Journal ArticleDOI
Support vector machines for drug discovery.
Kathrin Heikamp,Jürgen Bajorath +1 more
TLDR
SVMs are currently among the best-performing approaches for chemical and biological property prediction and the computational identification of active compounds and it is anticipated that their use in drug discovery will further increase.Abstract:
Introduction: Support vector machines (SVMs) are supervised machine learning algorithms for binary class label prediction and regression-based prediction of property values. In recent years, SVMs h...read more
Citations
More filters
Journal ArticleDOI
ADMET modeling approaches in drug discovery.
TL;DR: In silico prediction of ADMET is an important component of pharmaceutical R&D and has advanced alongside the progress of chemoinformatics, which has evolved from traditional chemometrics to advanced machine learning methods.
Journal ArticleDOI
Machine Learning Methods in Drug Discovery.
TL;DR: In this review, machine learning and deep learning algorithms utilized in drug discovery and associated techniques will be discussed and the applications that produce promising results and methods will be reviewed.
Journal ArticleDOI
Quantitative structure-activity relationship: promising advances in drug discovery platforms.
TL;DR: The aim of this review is to show how QSAR modeling can be applied in novel drug discovery, design and lead optimization in the absence of 3D structures of specific drug targets.
Journal ArticleDOI
Support Vector Machine Classification and Regression Prioritize Different Structural Features for Binary Compound Activity and Potency Value Prediction
TL;DR: This work compared SVM and SVR calculations for the same compound data sets to evaluate which features are responsible for predictions and, on the basis of systematic feature weight analysis, rather surprising results were obtained.
Journal ArticleDOI
Drug/nondrug classification using Support Vector Machines with various feature selection strategies
TL;DR: Testing SVM as a classification tool in a real-life drug discovery problem revealed that it could be a useful method for classification task in early-phase of drug discovery.
References
More filters
Journal ArticleDOI
A novel logic-based approach for quantitative toxicology prediction
TL;DR: The SVILP approach has a major advantage in that it uses ILP automatically and consistently to derive rules, mostly novel, describing fragments that are toxicity alerts, and has the potential of tackling many problems relevant to chemoinformatics including in silico drug design.
Journal ArticleDOI
Targeting multifunctional proteins by virtual screening: structurally diverse cytohesin inhibitors with differentiated biological functions.
Dagmar Stumpfe,Anke Bill,Nina Novak,Gerrit Loch,Heike Blockus,Hanna Geppert,Thomas Becker,Anton Schmitz,Michael Hoch,Waldemar Kolanus,Michael Famulok,Jürgen Bajorath +11 more
TL;DR: These findings demonstrate that, at least for the cytohesins, computational extrapolation from known active compounds was capable of identifying small molecular probes with highly diversified functional profiles.
Journal ArticleDOI
Beyond the scope of Free-Wilson analysis: building interpretable QSAR models with machine learning algorithms.
TL;DR: The results suggest that the R-group contribution can be used to interpret bioactivity data and highlight that theR-group signature based SVM modeling method is as interpretable as Free-Wilson analysis.
Journal ArticleDOI
Computational profiling of bioactive compounds using a target-dependent composite workflow.
TL;DR: An automated workflow using several methods to optimally browse target-ligand space according to existing knowledge on either ligand and target space under investigation was remarkably accurate in identifying the main target of 189 clinical candidates and proposed two novel off-targets which could be experimentally validated.
Journal ArticleDOI
StructRank: a new approach for ligand-based virtual screening.
TL;DR: This paper proposes a top-k ranking algorithm (StructRank) based on Support Vector Machines to solve the early recognition problem directly and shows that this ranking approach outperforms not only regression methods but another ranking approach recently proposed for QSAR ranking, RankSVM, in terms of actives found.