Open Source Drug Discovery with Bioclipse

Spjuth, Ola; Carlsson, Lars; Alvarsson, Jonathan; Georgiev, Valentin; Willighagen, Egon; Eklund, Martin

doi:10.2174/156802612804910287

Cited by 10 publications

(4 citation statements)

References 55 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…k-Nearest Neighbors, K-Partial Least Squares, and Self Organizing Maps and Kohonen maps for Mtb model building with this combined data set. In addition, efforts to make Mtb models more readily available may also be evaluated using free or open source resources like Bioclipse, − Chembench, and others. , This would then make the models globally accessible and perhaps increase the speed and efficiency of screening efforts in vitro .…”

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

“…Bioclipse is a workbench for the life sciences that provides open source drug discovery functionality [ 30 ]. Bioclipse decision support (DS) [ 17 ] provides a framework for making predictive models available to end users running on a local computer (off-line).…”

Section: Methodsmentioning

confidence: 99%

Large-scale ligand-based predictive modelling using support vector machines

et al. 2016

Self Cite

View full text Add to dashboard Cite

The increasing size of datasets in drug discovery makes it challenging to build robust and accurate predictive models within a reasonable amount of time. In order to investigate the effect of dataset sizes on predictive performance and modelling time, ligand-based regression models were trained on open datasets of varying sizes of up to 1.2 million chemical structures. For modelling, two implementations of support vector machines (SVM) were used. Chemical structures were described by the signatures molecular descriptor. Results showed that for the larger datasets, the LIBLINEAR SVM implementation performed on par with the well-established libsvm with a radial basis function kernel, but with dramatically less time for model building even on modest computer resources. Using a non-linear kernel proved to be infeasible for large data sizes, even with substantial computational resources on a computer cluster. To deploy the resulting models, we extended the Bioclipse decision support framework to support models from LIBLINEAR and made our models of logD and solubility available from within Bioclipse.Electronic supplementary materialThe online version of this article (doi:10.1186/s13321-016-0151-5) contains supplementary material, which is available to authorized users.

show abstract

“…One modeling approach that is increasingly used in QSAR is the combination of molecular signatures − with support vector machines (SVMs). , Molecular signatures are topological descriptors that describe, for each atom in a molecule, the neighboring atoms in a canonical fashion. They have been used for natural-product-likeness scoring, together with SVM in QSAR, − in molecular design for solvent selection, and in modeling cytochrome P450 inhibition, , and they have been shown to produce robust models for drug design . Norinder et al used molecular signatures together with both SVM and random forest when introducing conformal prediction in predictive modeling.…”

Section: Introductionmentioning

confidence: 99%

Benchmarking Study of Parameter Variation When Using Signature Fingerprints Together with Support Vector Machines

Alvarsson

Eklund

Andersson

et al. 2014

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

QSAR modeling using molecular signatures and support vector machines with a radial basis function is increasingly used for virtual screening in the drug discovery field. This method has three free parameters: C, γ, and signature height. C is a penalty parameter that limits overfitting, γ controls the width of the radial basis function kernel, and the signature height determines how much of the molecule is described by each atom signature. Determination of optimal values for these parameters is time-consuming. Good default values could therefore save considerable computational cost. The goal of this project was to investigate whether such default values could be found by using seven public QSAR data sets spanning a wide range of end points and using both a bit version and a count version of the molecular signatures. On the basis of the experiments performed, we recommend a parameter set of heights 0 to 2 for the count version of the signature fingerprints and heights 0 to 3 for the bit version. These are in combination with a support vector machine using C in the range of 1 to 100 and γ in the range of 0.001 to 0.1. When data sets are small or longer run times are not a problem, then there is reason to consider the addition of height 3 to the count fingerprint and a wider grid search. However, marked improvements should not be expected.

show abstract

Open Source Drug Discovery with Bioclipse

Cited by 10 publications

References 55 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

Large-scale ligand-based predictive modelling using support vector machines

Benchmarking Study of Parameter Variation When Using Signature Fingerprints Together with Support Vector Machines

Contact Info

Product

Resources

About