Certain drugs are nitroaromatic compounds, which are potentially toxic. As such, it is of practic... more Certain drugs are nitroaromatic compounds, which are potentially toxic. As such, it is of practical importance to assess and predict their mutagenic potency in the process of drug discovery. A classical quantitative structure-activity relationship (QSAR) model was developed using the linear partial least square (PLS) scheme to understand the underline mutagenic mechanism and a non-classical QSAR model was derived using the machine learning-based hierarchical support vector regression (HSVR) to predict the mutagenicity of nitroaromatic compounds based on a series of mutagenicity data (TA98 − S9). It was observed that HSVR performed better than PLS as manifested by the predictions of the samples in the training set, test set, and outlier set as well as various statistical validations. A mock test designated to mimic real challenges also confirmed the better performance of HSVR. Furthermore, HSVR exhibited superiority in predictivity, generalization capabilities, consistent performance, and robustness when compared with various published predictive models. PLS, conversely, revealed some mechanistically interpretable relationships between descriptors and mutagenicity. Thus, this two-QSAR approach using the predictive HSVR and interpretable PLS models in a synergistic fashion can be adopted to facilitate drug discovery and development by designing safer drug candidates with nitroaromatic moiety.
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Skin direct contact with chemical or physical substances is predisposed to allergic contact derma... more Skin direct contact with chemical or physical substances is predisposed to allergic contact dermatitis (ACD), producing various allergic reactions, namely rash, blister, or itchy, in the contacted skin area. ACD can be triggered by various extremely complicated adverse outcome pathways (AOPs) remains to be causal for biosafety warrant. As such, commercial products such as ointments or cosmetics can fulfill the topically safe requirements in animal and non-animal models including allergy. Europe, nevertheless, has banned animal tests for the safety evaluations of cosmetic ingredients since 2013, followed by other countries. A variety of non-animal in vitro tests addressing different key events of the AOP, the direct peptide reactivity assay (DPRA), KeratinoSens™, LuSens and human cell line activation test h-CLAT and U-SENS™ have been developed and were adopted in OECD test guideline to identify the skin sensitizers. Other methods, such as the SENS-IS are not yet fully validated and regulatorily accepted. A broad spectrum of in silico models, alternatively, to predict skin sensitization have emerged based on various animal and non-animal data using assorted modeling schemes. In this article, we extensively summarize a number of skin sensitization predictive models that can be used in the biopharmaceutics and cosmeceuticals industries as well as their future perspectives, and the underlined challenges are also discussed.
Zenodo (CERN European Organization for Nuclear Research), Dec 27, 2020
Table S1. Selected compounds for this study; their names, SMILES strings, CAS numbers, and observ... more Table S1. Selected compounds for this study; their names, SMILES strings, CAS numbers, and observed log <em>P</em><sub>app</sub> values; their predicted values by SVR A, SVR B, SVR C, and HSVR; data partitions; and references; Table S2. Optimal runtime parameters for the SVR models; Table S3. Confusion matrix for the qualitative predictive model; Table S4. The Cooper statistics and Kubat's G-mean calculated from the confusion matrix. Optimal runtime parameters for the SVR models; Figure S1. Histograms of: (A) log <em>P</em>app, (B) molecular weight (MW), (C) surface area (SA), (D) polar surface area (PSA), (E) number of hydrogen bond acceptor (HBA), (F) number of hydrogen bond donor (HBD), (G) and the <em>n</em>-octanol-water partition coefficient (log <em>P</em>) in the training set, test set, and outlier set.
Drug-induced liver injury (DILI) is a major factor in the development of drugs and the safety of ... more Drug-induced liver injury (DILI) is a major factor in the development of drugs and the safety of drugs. If the DILI cannot be effectively predicted during the development of the drug, it will cause the drug to be withdrawn from markets. Therefore, DILI is crucial at the early stages of drug research. This work presents a 2-class ensemble classifier model for predicting DILI, with 2D molecular descriptors and fingerprints on a dataset of 450 compounds. The purpose of our study is to investigate which are the key molecular fingerprints that may cause DILI risk, and then to obtain a reliable ensemble model to predict DILI risk with these key factors. Experimental results suggested that 8 molecular fingerprints are very critical for predicting DILI, and also obtained the best ratio of molecular fingerprints to molecular descriptors. The result of the 5-fold cross-validation of the ensemble vote classifier method obtain an accuracy of 77.25%, and the accuracy of the test set was 81.67%. This model could be used for drug-induced liver injury prediction.
ABSTRACT Thesis (Ph. D.)--University of Texas at Austin, 1997. Vita. Includes bibliographical ref... more ABSTRACT Thesis (Ph. D.)--University of Texas at Austin, 1997. Vita. Includes bibliographical references (leaves 110-119).
ABSTRACT When skeletons of Win compounds were used as templates, computer-assisted drug design le... more ABSTRACT When skeletons of Win compounds were used as templates, computer-assisted drug design led to the identification of a novel series of imidazolidinone derivatives with significant antiviral activity against enterovirus 71 (EV 71), the infection of which had resulted in about 80 fatalities during the 1998 epidemic outbreak in Taiwan. In addition to inhibiting all the genotypes (A, B, and C) of EV 71 in the submicromolar to low micromolar range, compounds 1 and 8 were extensively evaluated against a variety of viruses, showing potent activity against coxsackievirus A9 (IC(50) = 0.47-0.55 microM) and coxsackievirus A24 (IC(50) = 0.47-0.55 microM) as well as moderate activity against enterovirus 68 (IC(50) = 2.13 microM) and echovirus 9 (IC(50) = 2.6 microM). Our SAR studies revealed that imidazolidinone analogues with an aryl substituent at the para position of the phenoxyl ring, such as compounds 20, 21, 27, 57, 58, and 61, in general exhibited the highest activity against EV 71. Among them, compound 20 and its corresponding hydrochloride salt 57, in terms of potency and selectivity index, appear to be the most promising candidates in this series for further development of anti-EV-71 agents. Preliminary results of the study on the mode of action by a time-course experiment suggest that test compounds 1 and 8 can effectively inhibit the virus replication at the early stages, referring to virus attachment or uncoating. This indicates that the surface protein may be the target for this type of compounds.
Topical and transdermal drug delivery is an effective, safe, and preferred route of drug administ... more Topical and transdermal drug delivery is an effective, safe, and preferred route of drug administration. As such, skin permeability is one of the critical parameters that should be taken into consideration in the process of drug discovery and development. The ex vivo human skin model is considered as the best surrogate to evaluate in vivo skin permeability. This investigation adopted a novel two-QSAR scheme by collectively incorporating machine learning-based hierarchical support vector regression (HSVR) and classical partial least square (PLS) to predict the skin permeability coefficient and to uncover the intrinsic permeation mechanism, respectively, based on ex vivo excised human skin permeability data compiled from the literature. The derived HSVR model functioned better than PLS as represented by the predictive performance in the training set, test set, and outlier set in addition to various statistical estimations. HSVR also delivered consistent performance upon the applicatio...
ABSTRACT Thesis (Ph. D.)--University of Texas at Austin, 1997. Vita. Includes bibliographical ref... more ABSTRACT Thesis (Ph. D.)--University of Texas at Austin, 1997. Vita. Includes bibliographical references (leaves 110-119).
<p>Pharmacophore models (A) Hypo A, (B) Hypo B, and (C) Hypo C fitted to <b>22</b&... more <p>Pharmacophore models (A) Hypo A, (B) Hypo B, and (C) Hypo C fitted to <b>22</b> and (D) overlay of these three models, which are color-coded by red, blue, and green, respectively. The chemical features are described in <a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0090689#pone-0090689-g001" target="_blank">Figure 1</a>.</p
Type-II diabetes mellitus (T2DM) results from a combination of genetic and lifestyle factors, and... more Type-II diabetes mellitus (T2DM) results from a combination of genetic and lifestyle factors, and the prevalence of T2DM is increasing worldwide. Clinically, both α-glucosidase and α-amylase enzymes inhibitors can suppress peaks of postprandial glucose with surplus adverse effects, leading to efforts devoted to urgently seeking new anti-diabetes drugs from natural sources for delayed starch digestion. This review attempts to explore 10 families e.g., Bignoniaceae, Ericaceae, Dryopteridaceae, Campanulaceae, Geraniaceae, Euphorbiaceae, Rubiaceae, Acanthaceae, Rutaceae, and Moraceae as medicinal plants, and folk and herb medicines for lowering blood glucose level, or alternative anti-diabetic natural products. Many natural products have been studied in silico, in vitro, and in vivo assays to restrain hyperglycemia. In addition, natural products, and particularly polyphenols, possess diverse structures for exploring them as inhibitors of α-glucosidase and α-amylase. Interestingly, an in...
<p>Pharmacophore models (A) Hypo A, (B) Hypo B and (C) Hypo C fitted to <b>13</b&g... more <p>Pharmacophore models (A) Hypo A, (B) Hypo B and (C) Hypo C fitted to <b>13</b>. The chemical features are described in <a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0033829#pone-0033829-g002" target="_blank">Figure 2</a>.</p
Table S1. Optimal runtime parameters for the SVR models; Table S2. Selected compounds for this st... more Table S1. Optimal runtime parameters for the SVR models; Table S2. Selected compounds for this study, their names, SMILES strings, CAS numbers, observed log <em>P</em><sub>e</sub> values and predicted values by SVR A, SVR B, HSVR, and PLS, data partitions, and references;; Figure S1. Histograms of: (A) observed log <em>P</em><sub>e</sub>; (B) molecular weight (MW); (C) log <em>P</em>; (D) log <em>D </em>(distribution coefficient); (E) polar surface area (PSA); (F) fractional polar surface area (FPSA); and (G) dipole moment (<em>μ</em>) in density form for all molecules in the training set, test set, and outlier set.
Drug absorption is one of the critical factors that should be taken into account in the process o... more Drug absorption is one of the critical factors that should be taken into account in the process of drug discovery and development. The human colon carcinoma cell layer (Caco-2) model has been frequently used as a surrogate to preliminarily investigate the intestinal absorption. In this study, a quantitative structure–activity relationship (QSAR) model was generated using the innovative machine learning-based hierarchical support vector regression (HSVR) scheme to depict the exceedingly confounding passive diffusion and transporter-mediated active transport. The HSVR model displayed good agreement with the experimental values of the training samples, test samples, and outlier samples. The predictivity of HSVR was further validated by a mock test and verified by various stringent statistical criteria. Consequently, this HSVR model can be employed to forecast the Caco-2 permeability to assist drug discovery and development.
Diabetes mellitus (DM) is concomitant with significant morbidity and mortality and its prevalence... more Diabetes mellitus (DM) is concomitant with significant morbidity and mortality and its prevalence is accumulative in worldwide. The conventional antidiabetic agents are known to mitigate the symptoms of diabetes; however, they may also cause side and adverse effects. There is an imperative necessity to conduct preclinical and clinical trials for the discovery of alternative therapeutic agents that can overcome the drawbacks of current synthetic antidiabetic drugs. This study aimed to investigate the efficacy of lowering blood glucose and underlined mechanism of γ-mangostin, mangosteen (Garcinia mangostana) xanthones. The results showed γ-Mangostin had a antihyperglycemic ability in short (2 h)- and long-term (28 days) administrations to diet-induced diabetic mice. The long-term administration of γ-mangostin attenuated fasting blood glucose of diabetic mice and exhibited no hepatotoxicity and nephrotoxicity. Moreover, AMPK, PPARγ, α-amylase, and α-glucosidase were found to be the potential targets for simulating binds with γ-mangostin after molecular docking. To validate the docking results, the inhibitory potency of γ-mangostin againstα-amylase/α-glucosidase was higher than Acarbose via enzymatic assay. Interestingly, an allosteric relationship between γ-mangostin and insulin was also found in the glucose uptake of VSMC, FL83B, C2C12, and 3T3-L1 cells. Taken together, the results showed that γ-mangostin exerts anti-hyperglycemic activity through promoting glucose uptake and reducing saccharide digestion by inhibition of α-amylase/α-glucosidase with insulin sensitization, suggesting that γ-mangostin could be a new clue for drug discovery and development to treat diabetes.
Certain drugs are nitroaromatic compounds, which are potentially toxic. As such, it is of practic... more Certain drugs are nitroaromatic compounds, which are potentially toxic. As such, it is of practical importance to assess and predict their mutagenic potency in the process of drug discovery. A classical quantitative structure-activity relationship (QSAR) model was developed using the linear partial least square (PLS) scheme to understand the underline mutagenic mechanism and a non-classical QSAR model was derived using the machine learning-based hierarchical support vector regression (HSVR) to predict the mutagenicity of nitroaromatic compounds based on a series of mutagenicity data (TA98 − S9). It was observed that HSVR performed better than PLS as manifested by the predictions of the samples in the training set, test set, and outlier set as well as various statistical validations. A mock test designated to mimic real challenges also confirmed the better performance of HSVR. Furthermore, HSVR exhibited superiority in predictivity, generalization capabilities, consistent performance, and robustness when compared with various published predictive models. PLS, conversely, revealed some mechanistically interpretable relationships between descriptors and mutagenicity. Thus, this two-QSAR approach using the predictive HSVR and interpretable PLS models in a synergistic fashion can be adopted to facilitate drug discovery and development by designing safer drug candidates with nitroaromatic moiety.
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Skin direct contact with chemical or physical substances is predisposed to allergic contact derma... more Skin direct contact with chemical or physical substances is predisposed to allergic contact dermatitis (ACD), producing various allergic reactions, namely rash, blister, or itchy, in the contacted skin area. ACD can be triggered by various extremely complicated adverse outcome pathways (AOPs) remains to be causal for biosafety warrant. As such, commercial products such as ointments or cosmetics can fulfill the topically safe requirements in animal and non-animal models including allergy. Europe, nevertheless, has banned animal tests for the safety evaluations of cosmetic ingredients since 2013, followed by other countries. A variety of non-animal in vitro tests addressing different key events of the AOP, the direct peptide reactivity assay (DPRA), KeratinoSens™, LuSens and human cell line activation test h-CLAT and U-SENS™ have been developed and were adopted in OECD test guideline to identify the skin sensitizers. Other methods, such as the SENS-IS are not yet fully validated and regulatorily accepted. A broad spectrum of in silico models, alternatively, to predict skin sensitization have emerged based on various animal and non-animal data using assorted modeling schemes. In this article, we extensively summarize a number of skin sensitization predictive models that can be used in the biopharmaceutics and cosmeceuticals industries as well as their future perspectives, and the underlined challenges are also discussed.
Zenodo (CERN European Organization for Nuclear Research), Dec 27, 2020
Table S1. Selected compounds for this study; their names, SMILES strings, CAS numbers, and observ... more Table S1. Selected compounds for this study; their names, SMILES strings, CAS numbers, and observed log <em>P</em><sub>app</sub> values; their predicted values by SVR A, SVR B, SVR C, and HSVR; data partitions; and references; Table S2. Optimal runtime parameters for the SVR models; Table S3. Confusion matrix for the qualitative predictive model; Table S4. The Cooper statistics and Kubat's G-mean calculated from the confusion matrix. Optimal runtime parameters for the SVR models; Figure S1. Histograms of: (A) log <em>P</em>app, (B) molecular weight (MW), (C) surface area (SA), (D) polar surface area (PSA), (E) number of hydrogen bond acceptor (HBA), (F) number of hydrogen bond donor (HBD), (G) and the <em>n</em>-octanol-water partition coefficient (log <em>P</em>) in the training set, test set, and outlier set.
Drug-induced liver injury (DILI) is a major factor in the development of drugs and the safety of ... more Drug-induced liver injury (DILI) is a major factor in the development of drugs and the safety of drugs. If the DILI cannot be effectively predicted during the development of the drug, it will cause the drug to be withdrawn from markets. Therefore, DILI is crucial at the early stages of drug research. This work presents a 2-class ensemble classifier model for predicting DILI, with 2D molecular descriptors and fingerprints on a dataset of 450 compounds. The purpose of our study is to investigate which are the key molecular fingerprints that may cause DILI risk, and then to obtain a reliable ensemble model to predict DILI risk with these key factors. Experimental results suggested that 8 molecular fingerprints are very critical for predicting DILI, and also obtained the best ratio of molecular fingerprints to molecular descriptors. The result of the 5-fold cross-validation of the ensemble vote classifier method obtain an accuracy of 77.25%, and the accuracy of the test set was 81.67%. This model could be used for drug-induced liver injury prediction.
ABSTRACT Thesis (Ph. D.)--University of Texas at Austin, 1997. Vita. Includes bibliographical ref... more ABSTRACT Thesis (Ph. D.)--University of Texas at Austin, 1997. Vita. Includes bibliographical references (leaves 110-119).
ABSTRACT When skeletons of Win compounds were used as templates, computer-assisted drug design le... more ABSTRACT When skeletons of Win compounds were used as templates, computer-assisted drug design led to the identification of a novel series of imidazolidinone derivatives with significant antiviral activity against enterovirus 71 (EV 71), the infection of which had resulted in about 80 fatalities during the 1998 epidemic outbreak in Taiwan. In addition to inhibiting all the genotypes (A, B, and C) of EV 71 in the submicromolar to low micromolar range, compounds 1 and 8 were extensively evaluated against a variety of viruses, showing potent activity against coxsackievirus A9 (IC(50) = 0.47-0.55 microM) and coxsackievirus A24 (IC(50) = 0.47-0.55 microM) as well as moderate activity against enterovirus 68 (IC(50) = 2.13 microM) and echovirus 9 (IC(50) = 2.6 microM). Our SAR studies revealed that imidazolidinone analogues with an aryl substituent at the para position of the phenoxyl ring, such as compounds 20, 21, 27, 57, 58, and 61, in general exhibited the highest activity against EV 71. Among them, compound 20 and its corresponding hydrochloride salt 57, in terms of potency and selectivity index, appear to be the most promising candidates in this series for further development of anti-EV-71 agents. Preliminary results of the study on the mode of action by a time-course experiment suggest that test compounds 1 and 8 can effectively inhibit the virus replication at the early stages, referring to virus attachment or uncoating. This indicates that the surface protein may be the target for this type of compounds.
Topical and transdermal drug delivery is an effective, safe, and preferred route of drug administ... more Topical and transdermal drug delivery is an effective, safe, and preferred route of drug administration. As such, skin permeability is one of the critical parameters that should be taken into consideration in the process of drug discovery and development. The ex vivo human skin model is considered as the best surrogate to evaluate in vivo skin permeability. This investigation adopted a novel two-QSAR scheme by collectively incorporating machine learning-based hierarchical support vector regression (HSVR) and classical partial least square (PLS) to predict the skin permeability coefficient and to uncover the intrinsic permeation mechanism, respectively, based on ex vivo excised human skin permeability data compiled from the literature. The derived HSVR model functioned better than PLS as represented by the predictive performance in the training set, test set, and outlier set in addition to various statistical estimations. HSVR also delivered consistent performance upon the applicatio...
ABSTRACT Thesis (Ph. D.)--University of Texas at Austin, 1997. Vita. Includes bibliographical ref... more ABSTRACT Thesis (Ph. D.)--University of Texas at Austin, 1997. Vita. Includes bibliographical references (leaves 110-119).
<p>Pharmacophore models (A) Hypo A, (B) Hypo B, and (C) Hypo C fitted to <b>22</b&... more <p>Pharmacophore models (A) Hypo A, (B) Hypo B, and (C) Hypo C fitted to <b>22</b> and (D) overlay of these three models, which are color-coded by red, blue, and green, respectively. The chemical features are described in <a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0090689#pone-0090689-g001" target="_blank">Figure 1</a>.</p
Type-II diabetes mellitus (T2DM) results from a combination of genetic and lifestyle factors, and... more Type-II diabetes mellitus (T2DM) results from a combination of genetic and lifestyle factors, and the prevalence of T2DM is increasing worldwide. Clinically, both α-glucosidase and α-amylase enzymes inhibitors can suppress peaks of postprandial glucose with surplus adverse effects, leading to efforts devoted to urgently seeking new anti-diabetes drugs from natural sources for delayed starch digestion. This review attempts to explore 10 families e.g., Bignoniaceae, Ericaceae, Dryopteridaceae, Campanulaceae, Geraniaceae, Euphorbiaceae, Rubiaceae, Acanthaceae, Rutaceae, and Moraceae as medicinal plants, and folk and herb medicines for lowering blood glucose level, or alternative anti-diabetic natural products. Many natural products have been studied in silico, in vitro, and in vivo assays to restrain hyperglycemia. In addition, natural products, and particularly polyphenols, possess diverse structures for exploring them as inhibitors of α-glucosidase and α-amylase. Interestingly, an in...
<p>Pharmacophore models (A) Hypo A, (B) Hypo B and (C) Hypo C fitted to <b>13</b&g... more <p>Pharmacophore models (A) Hypo A, (B) Hypo B and (C) Hypo C fitted to <b>13</b>. The chemical features are described in <a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0033829#pone-0033829-g002" target="_blank">Figure 2</a>.</p
Table S1. Optimal runtime parameters for the SVR models; Table S2. Selected compounds for this st... more Table S1. Optimal runtime parameters for the SVR models; Table S2. Selected compounds for this study, their names, SMILES strings, CAS numbers, observed log <em>P</em><sub>e</sub> values and predicted values by SVR A, SVR B, HSVR, and PLS, data partitions, and references;; Figure S1. Histograms of: (A) observed log <em>P</em><sub>e</sub>; (B) molecular weight (MW); (C) log <em>P</em>; (D) log <em>D </em>(distribution coefficient); (E) polar surface area (PSA); (F) fractional polar surface area (FPSA); and (G) dipole moment (<em>μ</em>) in density form for all molecules in the training set, test set, and outlier set.
Drug absorption is one of the critical factors that should be taken into account in the process o... more Drug absorption is one of the critical factors that should be taken into account in the process of drug discovery and development. The human colon carcinoma cell layer (Caco-2) model has been frequently used as a surrogate to preliminarily investigate the intestinal absorption. In this study, a quantitative structure–activity relationship (QSAR) model was generated using the innovative machine learning-based hierarchical support vector regression (HSVR) scheme to depict the exceedingly confounding passive diffusion and transporter-mediated active transport. The HSVR model displayed good agreement with the experimental values of the training samples, test samples, and outlier samples. The predictivity of HSVR was further validated by a mock test and verified by various stringent statistical criteria. Consequently, this HSVR model can be employed to forecast the Caco-2 permeability to assist drug discovery and development.
Diabetes mellitus (DM) is concomitant with significant morbidity and mortality and its prevalence... more Diabetes mellitus (DM) is concomitant with significant morbidity and mortality and its prevalence is accumulative in worldwide. The conventional antidiabetic agents are known to mitigate the symptoms of diabetes; however, they may also cause side and adverse effects. There is an imperative necessity to conduct preclinical and clinical trials for the discovery of alternative therapeutic agents that can overcome the drawbacks of current synthetic antidiabetic drugs. This study aimed to investigate the efficacy of lowering blood glucose and underlined mechanism of γ-mangostin, mangosteen (Garcinia mangostana) xanthones. The results showed γ-Mangostin had a antihyperglycemic ability in short (2 h)- and long-term (28 days) administrations to diet-induced diabetic mice. The long-term administration of γ-mangostin attenuated fasting blood glucose of diabetic mice and exhibited no hepatotoxicity and nephrotoxicity. Moreover, AMPK, PPARγ, α-amylase, and α-glucosidase were found to be the potential targets for simulating binds with γ-mangostin after molecular docking. To validate the docking results, the inhibitory potency of γ-mangostin againstα-amylase/α-glucosidase was higher than Acarbose via enzymatic assay. Interestingly, an allosteric relationship between γ-mangostin and insulin was also found in the glucose uptake of VSMC, FL83B, C2C12, and 3T3-L1 cells. Taken together, the results showed that γ-mangostin exerts anti-hyperglycemic activity through promoting glucose uptake and reducing saccharide digestion by inhibition of α-amylase/α-glucosidase with insulin sensitization, suggesting that γ-mangostin could be a new clue for drug discovery and development to treat diabetes.
Uploads
Papers by Max Leong