In silico Prediction of Chemical Ames Mutagenicity

Xu, Congying; Cheng, Feixiong; Chen, Lei; Du, Ziyun; Li, Weihua; Liu, Guixia; Lee, Philip W.; Tang, Yun

doi:10.1021/ci300400a

Cited by 205 publications

(121 citation statements)

References 40 publications

Supporting

Mentioning

117

Contrasting

Unclassified

Order By: Relevance

“…Each of the methods has their strengths and weaknesses and it would appear that no one method stands out as best for Mtb active prediction. Others have previously shown SVM and Random Forest approaches to outperform Bayesian models in different areas 64 . Additional researchers have used ensembles of models rather than rely on a single model 75 .…”

Section: Discussionmentioning

confidence: 99%

Fusing Dual-Event Data Sets for Mycobacterium tuberculosis Machine Learning Models and Their Evaluation

Ekins

Freundlich

Reynolds

2013

J. Chem. Inf. Model.

View full text Add to dashboard Cite

The search for new tuberculosis treatments continues as we need to find molecules that can act more quickly, be accommodated in multi-drug regimens, and overcome ever increasing levels of drug resistance. Multiple large scale phenotypic high-throughput screens against Mycobacterium tuberculosis (Mtb) have generated dose response data, enabling the generation of machine learning models. These models also incorporated cytotoxicity data and were recently validated with a large external dataset. A cheminformatics data-fusion approach followed by Bayesian machine learning, Support Vector Machine or Recursive Partitioning model development (based on publicly available Mtb screening data) was used to compare individual datasets and subsequent combined models. A set of 1924 commercially available molecules with promising antitubercular activity (and lack of relative cytotoxicity to Vero cells) were used to evaluate the predictive nature of the models. We demonstrate that combining three datasets incorporating antitubercular and cytotoxicity data in Vero cells from our previous screens results in external validation receiver operator curve (ROC) of 0.83 (Bayesian or RP Forest). Models that do not have the highest five-fold cross validation ROC scores can outperform other models in a test set dependent manner. We demonstrate with predictions for a recently published set of Mtb leads from GlaxoSmithKline that no single machine learning model may be enough to identify compounds of interest. Dataset fusion represents a further useful strategy for machine learning construction as illustrated with Mtb. Coverage of chemistry and Mtb target spaces may also be limiting factors for the whole-cell screening data generated to date.

show abstract

Section: Discussionmentioning

confidence: 99%

Fusing Dual-Event Data Sets for Mycobacterium tuberculosis Machine Learning Models and Their Evaluation

Ekins

Freundlich

Reynolds

2013

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…48 The drug safety profiler includes the prediction of Cytochrome P450 (CYP) regioselectivity (CYP3A4, CYP2D6, CYP2C9, CYP2C19, and CYP1A2), probability of producing positive Ames (mutagenicity prediction), and human ether-a-go-go-related gene (hERG) (cardiotoxicity prediction). 49,50 The accuracy and sensitivity of all the above methods were successfully evaluated by the supplier, ACD/Labs. All the data sheets are available on the company website (http:// www.acdlabs.com).…”

Section: Prediction Of Drug-like Propertiesmentioning

confidence: 99%

Synergistic antibacterial effects of herbal extracts and antibiotics on methicillin-resistant Staphylococcus aureus: A computational and experimental study

Kuok

Hoi

et al. 2017

Exp Biol Med (Maywood)

View full text Add to dashboard Cite

Antibiotic resistant is a well-known threat to global health and methicillin-resistant Staphylococcus aureus is one of the most significant ones. These resistant bacteria kill thousands of people every year and therefore a new effective antimicrobial treatment is necessary. This study identified the herbs and their associated bioactive ingredients that can potential the effects of current antibiotics. These herbs have long history of human usage in China and have well-defined monograph in the Chinese Pharmacopeia. These indicate their relatively high clinical safety and may have a quicker drug development process than that of a new novel antibiotic. Based on the results of this study, the authors will perform further in vitro and animal studies, aiming to accumulate significant data for the application of clinical trial. AbstractAntibiotic resistance has become a serious global concern, and the discovery of antimicrobial herbal constituents may provide valuable solutions to overcome the problem. In this study, the effects of therapies combining antibiotics and four medicinal herbs on methicillinresistant Staphylococcus aureus (MRSA) were investigated. Specifically, the synergistic effects of Magnolia officinalis, Verbena officinalis, Momordica charantia, and Daphne genkwa in combination with oxacillin or gentamicin against methicillin-resistant (ATCC43300) and methicillin-susceptible (ATCC25923) S. aureus were examined. In vitro susceptibility and synergistic testing were performed to measure the minimum inhibitory concentration and fractional inhibitory concentration (FIC) index of the antibiotics and medicinal herbs against MRSA and methicillin-susceptible S. aureus. To identify the active constituents in producing these synergistic effects, in silico molecular docking was used to investigate the binding affinities of 139 constituents of the four herbs to the two common MRSA inhibitory targets, penicillin binding proteins 2a (PBP2a) and 4 (PBP4). The physicochemical and absorption, distribution, metabolism, and excretion properties and drug safety profiles of these compounds were also analyzed. D. genkwa extract potentiated the antibacterial effects of oxacillin against MRSA, as indicated by an FIC index value of 0.375. M. officinalis and V. officinalis produced partial synergistic effects when combined with oxacillin, whereas M. charantia was found to have no beneficial effects in inhibiting MRSA. Overall, tiliroside, pinoresinol, magnatriol B, and momorcharaside B were predicted to be PBP2a or PBP4 inhibitors with good drug-like properties. This study identifies compounds that deserve further investigation with the aim of developing therapeutic agents to modulate the effect of antibiotics on MRSA.

show abstract

“…[41][42][43] Another method, named ChemoTyper, 44 was also used to identify toxic substructures. Substructural alerts are derived directly from mechanistic knowledge, 40 so they are important tools to predict toxicity.…”

Section: Analysis Of Toxic Substructures or Substructural Alertsmentioning

confidence: 99%

In silico prediction of chemical aquatic toxicity with chemical category approaches and substructural alerts

et al. 2015

Self Cite

View full text Add to dashboard Cite

Aquatic toxicity is an important endpoint in the evaluation of chemically adverse effects on ecosystems.In this study, in silico models were developed for the prediction of chemical aquatic toxicity in different fish species. Firstly, a large data set containing 6422 data points on aquatic toxicity with 1906 diverse chemicals was constructed. Using molecular descriptors and fingerprints to represent the molecules, local and global models were then developed with five machine learning methods based on three fish species (rainbow trout, fathead minnow and bluegill sunfish). For the local models, both binary and ternary classification models were obtained for each of the three fish species. For the global models, data of all the three fish species were used together. The predictive accuracy of both the local and global models was around 0.8 for the test sets. Moreover, data of the sheepshead minnow were used as an external validation set. For the best local model (model 2), the predictive accuracy was 0.875 for the sheepshead minnow, while for the best global model (model 14), the predictive accuracy was 0.872 for the sheepshead minnow. The FN compounds in model 2 and model 14 were 18 and 10, respectively.Hence, model 14 was the best model, and thus could predict the toxicity of other fish species'. Furthermore, information gain and ChemoTyper methods were used to identify toxic substructures, which could significantly correlate with chemical aquatic toxicity. This study provides critical tools for an early evaluation of chemical aquatic toxicity in an environmental hazard assessment. † Electronic supplementary information (ESI) available. See

show abstract

In silico Prediction of Chemical Ames Mutagenicity

Cited by 205 publications

References 40 publications

Fusing Dual-Event Data Sets for Mycobacterium tuberculosis Machine Learning Models and Their Evaluation

Fusing Dual-Event Data Sets for Mycobacterium tuberculosis Machine Learning Models and Their Evaluation

Synergistic antibacterial effects of herbal extracts and antibiotics on methicillin-resistant Staphylococcus aureus: A computational and experimental study

In silico prediction of chemical aquatic toxicity with chemical category approaches and substructural alerts

Contact Info

Product

Resources

About