A Reinforcement Learning-guided Genetic Algorithm Integrating Medicinal Chemistryinspired Molecular Transformations

Despite advances in computational drug discovery, de novo drug design remains hindered by high licensing costs and the need for specialized programming expertise. We present LigandForge, a webserver for structure-guided de novo ligand generation. LigandForge integrates structural validation and binding-site characterization; voxel-based property grid construction for spatial mapping of electrostatics and hydrophobicity; chemistry-aware fragment assembly; multi-objective lead optimization; and retrosynthetic feasibility analysis. The platform utilizes a structure-guided framework to assemble molecules from curated fragment libraries while enforcing physicochemical constraints, including molecular weight, LogP, and hybridization states. Generated molecules are refined via reinforcement learning and genetic algorithms which are subsequently evaluated using composite metrics such as the quantitative estimate of drug-likeness. By leveraging RDKit for cheminformatics and NGL viewer for real-time 3D visualization, LigandForge provides a synthesis-aware environment that bridges the gap between macromolecular structural data and experimentally feasible lead compounds without requiring local software installation.

ObjectiveBisphenol A (BPA), a pervasive environmental pollutant, is increasingly associated with osteoarthritis (OA) development, yet its molecular mechanisms remain unknown. Currently, there is no definitive cure for OA.MethodsBPA targets were predicted using STITCH and Swiss Target Prediction, while OA-related targets were collected from GeneCards, OMIM, and the Therapeutic Target Database (TTD). Protein-protein interaction (PPI) networks were constructed using STRING and visualized in Cytoscape to identify hub targets. Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses were performed, and molecular docking with AutoDock evaluated BPA-core target interactions. We employed our Computational Analysis of Novel Drug Opportunities (CANDO) platform for de novo drug prediction.ResultsSystematic bioinformatics analysis identified 26 candidate targets, with ESR1, PTGS2, CCL2, FLNA, and TRPV1 as key hubs. Pathway analysis revealed involvement in calcium ion transport, muscle contraction, IL-17 signaling, and estrogen signaling. Molecular docking confirmed strong BPA-target binding affinities. CANDO predicted 14 potential OA treatments, including glucosamine, ibuprofen, celecoxib, indomethacin, palmitic acid, and linoleic acid. Notably, qRT-PCR validation revealed that ESR1, PTGS2, CCL2, and TRPV1 were highly expressed, whereas FLNA was expressed at lower levels in the osteoarthritis blood samples.ConclusionsThis study elucidates BPA’s molecular mechanisms in OA and identifies promising therapeutic candidates. The integration of network toxicology, molecular docking, and computational drug discovery provides a robust framework for understanding environmental toxicants and advancing OA therapies.Supplementary InformationThe online version contains supplementary material available at 10.1186/s40360-025-01069-w.

Corona virus disease 2019, known as COVID-19, is a type of viral infection, which may cause acute respiratory infection and severe pneumonia, for which there is no specific therapeutic treatment. The available drugs are used only for symptomatic relief. Among all the targets, RNA-dependent RNA polymerase (RdRp) has been proved as an optimistic drug target against severe acute respiratory syndrome corona virus 2 (SARS-CoV-2) to manage its replication process. There are number of molecules which have been approved by the FDA as RdRp inhibitors such as ribavirin, remdesivir, sofosbuvir, etc. The reported inhibitors for RdRp enzyme is being used by the various researchers for repurposing of drugs against SARS-Cov-2 RdRp enzyme by implementing different computational methodologies. Molecular modeling and cheminformatics approaches have been used for the design and identification of novel molecules having medicinal applications in various areas. The preliminary studies in computational drug discovery (CDD) and in silico approaches are important parts of the modern drug discovery practices, and they are frequently applied in the identification of new drugs or for the prediction of biological activity of chemical series. Now, in the ongoing corona pandemic, in silico modeling is being proved very helpful for easy identification of novel inhibitors. The current chapter presents recent reports on the application of computational modeling approaches for the design and identification of ligands against RdRp associated with SARS-CoV-2. Here, we will illustrate recently published computational studies for the identification or development of novel RdRp inhibitors applying different computational approaches, encompassing homology modeling, molecular docking, virtual screening, and molecular dynamics simulations. The chapter will also provide the reader an overall idea about a successful computational drug discovery research in this particular area of applications.

Network pharmacology and molecular docking are widely applied in drug discovery, yet fragmented workflows and inconsistent operations frequently undermine result reproducibility. Here, a standardized protocol integrating these approaches into a reproducible framework for drug screening and mechanism exploration is described, with the workflow organized into three sequential phases: data preparation, computational analysis, and validation. In the preparation phase, compound libraries from public databases are filtered via Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) criteria, including oral bioavailability, drug-likeness, and toxicity prediction, while potential therapeutic targets are obtained through target prediction and integration of disease-related databases to comprehensively identify drug-disease interaction candidates. In the computational analysis phase, overlapping targets undergo Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses and protein-protein interaction network topological analysis to identify core targets; molecular docking is configured with two standardized optional strategies with distinct advantages. The two-step progressive strategy employs AutoDock Vina for high-throughput preliminary screening of the compound library, followed by precise re-docking with YASARA, which eliminates false positives from high-throughput screening and generates protein-ligand complexes natively compatible with subsequent YASARA molecular dynamics (MD) simulations to avoid structural deviations caused by cross-software format conversion. The one-step strategy completes the full docking process via YASARA alone, which simplifies the operation workflow, improves experimental efficiency, and is fully applicable for specific research goals. In the validation phase, standardized MD simulations evaluate ligand-protein complex stability via core metrics of root mean square deviation (RMSD) and root mean square fluctuation (RMSF). This unified, reproducible pipeline enhances the reliability of network pharmacology and docking studies and facilitates cross-study comparisons in computational drug discovery.

Common challenges in the area of robotics include issues such as sensor modeling, dynamic operating environments, and limited on-broad computational resources. To improve decision making, robots need a dependable framework to facilitate communication between different modules and the optimal action for real-world applications. The Robotics Operating System (ROS) and Reinforcement Learning (RL) are two promising approaches that help accomplish precise control, seamless integration of sensors-actuators, and exhibit learned behavior. The ROS enables seamless communication between heterogeneous components, while RL focuses on learning optimal behaviors through trial-and-error scenarios. Combining the ROS and RL offers superior decision making, improved perception, enhanced automation, and reliability. This work focuses on investigating ROS-based RL applications across various domains, aiming to enhance understanding through comprehensive discussion, analysis, and summarization. We base our evaluation on the application area, type of RL algorithm used, and degree of ROS–RL integration. Additionally, we provide summary of seminal works that define the current state of the art, along with GitHub repositories and resources for research purposes. Based on the review of successfully implemented projects, we make recommendations highlighting the advantages and limitations of RL techniques for specific applications and environments. The ultimate goal of this work is to advance the robotics field by providing a comprehensive overview of the recent important works that incorporate both the ROS and RL, thereby improving the adaptability of these emerging techniques.

Oropharyngeal candidiasis (OPC), a fungal infection affecting the mouth and throat, imposes a substantial burden on vulnerable populations such as HIV/AIDS patients, cancer treatment recipients, and the elderly. Conventional antifungal medications are encountering increasing resistance and side effects, necessitating the exploration of novel therapeutic approaches. This review proposes a comprehensive strategy for developing a novel natural product- based antifungal formulation targeting OPC. The approach involves harnessing promising natural compounds with established antifungal properties and employing advanced delivery systems like mucoadhesive microemulsions to improve efficacy and minimize adverse effects. Additionally, the review explores the integration of computational methods to expedite the identification and development of potent antifungal agents. A comprehensive literature review was conducted using databases such as PubMed, Scopus, and Web of Science. Search terms included combinations of "oropharyngeal candidiasis," "natural antifungal agents," "flavonoids," "mucoadhesive microemulsions," "computational drug discovery," and "in vitro/in vivo studies." Priority was given to studies published within the last ten years. The review identifies promising natural compounds with antifungal activity against Candida species commonly associated with OPC. Additionally, several studies highlight the potential of computational tools such as molecular docking and in silico ADMET for rapidly identifying natural compounds with potent antifungal activity and favorable pharmacokinetic and safety profiles. A brief overview of in vitro and in vivo experiments is provided, emphasizing their role in validating the safety and efficacy of the proposed natural product-based antifungal formulation. Formulation and analytical aspects are also discussed. The multidisciplinary approach outlined, incorporating natural products, computational methods, advanced preclinical in vitro and in vivo experiments, and advanced delivery systems, offers promise for the rapid, cost-effective development of safe and effective optimized formulations to address the growing challenge of OPC, particularly in vulnerable populations.

As an efficient mode of public transportation, urban rail transit promotes sustainable development by reducing energy consumption and improving service quality. Numerous studies have been conducted on this subject. However, many existing methods struggle to adapt to environmental changes due to the complexity of actual line conditions. Therefore, based on deep deterministic policy gradient (DDPG) and genetic algorithm (GA), a new optimization algorithm GA-DDPG is proposed in this paper. This algorithm utilizes DDPG for continuous action control of trains and employs GA to optimize the noise generation hyperparameter of DDPG, thereby enhancing the learning and adaptive capabilities of the algorithm. Firstly, a reference system is established based on expert knowledge to ensure safe train operation and guide the training of the algorithm model. Then, under the intervention of reference system, the GA-DDPG is used to optimize and adjust the train operation control strategy to achieve a balance in punctuality, energy efficiency, and comfort. Finally, simulation experiment shows that GA-DDPG achieves at least 5.2% energy savings and 51.2% passenger comfort compared to DDPG. More experiments further demonstrate that GA-DDPG possesses better adaptability and robustness than DDPG when the environment changes.

This research work aims at evaluating the possibilities of using artificial intelligence in dynamic resource management and optimization of software system performance. In today’s complex world of application usage, normal methods of resource management are unable to cater to these dynamic needs and fulfill its usage potential. In this work, an assessment of three mainstream AI techniques – reinforcement learning, neural network, and genetic algorithm – is performed based on performance indicators such as resource utilization and consumption, average response time, throughput, costs, prediction capability, stability, and time taken to converge. The results show that the neural networks have the best resource acquisition performance as well as response rates, while the reinforcement learning has the best cost management and flexibility rates. As it has been pointed out, genetic algorithms are quite useful in finding optimization solutions, however real-time responsiveness is lack. Thus, the results provide significant understating of how to choose the proper AI technique depending on the specific application needs which in turn will be useful for organizations willing to improve their resource management using AI-based solutions.

It is pointed out that the genetic algorithms which have been shown to yield good performance for neural network weight optimization are really genetic hill-climbers, with a strong reliance on mutation rather than hyperplane sampling. Neural control problems are more appropriate for these genetic hill-climbers than supervised learning applications because in reinforcement learning applications gradient information is not directly available. Genetic reinforcement learning produces competitive results with the adaptive heuristic critic method, another reinforcement learning paradigm for neural networks that employs temporal difference methods. The genetic hill-climbing algorithm appears to be robust over a wide range of learning conditions. >

Novel vector quantiser design using reinforced learning as a pre-process

<title>Abstract</title> We present BiRLNN, a bidirectional molecular design framework that combines recurrent neural networks with reinforcement learning to optimize drug-like properties of generated compounds. Unlike traditional unidirectional models, our approach generates molecular sequences synchronously in both forward and backward directions, enabling more balanced exploration of chemical space while maintaining constraint requirements during molecular design. We employ Self-Referencing Embedded Strings representations to ensure 100% syntactic validity of generated molecules. To guide generation towards desirable pharmacological targets, we implement a multi-objective reward function based on quantitative estimate of drug-likeness and synthetic accessibility, and apply policy gradient-based reinforcement learning for fine-tuning. Simulation results show that our model covers a much larger part of the chemical space compared to unidirectional ones, allowing it to explore regions that contain molecules unreachable by the latter. Moreover, the reinforcement learning process successfully steers the generation process toward desirable compound classes with improved reward metrics. Our results demonstrate that BiRLNN offers a robust and flexible strategy for navigating chemical space in multi-objective drug design tasks.

Genetic algorithm, as a kind of evolutionary algorithm, has the characteristics of easy operation and global search, but its stochasticity is relatively strong and highly susceptible to parameters. When facing a large-scale scheduling problem, a strategy is needed to improve the parameter adaptability to make its solution more effective. Reinforcement learning, as an optimization method, has a strong autonomous learning capability. Therefore, this paper proposes a genetic algorithm based on reinforcement learning, which uses Q-learning to self-learning the crossover probability and improve the generalization ability of genetic algorithm, so as to achieve the solution of large-scale replacement flow shop scheduling problem.

A new hybrid solution is presented to improve the efficiency of intelligent warehouses with multirobot systems, where the genetic algorithm (GA) based task scheduling is combined with reinforcement learning (RL) based path planning for mobile robots. Reinforcement learning is an effective approach to search for a collision-free path in unknown dynamic environments. Genetic algorithm is a simple but splendid evolutionary search method that provides very good solutions for task allocation. In order to achieve higher efficiency of the intelligent warehouse system, we design a new solution by combining these two techniques and provide an effective and alternative way compared with other state-of-the-art methods. Simulation results demonstrate the effectiveness of the proposed approach regarding the optimization of travel time and overall efficiency of the intelligent warehouse system.

Filtering high-variability and high-severity defect reports from large test report databases is a challenging task in crowdtesting. Traditional optimization algorithms based on clustering and distance techniques have made progress but are limited by initial parameter settings and significantly decrease in efficiency with an increasing number of reports. To address this issue, this paper proposes a method that integrates reinforcement learning with genetic algorithms for crowdsourced testing report optimization, called Reinforcement Learning-based Genetic Algorithm for Crowdsourced Testing Report Optimization (RLGA). Its core goal is to identify distinct, high-severity defect reports from a large set. The method uses genetic algorithms to generate the optimal report selection sequence and adjusts the crossover probability (Pc) and mutation probability (Pm) dynamically with reinforcement learning based on the population’s average fitness, best fitness, and diversity. The reinforcement learning component uses a hybrid SARSA and Q-Learning strategy to update the Q-value table, allowing the algorithm to learn quickly in early iterations and expand the search space later to avoid local optima, thereby improving efficiency. To validate the RLGA method, this paper uses four public datasets and compares RLGA with six classic methods. The results indicate that RLGA outperforms BDDIV in terms of execution time and is less sensitive to the total number of test reports. In terms of optimization objectives, the test reports selected by RLGA have higher levels of defect severity and diversity than those selected by the random choice, BDDIV, and TSE methods. Regarding population diversity, RLGA effectively enhances the uniformity and diversity of individuals compared to random initialization. In terms of convergence speed, RLGA is superior to the GA, GA-SARSA, and GA-Q methods.

Beta-site APP cleaving enzyme 1 (BACE1) which plays a major role in Alzheimer’s disease (AD) is being currently considered as a promising target in AD therapeutics by designing inhibitors against it. But there exists very little information regarding the physiological function of the protein. Many highly potent BACE1 inhibitors failed in the clinical trials due to undesired side effects and toxicity. Thus more research to explore the physiological role of BACE1 is an urgent need. The protein is highly flexible and exhibits significant ligand-induced flexibility which poses a serious challenge in computer-aided drug designing. Recent advances in simulation methods as well as increase in computational resources shed novel insight into the ligand recognition process of BACE1, which stimulates the field of research that deals with devising novel methods to incorporate receptor flexibility in BACE1 for computational drug discovery. This chapter aims to provide up-to-date information of the physiological role of BACE1 as well as its localization and sorting pathways and discuss in details the inherent structural flexibility and ligand-induced motion of BACE1. Also, novel drug designing strategies developed targeting this receptor flexibility has been discussed in critical details which paves the path for developing novel method/algorithm in computational drug discovery of BACE1 inhibitors for AD.