Progress in computational toxicology

Ekins, Sean

doi:10.1016/j.vascn.2013.12.003

Cited by 96 publications

(74 citation statements)

References 188 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Much of this work was centered on models for Mycobacterium tuberculosis 83–85 taking account of cytotoxicity and prospectively evaluating them to show high hit rates compared to random screening 85–87 . We have since followed this with datasets for Chagas disease 88 and Ebola 89 to repurpose approved drugs as well as model ADME properties such as aqueous solubility, mouse liver microsomal stability 90 , Caco-2 cell permeability 62 , toxicology datasets 91 and transporters 66, 92–97 . By making the fingerprints 98 , and Bayesian model building algorithm open source 21, 62 there is the potential to further expand on this work.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets

Korotcov¹,

Tkachenko²,

et al. 2017

Self Cite

View full text Add to dashboard Cite

Machine learning methods have been applied to many datasets in pharmaceutical research for several decades. The relative ease and availability of fingerprint type molecular descriptors paired with Bayesian methods resulted in the widespread use of this approach for a diverse array of endpoints relevant to drug discovery. Deep learning is the latest machine learning algorithm attracting attention for many of pharmaceutical applications from docking to virtual screening. Deep learning is based on an artificial neural network with multiple hidden layers and has found considerable traction for many artificial intelligence applications. We have previously suggested the need for a comparison of different machine learning methods with deep learning across an array of varying datasets that is applicable to pharmaceutical research. Endpoints relevant to pharmaceutical research include absorption, distribution, metabolism, excretion and toxicity (ADME/Tox) properties, as well as activity against pathogens and drug discovery datasets. In this study, we have used datasets for solubility, probe-likeness, hERG, KCNQ1, bubonic plague, Chagas, tuberculosis and malaria to compare different machine learning methods using FCFP6 fingerprints. These datasets represent whole cell screens, individual proteins, physicochemical properties as well as a dataset with a complex endpoint. Our aim was to assess whether deep learning offered any improvement in testing when assessed using an array of metrics including AUC, F1 score, Cohen’s kappa, Matthews correlation coefficient and others. Based on ranked normalized scores for the metrics or datasets Deep Neural Networks (DNN) ranked higher than SVM, which in turn was ranked higher than all the other machine learning methods. Visualizing these properties for training and test sets using radar type plots indicates when models are inferior or perhaps over trained. These results also suggest the need for assessing deep learning further using multiple metrics with much larger scale comparisons, prospective testing as well as assessment of different fingerprints and DNN architectures beyond those used.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets

Korotcov¹,

Tkachenko²,

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…A similar computational model building and sharing approach could be taken for drug-metabolizing enzymes, nuclear receptors, and ion channels of interest for drug-drug interaction and toxicity prediction (Ekins 2014). The ChEMBL database has thousands of data sets curated from the literature for important drug targets, including transporters.…”

Section: Resultsmentioning

confidence: 99%

Making Transporter Models for Drug–Drug Interaction Prediction Mobile

2015

Self Cite

View full text Add to dashboard Cite

The past decade has seen increased numbers of studies publishing ligand-based computational models for drug transporters. Although they generally use small experimental data sets, these models can provide insights into structure-activity relationships for the transporter. In addition, such models have helped to identify new compounds as substrates or inhibitors of transporters of interest. We recently proposed that many transporters are promiscuous and may require profiling of new chemical entities against multiple substrates for a specific transporter. Furthermore, it should be noted that virtually all of the published ligand-based transporter models are only accessible to those involved in creating them and, consequently, are rarely shared effectively. One way to surmount this is to make models shareable or more accessible. The development of mobile apps that can access such models is highlighted here. These apps can be used to predict ligand interactions with transporters using Bayesian algorithms. We used recently published transporter data sets (MATE1, MATE2K, OCT2, OCTN2, ASBT, and NTCP) to build preliminary models in a commercial tool and in open software that can deliver the model in a mobile app. In addition, several transporter data sets extracted from the ChEMBL database were used to illustrate how such public data and models can be shared. Predicting drug-drug interactions for various transporters using computational models is potentially within reach of anyone with an iPhone or iPad. Such tools could help prioritize which substrates should be used for in vivo drug-drug interaction testing and enable open sharing of models. IntroductionWe are increasingly seeing medium-or high-throughput screens used to develop ligand-based models for individual transporters (Diao et al., 2009Zheng et al., 2009;Kido et al., 2011;Astorga et al., 2012;Ekins et al., 2012b;Greupink et al., 2012;Dong et al., 2013Dong et al., , 2014Sedykh et al., 2013;Wittwer et al., 2013;Xu et al., 2013). One of the significant limitations of this is that the models developed are rarely accessible outside of the research group developing them, likely because of the commercial software required. One way to surmount this is to develop models using open-source software. We previously showed that such "open models" produce validation statistics that are comparable to commercial tools (Gupta et al., 2010). Because many computational machine learning methods use molecular function class fingerprints of maximum diameter 6 (FCFP6) and extended connectivity fingerprints (ECFP6), we have described their implementation with the Chemistry Development Kit (CDK) (Steinbeck et al., 2003) components (Clark et al., 2014). We also recently described how an open-source Bayesian algorithm can be used with these descriptors to develop and validate thousands of data sets, including those from the ChEMBL database . In response to the shift toward mobile computing, we have developed apps for drug discovery, leveraging years of research in cheminformatics...

show abstract

“…The datasets can be downloaded, and the software can be used to generate many molecule descriptors (using the CDK) [ 37 , 38 ] and then QSAR models (through integration with the R statistical software). The software is considered not as user friendly as some commercial tools [ 39 ].…”

Section: Statistical-based Systemsmentioning

confidence: 99%

“…Each model has some statistics describing the model as well as a probability to provide more confi dence in the result. The software is simple to use, and drawbacks appear to be the lack of batch processing operation, the "black box" nature of the models, and the lack of capability to build or update the models on the website [ 39 ].…”

Section: Statistical-based Systemsmentioning

confidence: 99%

The Use of In Silico Models Within a Large Pharmaceutical Company

Brigo¹,

Muster²

2016

Methods in Molecular Biology

View full text Add to dashboard Cite

The present contribution describes how in silico models are applied at different stages of the drug discovery process in the pharmaceutical industry. A thorough description of the most relevant computational methods and tools is given along with an in-depth evaluation of their performance in the context of potential genotoxic impurities assessment.The challenges of predicting the outcome of highly complex studies are discussed followed by considerations on how novel ways to manage, store, share and analyze data may advance knowledge and facilitate modeling efforts.

show abstract

Progress in computational toxicology

Cited by 96 publications

References 188 publications

Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets

Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets

Making Transporter Models for Drug–Drug Interaction Prediction Mobile

The Use of In Silico Models Within a Large Pharmaceutical Company

Contact Info

Product

Resources

About