Multi-objective optimization methods in novel drug design

A Hyper-Transformer model for Controllable Pareto Front Learning with Split Feasibility Constraints

Controllable Pareto front learning (CPFL) approximates the Pareto optimal solution set and then locates a non-dominated point with respect to a given reference vector. However, decision-maker objectives were limited to a constraint region in practice, so instead of training on the entire decision space, we only trained on the constraint region. Controllable Pareto front learning with Split Feasibility Constraints (SFC) is a way to find the best Pareto solutions to a split multi-objective optimization problem that meets certain constraints. In the previous study, CPFL used a Hypernetwork model comprising multi-layer perceptron (Hyper-MLP) blocks. Transformer can be more effective than previous architectures on numerous modern deep learning tasks in certain situations due to their distinctive advantages. Therefore, we have developed a hyper-transformer (Hyper-Trans) model for CPFL with SFC. We use the theory of universal approximation for the sequence-to-sequence function to show that the Hyper-Trans model makes MED errors smaller in computational experiments than the Hyper-MLP model.

Advancing Efficacy Prediction for EHR-based Emulated Trials in Repurposing Heart Failure Therapies

Introduction

The High mortality rates associated with heart failure (HF) have propelled the strategy of drug repurposing, which seeks new therapeutic uses for existing, approved drugs to enhance the management of HF symptoms effectively. An emerging trend focuses on utilizing real-world data, like EHR, to mimic randomized controlled trials (RCTs) for evaluating treatment outcomes through what are known as emulated trials (ET). Nonetheless, the intricacies inherent in EHR data-comprising detailed patient histories in databases, the omission of certain biomarkers or specific diagnostic tests, and partial records of symptoms- introduce notable discrepancies between EHR data and the stringent standards of RCTs. This gap poses a substantial challenge in conducting an ET to accurately predict treatment efficacy.

Objective

The objective of this research is to predict the efficacy of drugs repurposed for HF in randomized trials by leveraging EHR in ET.

Methods

We proposed an ET framework to predict drug efficacy, integrating target prediction based on biomedical databases with statistical analysis using EHR data. Specifically, we developed a novel target prediction model that learns low-dimensional representations of drug molecules, protein sequences, and diverse biomedical associations from a knowledge graph. Additionally, we crafted strategies to improve the prediction by considering the interactions between HF drugs and biological factors in the context of HF prognostic markers.

Results

Our validation of the drug-target prediction model against the BETA benchmark demonstrated superior performance, with an average AUCROC of 97.7%, PRAUC of 97.4%, F1 score of 93.1%, and a General Score of 96.1%, surpassing existing baseline algorithms. Further analysis of our ET framework on identifying 17 repurposed drugs-derived from 266 phase 3 HF RCTs-using data from 59,000 patients at the Mayo Clinic highlighted the framework's remarkable predictive accuracy. This analysis took into account various factors such as biological variables (e.g., gender, age, ethnicity), HF medications (e.g., ACE inhibitors, Beta-blockers, ARBs, Loop Diuretics), types of HF (HFpEF and HFrEF), confounders, and prognostic markers (e.g., NT-proBNP, BUN, creatinine, and hemoglobin). The ET framework significantly improved the accuracy compared to the baseline efficacy analysis that utilized EHR data. Notably, the best results were improved in AUC-ROC from 75.71% to 93.57% and in PRAUC from 78.66% to 90.34%, compared to the baseline models.

Conclusion

Our study presents an ET framework that significantly enhances drug efficacy emulation by integrating EHR-based analysis with target prediction. We demonstrated substantial success in predicting the efficacy of 17 HF drugs repurposed for phase 3 RCTs, showcasing the framework's potential in advancing HF treatment strategies.

Toward structure-multiple activity relationships (SMARts) using computational approaches: A polypharmacological perspective

In the current era of biological big data, which are rapidly populating the biological chemical space, in silico polypharmacology drug design approaches help to decode structure-multiple activity relationships (SMARts). Current computational methods can predict or categorize multiple properties simultaneously, which aids the generation, identification, curation, prioritization, optimization, and repurposing of molecules. Computational methods have generated opportunities and challenges in medicinal chemistry, pharmacology, food chemistry, toxicology, bioinformatics, and chemoinformatics. It is anticipated that computer-guided SMARts could contribute to the full automatization of drug design and drug repurposing campaigns, facilitating the prediction of new biological targets, side and off-target effects, and drug-drug interactions.

A framework for controllable Pareto front learning with completed scalarization functions and its applications

Pareto Front Learning (PFL) was recently introduced as an efficient method for approximating the entire Pareto front, the set of all optimal solutions to a Multi-Objective Optimization (MOO) problem. In the previous work, the mapping between a preference vector and a Pareto optimal solution is still ambiguous, rendering its results. This study demonstrates the convergence and completion aspects of solving MOO with pseudoconvex scalarization functions and combines them into Hypernetwork in order to offer a comprehensive framework for PFL, called Controllable Pareto Front Learning. Extensive experiments demonstrate that our approach is highly accurate and significantly less computationally expensive than prior methods in term of inference time.

Medicinal chemistry strategies towards the development of non-covalent SARS-CoV-2 Mpro inhibitors

The main protease (Mpro) of SARS-CoV-2 is an attractive target in anti-COVID-19 therapy for its high conservation and major role in the virus life cycle. The covalent Mpro inhibitor nirmatrelvir (in combination with ritonavir, a pharmacokinetic enhancer) and the non-covalent inhibitor ensitrelvir have shown efficacy in clinical trials and have been approved for therapeutic use. Effective antiviral drugs are needed to fight the pandemic, while non-covalent Mpro inhibitors could be promising alternatives due to their high selectivity and favorable druggability. Numerous non-covalent Mpro inhibitors with desirable properties have been developed based on available crystal structures of Mpro. In this article, we describe medicinal chemistry strategies applied for the discovery and optimization of non-covalent Mpro inhibitors, followed by a general overview and critical analysis of the available information. Prospective viewpoints and insights into current strategies for the development of non-covalent Mpro inhibitors are also discussed.

Multi-and many-objective optimization: present and future in de novo drug design

de novo Drug Design (dnDD) aims to create new molecules that satisfy multiple conflicting objectives. Since several desired properties can be considered in the optimization process, dnDD is naturally categorized as a many-objective optimization problem (ManyOOP), where more than three objectives must be simultaneously optimized. However, a large number of objectives typically pose several challenges that affect the choice and the design of optimization methodologies. Herein, we cover the application of multi- and many-objective optimization methods, particularly those based on Evolutionary Computation and Machine Learning techniques, to enlighten their potential application in dnDD. Additionally, we comprehensively analyze how molecular properties used in the optimization process are applied as either objectives or constraints to the problem. Finally, we discuss future research in many-objective optimization for dnDD, highlighting two important possible impacts: i) its integration with the development of multi-target approaches to accelerate the discovery of innovative and more efficacious drug therapies and ii) its role as a catalyst for new developments in more fundamental and general methodological frameworks in the field.

Progress in the development of TRPV1 small-molecule antagonists: Novel Strategies for pain management

Transient receptor potential vanilloid 1 (TRPV1) channels are widely distributed in sensory nerve endings, the central nervous system, and other tissues, functioning as ion channel proteins responsive to thermal pain and chemical stimuli. In recent years, the TRPV1 receptor has garnered significant interest as a potential therapeutic approach for various pain-related disorders, particularly TRPV1 antagonists. The present review offers a comprehensive, systematic exploration of both first- and second-generation TRPV1 antagonists in the context of pain management. Antagonists are categorized and explicated according to their structural characteristics. Detailed examination of binding modes, structural features, and pharmacological activities, alongside a critical appraisal of the advantages and limitations inherent to typical compounds within each structural category, are undertaken. Detailed discussions of the binding modes, structural features, pharmacological activities, advantages, and limitations of typical compounds within each structural category offer valuable insights and guidance for the future research and development of safer, more effective, and more targeted TRPV1 antagonists.

Design of new chemical entities targeting both native and H275Y mutant influenza a virus by deep reinforcement learning

Influenza virus remains a major public health challenge due to its high morbidity and mortality and seasonal surge. Although antiviral drugs against the influenza virus are widely used as a first-line defense, the virus undergoes rapid genetic changes, resulting in the emergence of drug-resistant strains. Thus, new antiviral drugs that can outwit resistant strains are of significant importance. Herein, we used deep reinforcement learning (RL) algorithm to design new chemical entities (NCEs) that are able to bind to the native and H275Y mutant (oseltamivir-resistant) neuraminidases (NAs) of influenza A virus with better binding energy than oseltamivir. We generated more than 66211 NCEs, which were prioritized based on the filtering rules, structural alerts, and synthetic accessibility. Then, 18 NCEs with better MM/PBSA scores than oseltamivir were further analyzed in molecular dynamics (MD) simulations conducted for 100 ns. The MD experiments showed that 8 NCEs formed very stable complexes with the binding pocket of both native and H275Y mutant NAs of H1N1. Furthermore, most NCEs demonstrated much better binding affinity to group 2 (N2, N3, and N9) and influenza B virus NAs than oseltamivir. Although all 8 NCEs have non-sialic acid-like structures, they showed a similar binding mode as oseltamivir, indicating that it is possible to find new scaffolds with better binding and antiviral properties than sialic acid-like inhibitors. In conclusion, we have designed potential compounds as antiviral candidates for further synthesis and testing against wild and mutant influenza virus.Communicated by Ramaswamy H. Sarma.

Multifunctional polydopamine - Zn2+-curcumin coated additively manufactured ceramic bone grafts with enhanced biological properties

The lack of site-specific chemotherapeutic agents after osteosarcoma surgeries often induces severe side effects. We propose the utilization of curcumin as an alternative natural chemo-preventive drug for tumor-specific delivery systems with 3D printed tricalcium phosphate (TCP) based artificial bone grafts. The poor bioavailability and hydrophobic nature of curcumin restrict its clinical use. We have used polydopamine (PDA) coating with Zn2+ functionalization to enhance the curcumin release in the biological medium. The obtained PDA-Zn2+ complex is characterized by X-ray photoelectron spectroscopy (XPS). The presence of PDA-Zn2+ coating leads to ~2 times enhancement in curcumin release. We have computationally predicted and validated the optimized surface composition by a novel multi-objective optimization method. The experimental validation of the predicted compositions indicates that the PDA-Zn2+ coated curcumin immobilized delivery system leads to a ~12 folds decrease in osteosarcoma viability on day 11 as compared to only TCP. The osteoblast viability shows ~1.4 folds enhancement. The designed surface shows the highest ~90 % antibacterial efficacy against gram-positive and gram-negative bacteria. This unique strategy of curcumin delivery with PDA-Zn2+ coating is expected to find application in low-load bearing critical-sized tumor-resection sites.

Vegetation Evolution with Dynamic Maturity Strategy and Diverse Mutation Strategy for Solving Optimization Problems

We introduce two new search strategies to further improve the performance of vegetation evolution (VEGE) for solving continuous optimization problems. Specifically, the first strategy, named the dynamic maturity strategy, allows individuals with better fitness to have a higher probability of generating more seed individuals. Here, all individuals will first become allocated to generate a fixed number of seeds, and then the remaining number of allocatable seeds will be distributed competitively according to their fitness. Since VEGE performs poorly in getting rid of local optima, we propose the diverse mutation strategy as the second search operator with several different mutation methods to increase the diversity of seed individuals. In other words, each generated seed individual will randomly choose one of the methods to mutate with a lower probability. To evaluate the performances of the two proposed strategies, we run our proposal (VEGE + two strategies), VEGE, and another seven advanced evolutionary algorithms (EAs) on the CEC2013 benchmark functions and seven popular engineering problems. Finally, we analyze the respective contributions of these two strategies to VEGE. The experimental and statistical results confirmed that our proposal can significantly accelerate convergence and improve the convergence accuracy of the conventional VEGE in most optimization problems.

Computer-aided multi-objective optimization in small molecule discovery

Molecular discovery is a multi-objective optimization problem that requires identifying a molecule or set of molecules that balance multiple, often competing, properties. Multi-objective molecular design is commonly addressed by combining properties of interest into a single objective function using scalarization, which imposes assumptions about relative importance and uncovers little about the trade-offs between objectives. In contrast to scalarization, Pareto optimization does not require knowledge of relative importance and reveals the trade-offs between objectives. However, it introduces additional considerations in algorithm design. In this review, we describe pool-based and de novo generative approaches to multi-objective molecular discovery with a focus on Pareto optimization algorithms. We show how pool-based molecular discovery is a relatively direct extension of multi-objective Bayesian optimization and how the plethora of different generative models extend from single-objective to multi-objective optimization in similar ways using non-dominated sorting in the reward function (reinforcement learning) or to select molecules for retraining (distribution learning) or propagation (genetic algorithms). Finally, we discuss some remaining challenges and opportunities in the field, emphasizing the opportunity to adopt Bayesian optimization techniques into multi-objective de novo design.

Comparative docking studies of drugs and phytocompounds for emerging variants of SARS-CoV-2

In the last three years, COVID-19 has impacted the world with back-to-back waves leading to devastating consequences. SARS-CoV-2, the causative agent of COVID-19, was first detected in 2019 and since then has spread to 228 countries. Even though the primary focus of research groups was diverted to fight against COVID-19, yet no dedicated drug has been developed to combat the emergent life-threatening medical conditions. In this study, 35 phytocompounds and 43 drugs were investigated for comparative docking analysis. Molecular docking and virtual screening were performed against SARS-CoV-2 spike glycoprotein of 13 variants using AutoDock Vina tool 1.5.6 and Discovery Studio, respectively, to identify the most efficient drugs. Selection of the most suitable compounds with the best binding affinity was done after screening for toxicity, ADME (absorption, distribution, metabolism and excretion) properties and drug-likeliness. The potential candidates were discovered to be Liquiritin (binding affinities ranging between -7.0 and -8.1 kcal/mol for the 13 variants) and Apigenin (binding affinities ranging between -6.8 and -7.3 kcal/mol for the 13 variants) based on their toxicity and consistent binding affinity with the Spike protein of all variants. The stability of the protein-ligand complex was determined using Molecular dynamics (MD) simulation of Apigenin with the Delta plus variant of SARS-CoV-2. Furthermore, Liquiritin and Apigenin were also found to be less toxic than the presently used drugs and showed promising results based on in silico studies, though, confirmation using in vitro studies is required. This in-depth comparative investigation suggests potential drug candidates to fight against SARS-CoV-2 variants.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13205-022-03450-6.

Detecting Drug–Target Interactions with Feature Similarity Fusion and Molecular Graphs

Simple Summary

Accurate identification of potential targets for drugs to interact with can accelerate drug development. The identification of drug–target interactions can provide insights into hidden drug efficacy. This paper presents a prediction model based on feature similarity fusion that can identify crucial features of drugs and targets to help predict drug–target interactions.

Abstract

The key to drug discovery is the identification of a target and a corresponding drug compound. Effective identification of drug–target interactions facilitates the development of drug discovery. In this paper, drug similarity and target similarity are considered, and graphical representations are used to extract internal structural information and intermolecular interaction information about drugs and targets. First, drug similarity and target similarity are fused using the similarity network fusion (SNF) method. Then, the graph isomorphic network (GIN) is used to extract the features with information about the internal structure of drug molecules. For target proteins, feature extraction is carried out using TextCNN to efficiently capture the features of target protein sequences. Three different divisions (CVD, CVP, CVT) are used on the standard dataset, and experiments are carried out separately to validate the performance of the model for drug–target interaction prediction. The experimental results show that our method achieves better results on AUC and AUPR. The docking results also show the superiority of the proposed model in predicting drug–target interactions.

Applications of Model-Based Target Pharmacology Assessment in Defining Drug Design and DMPK Strategies: GSK Experiences

Many critical decisions faced in early discovery require a thorough understanding of the dynamic behavior of pharmacological pathways following target engagement. From fundamental decisions on the optimal target to pursue and the ultimate drug product profile (combination of modality, potency, and compound properties) expected to elicit the desired clinical outcome to tactical program decisions such as what chemical series to pursue, what chemical properties require optimization, and what compounds to synthesize and progress, all demand detailed consideration of pharmacodynamics. Model-based target pharmacology assessment (mTPA) is a computational approach centered around large-scale virtual exploration of pharmacokinetic and pharmacodynamic models built early in discovery to guide these decisions. The present work summarizes several examples (use cases) from programs at GlaxoSmithKline that demonstrate the utility of mTPA throughout the drug discovery lifecycle.

Moving Average-Based Multitasking In Silico Classification Modeling: Where Do We Stand and What Is Next?

Conventional in silico modeling is often viewed as 'one-target' or 'single-task' computer-aided modeling since it mainly relies on forecasting an endpoint of interest from similar input data. Multitasking or multitarget in silico modeling, in contrast, embraces a set of computational techniques that efficiently integrate multiple types of input data for setting up unique in silico models able to predict the outcome(s) relating to various experimental and/or theoretical conditions. The latter, specifically, based upon the Box-Jenkins moving average approach, has been applied in the last decade to several research fields including drug and materials design, environmental sciences, and nanotechnology. The present review discusses the current status of multitasking computer-aided modeling efforts, meanwhile describing both the existing challenges and future opportunities of its underlying techniques. Some important applications are also discussed to exemplify the ability of multitasking modeling in deriving holistic and reliable in silico classification-based models as well as in designing new chemical entities, either through fragment-based design or virtual screening. Focus will also be given to some software recently developed to automate and accelerate such types of modeling. Overall, this review may serve as a guideline for researchers to grasp the scope of multitasking computer-aided modeling as a promising in silico tool.

Nextcast: A software suite to analyse and model toxicogenomics data

The recent advancements in toxicogenomics have led to the availability of large omics data sets, representing the starting point for studying the exposure mechanism of action and identifying candidate biomarkers for toxicity prediction. The current lack of standard methods in data generation and analysis hampers the full exploitation of toxicogenomics-based evidence in regulatory risk assessment. Moreover, the pipelines for the preprocessing and downstream analyses of toxicogenomic data sets can be quite challenging to implement. During the years, we have developed a number of software packages to address specific questions related to multiple steps of toxicogenomics data analysis and modelling. In this review we present the Nextcast software collection and discuss how its individual tools can be combined into efficient pipelines to answer specific biological questions. Nextcast components are of great support to the scientific community for analysing and interpreting large data sets for the toxicity evaluation of compounds in an unbiased, straightforward, and reliable manner. The Nextcast software suite is available at: ( https://github.com/fhaive/nextcast).