Accurate Solubility Prediction with Error Bars for Electrolytes:  A Machine Learning Approach

Schwaighofer, Anton; Schroeter, Timon; Mika, Sebastian; Laub, Julian; Laak, Antonius ter; Sülzle, Detlev; Ganzer, Ursula; Heinrich, Nikolaus; Müller, Klaus Robert

doi:10.1021/ci600205g

Cited by 73 publications

(85 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A good QSAR model not only has good summary statistics such as RMSECV and Q 2 , but also yields high stability of predictions for each sample. Several studies have indicated that the high stability of predictions of models correlates with the accuracy of predictions [63][64][65][66][67]. Thus, the standard deviation of prediction errors for each sample can be used as an additional metric characterizing the Fig.…”

Section: Ace Datamentioning

confidence: 99%

Toward better QSAR/QSPR modeling: simultaneous outlier detection and variable selection using distribution of model features

Cao

Liang

et al. 2010

J Comput Aided Mol Des

View full text Add to dashboard Cite

Building a robust and reliable QSAR/QSPR model should greatly consider two aspects: selecting the optimal variable subset from a large pool of molecular descriptors and detecting outliers from a pool of samples. The two problems have the specific similarity and complementarity to some extent. Given a particular learning algorithm on a particular data set, one should consider how the interaction could happen between variable selection and outlier detection. In this paper, we describe a consistent methodology for simultaneously performing variable subset selection and outlier detection using the idea of statistical distribution which can be simulated by the establishment of many cross-predictive linear models. The approach exploits the fact that the distribution of linear model coefficients provides a mechanism for ranking and interpreting the effects of variable, while the distribution of prediction errors provides a mechanism for differentiating the outliers from normal samples. The use of statistic of these distributions, namely mean value and standard deviation, inherently provides a feasible way to effectively describe the information contained by the original samples. Several examples are used to demonstrate the prediction ability of our proposed approach through the comparison of different approaches as well as their combinations.

show abstract

Section: Ace Datamentioning

confidence: 99%

Toward better QSAR/QSPR modeling: simultaneous outlier detection and variable selection using distribution of model features

Cao

Liang

et al. 2010

J Comput Aided Mol Des

View full text Add to dashboard Cite

show abstract

“…Furthermore, Gaussian Processes provides an estimate of uncertainty together with each prediction. Despite these strengths there have been only a small number of published examples of its application to QSAR and ADME modeling [5][6][7][14][15][16].…”

Section: Application Of Modeling Techniquesmentioning

confidence: 99%

“…Automatic model generation requires unsupervised computational techniques which do not require any input from a user, are able to deal with a large number of descriptors and are not prone to overtraining. In recent years, a variety of such modern modeling techniques have been applied to QSAR modeling; some examples include Bayesian Neural Networks [3], Associative Neural Networks [4] and Gaussian Processes [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Automatic QSAR modeling of ADME properties: blood–brain barrier penetration and aqueous solubility

Obrezanova

Gola

Champness

et al. 2008

J Comput Aided Mol Des

View full text Add to dashboard Cite

In this article, we present an automatic model generation process for building QSAR models using Gaussian Processes, a powerful machine learning modeling method. We describe the stages of the process that ensure models are built and validated within a rigorous framework: descriptor calculation, splitting data into training, validation and test sets, descriptor filtering, application of modeling techniques and selection of the best model. We apply this automatic process to data sets of blood-brain barrier penetration and aqueous solubility and compare the resulting automatically generated models with 'manually' built models using external test sets. The results demonstrate the effectiveness of the automatic model generation process for two types of data sets commonly encountered in building ADME QSAR models, a small set of in vivo data and a large set of physico-chemical data.

show abstract

“…Models encode relationships between molecular structure and properties, but interpreting and visualising this information to design better molecules has been almost impossible. This is particularly true of models built with modern machine learning techniques such as artificial neural networks [5], Gaussian processes [6] [7], Fig. 3.…”

mentioning

confidence: 99%

Beyond Profiling: Using ADMET Models to Guide Decisions

Segall

Champness

Obrezanova

et al. 2009

Chemistry & Biodiversity

View full text Add to dashboard Cite

ADMET Models, whether in silico or in vitro, are commonly used to 'profile' molecules, to identify potential liabilities or filter out molecules expected to have undesirable properties. While useful, this is the most basic application of such models. Here, we will show how models may be used to go 'beyond profiling' to guide key decisions in drug discovery. For example, selection of chemical series to focus resources with confidence or design of improved molecules targeting structural modifications to improve key properties. To prioritise molecules and chemical series, the success criteria for properties and their relative importance to a project's objective must be defined. Data from models (experimental or predicted) may then be used to assess each molecule's balance of properties against those requirements. However, to make decisions with confidence, the uncertainties in all of the data must also be considered. In silico models encode information regarding the relationship between molecular structure and properties. This is used to predict the property value of a novel molecule. However, further interpretation can yield information on the contributions of different groups in a molecule to the property and the sensitivity of the property to structural changes. Visualising this information can guide the redesign process. In this article, we describe methods to achieve these goals and drive drug-discovery decisions and illustrate the results with practical examples.

show abstract

Accurate Solubility Prediction with Error Bars for Electrolytes: A Machine Learning Approach

Cited by 73 publications

References 52 publications

Toward better QSAR/QSPR modeling: simultaneous outlier detection and variable selection using distribution of model features

Toward better QSAR/QSPR modeling: simultaneous outlier detection and variable selection using distribution of model features

Automatic QSAR modeling of ADME properties: blood–brain barrier penetration and aqueous solubility

Beyond Profiling: Using ADMET Models to Guide Decisions

Contact Info

Product

Resources

About