1.
Alvarsson, Jonathan, et al.
(författare)
Benchmarking Study of Parameter Variation When Using Signature Fingerprints Together with Support Vector Machines
2014
Ingår i: Journal of Chemical Information and Modeling. - : American Chemical Society (ACS). - 1549-9596 .- 1549-960X. ; 54:11, s. 3211-3217
Tidskriftsartikel (refereegranskat) abstract
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, ?, and signature height. C is a penalty parameter that limits overfitting, ? 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 gamma 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.
2.
Alvarsson, Jonathan, et al.
(författare)
Large-scale ligand-based predictive modelling using support vector machines
2016
Ingår i: Journal of Cheminformatics. - : Springer Science and Business Media LLC. - 1758-2946. ; 8
Tidskriftsartikel (refereegranskat) abstract
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.
3.
Alvarsson, Jonathan, 1981-
(författare)
Ligand-based Methods for Data Management and Modelling
2015
Doktorsavhandling (övrigt vetenskapligt/konstnärligt) abstract
Drug discovery is a complicated and expensive process in the billion dollar range. One way of making the drug development process more efficient is better information handling, modelling and visualisation. The majority of todays drugs are small molecules, which interact with drug targets to cause an effect. Since the 1980s large amounts of compounds have been systematically tested by robots in so called high-throughput screening. Ligand-based drug discovery is based on modelling drug molecules. In the field known as Quantitative Structure–Activity Relationship (QSAR) molecules are described by molecular descriptors which are used for building mathematical models. Based on these models molecular properties can be predicted and using the molecular descriptors molecules can be compared for, e.g., similarity. Bioclipse is a workbench for the life sciences which provides ligand-based tools through a point and click interface. The aims of this thesis were to research, and develop new or improved ligand-based methods and open source software, and to work towards making these tools available for users through the Bioclipse workbench. To this end, a series of molecular signature studies was done and various Bioclipse plugins were developed.An introduction to the field is provided in the thesis summary which is followed by five research papers. Paper I describes the Bioclipse 2 software and the Bioclipse scripting language. In Paper II the laboratory information system Brunn for supporting work with dose-response studies on microtiter plates is described. In Paper III the creation of a molecular fingerprint based on the molecular signature descriptor is presented and the new fingerprints are evaluated for target prediction and found to perform on par with industrial standard commercial molecular fingerprints. In Paper IV the effect of different parameter choices when using the signature fingerprint together with support vector machines (SVM) using the radial basis function (RBF) kernel is explored and reasonable default values are found. In Paper V the performance of SVM based QSAR using large datasets with the molecular signature descriptor is studied, and a QSAR model based on 1.2 million substances is created and made available from the Bioclipse workbench.
4.
Alvarsson, Jonathan, et al.
(författare)
Ligand-Based Target Prediction with Signature Fingerprints
2014
Ingår i: Journal of Chemical Information and Modeling. - : American Chemical Society (ACS). - 1549-9596 .- 1549-960X. ; 54:10, s. 2647-2653
Tidskriftsartikel (refereegranskat) abstract
When evaluating a potential drug candidate it is desirable to predict target interactions in silico prior to synthesis in order to assess, e.g., secondary pharmacology. This can be done by looking at known target binding profiles of similar compounds using chemical similarity searching. The purpose of this study was to construct and evaluate the performance of chemical fingerprints based on the molecular signature descriptor for performing target binding predictions. For the comparison we used the area under the receiver operating characteristics curve (AUC) complemented with net reclassification improvement (NRI). We created two open source signature fingerprints, a bit and a count version, and evaluated their performance compared to a set of established fingerprints with regards to predictions of binding targets using Tanimoto-based similarity searching on publicly available data sets extracted from ChEMBL. The results showed that the count version of the signature fingerprint performed on par with well-established fingerprints such as ECFP. The count version outperformed the bit version slightly; however, the count version is more complex and takes more computing time and memory to run so its usage should probably be evaluated on a case-by-case basis. The NRI based tests complemented the AUC based ones and showed signs of higher power.
5.
Eklund, Martin, et al.
(författare)
The C1C2 : a framework for simultaneous model selection and assessment
2008
Ingår i: BMC Bioinformatics. - : Springer Science and Business Media LLC. - 1471-2105. ; 9, s. 360-
Tidskriftsartikel (refereegranskat) abstract
BACKGROUND: There has been recent concern regarding the inability of predictive modeling approaches to generalize to new data. Some of the problems can be attributed to improper methods for model selection and assessment. Here, we have addressed this issue by introducing a novel and general framework, the C1C2, for simultaneous model selection and assessment. The framework relies on a partitioning of the data in order to separate model choice from model assessment in terms of used data. Since the number of conceivable models in general is vast, it was also of interest to investigate the employment of two automatic search methods, a genetic algorithm and a brute-force method, for model choice. As a demonstration, the C1C2 was applied to simulated and real-world datasets. A penalized linear model was assumed to reasonably approximate the true relation between the dependent and independent variables, thus reducing the model choice problem to a matter of variable selection and choice of penalizing parameter. We also studied the impact of assuming prior knowledge about the number of relevant variables on model choice and generalization error estimates. The results obtained with the C1C2 were compared to those obtained by employing repeated K-fold cross-validation for choosing and assessing a model. RESULTS: The C1C2 framework performed well at finding the true model in terms of choosing the correct variable subset and producing reasonable choices for the penalizing parameter, even in situations when the independent variables were highly correlated and when the number of observations was less than the number of variables. The C1C2 framework was also found to give accurate estimates of the generalization error. Prior information about the number of important independent variables improved the variable subset choice but reduced the accuracy of generalization error estimates. Using the genetic algorithm worsened the model choice but not the generalization error estimates, compared to using the brute-force method. The results obtained with repeated K-fold cross-validation were similar to those produced by the C1C2 in terms of model choice, however a lower accuracy of the generalization error estimates was observed. CONCLUSION: The C1C2 framework was demonstrated to work well for finding the true model within a penalized linear model class and accurately assess its generalization error, even for datasets with many highly correlated independent variables, a low observation-to-variable ratio, and model assumption deviations. A complete separation of the model choice and the model assessment in terms of data used for each task improves the estimates of the generalization error.
6.
Freyhult, Eva, et al.
(författare)
Unbiased descriptor and parameter selection confirms the potential of proteochemometric modelling
2005
Ingår i: BMC Bioinformatics. - : Springer Science and Business Media LLC. - 1471-2105. ; 6, s. 50-
Tidskriftsartikel (refereegranskat) abstract
Background Proteochemometrics is a new methodology that allows prediction of protein function directly from real interaction measurement data without the need of 3D structure information. Several reported proteochemometric models of ligand-receptor interactions have already yielded significant insights into various forms of bio-molecular interactions. The proteochemometric models are multivariate regression models that predict binding affinity for a particular combination of features of the ligand and protein. Although proteochemometric models have already offered interesting results in various studies, no detailed statistical evaluation of their average predictive power has been performed. In particular, variable subset selection performed to date has always relied on using all available examples, a situation also encountered in microarray gene expression data analysis. Results A methodology for an unbiased evaluation of the predictive power of proteochemometric models was implemented and results from applying it to two of the largest proteochemometric data sets yet reported are presented. A double cross-validation loop procedure is used to estimate the expected performance of a given design method. The unbiased performance estimates (P2) obtained for the data sets that we consider confirm that properly designed single proteochemometric models have useful predictive power, but that a standard design based on cross validation may yield models with quite limited performance. The results also show that different commercial software packages employed for the design of proteochemometric models may yield very different and therefore misleading performance estimates. In addition, the differences in the models obtained in the double CV loop indicate that detailed chemical interpretation of a single proteochemometric model is uncertain when data sets are small. Conclusion The double CV loop employed offer unbiased performance estimates about a given proteochemometric modelling procedure, making it possible to identify cases where the proteochemometric design does not result in useful predictive models. Chemical interpretations of single proteochemometric models are uncertain and should instead be based on all the models selected in the double CV loop employed here.
7.
Kontijevskis, Aleksejs, et al.
(författare)
Computational proteomics analysis of HIV-1 protease interactome
2007
Ingår i: Proteins. - : Wiley. - 0887-3585 .- 1097-0134. ; 68:1, s. 305-312
Tidskriftsartikel (refereegranskat) abstract
HIV-1 protease is a small homodimeric enzyme that ensures maturation of HIV virions by cleaving the viral precursor Gag and Gag-Pol polyproteins into structural and functional elements. The cleavage sites in the viral polyproteins share neither sequence homology nor binding motif and the specificity of the HIV-1 protease is therefore only partially understood. Using an extensive data set collected from 16 years of HIV proteome research we have here created a general and predictive rule-based model for HIV-1 protease specificity based on rough sets. We demonstrate that HIV-1 protease specificity is much more complex than previously anticipated, which cannot be defined based solely on the amino acids at the substrate's scissile bond or by any other single substrate amino acid position only. Our results show that the combination of at least three particular amino acids is needed in the substrate for a cleavage event to occur. Only by combining and analyzing massive amounts of HIV proteome data it was possible to discover these novel and general patterns of physico-chemical substrate cleavage determinants. Our study is an example how computational biology methods can advance the understanding of the viral interactomes.
8.
Kontijevskis, Aleksejs, et al.
(författare)
Proteochemometrics mapping of the interaction space for retroviral proteases and their substrates
2009
Ingår i: Bioorganic & Medicinal Chemistry. - : Elsevier BV. - 0968-0896 .- 1464-3391. ; 17:14, s. 5229-5237
Tidskriftsartikel (refereegranskat) abstract
Understanding the complex interactions of retroviral proteases with their ligands is an important scientific challenge in efforts to achieve control of retroviral infections. Development of drug resistance because of high mutation rates and extensive polymorphisms causes major problems in treating the deadly diseases these viruses cause, and prompts efforts to identify new strategies. Here we report a comprehensive analysis of the interaction of 63 retroviral proteases from nine different viral species with their substrates and inhibitors based on publicly available data from the past 17years of retroviral research. By correlating physico-chemical descriptions of retroviral proteases and substrates to their biological activities we constructed a highly statistically valid 'proteochemometric' model for the interactome of retroviral proteases. Analysis of the model indicated amino acid positions in retroviral proteases with the highest influence on ligand activity and revealed general physicochemical properties essential for tight binding of substrates across multiple retroviral proteases. Hexapeptide inhibitors developed based on the discovered general properties effectively inhibited HIV-1 proteases in vitro, and some exhibited uniformly high inhibitory activity against all HIV-1 proteases mutants evaluated. A generalized proteochemometric model for retroviral proteases interactome has been created and analysed in this study. Our results demonstrate the feasibility of using the developed general strategy in the design of inhibitory peptides that can potentially serve as templates for drug resistance-improved HIV retardants.
9.
Kopanchuk, Sergei, et al.
(författare)
Co-operative regulation of ligand binding to melanocortin receptor subtypes : evidence for interacting binding sites
2005
Ingår i: European Journal of Pharmacology. - : Elsevier BV. - 0014-2999 .- 1879-0712. ; 512:2-3, s. 85-95
Tidskriftsartikel (refereegranskat) abstract
This study evaluates the binding the melanocyte stimulating hormone peptide analogue [125I]NDP-MSH to melanocortin receptors MC1, MC3, MC4 and MC5 in insect cell membranes produced by baculovirus expression systems. The presence of Ca2+ was found to be mandatory to achieve specific [125I]NDP-MSH binding to the melanocortin receptors. Although association kinetics of [125I]NDP-MSH followed the regularities of simple bimolecular reactions, the dissociation of [125I]NDP-MSH from the melanocortin receptors was heterogeneous. Eleven linear and cyclic MSH peptides studied displaced the [125I]NDP-MSH binding to the studied melanocortin receptors, with the shapes of their competition curves varying from biphasic or shallow to super-steep (Hill coefficients ranging from 0.4 to 1.5). Notably the same peptide often gave highly different patterns on different melanocortin receptor subtypes; e.g. the MC4 receptor selective antagonist HS131 gave a Hill coefficient of 1.5 on the MC1 receptor but 0.5-0.7 on the MC(3-5) receptors. Adding a mask of one of the peptides to block its high affinity binding did not prevent other competing peptides to yield biphasic competition curves. The data indicate that the binding of MSH peptides to melanocortin receptors are governed by a complex dynamic homotropic co-operative regulations.
10.
Kopanchuk, Sergei, et al.
(författare)
Kinetic evidence for tandemly arranged ligand binding sites in melanocortin 4 receptor complexes
2006
Ingår i: Neurochemistry International. - : Elsevier BV. - 0197-0186 .- 1872-9754. ; 49:5, s. 533-542
Tidskriftsartikel (refereegranskat) abstract
The melanocortin 4 receptor (MC(4)R) binding of the peptide analogue of melanocyte stimulating hormone, [(125)I]NDP-MSH, and the low molecular weight radionucleid 1-(D-1,2,3,4-tetrahydroisoquinoline-3-carboxy-D-4-(125)iodophenylalanyl)-4-cyclohexyl-4-[(1,2,4-triazol-1-yl)methyl]piperidine trifluoroacetate ([(125)I]THIQ) were compared. Kinetic analysis indicated heterogeneity in the binding of both radioligands, the binding apparently proceeding to two tandemly arranged interconnected mutually dependent binding sites. Steric considerations and BRET analysis of Rluc and GFP tagged receptors proposed that these sites are located on different subunits of receptor dimers, which form receptor complexes. According to the minimal model proposed, ligand binding proceeds consecutively to the two binding sites of the dimer. After binding of the first ligand conformational transformations of the complex occur, which is followed by binding of the second ligand. When both receptor units have bound [(125)I]NDP-MSH, the radioligand can be released only from one unit. The [(125)I]NDP-MSH bound to the remaining unit stays practically irreversibly bound due to a very slow retransformation rate of the transformed complex. The considerably faster binding of [(125)I]THIQ did not allow accurate kinetic differentiation of the two binding sites. However, addition of NDP-MSH as well as a fragment of the human agouti protein, hAGRP(83-132) to the preformed [(125)I]THIQ-MC(4)R complex drastically retarded the release of [(125)I]THIQ from the complex, blocking conformational transformations in the complex by binding into the second binding site. The consecutive binding of ligands to the MC(4)R dimers has substantial impact on the apparent ligand potencies, when determined in competition with the two different radioligands applied herein; the apparent potencies of the same ligand differing up to three orders of magnitude when assayed in competition with [(125)I]NDP-MSH or [(125)I]THIQ.
