Case Study on Anticocaine Addiction Drug Development with Chatbots

The birth of ChatGPT, a cutting-edge language model-based chatbot developed by OpenAI, ushered in a new era in AI. However, due to potential pitfalls, its role in rigorous scientific research is not clear yet. This paper vividly showcases its innovative application within the field of drug discovery. Focused specifically on developing anticocaine addiction drugs, the study employs GPT-4 as a virtual guide, offering strategic and methodological insights to researchers working on generative models for drug candidates. The primary objective is to generate optimal drug-like molecules with desired properties. By leveraging the capabilities of ChatGPT, the study introduces a novel approach to the drug discovery process. This symbiotic partnership between AI and researchers transforms how drug development is approached. Chatbots become facilitators, steering researchers toward innovative methodologies and productive paths for creating effective drug candidates. This research sheds light on the collaborative synergy between human expertise and AI assistance, wherein ChatGPT's cognitive abilities enhance the design and development of pharmaceutical solutions. This paper not only explores the integration of advanced AI in drug discovery but also reimagines the landscape by advocating for AI-powered chatbots as trailblazers in revolutionizing therapeutic innovation.

Deep Learning with Geometry-Enhanced Molecular Representation for Augmentation of Large-Scale Docking-Based Virtual Screening

Structure-based virtual screening has been a crucial tool in drug discovery for decades. However, as the chemical space expands, the existing structure-based virtual screening techniques based on molecular docking and scoring struggle to handle billion-entry ultralarge libraries due to the high computational cost. To address this challenge, people have resorted to machine learning techniques to enhance structure-based virtual screening for efficiently exploring the vast chemical space. In those cases, compounds are usually treated as sequential strings or two-dimensional topology graphs, limiting their ability to incorporate three-dimensional structural information for downstream tasks. We herein propose a novel deep learning protocol, GEM-Screen, which utilizes the geometry-enhanced molecular representation of the compounds docking to a specific target and is trained on docking scores of a small fraction of a library through an active learning strategy to approximate the docking outcome for yet nontraining entries. This protocol is applied to virtual screening campaigns against the AmpC and D4 targets, demonstrating that GEM-Screen enriches more than 90% of the hit scaffolds for AmpC in the top 4% of model predictions and more than 80% of the hit scaffolds for D4 in the same top-ranking size of library. GEM-Screen can be used in conjunction with traditional docking programs for docking of only the top-ranked compounds to avoid the exhaustive docking of the whole library, thus allowing for discovering top-scoring compounds from billion-entry libraries in a rapid yet accurate fashion.

ChatGPT in Drug Discovery: A Case Study on Anti-Cocaine Addiction Drug Development with Chatbots

The birth of ChatGPT, a cutting-edge language model-based chatbot developed by OpenAI, ushered in a new era in AI. However, due to potential pitfalls, its role in rigorous scientific research is not clear yet. This paper vividly showcases its innovative application within the field of drug discovery. Focused specifically on developing anti-cocaine addiction drugs, the study employs GPT-4 as a virtual guide, offering strategic and methodological insights to researchers working on generative models for drug candidates. The primary objective is to generate optimal drug-like molecules with desired properties. By leveraging the capabilities of ChatGPT, the study introduces a novel approach to the drug discovery process. This symbiotic partnership between AI and researchers transforms how drug development is approached. Chatbots become facilitators, steering researchers towards innovative methodologies and productive paths for creating effective drug candidates. This research sheds light on the collaborative synergy between human expertise and AI assistance, wherein ChatGPT's cognitive abilities enhance the design and development of potential pharmaceutical solutions. This paper not only explores the integration of advanced AI in drug discovery but also reimagines the landscape by advocating for AI-powered chatbots as trailblazers in revolutionizing therapeutic innovation.

Revolutionizing Medicinal Chemistry: The Application of Artificial Intelligence (AI) in Early Drug Discovery

Artificial intelligence (AI) has permeated various sectors, including the pharmaceutical industry and research, where it has been utilized to efficiently identify new chemical entities with desirable properties. The application of AI algorithms to drug discovery presents both remarkable opportunities and challenges. This review article focuses on the transformative role of AI in medicinal chemistry. We delve into the applications of machine learning and deep learning techniques in drug screening and design, discussing their potential to expedite the early drug discovery process. In particular, we provide a comprehensive overview of the use of AI algorithms in predicting protein structures, drug-target interactions, and molecular properties such as drug toxicity. While AI has accelerated the drug discovery process, data quality issues and technological constraints remain challenges. Nonetheless, new relationships and methods have been unveiled, demonstrating AI's expanding potential in predicting and understanding drug interactions and properties. For its full potential to be realized, interdisciplinary collaboration is essential. This review underscores AI's growing influence on the future trajectory of medicinal chemistry and stresses the importance of ongoing synergies between computational and domain experts.

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.

Auto3D: Automatic Generation of the Low-Energy 3D Structures with ANI Neural Network Potentials

Computational programs accelerate the chemical discovery processes but often need proper three-dimensional molecular information as part of the input. Getting optimal molecular structures is challenging because it requires enumerating and optimizing a huge space of stereoisomers and conformers. We developed the Python-based Auto3D package for generating the low-energy 3D structures using SMILES as the input. Auto3D is based on state-of-the-art algorithms and can automatize the isomer enumeration and duplicate filtering process, 3D building process, geometry optimization, and ranking process. Tested on 50 molecules with multiple unspecified stereocenters, Auto3D is guaranteed to find the stereoconfiguration that yields the lowest-energy conformer. With Auto3D, we provide an extension of the ANI model. The new model, dubbed ANI-2xt, is trained on a tautomer-rich data set. ANI-2xt is benchmarked with DFT methods on geometry optimization and electronic and Gibbs free energy calculations. Compared with ANI-2x, ANI-2xt provides a 42% error reduction for tautomeric reaction energy calculations when using the gold-standard coupled-cluster calculation as the reference. ANI-2xt can accurately predict the energies and is several orders of magnitude faster than DFT methods.

MO-MEMES: A method for accelerating virtual screening using multi-objective Bayesian optimization

The pursuit of potential inhibitors for novel targets has become a very important problem especially over the last 2 years with the world in the midst of the COVID-19 pandemic. This entails performing high throughput screening exercises on drug libraries to identify potential “hits”. These hits are identified using analysis of their physical properties like binding affinity to the target receptor, octanol-water partition coefficient (LogP) and more. However, drug libraries can be extremely large and it is infeasible to calculate and analyze the physical properties for each of those molecules within acceptable time and moreover, each molecule must possess a multitude of properties apart from just the binding affinity. To address this problem, in this study, we propose an extension to the Machine learning framework for Enhanced MolEcular Screening (MEMES) framework for multi-objective Bayesian optimization. This approach is capable of identifying over 90% of the most desirable molecules with respect to all required properties while explicitly calculating the values of each of those properties on only 6% of the entire drug library. This framework would provide an immense boost in identifying potential hits that possess all properties required for a drug molecules.

Identification of Potential Cytochrome P450 3A5 Inhibitors: An Extensive Virtual Screening through Molecular Docking, Negative Image-Based Screening, Machine Learning and Molecular Dynamics Simulation Studies

Cytochrome P450 3A5 (CYP3A5) is one of the crucial CYP family members and has already proven to be an important drug target for cardiovascular diseases. In the current study, the PubChem database was screened through molecular docking and high-affinity molecules were adopted for further assessment. A negative image-based (NIB) model was used for a similarity search by considering the complementary shape and electrostatics of the target and small molecules. Further, the molecules were segregated into active and inactive groups through six machine learning (ML) matrices. The active molecules found in each ML model were used for in silico pharmacokinetics and toxicity assessments. A total of five molecules followed the acceptable pharmacokinetics and toxicity profiles. Several potential binding interactions between the proposed molecules and CYP3A5 were observed. The dynamic behavior of the selected molecules in the CYP3A5 was explored through a molecular dynamics (MD) simulation study. Several parameters obtained from the MD simulation trajectory explained the stability of the protein–ligand complexes in dynamic states. The high binding affinity of each molecule was revealed by the binding free energy calculation through the MM-GBSA methods. Therefore, it can be concluded that the proposed molecules might be potential CYP3A5 molecules for therapeutic application in cardiovascular diseases subjected to in vitro/in vivo validations.

Emerging frontiers in virtual drug discovery: From quantum mechanical methods to deep learning approaches

Virtual screening-based approaches to discover initial hit and lead compounds have the potential to reduce both the cost and time of early drug discovery stages, as well as to find inhibitors for even challenging target sites such as protein-protein interfaces. Here in this review, we provide an overview of the progress that has been made in virtual screening methodology and technology on multiple fronts in recent years. The advent of ultra-large virtual screens, in which hundreds of millions to billions of compounds are screened, has proven to be a powerful approach to discover highly potent hit compounds. However, these developments are just the tip of the iceberg, with new technologies and methods emerging to propel the field forward. Examples include novel machine-learning approaches, which can reduce the computational costs of virtual screening dramatically, while progress in quantum-mechanical approaches can increase the accuracy of predictions of various small molecule properties.

Application of random forest based on semi-automatic parameter adjustment for optimization of anti-breast cancer drugs

The optimization of drug properties in the process of cancer drug development is very important to save research and development time and cost. In order to make the anti-breast cancer drug candidates with good biological activity, this paper collected 1974 compounds, firstly, the top 20 molecular descriptors that have the most influence on biological activity were screened by using XGBoost-based data feature selection; secondly, on this basis, take pIC50 values as feature data and use a variety of machine learning algorithms to compare, soas to select a most suitable algorithm to predict the IC50 and pIC50 values. It is preliminarily found that the effects of Random Forest, XGBoost and Gradient-enhanced algorithms are good and have little difference, and the Support vector machine is the worst. Then, using the Semi-automatic parameter adjustment method to adjust the parameters of Random Forest, XGBoost and Gradient-enhanced algorithms to find the optimal parameters. It is found that the Random Forest algorithm has high accuracy and excellent anti over fitting, and the algorithm is stable. Its prediction accuracy is 0.745. Finally, the accuracy of the results is verified by training the model with the preliminarily selected data, which provides an innovative solution for the optimization of the properties of anti- breast cancer drugs, and can provide better support for the early research and development of anti-breast cancer drugs.

POH1/Rpn11/PSMD14: a journey from basic research in fission yeast to a prognostic marker and a druggable target in cancer cells

POH1/Rpn11/PSMD14 is a highly conserved protein in eukaryotes from unicellular organisms to human and has a crucial role in cellular homoeostasis. It is a subunit of the regulatory particle of the proteasome, where it acts as an intrinsic deubiquitinase removing polyubiquitin chains from substrate proteins. This function is not only coupled to the translocation of substrates into the core of the proteasome and their subsequent degradation but also, in some instances, to the stabilisation of ubiquitinated proteins through their deubiquitination. POH1 was initially discovered as a functional homologue of the fission yeast gene pad1⁺, which confers drug resistance when overexpressed. In translational studies, expression of POH1 has been found to be increased in several tumour types relative to normal adjacent tissue and to correlate with tumour progression, higher tumour grade, decreased sensitivity to cytotoxic drugs and poor prognosis. Proteasome inhibitors targeting the core particle of the proteasome are highly active in the treatment of myeloma, and recently developed POH1 inhibitors, such as capzimin and thiolutin, have shown promising anticancer activity in cell lines of solid tumours and leukaemia. Here we give an overview of POH1 function in the cell, of its potential role in oncogenesis and of recent progress in developing POH1-targeting drugs.

Improving protein-ligand docking and screening accuracies by incorporating a scoring function correction term

Scoring functions are important components in molecular docking for structure-based drug discovery. Traditional scoring functions, generally empirical- or force field-based, are robust and have proven to be useful for identifying hits and lead optimizations. Although multiple highly accurate deep learning- or machine learning-based scoring functions have been developed, their direct applications for docking and screening are limited. We describe a novel strategy to develop a reliable protein–ligand scoring function by augmenting the traditional scoring function Vina score using a correction term (OnionNet-SFCT). The correction term is developed based on an AdaBoost random forest model, utilizing multiple layers of contacts formed between protein residues and ligand atoms. In addition to the Vina score, the model considerably enhances the AutoDock Vina prediction abilities for docking and screening tasks based on different benchmarks (such as cross-docking dataset, CASF-2016, DUD-E and DUD-AD). Furthermore, our model could be combined with multiple docking applications to increase pose selection accuracies and screening abilities, indicating its wide usage for structure-based drug discoveries. Furthermore, in a reverse practice, the combined scoring strategy successfully identified multiple known receptors of a plant hormone. To summarize, the results show that the combination of data-driven model (OnionNet-SFCT) and empirical scoring function (Vina score) is a good scoring strategy that could be useful for structure-based drug discoveries and potentially target fishing in future.