Identifying novel factor XIIa inhibitors with PCA-GA-SVM developed vHTS models

Machine Learning Reinforced Genetic Algorithm for Massive Targeted Discovery of Selectively Cytotoxic Inorganic Nanoparticles

Nanoparticles (NPs) have been employed as drug delivery systems (DDSs) for several decades, primarily as passive carriers, with limited selectivity. However, recent publications have shed light on the emerging phenomenon of NPs exhibiting selective cytotoxicity against cancer cell lines, attributable to distinct metabolic disparities between healthy and pathological cells. This study revisits the concept of NPs selective cytotoxicity, and for the first time proposes a high-throughput in silico screening approach to massive targeted discovery of selectively cytotoxic inorganic NPs. In the first step, this work trains a gradient boosting regression model to predict viability of NP-treated cell lines. The model achieves mean cross-validation (CV) Q2 = 0.80 and root mean square error (RMSE) of 13.6. In the second step, this work develops a machine learning (ML) reinforced genetic algorithm (GA), capable of screening >14 900 candidates/min, to identify the best-performing selectively cytotoxic NPs. As proof-of-concept, DDS candidates for the treatment of liver cancer are screened on HepG2 and hepatocytes cell lines resulting in Ag NPs with selective toxicity score of 42%. This approach opens the door for clinical translation of NPs, expanding their therapeutic application to a wider range of chemical space of NPs and living organisms such as bacteria and fungi.

Optimal decision-making in high-throughput virtual screening pipelines

The need for efficient computational screening of molecular candidates that possess desired properties frequently arises in various scientific and engineering problems, including drug discovery and materials design. However, the enormous search space containing the candidates and the substantial computational cost of high-fidelity property prediction models make screening practically challenging. In this work, we propose a general framework for constructing and optimizing a high-throughput virtual screening (HTVS) pipeline that consists of multi-fidelity models. The central idea is to optimally allocate the computational resources to models with varying costs and accuracy to optimize the return on computational investment. Based on both simulated and real-world data, we demonstrate that the proposed optimal HTVS framework can significantly accelerate virtual screening without any degradation in terms of accuracy. Furthermore, it enables an adaptive operational strategy for HTVS, where one can trade accuracy for efficiency.

Coumarins as factor XIIa inhibitors: Potency and selectivity improvements using a fragment-based strategy

Previously, we described weak coumarin inhibitors of factor XIIa, a promising target for artificial surface-induced thrombosis and various inflammatory diseases. In this work, we used fragment-based drug discovery approach to improve our coumarin series. First, we screened about 200 fragments for the S1 pocket. The S1 pocket of trypsin-like serine proteases, such as factor XIIa, is highly conserved and is known to drive a major part of the association energy. From the screening, we selected fragments displaying a micromolar activity and studied their selectivity on other serine proteases. Then, these fragments were merged to our coumarin templates, leading to the generation of nanomolar inhibitors. The mechanism of inhibition was further studied by mass spectrometry demonstrating the covalent binding through the formation of an acyl enzyme complex. The most potent compound was tested in plasma to evaluate its stability and efficacy on coagulation assays. It exhibited a plasmatic half-life of 1.9 h and a good selectivity for the intrinsic coagulation pathway over the extrinsic one.

Experimentally Validated Novel Factor XIIa Inhibitors Identified by Docking and Quantum Chemical Post-processing

Antithrombotic agents based on factor XIIa inhibitors can become a new class of drugs to manage conditions associated with thrombosis. Herein, we report identification of two novel classes of factor XIIa inhibitors. The first one is triazolopyrimidine derivatives designed on the basis of the literature aminotriazole hit and identified using virtual screening of the focused library. The second class is a spirocyclic furo[3,4-c]pyrrole derivatives identified by virtual screening of a large chemical library of drug-like compounds performed in a previous study but confirmed in vitro here. In both cases, the prediction of inhibitory activity is based on the score of the SOL docking program, which uses the MMFF94 force field to calculate the binding energy. For the best ligands selected in virtual screening of the large chemical library, postprocessing with the PM7 semiempirical quantum-chemical method was used to calculate the enthalpy of protein-ligand binding to prioritize 16 compounds for testing in enzymatic assay, and one of them demonstrated micromolar activity. For triazolopyrimidine library, 21 compounds were prioritized for the testing based on docking scores, and visual inspection of docking poses. Of these, 4 compounds showed inhibition of factor XIIa at 30 μM.

Optimal high-throughput virtual screening pipeline for efficient selection of redox-active organic materials

As global interest in renewable energy continues to increase, there has been a pressing need for developing novel energy storage devices based on organic electrode materials that can overcome the shortcomings of the current lithium-ion batteries. One critical challenge for this quest is to find materials whose redox potential (RP) meets specific design targets. In this study, we propose a computational framework for addressing this challenge through the effective design and optimal operation of a high-throughput virtual screening (HTVS) pipeline that enables rapid screening of organic materials that satisfy the desired criteria. Starting from a high-fidelity model for estimating the RP of a given material, we show how a set of surrogate models with different accuracy and complexity may be designed to construct a highly accurate and efficient HTVS pipeline. We demonstrate that the proposed HTVS pipeline construction and operation strategies substantially enhance the overall screening throughput.

Amide-functionalized 1,2,4-Triazol-5-amines as Covalent Inhibitors of Blood Coagulation Factor XIIa and Thrombin

To counteract thrombosis, new safe and efficient antithrombotics are required. We herein report the design, synthesis, and biological activity of a series of amide-functionalized acylated 1,2,4-triazol-5-amines as selective inhibitors of blood coagulation factor XIIa and thrombin. The introduction of an amide moiety into the main scaffold of 3-aryl aminotriazoles added certain three-dimensional properties to synthesized compounds and allowed them to reach binding sites in FXIIa and thrombin previously unaddressed by non-functionalized 1,2,4-triazol-5-amines. Among synthesized compounds, one quinoxaline-derived aminotriazole bearing N-butylamide moiety inhibited FXIIa with the IC50 value of 28 nM, whereas the N-phenylamide-derived aminotriazole inhibited thrombin with the IC50 value of 41 nM. Performed mass-shift experiments and molecular modeling studies proved the covalent mechanism of FXIIa and thrombin inhibition by synthesized compounds. In plasma coagulation tests, developed aminotriazoles showed anticoagulant properties mainly affecting the intrinsic blood coagulation pathway, activation of which is associated with thrombosis but is negligible for hemostasis.

Artificial intelligence and machine-learning approaches in structure and ligand-based discovery of drugs affecting central nervous system

CNS disorders are indications with a very high unmet medical needs, relatively smaller number of available drugs, and a subpar satisfaction level among patients and caregiver. Discovery of CNS drugs is extremely expensive affair with its own unique challenges leading to extremely high attrition rates and low efficiency. With explosion of data in information age, there is hardly any aspect of life that has not been touched by data driven technologies such as artificial intelligence (AI) and machine learning (ML). Drug discovery is no exception, emergence of big data via genomic, proteomic, biological, and chemical technologies has driven pharmaceutical giants to collaborate with AI oriented companies to revolutionise drug discovery, with the goal of increasing the efficiency of the process. In recent years many examples of innovative applications of AI and ML techniques in CNS drug discovery has been reported. Research on therapeutics for diseases such as schizophrenia, Alzheimer's and Parkinsonism has been provided with a new direction and thrust from these developments. AI and ML has been applied to both ligand-based and structure-based drug discovery and design of CNS therapeutics. In this review, we have summarised the general aspects of AI and ML from the perspective of drug discovery followed by a comprehensive coverage of the recent developments in the applications of AI/ML techniques in CNS drug discovery.

New Blood Coagulation Factor XIIa Inhibitors: Molecular Modeling, Synthesis, and Experimental Confirmation

In the modern world, complications caused by disorders in the blood coagulation system are found in almost all areas of medicine. Thus, the development of new, more advanced drugs that can prevent pathological conditions without disrupting normal hemostasis is an urgent task. The blood coagulation factor XIIa is one of the most promising therapeutic targets for the development of anticoagulants based on its inhibitors. The initial stage of drug development is directly related to computational methods of searching for a lead compound. In this study, docking followed by quantum chemical calculations was used to search for noncovalent low-molecular-weight factor XIIa inhibitors in a focused library of druglike compounds. As a result of the study, four low-molecular-weight compounds were experimentally confirmed as factor XIIa inhibitors. Selectivity testing revealed that two of the identified factor XIIa inhibitors were selective over the coagulation factors Xa and XIa.

Microscale Parallel Synthesis of Acylated Aminotriazoles Enabling the Development of Factor XIIa and Thrombin Inhibitors

Herein we report a microscale parallel synthetic approach allowing for rapid access to libraries of N-acylated aminotriazoles and screening of their inhibitory activity against factor XIIa (FXIIa) and thrombin, which are targets for antithrombotic drugs. This approach, in combination with post-screening structure optimization, yielded a potent 7 nM inhibitor of FXIIa and a 25 nM thrombin inhibitor; both compounds showed no inhibition of the other tested serine proteases. Selected N-acylated aminotriazoles exhibited anticoagulant properties in vitro influencing the intrinsic blood coagulation pathway, but not extrinsic coagulation. Mechanistic studies of FXIIa inhibition suggested that synthesized N-acylated aminotriazoles are covalent inhibitors of FXIIa. These synthesized compounds may serve as a promising starting point for the development of novel antithrombotic drugs.

Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: State-of-the-arts and future directions

Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML-driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML-powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state-of-the-art of AI/ML-guided CNS drug discovery, focusing on blood-brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.

Capillary electrophoresis as a fragment screening tool to cross-validate hits from chromogenic assay: Application to FXIIa

In this study, a partial-filling affinity capillary electrophoresis (pf-ACE) method was developed for the cross-validation of fragment hits revealed by chromogenic factor XIIa (FXIIa) assay. Chromogenic assay produces false positives, mainly due to spectrophotometric interferences and sample purity issues. pf-ACE was selected as counter-screening technology because of its separative character and the fact that the target does not have to be attached or tagged. The effects of protein plug length, applied voltage and composition of the running buffer were examined and optimized. Detection limit in terms of dissociation constant was estimated at 400 μM. The affinity evaluation was performed close to physiological conditions (pH 7.4, ionic strength 0.13 mol L^-1) in a poly (ethylene oxide)-coated capillary of 75 μm internal diameter x 33 cm length with an applied voltage of 3 kV. This method uncovered chromogenic assay's false positives due to zinc contamination. Moreover, pf-ACE supported the evaluation of compounds absorbing at 405 nm.

Factor XIIIa inhibitors as potential novel drugs for venous thromboembolism

Human factor XIIIa (FXIIIa) is a multifunctional transglutaminase with a significant role in hemostasis. FXIIIa catalyzes the last step in the coagulation process. It stabilizes the blood clot by cross-linking the α- and γ-chains of fibrin. It also protects the newly formed clot from plasmin-mediated fibrinolysis, primarily by cross-linking α2-antiplasmin to fibrin. Furthermore, FXIIIa is a major determinant of clot size and clot's red blood cells content. Therefore, inhibitors targeting FXIIIa have been considered to develop a new generation of anticoagulants to prevent and/or treat venous thromboembolism. Several inhibitors of FXIIIa have been discovered or designed including active site and allosteric site small molecule inhibitors as well as natural and modified polypeptides. This work reviews the structural, biochemical, and pharmacological aspects of FXIIIa inhibitors so as to advance their molecular design to become more clinically relevant.

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

Identifying de-NEDDylation inhibitors: Virtual high-throughput screens targeting SENP8

Protein modification can have far-reaching effects. NEDDylation, a protein modification process with the protein NEDD8, stabilizes and modifies how the targeted protein interacts with other proteins. Its role in system regulation makes it a prime therapeutic target, and virtual high-throughput screening has already identified new NEDD8 inhibitors. SENP8 matures the NEDD8 proenzyme into the active form and regulates NEDDylation by removing NEDD8 from over-NEDDylated proteins. In this work, SENP8 inhibitor candidates were identified in two rounds of virtual high-throughput screening. Of the ten candidates identified in the first round of screening, four were active in validation experiments to yield an experimental hit rate of 40%. Of the five candidates identified in the second round of screening, one was active in validation experiments to yield an experimental hit rate of 20%. Results indicate virtual high-throughput screening improved hit rates over traditional high-throughput screening. The SENP8 inhibitor candidates can be used to interrogate the NEDDylation regulation mechanism.

Virtual high-throughput screens identifying hPK-M2 inhibitors: Exploration of model extrapolation

Glycolysis with PK-M2 occurs typically in anaerobic conditions and atypically in aerobic conditions, which is known as the Warburg effect. The Warburg effect is found in many oncogenic situations and is believed to provide energy and biomass for oncogenesis to persist. The work presented targets human PK-M2 (hPK-M2) in a virtual high-throughput screen to identify new inhibitors and leads for further study. In the initial screen, one of the 12 candidates selected for experimental validation showed biological activity (hit-rate = 8.13%). In the second screen with retrained models, six of 11 candidates selected for experimental validation showed biological activity (hit-rate: 54.5%). Additionally, four different scaffolds were identified for further analysis when examining the tested candidates and compounds in the training data. Finally, extrapolation was necessary to identify a sufficient number of candidates to test in the second screen. Examination of the results suggested stepwise extrapolation to maximize efficiency.

Advances with support vector machines for novel drug discovery

INTRODUCTION

Novel drug discovery remains an enormous challenge, with various computer-aided drug design (CADD) approaches having been widely employed for this purpose. CADD, specifically the commonly used support vector machines (SVMs), can employ machine learning techniques. SVMs and their variations offer numerous drug discovery applications, which range from the classification of substances (as active or inactive) to the construction of regression models and the ranking/virtual screening of databased compounds. Areas covered: Herein, the authors consider some of the applications of SVMs in medicinal chemistry, illustrating their main advantages and disadvantages, as well as trends in their utilization, via the available published literature. The aim of this review is to provide an up-to-date review of the recent applications of SVMs in drug discovery as described by the literature, thereby highlighting their strengths, weaknesses, and future challenges. Expert opinion: Techniques based on SVMs are considered as powerful approaches in early drug discovery. The ability of SVMs to classify active or inactive compounds has enabled the prioritization of substances for virtual screening. Indeed, one of the main advantages of SVMs is related to their potential in the analysis of nonlinear problems. However, despite successes in employing SVMs, the challenges of improving accuracy remain.

Identifying new clotting factor XIa inhibitors in virtual high-throughput screens using PCA-GA-SVM models and signature

Blood Clotting Factor XI is an important actor in the clotting mechanism: it activates downstream zymogen involved in the clotting process. It can be targeted for activation or inhibition depending on treatment goals to enhance or inhibit clotting. In terms of antithrombosis treatment, Factor XI has emerged as a promising target to focus on. In this work, an iterative virtual high-throughput screening pipeline was proposed that can supplement current efforts to find inhibitors. The first iteration identified 11 compounds to test with 3 active for a hit-rate of 27.3%. The second iteration of the pipeline identified another 11 compounds to test with 7 active for a hit-rate of 63.6%. © 2018 American Institute of Chemical Engineers Biotechnol. Prog., 34:1553-1565, 2018.

Recent applications of machine learning in medicinal chemistry

In recent decades, artificial intelligence and machine learning have played a significant role in increasing the efficiency of processes across a wide spectrum of industries. When it comes to the pharmaceutical and biotechnology sectors, numerous tools enabled by advancement of computer science have been developed and are now routinely utilized. However, there are many aspects of the drug discovery process, which can further benefit from refinement of computational methods and tools, as well as improvement of accessibility of these new technologies. In this review, examples of recent developments in machine learning application are described, which have the potential to impact different parts of the drug discovery and development flow scheme. Notably, new deep learning-based approaches across compound design and synthesis, prediction of binding, activity and ADMET properties, as well as applications of genetic algorithms are highlighted.

Pharmaceutical Machine Learning: Virtual High-Throughput Screens Identifying Promising and Economical Small Molecule Inhibitors of Complement Factor C1s

When excessively activated, C1 is insufficiently regulated, which results in tissue damage. Such tissue damage causes the complement system to become further activated to remove the resulting tissue damage, and a vicious cycle of activation/tissue damage occurs. Current Food and Drug Administration approved treatments include supplemental recombinant C1 inhibitor, but these are extremely costly and a more economical solution is desired. In our work, we have utilized an existing data set of 136 compounds that have been previously tested for activity against C1. Using these compounds and the activity data, we have created models using principal component analysis, genetic algorithm, and support vector machine approaches to characterize activity. The models were then utilized to virtually screen the 72 million compound PubChem repository. This first round of virtual high-throughput screening identified many economical and promising inhibitor candidates, a subset of which was tested to validate their biological activity. These results were used to retrain the models and rescreen PubChem in a second round vHTS. Hit rates for the first round vHTS were 57%, while hit rates for the second round vHTS were 50%. Additional structure⁻property analysis was performed on the active and inactive compounds to identify interesting scaffolds for further investigation.