QSAR modeling for cytotoxicity of sulfur-containing Shikonin oxime derivatives targeting HCT-15, MGC-803, BEL-7402, and MCF-7 cell lines.

Targeting cancer cells through drug-based treatment or combination therapy protocols involving chemical compounds can be challenging due to multiple factors, including their resistance to bioactive compounds and the potential of drugs to damage healthy cells. This study aims to investigate the relationship between the structure of novel sulfur-containing shikonin oxime compounds and the corresponding cytotoxicity against four cancer types, namely colon, gastric, liver, and breast cancers, through computational chemistry tools. This investigation is suggested to help build insights into how the structure of the compounds influences their activity and understand the mechanisms behind it and subsequently might be used in multi-cancer drug design process to propose novel optimized compounds that potentially exhibit the desired activity. The findings showed that the cytotoxic activity against the four cancer types was accurately predictable (R2 > 0.7, NRMSE <20%) by a combination of search and machine learning algorithms, based on the information on the structure of the compounds, including their lipophilicity, surface area, and volume. Overall, this study is supposed to play a crucial role in effective multi-cancer drug design in cancer research areas.

Reducing overconfident errors in molecular property classification using Posterior Network.

Deep-learning-based classification models are increasingly used for predicting molecular properties in drug development. However, traditional classification models using the Softmax function often give overconfident mispredictions for out-of-distribution samples, highlighting a critical lack of accurate uncertainty estimation. Such limitations can result in substantial costs and should be avoided during drug development. Inspired by advances in evidential deep learning and Posterior Network, we replaced the Softmax function with a normalizing flow to enhance the uncertainty estimation ability of the model in molecular property classification. The proposed strategy was evaluated across diverse scenarios, including simulated experiments based on a synthetic dataset, ADMET predictions, and ligand-based virtual screening. The results demonstrate that compared with the vanilla model, the proposed strategy effectively alleviates the problem of giving overconfident but incorrect predictions. Our findings support the promising application of evidential deep learning in drug development and offer a valuable framework for further research.

HT_PREDICT: a machine learning-based computational open-source tool for screening HDAC6 inhibitors.

Histone deacetylase 6 (HDAC6) is a promising drug target for the treatment of human diseases such as cancer, neurodegenerative diseases (in particular, Alzheimer's disease), and multiple sclerosis. Considerable attention is paid to the development of selective non-toxic HDAC6 inhibitors. To this end, we successfully form a set of 3854 compounds and proposed adequate regression QSAR models for HDAC6 inhibitors. The models have been developed using the PubChem, Klekota-Roth, 2D atom pair fingerprints, and RDkit descriptors and the gradient boosting, support vector machines, neural network, and k-nearest neighbours methods. The models are integrated into the developed HT_PREDICT application, which is freely available at https://htpredict.streamlit.app/. In vitro studies have confirmed the predictive ability of the proposed QSAR models integrated into the HT_PREDICT web application. In addition, the virtual screening performed with the HT_PREDICT web application allowed us to propose two promising inhibitors for further investigations.

Synthetic Modification and Insecticidal Activity of 4-epi-cis-Dihydroagarofuran Derivatives.

To synthesize the fundamental framework of dihydroagarofuran, a novel strategy was devised for constructing the C-ring through a dearomatization reaction using 6-methoxy-1-tetralone as the initial substrate. Subsequently, the dihydroagarofuran skeleton was assembled via two consecutive Michael addition reactions. The conjugated diene and trans-dihydroagarofuran skeleton were modified. The insecticidal activities of 33 compounds against Mythimna separata were evaluated. Compounds 11-5 exhibited an LC50 value of 0.378 mg/mL. The activity exhibited a remarkable 29-fold increase compared to positive control Celangulin V, which was widely recognized as the most renowned natural dihydroagarofuran polyol ester insecticidal active compound. Docking experiments between synthetic compounds and target proteins revealed the shared binding sites with Celangulin V. Structure-activity relationship studies indicated that methyl groups at positions C4 and C10 significantly improved insecticidal activity, while ether groups with linear chains displayed enhanced activity; in particular, the allyl ether group demonstrated optimal efficacy. Furthermore, a three-dimensional quantitative structure-activity relationship model was established to investigate the correlation between the skeletal structure and activity. These research findings provide valuable insights for discovering and developing dihydroagarofuran-like compounds.

Phenolic Acid-ß-Cyclodextrin Complexation Study to Mask Bitterness in Wheat Bran: A Machine Learning-Based QSAR Study.

The need to solvate and encapsulate hydro-sensitive molecules drives noticeable trends in the applications of cyclodextrins in the pharmaceutical industry, in foods, polymers, materials, and in agricultural science. Among them, ß-cyclodextrin is one of the most used for the entrapment of phenolic acid compounds to mask the bitterness of wheat bran. In this regard, there is still a need for good data and especially for a robust predictive model that assesses the bitterness masking capabilities of ß-cyclodextrin for various phenolic compounds. This study uses a dataset of 20 phenolic acids docked into the ß-cyclodextrin cavity to generate three different binding constants. The data from the docking study were combined with topological, topographical, and quantum-chemical features from the ligands in a machine learning-based structure-activity relationship study. Three different models for each binding constant were computed using a combination of the genetic algorithm (GA) and multiple linear regression (MLR) approaches. The developed ML/QSAR models showed a very good performance, with high predictive ability and correlation coefficients of 0.969 and 0.984 for the training and test sets, respectively. The models revealed several factors responsible for binding with cyclodextrin, showing positive contributions toward the binding affinity values, including such features as the presence of six-membered rings in the molecule, branching, electronegativity values, and polar surface area.

Design, Synthesis, Antitumor, and Antiplasmodial Evaluation of New 7-Chloroquinoline-Benzimidazole Hybrids.

Newly synthesized 7-chloro-4-aminoquinoline-benzimidazole hybrids were characterized by NMR and elemental analysis. Compounds were tested for their effects on the growth of the non-tumor cell line MRC-5 (human fetal lung fibroblasts) and carcinoma (HeLa and CaCo-2), leukemia, and lymphoma (Hut78, THP-1, and HL-60) cell lines. The obtained results, expressed as the concentration at which 50% inhibition of cell growth is achieved (IC50 value), show that the tested compounds affect cell growth differently depending on the cell line and the applied dose (IC50 ranged from 0.2 to >100 µM). Also, the antiplasmodial activity of these hybrids was evaluated against two P. falciparum strains (Pf3D7 and PfDd2). The tested compounds showed potent antiplasmodial activity, against both strains, at nanomolar concentrations. Quantitative structure-activity relationship (QSAR) analysis resulted in predictive models for antiplasmodial activity against the 3D7 strain (R2 = 0.886; Rext2 = 0.937; F = 41.589) and Dd2 strain (R2 = 0.859; Rext2 = 0.878; F = 32.525) of P. falciparum. QSAR models identified the structural features of these favorable effects on antiplasmodial activities.

A Review of Machine Learning and QSAR/QSPR Predictions for Complexes of Organic Molecules with Cyclodextrins.

Cyclodextrins are macrocyclic rings composed of glucose residues. Due to their remarkable structural properties, they can form host-guest inclusion complexes, which is why they are frequently used in the pharmaceutical, cosmetic, and food industries, as well as in environmental and analytical chemistry. This review presents the reports from 2011 to 2023 on the quantitative structure-activity/property relationship (QSAR/QSPR) approach, which is primarily employed to predict the thermodynamic stability of inclusion complexes. This article extensively discusses the significant developments related to the size of available experimental data, the available sets of descriptors, and the machine learning (ML) algorithms used, such as support vector machines, random forests, artificial neural networks, and gradient boosting. As QSAR/QPR analysis only requires molecular structures of guests and experimental values of stability constants, this approach may be particularly useful for predicting these values for complexes with randomly substituted cyclodextrins, as well as for estimating their dependence on pH. This work proposes solutions on how to effectively use this knowledge, which is especially important for researchers who will deal with this topic in the future. This review also presents other applications of ML in relation to CD complexes, including the prediction of physicochemical properties of CD complexes, the development of analytical methods based on complexation with CDs, and the optimisation of experimental conditions for the preparation of the complexes.

Exploring putative drug properties associated with TNF-alpha inhibition and identification of potential targets in cardiovascular disease using machine learning-assisted QSAR modeling and virtual reverse pharmacology approach.

Cardiovascular disease is a chronic inflammatory disease with high mortality rates. TNF-alpha is pro-inflammatory and associated with the disease, but current medications have adverse effects. Therefore, efficient inhibitors are urgently needed as alternatives. This study represents a structural-activity relationship investigation of TNF-alpha, curated from the ChEMBL database. Exploratory data analysis was performed to visualize the physicochemical properties of different bioactivity groups. The extracted molecules were subjected to PubChem and SubStructure fingerprints, and a QSAR-based Random Forest (QSAR-RF) model was generated using the WEKA tool. The QSAR random Forest model was built based on the SubStructure fingerprint with a correlation coefficient of 0.992 and 0.716 as the respective tenfold cross-validation scores. The variance important plot (VIP) method was used to extract the important features for TNF-alpha inhibition. The Substructure-based QSAR-RF (SS-QSAR-RF) model was validated using molecules from PubChem and ZINC databases. The generated model also predicts the pIC50 value of the molecules selected from the docking study followed by molecular dynamic simulation with the time step of 100 ns. Through virtual reverse pharmacology, we determined the main drug targets from the top four hit compounds obtained via molecular docking study. Our analysis included an integrated bioinformatics approach to pinpoint crucial targets like EGRF, HSP900A1, STAT3, PSEN1, AKT1, and MDM2. Further, GO and KEGG pathways analysis identified relevant cardiovascular disease-related pathways for the hub gene involved. However, this study provides valuable insights, it is important to note that it lacks experimental application. Future research may benefit from conducting in-vitro and in-vivo studies.

Synthesis, biological evaluation, theoretical calculations, QSAR and molecular docking studies of novel arylaminonaphthols as potent antioxidants and BChE inhibitors.

A completely green protocol was developed for the synthesis of a series of arylaminonaphthol derivatives in the presence of N-ethylethanolamine (NEEA) as a catalyst under ultrasonic irradiation and solventless conditions. The major assets of this methodology were the use of non-toxic organic medium, available catalyst, mild reaction condition, and good to excellent yield of desired products. All of the synthesized products were screened for their in vitro antioxidant activity using DPPH, ABTS, and Ferric-phenanthroline assays and it was found that most of them are potent antioxidant agents. Also, their butyrylcholinesterase inhibitory activity has been investigated in vitro. All tested compounds exhibited potential inhibitory activity toward BuChE when compared to standard reference drug galantamine, however, compounds 4r, 4u, 4 g and 4x gave higher butyrylcholinesterase inhibitory with IC50 values of 14.78 ± 0.65 µM, 16.18 ± 0.50 µM, 20.00 ± 0.50 µM, and 20.28 ± 0.08 µM respectively. On the other hand, we employed density functional theory (DFT), calculations to analyze molecular geometry and global reactivity descriptors, and MESP analysis to predict electrophilic and nucleophilic attacks. A quantitative structure-activity relationship (QSAR) investigation was conducted on the antioxidant and butyrylcholinesterase properties of 25 arylaminonaphthol derivatives, resulting in robust and satisfactory models. To evaluate their anti-Alzheimer's activity, compounds 4 g, 4q, 4r, 4u, and 4x underwent docking simulations at the active site of the acetylcholinesterase (AChE) and butyrylcholinesterase (BChE), revealing why these compounds displayed superior activity, consistent with the biological findings.

Multi-Task ADME/PK prediction at industrial scale: leveraging large and diverse experimentaldatasets.

ADME (Absorption, Distribution, Metabolism, Excretion) properties are key parameters to judge whether a drug candidate exhibits a desired pharmacokinetic (PK) profile. In this study, we tested multi-task machine learning (ML) models to predict ADME and animal PK endpoints trained on in-house data generated at Boehringer Ingelheim. Models were evaluated both at the design stage of a compound (i. e., no experimental data of test compounds available) and at testing stage when a particular assay would be conducted (i. e., experimental data of earlier conducted assays may be available). Using realistic time-splits, we found a clear benefit in performance of multi-task graph-based neural network models over single-task model, which was even stronger when experimental data of earlier assays is available. In an attempt to explain the success of multi-task models, we found that especially endpoints with the largest numbers of data points (physicochemical endpoints, clearance in microsomes) are responsible for increased predictivity in more complex ADME and PK endpoints. In summary, our study provides insight into how data for multiple ADME/PK endpoints in a pharmaceutical company can be best leveraged to optimize predictivity of ML models.

4D-QSAR, ADMET properties, and molecular dynamics simulations for designing N-substituted urea/thioureas as human glutaminyl cyclase inhibitors.

Human glutaminyl cyclase (hQC) inhibitors have great potential to be used as anti- Alzheimer's disease (AD) agents by reducing the toxic pyroform of ß-amyloid in the brains of AD patients. The four-dimensional quantitative structure activity relationship (4D-QSAR) model of N-substituted urea/thioureas was established with satisfying predictive ability and statistical reliability (Q2 = 0.521, R2 = 0.933, R2prep = 0.619). By utilizing the developed 4D-QSAR model, a set of new N-substituted urea/thioureas was designed and evaluated for their Absorption Distribution Metabolism Excretion and Toxicity (ADMET) properties. The results of molecular dynamics (MD) simulations, Principal component analysis (PCA), free energy landscape (FEL), dynamic cross-correlation matrix (DCCM) and molecular mechanics generalized Born Poisson-Boltzmann surface area (MM-PBSA) free energy calculations, revealed that the designed compounds were remained stable in protein binding pocket and compounds b ∼ f (-35.1 to -44.55 kcal/mol) showed higher binding free energy than that of compound 14 (-33.51 kcal/mol). The findings of this work will be a theoretical foundation for further research and experimental validation of urea/thiourea derivatives as hQC inhibitors.

Fragment-based QSAR study to explore the structural requirements of DPP-4 inhibitors: a stepping stone towards better type 2 diabetes mellitus management.

Dipeptidyl peptidase-4 (DPP-4) inhibitors belong to a prominent group of pharmaceutical agents that are used in the governance of type 2 diabetes mellitus (T2DM). They exert their antidiabetic effects by inhibiting the incretin hormones like glucagon-like peptide-1 and glucose-dependent insulinotropic polypeptide which, play a pivotal role in the regulation of blood glucose homoeostasis in our body. DPP-4 inhibitors have emerged as an important class of oral antidiabetic drugs for the treatment of T2DM. Surprisingly, only a few 2D-QSAR studies have been reported on DPP-4 inhibitors. Here, fragment-based QSAR (Laplacian-modified Bayesian modelling and Recursive partitioning (RP) approaches have been utilized on a dataset of 108 DPP-4 inhibitors to achieve a deeper understanding of the association among their molecular structures. The Bayesian analysis demonstrated satisfactory ROC values for the training as well as the test sets. Meanwhile, the RP analysis resulted in decision tree 3 with 2 leaves (Tree 3: 2 leaves). This present study is an effort to get an insight into the pivotal fragments modulating DPP-4 inhibition.

Safer and greener chemicals for the aquatic ecosystem: Chemometric modeling of the prolonged and chronic aquatic toxicity of chemicals on Oryzias latipes.

In the modern era, chemicals and their products have been used everywhere like agriculture, healthcare, food, cosmetics, pharmaceuticals, household products, clothing industry, etc. These chemicals find their way to reach the aquatic ecosystem (directly/indirectly) and cause severe chronic and prolonged toxic effects to aquatic species which is also then translated to human beings. Prolonged and chronic toxicity data of many chemicals that are used daily is not available due to high experimentation testing costs, time investment, and the requirement of a large number of animal sacrifices. Thus, in silico approaches (e.g., QSAR (quantitative structure-activity relationship)) are the best alternative for chronic and prolonged toxicity predictions. The present work offers multi-endpoint (five endpoints: chronic_LOEC, prolonged_14D_LC50, prolonged_14D_NOEC, prolonged_21D_LC50, prolonged_21D_NOEC) QSAR models for addressing the prolonged and chronic aquatic toxicity of chemicals toward fish (O. latipes). The statistical results (R2 =0.738-0.869, QLOO2 =0.712-0.831, Q(F1)2 =0.618-0.731) of the developed models show that they were robust, reliable, reproducible, accurate, and predictive. Some of the features that are responsible for prolonged and chronic toxicity of chemicals towards O. latipes are as follows: the presence of substituted benzene, hydrophobicity, unsaturation, electronegativity, the presence of long-chain fragments, the presence of a greater number of atoms at conjugation, and the presence of halogen atoms. On the other hand, hydrophilicity and graph density descriptors retard the aquatic chronic and prolonged toxicity of chemicals toward O. latipes. The PPDB (pesticide properties database) and experimental and investigational classes of drugs from the DrugBank database were also screened using the developed model. Thus, these multi-endpoint models will be helpful for data-gap filling and provide a broad range of applicability. Therefore, this research will aid in the in silico QSAR (quantitative structure-activity relationship) prediction (non-animal testing) of the prolonged and chronic toxicity of untested and new toxic chemicals/drugs/pesticides, design and development of eco-friendly, novel, and safer chemicals, and help to protect the aquatic ecosystem from exposure to toxic and hazardous chemicals.

From molecular descriptors to the developmental toxicity prediction of pesticides/veterinary drugs/bio-pesticides against zebrafish embryo: Dual computational toxicological approaches for prioritization.

The escalating introduction of pesticides/veterinary drugs into the environment has necessitated a rapid evaluation of their potential risks to ecosystems and human health. The developmental toxicity of pesticides/veterinary drugs was less explored, and much less the large-scale predictions for untested pesticides, veterinary drugs and bio-pesticides. Alternative methods like quantitative structure-activity relationship (QSAR) are promising because their potential to ensure the sustainable and safe use of these chemicals. We collected 133 pesticides and veterinary drugs with half-maximal active concentration (AC50) as the zebrafish embryo developmental toxicity endpoint. The QSAR model development adhered to rigorous OECD principles, ensuring that the model possessed good internal robustness (R2 > 0.6 and QLOO2 > 0.6) and external predictivity (Rtest2 > 0.7, QFn2 >0.7, and CCCtest > 0.85). To further enhance the predictive performance of the model, a quantitative read-across structure-activity relationship (q-RASAR) model was established using the combined set of RASAR and 2D descriptors. Mechanistic interpretation revealed that dipole moment, the presence of C-O fragment at 10 topological distance, molecular size, lipophilicity, and Euclidean distance (ED)-based RA function were main factors influencing toxicity. For the first time, the established QSAR and q-RASAR models were combined to prioritize the developmental toxicity of a vast array of true external compounds (pesticides/veterinary drugs/bio-pesticides) lacking experimental values. The prediction reliability of each query molecule was evaluated by leverage approach and prediction reliability indicator. Overall, the dual computational toxicology models can inform decision-making and guide the design of new pesticides/veterinary drugs with improved safety profiles.

Unveiling critical structural features for effective HDAC8 inhibition: a comprehensive study using quantitative read-across structure-activity relationship (q-RASAR) and pharmacophore modeling.

Histone deacetylases constitute a group of enzymes that participate in several biological processes. Notably, inhibiting HDAC8 has become a therapeutic strategy for various diseases. The current inhibitors for HDAC8 lack selectivity and target multiple HDACs. Consequently, there is a growing recognition of the need for selective HDAC8 inhibitors to enhance the effectiveness of therapeutic interventions. In our current study, we have utilized a multi-faceted approach, including Quantitative Structure-Activity Relationship (QSAR) combined with Quantitative Read-Across Structure-Activity Relationship (q-RASAR) modeling, pharmacophore mapping, molecular docking, and molecular dynamics (MD) simulations. The developed q-RASAR model has a high statistical significance and predictive ability (Q2F1:0.778, Q2F2:0.775). The contributions of important descriptors are discussed in detail to gain insight into the crucial structural features in HDAC8 inhibition. The best pharmacophore hypothesis exhibits a high regression coefficient (0.969) and a low root mean square deviation (0.944), highlighting the importance of correctly orienting hydrogen bond acceptor (HBA), ring aromatic (RA), and zinc-binding group (ZBG) features in designing potent HDAC8 inhibitors. To confirm the results of q-RASAR and pharmacophore mapping, molecular docking analysis of the five potent compounds (44, 54, 82, 102, and 118) was performed to gain further insights into these structural features crucial for interaction with the HDAC8 enzyme. Lastly, MD simulation studies of the most active compound (54, mapped correctly with the pharmacophore hypothesis) and the least active compound (34, mapped poorly with the pharmacophore hypothesis) were carried out to validate the observations of the studies above. This study not only refines our understanding of essential structural features for HDAC8 inhibition but also provides a robust framework for the rational design of novel selective HDAC8 inhibitors which may offer insights to medicinal chemists and researchers engaged in the development of HDAC8-targeted therapeutics.

Investigation of 3-Phenylcoumarin Derivatives as Potential Multi-target Inhibitors for Human Cholinesterases and Monoamine oxidases: A Computational Approach.

Alzheimer's disease (AD) is the predominant etiology of dementia, impacting a global population of approximately 50 million individuals. In the field of medicinal chemistry, there have been notable advancements in the utilization of monoamine oxidase (MAO) and cholinesterase (ChE) inhibitors for the purpose of addressing the neurotransmitter shortage associated with Alzheimer's disease (AD). A selection of previously synthesized 3-Phenylcoumarin derivatives (5a-m) were selected for examination in the pursuit of potential multi-targeting inhibitors of MAO-A, MAO-B, AChE, and BChE. The stability and reactivity of the compounds were investigated through the utilization of density functional theory (DFT) simulations. Subsequently, a CoMFA technique, grounded in 3D-QSAR principles, was employed to construct a model and predict the inhibitory properties of analogues belonging to the class of 3-phenylcoumarin derivatives. Through the application of molecular docking methodologies, we have employed predictive analyses to determine the potential binding interactions and stability of the drugs under investigation. The results obtained from the present investigation indicate that the 3-phenylcoumarin derivatives possess a reactive electronic characteristic that is crucial for their anti-cholinesterase activity. Compound 5a demonstrated a noteworthy binding score with AChE, BChE, MAO-A and MAO-B, respectively, indicating a robust binding affinity.

Quantitative structure-activity relationship of 2,6-dimethoxy-N-(3-(4-substituted phenyl)isoxazol-5-yl)benzamide for the inhibition of chitin synthesis.

Previously, we found that 5-(2,6-dimethoxybenzoylamino)-3-phenylisoxazoles (IOXs) inhibit chitin synthesis in the cultured integument of Chilo suppressalis. In this study, IOXs with various substituents at the para-position of the 3-phenyl ring were synthesized, and the concentrations required to inhibit chitin synthesis to 50% (IC50) were determined for all compounds. The introduction of halogens-such as F, Cl, and Br-and small alkyls-such as Me, Et, Pr, and n-Bu-at the 3-phenyl ring slightly enhanced the activity. However, the activity decreased drastically with the introduction of NO2, CF3, and t-Bu. The quantitative analysis of the substituent effect at the 3-phenyl ring on chitin-synthesis inhibition using the Hansch-Fujita method showed that the hydrophobic substituent with the optimum value was favored for the activity, but the bulky substituent in terms of E s was detrimental to the activity.

Design, Synthesis, Antifungal Activity, and 3D-QSAR Study of Novel Quinoxaline-2-Oxyacetate Hydrazide.

Plant pathogenic fungi pose a major threat to global food security, ecosystem services, and human livelihoods. Effective and broad-spectrum fungicides are needed to combat these pathogens. In this study, a novel antifungal 2-oxyacetate hydrazide quinoxaline scaffold as a simple analogue was designed and synthesized. Their antifungal activities were evaluated against Botrytis cinerea (B. cinerea), Altemaria solani (A. solani), Gibberella zeae (G. zeae), Rhizoctonia solani (R. solani), Colletotrichum orbiculare (C. orbiculare), and Alternaria alternata (A. alternata). These results demonstrated that most compounds exhibited remarkable inhibitory activities and possessed better efficacy than ridylbacterin, such as compound 15 (EC50 = 0.87 µg/mL against G. zeae, EC50 = 1.01 µg/mL against C. orbiculare) and compound 1 (EC50 = 1.54 µg/mL against A. alternata, EC50 = 0.20 µg/mL against R. solani). The 3D-QSAR analysis of quinoxaline-2-oxyacetate hydrazide derivatives has provided new insights into the design and optimization of novel antifungal drug molecules based on quinoxaline.

In silico screening of Fyn kinase inhibitors using classification-based QSAR model, molecular docking, molecular dynamics and ADME study.

This study aimed to use a computational approach that combined the classification-based QSAR model, molecular docking, ADME studies, and molecular dynamics (MD) to identify potential inhibitors of Fyn kinase. First, a robust classification model was developed from a dataset of 1,078 compounds with known Fyn kinase inhibitory activity, using the XGBoost algorithm. After that, molecular docking was performed between potential compounds identified from the QSAR model and Fyn kinase to assess their binding strengths and key interactions, followed by MD simulations. ADME studies were additionally conducted to preliminarily evaluate the pharmacokinetics and drug-like characteristics of these compounds. The results showed that our obtained model exhibited good predictive performance with an accuracy of 0.95 on the test set, affirming its reliability in identifying potent Fyn kinase inhibitors. Through the application of this model in conjunction with molecular docking and ADME studies, nine compounds were identified as potential Fyn kinase inhibitors, including 208 (ZINC70708110), 728 (ZINC8792432), 734 (ZINC8792187), 736 (ZINC8792350), 738 (ZINC8792286), 739 (ZINC8792309), 817 (ZINC33901069), 852 (ZINC20759145), and 1227 (ZINC100006936). MD simulations further demonstrated that the four most promising compounds, 728, 734, 736, and 852 exhibited stable binding with Fyn kinase during the simulation process. Additionally, a web-based platform ( https://fynkinase.streamlit.app/ ) has been developed to streamline the screening process. This platform enables users to predict the activity of their substances of interest on Fyn kinase from their SMILES, using our classification-based QSAR model and molecular docking.