Saha I.,University of Warsaw |
Saha I.,National Research Council Italy |
Saha I.,Wroclaw University |
Rak B.,University of Warsaw |
And 9 more authors.
Journal of Chemical Information and Modeling | Year: 2015
(Graph Presented) The Cyclin-Dependent Kinases (CDKs) are the core components coordinating eukaryotic cell division cycle. Generally the crystal structure of CDKs provides information on possible molecular mechanisms of ligand binding. However, reliable and robust estimation of ligand binding activity has been a challenging task in drug design. In this regard, various machine learning techniques, such as Support Vector Machine, Naive Bayesian classifier, Decision Tree, and K-Nearest Neighbor classifier, have been used. The performance of these heterogeneous classification techniques depends on proper selection of features from the data set. This fact motivated us to propose an integrated classification technique using Genetic Algorithm (GA), Rotational Feature Selection (RFS) scheme, and Ensemble of Machine Learning methods, named as the Genetic Algorithm integrated Rotational Ensemble based classification technique, for the prediction of ligand binding activity of CDKs. This technique can automatically find the important features and the ensemble size. For this purpose, GA encodes the features and ensemble size in a chromosome as a binary string. Such encoded features are then used to create diverse sets of training points using RFS in order to train the machine learning method multiple times. The RFS scheme works on Principal Component Analysis (PCA) to preserve the variability information of the rotational nonoverlapping subsets of original data. Thereafter, the testing points are fed to the different instances of trained machine learning method in order to produce the ensemble result. Here accuracy is computed as a final result after 10-fold cross validation, which also used as an objective function for GA to maximize. The effectiveness of the proposed classification technique has been demonstrated quantitatively and visually in comparison with different machine learning methods for 16 ligand binding CDK docking and rescoring data sets. In addition, the best possible features have been reported for CDK docking and rescoring data sets separately. Finally, the Friedman test has been conducted to judge the statistical significance of the results produced by the proposed technique. The results indicate that the integrated classification technique has high relevance in predicting of protein-ligand binding activity. © 2015 American Chemical Society.
Colomer I.,University of Leeds |
Adeniji O.,University of Leeds |
Burslem G.M.,University of Leeds |
Craven P.,University of Leeds |
And 6 more authors.
Bioorganic and Medicinal Chemistry | Year: 2015
The application of [4+2] cycloadditions between alkenes and an N-benzoyl iminium species, generated in situ under acidic conditions, is described in the synthesis of diverse molecular scaffolds. The key reaction led to the formation of cyclic imidates in good yield and with high regioselectivity. It was demonstrated that the cyclic imidates may be readily converted into 1,3-amino alcohols. Incorporation of orthogonally-reactive functionality, such as aryl and alkyl bromides, into the cycloaddition substrates enabled the synthesis of additional scaffolds. For one scaffold, the synthesis of exemplar screening compounds was undertaken to demonstrate potential value in small molecule library production. © 2015 Elsevier Ltd. All rights reserved.
Pompei M.,I.R.B.M. |
Francesco M.E.D.,Merck And Co. |
Pesci S.,I.R.B.M. |
Koch U.,Lead Discovery Center |
And 4 more authors.
Bioorganic and Medicinal Chemistry Letters | Year: 2010
Hepatitis C represents a serious worldwide health-care problem. Recently, we have disclosed a novel class of P2-P4 macrocyclic inhibitors of NS3/4A protease containing a carbamate functionality as capping group at the P3 N-terminus. Herein we report our work aimed at further depeptidizing the P3 region by replacement of the urethane function with a succinamide motif. This peptidomimetic approach has led to the discovery of novel P2-P4 macrocyclic inhibitors of HCV NS3/4A protease with sub-nanomolar enzyme affinities. In addition to being potent inhibitors of HCV subgenomic replication, optimized analogues within this series have also presented attractive PK properties and showed promising liver levels in rat following oral administration. © 2009 Elsevier Ltd. All rights reserved.
Zimmermann G.,Max Planck Institute of Molecular Physiology |
Zimmermann G.,TU Dortmund |
Schultz-Fademrecht C.,Lead Discovery Center |
Kuchler P.,Max Planck Institute of Molecular Physiology |
And 10 more authors.
Journal of Medicinal Chemistry | Year: 2014
K-Ras is one of the most frequently mutated signal transducing human oncogenes. Ras signaling activity requires correct cellular localization of the GTPase. The spatial organization of K-Ras is controlled by the prenyl binding protein PDEδ, which enhances Ras diffusion in the cytosol. Inhibition of the Ras-PDEδ interaction by small molecules impairs Ras localization and signaling. Here we describe in detail the identification and structure guided development of Ras-PDEδ inhibitors targeting the farnesyl binding pocket of PDEδ with nanomolar affinity. We report kinetic data that characterize the binding of the most potent small molecule ligands to PDEδ and prove their binding to endogenous PDEδ in cell lysates. The PDEδ inhibitors provide promising starting points for the establishment of new drug discovery programs aimed at cancers harboring oncogenic K-Ras. © 2014 American Chemical Society.