Molecular Similarity in Predictive Toxicology with a Focus on the q-RASAR Technique.

The concept of similarity is an important aspect in various in silico-based prediction approaches. Most of these approaches follow the basic similarity property principle that states that two or more compounds having a high level of similarity are expected to exert similar biological activity or physicochemical property. Although in some cases this principle fails to predict the biological activity or property efficiently for certain compounds, it is applicable to most of the compounds in a given dataset. With the emerging need to efficiently fill data gaps in the regulatory context, Read-Across (RA), a similarity-based approach, has gained popularity, since this is not a statistical approach like QSAR, which requires a sizeable amount of data points to train a meaningful model. The basic idea behind Read-Across is the identification of the close source neighbors, and based on the similarity considerations, predictions are made for the query compound. Although RA is originally an unsupervised prediction method, recent efforts for quantitative Read-Across (qRA) have introduced supervised similarity-based weightage for quantitative predictions. RA is a useful tool in predictive toxicology, but one of its important drawbacks is the lack of interpretability of the features (especially for q-RA) used to generate the Read-Across-based predictions. To bridge this gap, a novel quantitative Read-Across Structure-Activity Relationship (q-RASAR) approach has recently been proposed, which combines the concepts of QSAR and Read-Across, generating statistically reliable and predictive models using similarity and error-based descriptors. The q-RASAR models are simple and interpretable and can be efficiently used to identify not only the essential features but also the nature of the source and query compounds. In this chapter, we have discussed the concepts and various studies on RA, q-RA, and q-RASAR along with some of the tools available from different research groups.

Integration of QSAR and NAM in the Read-Across Process for an Effective and Relevant Toxicological Assessment.

Read-Across (RAx) serves as a strategy to fill a data gap in the toxicological profile of a substance (target) using existing information on similar source substances. The principle is applied also to a category of substances for which similarity may follow a regular trend. Demonstration of similarity is not trivial and requires the analysis of different steps, starting from the precise analytical characterization of both target and source substances and including the analysis of the impact that each minor difference can have on the final outcome. Application of QSARs and performing new experimental tests within the new approach methodologies (NAMs) is necessary to increase confidence in the final prediction and reduce the uncertainty.

QSAR: Using the Past to Study the Present.

Quantitative structure-activity relationships (QSAR) is a method for predicting the physical and biological properties of small molecules; it is in use in industry and public services. However, as any scientific method, it is challenged by more and more requests, especially considering its possible role in assessing the safety of new chemicals. To answer the question whether QSAR, by exploiting available knowledge, can build new knowledge, the chapter reviews QSAR methods in search of a QSAR epistemology. QSAR stands on tree pillars, i.e., biological data, chemical knowledge, and modeling algorithms. Usually the biological data, resulting from good experimental practice, are taken as a true picture of the world; chemical knowledge has scientific bases; so if a QSAR model is not working, blame modeling. The role of modeling in developing scientific theories, and in producing knowledge, is so analyzed. QSAR is a mature technology and is part of a large body of in silico methods and other computational methods. The active debate about the acceptability of the QSAR models, about the way to communicate them, and the explanation to provide accompanies the development of today QSAR models. An example about predicting possible endocrine-disrupting chemicals (EDC) shows the many faces of modern QSAR methods.

Applicability Domain for Trustable Predictions.

In the rapidly evolving landscape of artificial intelligence (AI) and machine learning (ML), understanding and correctly applying the concept of the applicability domain (AD) has emerged as an essential part. This chapter begins with an introduction and background on the critical area of AD. It dives into the definition and different methodologies associated with the applicability domain, laying a solid foundation for further exploration. A detailed examination of AD's role within the framework of AI and ML is undertaken, supported by in-depth theoretical foundations. The paper then proceeds to delineate the various measures of AD in AI and ML, offering insights into methods like DA index (κ, γ, δ), class probability estimation, and techniques involving local vicinity, boosting, classification neural networks, and subgroup discovery (SGD), among others. We also discussed a series of AD methods employed in Quantitative Structure-Activity Relationship (QSAR) studies. Lastly, the diverse applications of AD are addressed, underlining its widespread influence across different sectors. This chapter is intended to offer a thorough understanding of AD and its applications, particularly in AI and ML, leading to more informed research and decision-making in these fields as a good amount of literature already exists regarding AD of QSAR modeling.

Automated Workflows for Data Curation and Machine Learning to Develop Quantitative Structure-Activity Relationships.

The recent advancements in machine learning and the new availability of large chemical datasets made the development of tools and protocols for computational chemistry a topic of high interest. In this chapter a standard procedure to develop Quantitative Structure-Activity Relationship (QSAR) models was presented and implemented in two freely available and easy-to-use workflows. The first workflow helps the user retrieving chemical data (SMILES) from the web, checking their correctness and curating them to produce consistent and ready-to-use datasets for cheminformatic. The second workflow implements six machine learning methods to develop classification QSAR models. Models can be additionally used to predict external chemicals. Calculation and selection of chemical descriptors, tuning of models' hyperparameters, and methods to handle data unbalancing are also incorporated in the workflow. Both the workflows are implemented in KNIME and represent a useful tool for computational scientists, as well as an intuitive and straightforward introduction to QSAR.

Development, Use, and Validation of (Q)SARs for Predicting Genotoxicity and Carcinogenicity: Experiences from Italian National Institute of Health Activities.

In silico approaches are now increasingly accepted in several areas of toxicology to rapidly assess chemical hazard without the need for animal testing. Among in silico tools, quantitative and qualitative structure-activity approaches ((Q)SARs) are the most typically applied methods to predict hazard in the absence of experimental data. This paper provides an overview of different protocols that can be applied while dealing with (Q)SARs in different scenarios, namely, (Q)SAR development, use, and validation. Examples of protocols adopted in the three scenarios are reported, derived from the authors' experience in working at the Predictive Toxicology unit of the Italian National Institute of Health, focusing on the endpoints of carcinogenicity and genotoxicity.The illustrated activities are in line with the Institute's mission, the main center of research, control, and technical-scientific advice on public health in Italy.

New dynamic scoring method for deep evaluation of naloxegol as ß-tubulin binding inhibitor.

We report a new scoring method for rating the performance of ligands on same protein, using their extensive dynamic flexibility properties, binding with protein and impact on receptor protein. Based on molecular dynamics (MD), this method is more accurate than single-point energy calculations. This method identified an ideal FDA-approved drug as ß-tubulin microtubule inhibitor with improved attributes compared to commercial microtubule disassembly inhibitor, Paclitaxel (PTX). We started with virtual screening (VS) of FDA-approved drugs inside PTX's binding pocket (A) of human ß-tubulin protein. Screened ligands (>80% score) were evaluated for non-permeation through blood-brain barrier (BBB) as targets were body cancers, gastrointestinal absorption, Lipinski, non-efflux from central nervous system (CNS) by p-glycoprotein (Pgp), and ADMET analysis. This identified FDA-approved Naloxegol drug with superior attributes compared to PTX. Pocket (A) specific docking of chain length variable derivatives of Naloxegol gave docked poses that underwent MD run to give a range of properties and their descriptors (RMSD, RMSF, RoG, H-bonds, hydrophobic interaction and SASA). QSPR validated that MD properties dependent upon [-CH2-CH2-O-]n=0-7 chain length of Naloxegol. MD data underwent normalization, PCA analysis and scoring against PTX. One Naloxegol derivative scored higher than PTX as a potential microtubule disassembly inhibitor.

Research on Bitter Peptides in the Field of Bioinformatics: A Comprehensive Review.

Bitter peptides are small molecular peptides produced by the hydrolysis of proteins under acidic, alkaline, or enzymatic conditions. These peptides can enhance food flavor and offer various health benefits, with attributes such as antihypertensive, antidiabetic, antioxidant, antibacterial, and immune-regulating properties. They show significant potential in the development of functional foods and the prevention and treatment of diseases. This review introduces the diverse sources of bitter peptides and discusses the mechanisms of bitterness generation and their physiological functions in the taste system. Additionally, it emphasizes the application of bioinformatics in bitter peptide research, including the establishment and improvement of bitter peptide databases, the use of quantitative structure-activity relationship (QSAR) models to predict bitterness thresholds, and the latest advancements in classification prediction models built using machine learning and deep learning algorithms for bitter peptide identification. Future research directions include enhancing databases, diversifying models, and applying generative models to advance bitter peptide research towards deepening and discovering more practical applications.

Acetylation of Oleanolic Acid Dimers as a Method of Synthesis of Powerful Cytotoxic Agents.

Oleanolic acid, a naturally occurring triterpenoid compound, has garnered significant attention in the scientific community due to its diverse pharmacological properties. Continuing our previous work on the synthesis of oleanolic acid dimers (OADs), a simple, economical, and safe acetylation reaction was performed. The newly obtained derivatives (AcOADs, 3a-3n) were purified using two methods. The structures of all acetylated dimers (3a-3n) were determined based on spectral methods (IR, NMR). For all AcOADs (3a-3n), the relationship between the structure and the expected directions of pharmacological activity was determined using a computational method (QSAR computational analysis). All dimers were also tested for their cytotoxic activity on the SKBR-3, SKOV-3, PC-3, and U-87 cancer cell lines. HDF cell line was applied to evaluate the Selectivity Index of the tested compounds. All cytotoxic tests were performed with the application of the MTT assay. Finally, all dimers of oleanolic acid were subjected to DPPH and CUPRAC tests to evaluate their antioxidant activity. The obtained results indicate a very high level of cytotoxic activity (IC50 for most AcOADs below 5.00 µM) and a fairly high level of antioxidant activity (Trolox equivalent in some cases above 0.04 mg/mL).

Robustaflavone as a novel scaffold for inhibitors of native and auto-proteolysed human neutrophil elastase.

Human neutrophil elastase (HNE) plays a key role in initiating inflammation in the cardiopulmonary and systemic contexts. Pathological auto-proteolysed two-chain (tc) HNE exhibits reduced binding affinity with inhibitors. Using AutoDock Vina v1.2.0, 66 flavonoid inhibitors, sivelestat and alvelestat were docked with single-chain (sc) HNE and tcHNE. Schrodinger PHASE v13.4.132 was used to generate a 3D-QSAR model. Molecular dynamics (MD) simulations were conducted with AMBER v18. The 3D-QSAR model for flavonoids with scHNE showed r2 = 0.95 and q2 = 0.91. High-activity compounds had hydrophobic A/A2 and C/C2 rings in the S1 subsite, with hydrogen bond donors at C5 and C7 positions of the A/A2 ring, and the C4' position of the B/B1 ring. All flavonoids except robustaflavone occupied the S1'-S2' subsites of tcHNE with decreased AutoDock binding affinities. During MD simulations, robustaflavone remained highly stable with both HNE forms. Principal Component Analysis suggested that robustaflavone binding induced structural stability in both HNE forms. Cluster analysis and free energy landscape plots showed that robustaflavone remained within the sc and tcHNE binding site throughout the 100 ns MD simulation. The robustaflavone scaffold likely inhibits both tcHNE and scHNE. It is potentially superior to sivelestat and alvelestat and can aid in developing therapeutics targeting both forms of HNE.

Machine learning-based q-RASAR predictions of the bioconcentration factor of organic molecules estimated following the organisation for economic co-operation and development guideline 305.

In this study, we utilized an innovative quantitative read-across (RA) structure-activity relationship (q-RASAR) approach to predict the bioconcentration factor (BCF) values of a diverse range of organic compounds, based on a dataset of 575 compounds tested using Organisation for Economic Co-operation and Development Test Guideline 305 for bioaccumulation in fish. Initially, we constructed the q-RASAR model using the partial least squares regression method, yielding promising statistical results for the training set (R2 =0.71, Q2LOO=0.68, mean absolute error [MAE]training=0.54). The model was further validated using the test set (Q2F1=0.77, Q2F2=0.75, MAEtest=0.51). Subsequently, we explored the q-RASAR method using other regression-based supervised machine-learning algorithms, demonstrating favourable results for the training and test sets. All models exhibited R2 and Q2F1 values exceeding 0.7, Q2LOO values greater than 0.6, and low MAE values, indicating high model quality and predictive capability for new, unidentified chemical substances. These findings represent the significance of the RASAR method in enhancing predictivity for new unknown chemicals due to the incorporation of similarity functions in the RASAR descriptors, independent of a specific algorithm.

A new parameter for quantitatively characterizing antibiotic hormesis: QSAR construction and joint toxic action judgment.

Antibiotics usually induce the hormetic effects on bacteria, featured by low-dose stimulation and high-dose inhibition, which challenges the central belief in toxicity assessment and environmental risk assessment of antibiotics. However, there are currently no ideal parameters to quantitatively characterize hormesis. In this study, an effective area in hormesis (AH) was developed to quantify the biphasic dose-responses of single antibiotics (sulfonamides (SAs), sulfonamides potentiators (SAPs), and tetracyclines (TCs)) and binary mixtures (SAs-SAPs, SAs-TCs, and SAs-SAs) to the bioluminescence of Aliivibrio fischeri. Using Ebind (the lowest interaction energy between antibiotic and target protein) and Kow (octanol-water partition coefficient) as the structural descriptors, the reliable quantitative structure-activity relationship (QSAR) models were constructed for the AH values of test antibiotics and mixtures. Furthermore, a novel method based on AH was established to judge the joint toxic actions of binary antibiotics, which mainly exhibited synergism. The results also indicated that SAPs (or TCs) contributed more than SAs in the hormetic effects of antibiotic mixtures. This study proposes a new quantitative parameter for characterizing and predicting antibiotic hormesis, and considers hormesis as an integrated whole to reveal the combined effects of antibiotics, which will promote the development of risk evaluation for antibiotics and their mixtures.

Investigating PCB degradation by indigenous fungal strains isolated from the transformer oil-contaminated site: degradation kinetics, Bayesian network, artificial neural networks, QSAR with DFT, molecular docking, and molecular dynamics simulation.

The widespread prevalence of polychlorinated biphenyls (PCBs) in the environment has raised major concerns due to the associated risks to human health, wildlife, and ecological systems. Here, we investigated the degradation kinetics, Bayesian network (BN), quantitative structure-activity relationship-density functional theory (QSAR-DFT), artificial neural network (ANN), molecular docking (MD), and molecular dynamics stimulation (MS) of PCB biodegradation, i.e., PCB-10, PCB-28, PCB-52, PCB-138, PCB-153, and PCB-180 in the soil system using fungi isolated from the transformer oil-contaminated sites. Results revealed that the efficacy of PCB biodegradation best fits the first-order kinetics (R2 ≥ 0.93). The consortium treatment (29.44-74.49%) exhibited more efficient degradation of PCBs than those of Aspergillus tamarii sp. MN69 (27.09-71.25%), Corynespora cassiicola sp. MN69 (23.76-57.37%), and Corynespora cassiicola sp. MN70 (23.09-54.98%). 3'-Methoxy-2, 4, 4'-trichloro-biphenyl as an intermediate derivative was detected in the fungal consortium treatment. The BN analysis predicted that the biodegradation efficiency of PCBs ranged from 11.6 to 72.9%. The ANN approach showed the importance of chemical descriptors in decreasing order, i.e., LUMO > MW > IP > polarity no. > no. of chlorine > Wiener index > Zagreb index > HOMU > Pogliani index > APE in PCB removal. Furthermore, the QSAR-DFT model between the chemical descriptors and rate constant (log K) exhibited a high fit and good robustness of R2 = 99.12% in predicting ability. The MD and MS analyses showed the lowest binding energy through normal mode analysis (NMA), implying stability in the interactions of the docked complexes. These findings provide crucial insights for devising strategies focused on natural attenuation, holding substantial potential for mitigating PCB contamination within the environment.

Computer-aided discovery of novel SmDHODH inhibitors for schistosomiasis therapy: Ligand-based drug design, molecular docking, molecular dynamic simulations, drug-likeness, and ADMET studies.

Schistosomiasis, also known as bilharzia or snail fever, is a tropical parasitic disease resulting from flatworms of the Schistosoma genus. This often overlooked disease has significant impacts in affected regions, causing enduring morbidity, hindering child development, reducing productivity, and creating economic burdens. Praziquantel (PZQ) is currently the only treatment option for schistosomiasis. Given the potential rise of drug resistance and the limited treatment choices available, there is a need to develop more effective inhibitors for this neglected tropical disease (NTD). In view of this, quantitative structure-activity relationship studies (QSAR), molecular docking, molecular dynamics simulations, drug-likeness, and ADMET predictions were applied to 31 inhibitors of Schistosoma mansoni Dihydroorotate dehydrogenase (SmDHODH). The designed QSAR model demonstrated robust statistical parameters including an R2 of 0.911, R2adj of 0.890, Q2cv of 0.686, R2pred of 0.807, and cR2p of 0.825, confirming its robustness. Compound 26, identified as the most active derivative, emerged as a lead candidate for new potential inhibitors through ligand-based drug design. Subsequently, 12 novel compounds (26A-26L) were designed with enhanced inhibition activity and binding affinity. Molecular docking studies revealed strong and stable interactions, including hydrogen bonding and hydrophobic interactions, between the designed compounds and the target receptor. Molecular dynamics simulations over 100 nanoseconds and MM-PBSA free binding energy (ΔGbind) calculations validated the stability of the two best-designed molecules (26A and 26L). Furthermore, drug-likeness and ADMET prediction analyses affirmed the potential of these designed compounds, suggesting their promise as innovative agents for treating schistosomiasis.

Combining QSAR and SSD to predict aquatic toxicity and species sensitivity of pyrethroid and organophosphate pesticides.

The widespread use of pyrethroid and organophosphate pesticides necessitates accurate toxicity predictions for regulatory compliance. In this study QSAR and SSD models for six pyrethroid and four organophosphate compounds using QSAR Toolbox and SSD Toolbox have been developed. The QSAR models, described by the formula 48 h-EC50 or 96 h-LC50 = x + y * log Kow, were validated for predicting 48 h-EC50 values for acute Daphnia toxicity and 96 h-LC50 values for acute fish toxicity, meeting criteria of n ≥10, r2 ≥0.7, and Q2 >0.5. Predicted 48 h-EC50 values for pyrethroids ranged from 3.95 × 10-5 mg/L (permethrin) to 8.21 × 10-3 mg/L (fenpropathrin), and 96 h-LC50 values from 3.89 × 10-5 mg/L (permethrin) to 1.68 × 10-2 mg/L (metofluthrin). For organophosphates, 48 h-EC50 values ranged from 2.00 × 10-5 mg/L (carbophenothion) to 3.76 × 10-2 mg/L (crufomate) and 96 h-LC50 values from 3.81 × 10-3 mg/L (carbophenothion) to 12.3 mg/L (crufomate). These values show a good agreement with experimental data, though some, like Carbophenothion, overestimated toxicity. HC05 values, indicating hazardous concentrations for 5% of species, range from 0.029 to 0.061 µg/L for pyrethroids and 0.030 to 0.072 µg/L for organophosphates. These values aid in establishing environmental quality standards (EQS). Compared to existing EQS, HC05 values for pyrethroids were less conservative, while those for organophosphates were comparable.

Data-Driven Modelling of Substituted Pyrimidine and Uracil-Based Derivatives Validated with Newly Synthesized and Antiproliferative Evaluated Compounds.

The pyrimidine heterocycle plays an important role in anticancer research. In particular, the pyrimidine derivative families of uracil show promise as structural scaffolds relevant to cervical cancer. This group of chemicals lacks data-driven machine learning quantitative structure-activity relationships (QSARs) that allow for generalization and predictive capabilities in the search for new active compounds. To achieve this, a dataset of pyrimidine and uracil compounds from ChEMBL were collected and curated. A workflow was developed for data-driven machine learning QSAR using an intuitive dataset design and forwards selection of molecular descriptors. The model was thoroughly externally validated against available data. Blind validation was also performed by synthesis and antiproliferative evaluation of new synthesized uracil-based and pyrimidine derivatives. The most active compound among new synthesized derivatives, 2,4,5-trisubstituted pyrimidine was predicted with the QSAR model with differences of 0.02 compared to experimentally tested activity.

Molecular similarity in chemical informatics and predictive toxicity modeling: from quantitative read-across (q-RA) to quantitative read-across structure-activity relationship (q-RASAR) with the application of machine learning.

This article aims to provide a comprehensive critical, yet readable, review of general interest to the chemistry community on molecular similarity as applied to chemical informatics and predictive modeling with a special focus on read-across (RA) and read-across structure-activity relationships (RASAR). Molecular similarity-based computational tools, such as quantitative structure-activity relationships (QSARs) and RA, are routinely used to fill the data gaps for a wide range of properties including toxicity endpoints for regulatory purposes. This review will explore the background of RA starting from how structural information has been used through to how other similarity contexts such as physicochemical, absorption, distribution, metabolism, and elimination (ADME) properties, and biological aspects are being characterized. More recent developments of RA's integration with QSAR have resulted in the emergence of novel models such as ToxRead, generalized read-across (GenRA), and quantitative RASAR (q-RASAR). Conventional QSAR techniques have been excluded from this review except where necessary for context.

Leveraging In Silico Structure-Activity Models to Predict Acute Honey Bee (Apis mellifera) Toxicity for Agrochemicals.

In the realm of crop protection products, ensuring the safety of pollinators stands as a pivotal aspect of advancing sustainable solutions. Extensive research has been dedicated to this crucial topic as well as new approach methodologies in toxicity testing. Hence, within the agricultural and chemical industries, prioritizing pollinator safety remains a constant objective during the development of predictive tools. One of these tools includes computational models like quantitative structure-activity relationships (QSARs) that are valuable in predicting the toxicity of chemicals. This research uses bee toxicity data to develop artificial neural network classification models for predicting honey bee acute toxicity. Bee toxicity data from 1542 compounds were used to develop models; the sensitivity and specificity of the best model were 0.90 and 0.91, respectively. These in silico models can aid in the discovery of next-generation crop protection products. These tools can guide the screening and selection of next-generation crop protection molecules with high margins of safety to pollinators, and candidates with favorable sustainability profiles can be identified at the early discovery stage as precursors to in vivo data generation.

Design, Synthesis, Antifungal Evaluation, and Three-Dimensional Quantitative Structure-Activity Relationship of Novel 5-Sulfonyl-1,3,4-thiadiazole Flavonoids.

Plant pathogenic fungi frequently disrupt the normal physiological and biochemical functions of plants, leading to diseases, compromising plant health, and ultimately reducing crop yield. This study aimed to address this challenge by identifying antifungal agents with innovative structures and novel mechanisms of action. We designed and synthesized a series of flavonoid derivatives substituted with 5-sulfonyl-1,3,4-thiadiazole and evaluated their antifungal activity against five phytopathogenic fungi. Most flavonoid derivatives demonstrated excellent antifungal activity against Botrytis cinerea (B. cinerea), Alternaria solani (A. solani), Rhizoctorzia solani (R. solani), Fusarium graminearum (F. graminearum), and Colletotrichum orbiculare (C. orbiculare). Specifically, the EC50 values of 38 target compounds against R. solani were below 4 µg/mL, among which the compounds C13 (EC50 = 0.49 µg/mL), C15 (EC50 = 0.37 µg/mL), and C19 (EC50 = 0.37 µg/mL) had the most prominent antifungal activity, superior to that of the control drug carbendazim (EC50 = 0.52 µg/mL). Scanning electron microscopy (SEM) and transmission electron microscopy (TEM) images of the cellular ultrastructures of R. solani mycelia and cells after treatment with the compound C19 revealed sprawling growth of hyphae, a distorted outline of their cell walls, and reduced mitochondrial numbers. Studying the 3D-QSAR between the molecular structure and antifungal activity of 5-sulfonyl-1,3,4-thiadiazole-substituted flavonoid derivatives could significantly improve conventional drug molecular design pathways and facilitate the development of novel antifungal leads.

Predicting biological activity and design of 5-HT6 antagonists through assessment of ANN-QSAR models in the context of Alzheimer's disease.

CONTEXT: Alzheimer's disease (AD) is the leading cause of dementia around the world, totaling about 55 million cases, with an estimated growth to 74.7 million cases in 2030, which makes its treatment widely desired. Several studies and strategies are being developed considering the main theories regarding its origin since it is not yet fully understood. Among these strategies, the 5-HT6 receptor antagonism emerges as an auspicious and viable symptomatic treatment approach for AD. The 5-HT6 receptor belongs to the G protein-coupled receptor (GPCR) family and is closely implicated in memory loss processes. As a serotonin receptor, it plays an important role in cognitive function. Consequently, targeting this receptor presents a compelling therapeutic opportunity. By employing antagonists to block its activity, the 5-HT6 receptor's functions can be effectively modulated, leading to potential improvements in cognition and memory. METHODS: Addressing this challenge, our research explored a promising avenue in drug discovery for AD, employing Artificial Neural Networks-Quantitative Structure-Activity Relationship (ANN-QSAR) models. These models have demonstrated great potential in predicting the biological activity of compounds based on their molecular structures. By harnessing the capabilities of machine learning and computational chemistry, we aimed to create a systematic approach for analyzing and forecasting the activity of potential drug candidates, thus streamlining the drug discovery process. We assembled a diverse set of compounds targeting this receptor and utilized density functional theory (DFT) calculations to extract essential molecular descriptors, effectively representing the structural features of the compounds. Subsequently, these molecular descriptors served as input for training the ANN-QSAR models alongside corresponding biological activity data, enabling us to predict the potential efficacy of novel compounds as 5-hydroxytryptamine receptor 6 (5-HT6) antagonists. Through extensive analysis and validation of ANN-QSAR models, we identified eight new promising compounds with therapeutic potential against AD.