AI-assisted models to predict chemotherapy drugs modified with C60 fullerene derivatives.

Employing quantitative structure-activity relationship (QSAR)/ quantitative structure-property relationship (QSPR) models, this study explores the application of fullerene derivatives as nanocarriers for breast cancer chemotherapy drugs. Isolated drugs and two drug-fullerene complexes (i.e., drug-pristine C60 fullerene and drug-carboxyfullerene C60-COOH) were investigated with the protein CXCR7 as the molecular docking target. The research involved over 30 drugs and employed Pearson's hard-soft acid-base theory and common QSAR/QSPR descriptors to build predictive models for the docking scores. Energetic descriptors were computed using quantum chemistry at the density functional-based tight binding DFTB3 level. The results indicate that drug-fullerene complexes interact more with CXCR7 than isolated drugs. Specific binding sites were identified, with varying locations for each drug complex. Predictive models, developed using multiple linear regression and IBM Watson artificial intelligence (AI), achieved mean absolute percentage errors below 12%, driven by AI-identified key variables. The predictive models included mainly quantitative descriptors collected from datasets as well as computed ones. In addition, a water-soluble fullerene was used to compare results obtained by DFTB3 with a conventional density functional theory approach. These findings promise to enhance breast cancer chemotherapy by leveraging fullerene-based drug nanocarriers.

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.

Development of QSARs for cysteine-containing di- and tripeptides with antioxidant activity:influence of the cysteine position.

Antioxidants agents play an essential role in the food industry for improving the oxidative stability of food products. In the last years, the search for new natural antioxidants has increased due to the potential high toxicity of chemical additives. Therefore, the synthesis and evaluation of the antioxidant activity in peptides is a field of current research. In this study, we performed a Quantitative Structure Activity Relationship analysis (QSAR) of cysteine-containing 19 dipeptides and 19 tripeptides. The main objective is to bring information on the relationship between the structure of peptides and their antioxidant activity. For this purpose, 1D and 2D molecular descriptors were calculated using the PaDEL software, which provides information about the structure, shape, size, charge, polarity, solubility and other aspects of the compounds. Different QSAR model for di- and tripeptides were developed. The statistic parameters for di-peptides model (R2train = 0.947 and R2test = 0.804) and for tripeptide models (R2train = 0.923 and R2test = 0.847) indicate that the generated models have high predictive capacity. Then, the influence of the cysteine position was analyzed predicting the antioxidant activity for new di- and tripeptides, and comparing them with glutathione. In dipeptides, excepting SC, TC and VC, the activity increases when cysteine is at the N-terminal position. For tripeptides, we observed a notable increase in activity when cysteine is placed in the N-terminal position.

2D/3D-QSAR Model Development Based on a Quinoline Pharmacophoric Core for the Inhibition of Plasmodium falciparum: An In Silico Approach with Experimental Validation.

Malaria is an infectious disease caused by Plasmodium spp. parasites, with widespread drug resistance to most antimalarial drugs. We report the development of two 3D-QSAR models based on comparative molecular field analysis (CoMFA), comparative molecular similarity index analysis (CoMSIA), and a 2D-QSAR model, using a database of 349 compounds with activity against the P. falciparum 3D7 strain. The models were validated internally and externally, complying with all metrics (q2 > 0.5, r2test > 0.6, r2m > 0.5, etc.). The final models have shown the following statistical values: r2test CoMFA = 0.878, r2test CoMSIA = 0.876, and r2test 2D-QSAR = 0.845. The models were experimentally tested through the synthesis and biological evaluation of ten quinoline derivatives against P. falciparum 3D7. The CoMSIA and 2D-QSAR models outperformed CoMFA in terms of better predictive capacity (MAE = 0.7006, 0.4849, and 1.2803, respectively). The physicochemical and pharmacokinetic properties of three selected quinoline derivatives were similar to chloroquine. Finally, the compounds showed low cytotoxicity (IC50 > 100 µM) on human HepG2 cells. These results suggest that the QSAR models accurately predict the toxicological profile, correlating well with experimental in vivo data.

Arylamines QSAR-Based Design and Molecular Dynamics of New Phenylthiophene and Benzimidazole Derivatives with Affinity for the C111, Y268, and H73 Sites of SARS-CoV-2 PLpro Enzyme.

A non-structural SARS-CoV-2 protein, PLpro, is involved in post-translational modifications in cells, allowing the evasion of antiviral immune response mechanisms. In this study, potential PLpro inhibitory drugs were designed using QSAR, molecular docking, and molecular dynamics. A combined QSAR equation with physicochemical and Free-Wilson descriptors was formulated. The r2, q2, and r2test values were 0.833, 0.770, and 0.721, respectively. From the equation, it was found that the presence of an aromatic ring and a basic nitrogen atom is crucial for obtaining good antiviral activity. Then, a series of structures for the binding sites of C111, Y268, and H73 of PLpro were created. The best compounds were found to exhibit pIC50 values of 9.124 and docking scoring values of -14 kcal/mol. The stability of the compounds in the cavities was confirmed by molecular dynamics studies. A high number of stable contacts and good interactions over time were exhibited by the aryl-thiophenes Pred14 and Pred15, making them potential antiviral candidates.

Py-CoMFA, docking, and molecular dynamics simulations of Leishmania (L.) amazonensis arginase inhibitors.

Leishmaniasis is a disease caused by a protozoan of the genus Leishmania, affecting millions of people, mainly in tropical countries, due to poor social conditions and low economic development. First-line chemotherapeutic agents involve highly toxic pentavalent antimonials, while treatment failure is mainly due to the emergence of drug-resistant strains. Leishmania arginase (ARG) enzyme is vital in pathogenicity and contributes to a higher infection rate, thus representing a potential drug target. This study helps in designing ARG inhibitors for the treatment of leishmaniasis. Py-CoMFA (3D-QSAR) models were constructed using 34 inhibitors from different chemical classes against ARG from L. (L.) amazonensis (LaARG). The 3D-QSAR predictions showed an excellent correlation between experimental and calculated pIC50 values. The molecular docking study identified the favorable hydrophobicity contribution of phenyl and cyclohexyl groups as substituents in the enzyme allosteric site. Molecular dynamics simulations of selected protein-ligand complexes were conducted to understand derivatives' interaction modes and affinity in both active and allosteric sites. Two cinnamide compounds, 7g and 7k, were identified, with similar structures to the reference 4h allosteric site inhibitor. These compounds can guide the development of more effective arginase inhibitors as potential antileishmanial drugs.

The evaluation of skin sensitization potential of the UVCB substance diisopentyl phthalate by in silico and in vitro methods.

Diisopentyl phthalate (DiPeP) is primarily used as a plasticizer or additive within the production of polyvinyl chloride (PVC), and has many additional industrial applications. Its metabolites were recently found in urinary samples of pregnant women; thus, this substance is of concern as relates to human exposure. Depending upon the nature of the alcohol used in its synthesis, DiPeP may exist either as a mixture consisting of several branched positional isomers, or as a single defined structure. This article investigates the skin sensitization potential and immunomodulatory effects of DiPeP CAS No. 84777-06-0, which is currently marketed and classified as a UVCB substance, by in silico and in vitro methods. Our findings showed an immunomodulatory effect for DiPeP in LPS-induced THP-1 activation assay (increased CD54 expression). In silico predictions using QSAR TOOLBOX 4.5, ToxTree, and VEGA did not identify DiPeP, in the form of a discrete compound, as a skin sensitizer. The keratinocyte activation (Key Event 2 (KE2) of the adverse outcome pathway (AOP) for skin sensitization) was evaluated by two different test methods (HaCaT assay and RHE assay), and results were discordant. While the HaCaT assay showed that DiPeP can activate keratinocytes (increased levels of IL-6, IL-8, IL-1α, and ILA gene expression), in the RHE assay, DiPeP slightly increased IL-6 release. Although inconclusive for KE2, the role of DiPeP in KE3 (dendritic cell activation) was demonstrated by the increased levels of CD54 and IL-8 and TNF-α in THP-1 cells (THP-1 activation assay). Altogether, findings were inconclusive regarding the skin sensitization potential of the UVCB DiPeP-disagreeing with the results of DiPeP in the form of discrete compound (skin sensitizer by the LLNA assay). Additional studies are needed to elucidate the differences between DiPeP isomer forms, and to better understand the applicability domains of non-animal methods in identifying skin sensitization hazards of UVCB substances.

Insecticidal, antifeedant and acetylcholinesterase inhibitory activity of sesquiterpenoids derived from eudesmane, their molecular docking and QSAR.

This work evaluated the insecticidal, antifeedant and AChE inhibitory activity of compounds with eudesmane skeleton. The insecticidal activity was tested against larvae of Drosophila melanogaster and Cydia pomonella, the compounds 3 and 4 were the most active (LC50 of 104.2 and 106.7 µM; 82.0 and 84.4 µM, respectively). Likewise, the mentioned compounds were those that showed the highest acetylcholinesterase inhibitory activity, with IC50 of 0.26 ± 0.016 and 0.77 ± 0.016 µM, respectively. Enzyme kinetic studies, as well as molecular docking, show that the compounds would be non-competitive inhibitors of the enzyme. The antifeedant activity on Plodia interpunctella larvae showed an antifeedant index (AI) of 99% at 72 h for compounds 16, 27 and 20. The QSAR studies show that the properties associated with the polarity of the compounds would be responsible for the biological activities found.

Examining evolutionary scale modeling-derived different-dimensional embeddings in the antimicrobial peptide classification through a KNIME workflow.

Molecular features play an important role in different bio-chem-informatics tasks, such as the Quantitative Structure-Activity Relationships (QSAR) modeling. Several pre-trained models have been recently created to be used in downstream tasks, either by fine-tuning a specific model or by extracting features to feed traditional classifiers. In this regard, a new family of Evolutionary Scale Modeling models (termed as ESM-2 models) was recently introduced, demonstrating outstanding results in protein structure prediction benchmarks. Herein, we studied the usefulness of the different-dimensional embeddings derived from the ESM-2 models to classify antimicrobial peptides (AMPs). To this end, we built a KNIME workflow to use the same modeling methodology across experiments in order to guarantee fair analyses. As a result, the 640- and 1280-dimensional embeddings derived from the 30- and 33-layer ESM-2 models, respectively, are the most valuable  since statistically better performances were achieved by the QSAR models built from them. We also fused features of the different ESM-2 models, and it was concluded that the fusion contributes to getting better QSAR models than using features of a single ESM-2 model. Frequency studies revealed that only a portion of the ESM-2 embeddings is valuable for modeling tasks since between 43% and 66% of the features were never used. Comparisons regarding state-of-the-art deep learning (DL) models confirm that when performing methodologically principled studies in the prediction of AMPs, non-DL based QSAR models yield comparable-to-superior performances to DL-based QSAR models. The developed KNIME workflow is available-freely at https://github.com/cicese-biocom/classification-QSAR-bioKom. This workflow can be valuable to avoid unfair comparisons regarding new computational methods, as well as to propose new non-DL based QSAR models.

Prediction of compound-target interaction using several artificial intelligence algorithms and comparison with a consensus-based strategy.

For understanding a chemical compound's mechanism of action and its side effects, as well as for drug discovery, it is crucial to predict its possible protein targets. This study examines 15 developed target-centric models (TCM) employing different molecular descriptions and machine learning algorithms. They were contrasted with 17 third-party models implemented as web tools (WTCM). In both sets of models, consensus strategies were implemented as potential improvement over individual predictions. The findings indicate that TCM reach f1-score values greater than 0.8. Comparing both approaches, the best TCM achieves values of 0.75, 0.61, 0.25 and 0.38 for true positive/negative rates (TPR, TNR) and false negative/positive rates (FNR, FPR); outperforming the best WTCM. Moreover, the consensus strategy proves to have the most relevant results in the top 20 % of target profiles. TCM consensus reach TPR and FNR values of 0.98 and 0; while on WTCM reach values of 0.75 and 0.24. The implemented computational tool with the TCM and their consensus strategy at: https://bioquimio.udla.edu.ec/tidentification01/ . Scientific Contribution: We compare and discuss the performances of 17 public compound-target interaction prediction models and 15 new constructions. We also explore a compound-target interaction prioritization strategy using a consensus approach, and we analyzed the challenging involved in interactions modeling.

Development of a standardized methodology for transfer learning with QSAR models: a purely data-driven approach for source task selection.

Transfer learning is a machine learning technique that works well with chemical endpoints, with several papers confirming its efficiency. Although effective, because the choice of source/assistant tasks is non-trivial, the application of this technique is severely limited by the domain knowledge of the modeller. Considering this limitation, we developed a purely data-driven approach for source task selection that abstracts the need for domain knowledge. To achieve this, we created a supervised learning setting in which transfer outcome (positive/negative) is the variable to be predicted, and a set of six transferability metrics, calculated based on information from target and source datasets, are the features for prediction. We used the ChEMBL database to generate 100,000 transfers using random pairing, and with these transfers, we trained and evaluated our transferability prediction model (TP-Model). Our TP-Model achieved a 135-fold increase in precision while achieving a sensitivity of 92%, demonstrating a clear superiority against random search. In addition, we observed that transfer learning could provide considerable performance increases when applicable, with an average Matthews Correlation Coefficient (MCC) increase of 0.19 when using a single source and an average MCC increase of 0.44 when using multiple sources.

Rethinking the applicability domain analysis in QSAR models.

Notwithstanding the wide adoption of the OECD principles (or best practices) for QSAR modeling, disparities between in silico predictions and experimental results are frequent, suggesting that model predictions are often too optimistic. Of these OECD principles, the applicability domain (AD) estimation has been recognized in several reports in the literature to be one of the most challenging, implying that the actual reliability measures of model predictions are often unreliable. Applying tree-based error analysis workflows on 5 QSAR models reported in the literature and available in the QsarDB repository, i.e., androgen receptor bioactivity (agonists, antagonists, and binders, respectively) and membrane permeability (highest membrane permeability and the intrinsic permeability), we demonstrate that predictions erroneously tagged as reliable (AD prediction errors) overwhelmingly correspond to instances in subspaces (cohorts) with the highest prediction error rates, highlighting the inhomogeneity of the AD space. In this sense, we call for more stringent AD analysis guidelines which require the incorporation of model error analysis schemes, to provide critical insight on the reliability of underlying AD algorithms. Additionally, any selected AD method should be rigorously validated to demonstrate its suitability for the model space over which it is applied. These steps will ultimately contribute to more accurate estimations of the reliability of model predictions. Finally, error analysis may also be useful in "rational" model refinement in that data expansion efforts and model retraining are focused on cohorts with the highest error rates.

Fluorinated benzoxazinones designed via MIA-QSAR, docking and molecular dynamics as protoporphyrinogen IX oxidase inhibitors.

BACKGROUND: Fluorine plays a significant role in agrochemical science because approximately 25% of herbicides licensed worldwide contain this element. In a pool of previously synthesized benzoxazinones, some compounds contained fluorine and demonstrated inhibitory activities against protoporphyrinogen IX oxidase (PPO). Therefore, three data sets of benzoxazinone derivatives with known inhibitory activity against PPO were employed to build a multivariate image analysis applied to a quantitative structure-activity relationships (MIA-QSAR) model to identify improved analogs with at least one fluorine substituent. RESULTS: The QSAR model was vigorously validated and demonstrated to be highly predictive (r2 = 0.85, q2 = 0.71, and r2 pred = 0.88); thus, the model can provide reliable estimations for the PPO inhibitory activity of unknown derivatives. From these compounds, a couple of N-substituted benzoxazinones that contained the -CH2CHF2 group were found with predicted pKi values larger than 8 (Ki in mol L-1) and higher lipophilicity than the most active data set compounds. In addition, we carried out a systematic investigation of the binding mode of PPO by performing computational docking followed by molecular dynamics simulations. The proposed binding mode was consistent with experimental studies, and several potential key residues were identified. CONCLUSION: Two new proposed benzoxazinones exhibited better performance than compounds of the data set, and fluorine substituents played pivotal roles in describing the biological activities. © 2024 Society of Chemical Industry.

Leishmanicidal activity and 4D quantitative structure-activity relationship and molecular docking studies of vanillin-containing 1,2,3-triazole derivatives.

Aim: The assessment of the antileishmanial potential of 22 vanillin-containing 1,2,3-triazole derivatives against Leishmania braziliensis is reported. Materials & methods: Initial screening was performed against the parasite promastigote form. The most active compound, 4b, targeted parasites within amastigotes (IC50 = 4.2 ± 1.0 µmol l-1), presenting low cytotoxicity and a selective index value of 39. 4D quantitative structure-activity relationship and molecular docking studies provided insights into structure-activity and biological effects. Conclusion: A vanillin derivative with significant antileishmanial activity was identified. Enhanced activity was linked to increased electrostatic and Van der Waals interactions near the benzyl ring of the derivatives. Molecular docking indicated the inhibition of the Leishmania amazonensis sterol 14α-demethylase, using Leishmania infantum sterol 14α-demethylase as a model, without affecting the human isoform. Inhibition was active site competition with lanosterol.

Tetrahydrocurcumin Derivatives Enhanced the Anti-Inflammatory Activity of Curcumin: Synthesis, Biological Evaluation, and Structure-Activity Relationship Analysis.

Tetrahydrocurcumin, the most abundant curcumin transformation product in biological systems, can potentially be a new alternative therapeutic agent with improved anti-inflammatory activity and higher bioavailability than curcumin. In this article, we describe the synthesis and evaluation of the anti-inflammatory activities of tetrahydrocurcumin derivatives. Eleven tetrahydrocurcumin derivatives were synthesized via Steglich esterification on both sides of the phenolic rings of tetrahydrocurcumin with the aim of improving the anti-inflammatory activity of this compound. We showed that tetrahydrocurcumin (2) inhibited TNF-α and IL-6 production but not PGE2 production. Three tetrahydrocurcumin derivatives inhibited TNF-α production, five inhibited IL-6 production, and three inhibited PGE2 production. The structure-activity relationship analysis suggested that two factors could contribute to the biological activities of these compounds: the presence or absence of planarity and their structural differences. Among the tetrahydrocurcumin derivatives, cyclic compound 13 was the most active in terms of TNF-α production, showing even better activity than tetrahydrocurcumin. Acyclic compound 11 was the most effective in terms of IL-6 production and retained the same effect as tetrahydrocurcumin. Moreover, acyclic compound 12 was the most active in terms of PGE2 production, displaying better inhibition than tetrahydrocurcumin. A 3D-QSAR analysis suggested that the anti-inflammatory activities of tetrahydrocurcumin derivatives could be increased by adding bulky groups at the ends of compounds 2, 11, and 12.

Ligand-Based Drug Design of Genipin Derivatives with Cytotoxic Activity against HeLa Cell Line: A Structural and Theoretical Study.

Cervical cancer is a malignant neoplastic disease, mainly associated to HPV infection, with high mortality rates. Among natural products, iridoids have shown different biological activities, including cytotoxic and antitumor effects, in different cancer cell types. Geniposide and its aglycone Genipin have been assessed against different types of cancer. In this work, both iridoids were evaluated against HeLa and three different cervical cancer cell lines. Furthermore, we performed a SAR analysis incorporating 13 iridoids with a high structural similarity to Geniposide and Genipin, also tested in the HeLa cell line and at the same treatment time. Derived from this analysis, we found that the dipole moment (magnitude and direction) is key for their cytotoxic activity in the HeLa cell line. Then, we proceeded to the ligand-based design of new Genipin derivatives through a QSAR model (R2 = 87.95 and Q2 = 62.33) that incorporates different quantum mechanic molecular descriptor types (ρ, ΔPSA, ∆Polarizability2, and logS). Derived from the ligand-based design, we observed that the presence of an aldehyde or a hydroxymethyl in C4, hydroxyls in C1, C6, and C8, and the lack of the double bond in C7-C8 increased the predicted biological activity of the iridoids. Finally, ten simple iridoids (D9, D107, D35, D36, D55, D56, D58, D60, D61, and D62) are proposed as potential cytotoxic agents against the HeLa cell line based on their predicted IC50 value and electrostatic features.

QSAR Studies, Synthesis, and Biological Evaluation of New Pyrimido-Isoquinolin-Quinone Derivatives against Methicillin-Resistant Staphylococcus aureus.

According to the WHO, antimicrobial resistance is among the top 10 threats to global health. Due to increased resistance rates, an increase in the mortality and morbidity of patients has been observed, with projections of more than 10 million deaths associated with infections caused by antibacterial resistant microorganisms. Our research group has developed a new family of pyrimido-isoquinolin-quinones showing antibacterial activities against multidrug-resistant Staphylococcus aureus. We have developed 3D-QSAR CoMFA and CoMSIA studies (r2 = 0.938; 0.895), from which 13 new derivatives were designed and synthesized. The compounds were tested in antibacterial assays against methicillin-resistant Staphylococcus aureus and other bacterial pathogens. There were 12 synthesized compounds active against Gram-positive pathogens in concentrations ranging from 2 to 32 µg/mL. The antibacterial activity of the derivatives is explained by the steric, electronic, and hydrogen-bond acceptor properties of the compounds.

Artificial intelligence-guided approach for efficient virtual screening of hits against Schistosoma mansoni.

Background: The impact of schistosomiasis, which affects over 230 million people, emphasizes the urgency of developing new antischistosomal drugs. Artificial intelligence is vital in accelerating the drug discovery process. Methodology & results: We developed classification and regression machine learning models to predict the schistosomicidal activity of compounds not experimentally tested. The prioritized compounds were tested on schistosomula and adult stages of Schistosoma mansoni. Four compounds demonstrated significant activity against schistosomula, with 50% effective concentration values ranging from 9.8 to 32.5 µM, while exhibiting no toxicity in animal and human cell lines. Conclusion: These findings represent a significant step forward in the discovery of antischistosomal drugs. Further optimization of these active compounds can pave the way for their progression into preclinical studies.

MASSA Algorithm: an automated rational sampling of training and test subsets for QSAR modeling.

QSAR models capable of predicting biological, toxicity, and pharmacokinetic properties were widely used to search lead bioactive molecules in chemical databases. The dataset's preparation to build these models has a strong influence on the quality of the generated models, and sampling requires that the original dataset be divided into training (for model training) and test (for statistical evaluation) sets. This sampling can be done randomly or rationally, but the rational division is superior. In this paper, we present MASSA, a Python tool that can be used to automatically sample datasets by exploring the biological, physicochemical, and structural spaces of molecules using PCA, HCA, and K-modes. The proposed algorithm is very useful when the variables used for QSAR are not available or to construct multiple QSAR models with the same training and test sets, producing models with lower variability and better values for validation metrics. These results were obtained even when the descriptors used in the QSAR/QSPR were different from those used in the separation of training and test sets, indicating that this tool can be used to build models for more than one QSAR/QSPR technique. Finally, this tool also generates useful graphical representations that can provide insights into the data.