Concomitant Transapical Transcatheter Aortic Valve Implantation and Transapical Mitral Valve Repair With NeoChord Implantation.

One-third of the patients with severe symptomatic aortic valve stenosis (sAS) present with hemodynamic relevant mitral valve insufficiency (rMI). In patients who undergo conventional surgery, the rMI never would be left untreated; however, in cases of transcatheter aortic valve implantation (TAVI), the impact of rMI is often overlooked and left untreated. The combination of transapical TAVI (TA-TAVI) and NeoChord implantation represents a novel, promising therapeutic option for high-risk-surgery patients with sAS and rMI due to a prolapsed or flailed leaflet. This case report describes 2 patients (1 male, 1 female; mean age 82 years) who underwent TA-TAVI and concomitant NeoChord implantation at our institute. Both presented with sAS and rMI due to a prolapse of the P2 segment of the mitral valve. At first, the TA-TAVI was implanted under angio-guidance, followed by three-dimensional echo-guided implantation of the NeoChords, through the same approach, which was slightly posterior and lateral to the apex. TA-TAVI using an Edwards Sapien 3 (26 mm, n = 1 and 29 mm, n = 1) and NeoChord implantation (2 in the first and 3 in the second patient) was successful in both cases. Post-intervention discharge echo indicated no paravalvular or central insufficiency after the procedure and only a trace of mitral valve insufficiency. TA-TAVI and concomitant NeoChord implantation is a feasible and promising treatment option for high-risk patients with rMI. Despite its technical demands, in experienced hands, it is a safe procedure for those not well suited for surgical intervention.

Efficiency of different measures for defining the applicability domain of classification models.

The goal of defining an applicability domain for a predictive classification model is to identify the region in chemical space where the model's predictions are reliable. The boundary of the applicability domain is defined with the help of a measure that shall reflect the reliability of an individual prediction. Here, the available measures are differentiated into those that flag unusual objects and which are independent of the original classifier and those that use information of the trained classifier. The former set of techniques is referred to as novelty detection while the latter is designated as confidence estimation. A review of the available confidence estimators shows that most of these measures estimate the probability of class membership of the predicted objects which is inversely related to the error probability. Thus, class probability estimates are natural candidates for defining the applicability domain but were not comprehensively included in previous benchmark studies. The focus of the present study is to find the best measure for defining the applicability domain for a given binary classification technique and to determine the performance of novelty detection versus confidence estimation. Six different binary classification techniques in combination with ten data sets were studied to benchmark the various measures. The area under the receiver operating characteristic curve (AUC ROC) was employed as main benchmark criterion. It is shown that class probability estimates constantly perform best to differentiate between reliable and unreliable predictions. Previously proposed alternatives to class probability estimates do not perform better than the latter and are inferior in most cases. Interestingly, the impact of defining an applicability domain depends on the observed area under the receiver operator characteristic curve. That means that it depends on the level of difficulty of the classification problem (expressed as AUC ROC) and will be largest for intermediately difficult problems (range AUC ROC 0.7-0.9). In the ranking of classifiers, classification random forests performed best on average. Hence, classification random forests in combination with the respective class probability estimate are a good starting point for predictive binary chemoinformatic classifiers with applicability domain. Graphical abstract .

Computational Chemistry in the Pharmaceutical Industry: From Childhood to Adolescence.

Computational chemistry within the pharmaceutical industry has grown into a field that proactively contributes to many aspects of drug design, including target selection and lead identification and optimization. While methodological advancements have been key to this development, organizational developments have been crucial to our success as well. In particular, the interaction between computational and medicinal chemistry and the integration of computational chemistry into the entire drug discovery process have been invaluable. Over the past ten years we have shaped and developed a highly efficient computational chemistry group for small-molecule drug discovery at Bayer HealthCare that has significantly impacted the clinical development pipeline. In this article we describe the setup and tasks of the computational group and discuss external collaborations. We explain what we have found to be the most valuable and productive methods and discuss future directions for computational chemistry method development. We share this information with the hope of igniting interesting discussions around this topic.

[Intensive care treatment of patients with left ventricular assist devices]. / Intensivbehandlung von Kranken mit Linksherzersatz.

Apart from heart transplantation, implantation of a left ventricular assist device (LVAD) is the only established surgical treatment for therapy-refractory terminal left heart failure, The specific intensive care unit (ICU) management of these patients depends on the reason for the ICU admission and requires understanding of the characteristic hemodynamics of non-pulsatile LVADs as well as of the inherent problems. Knowledge about the specific features in hemodynamic monitoring, understanding of pump characteristics, management of anticoagulation and hemostasis and the handling of problems, such as right heart failure, aortic valve insufficiency and infections is essential. The management of unconscious LVAD patients can be challenging. It requires a sophisticated transthoracic and transesophageal echocardiography (TTE/TEE) examination, targeted laboratory diagnostics and consideration of possible alternative diagnoses. Professional interdisciplinary cooperation and exchange of current knowledge is crucial.

Chemogenomic analysis of G-protein coupled receptors and their ligands deciphers locks and keys governing diverse aspects of signalling.

Understanding the molecular mechanism of signalling in the important super-family of G-protein-coupled receptors (GPCRs) is causally related to questions of how and where these receptors can be activated or inhibited. In this context, it is of great interest to unravel the common molecular features of GPCRs as well as those related to an active or inactive state or to subtype specific G-protein coupling. In our underlying chemogenomics study, we analyse for the first time the statistical link between the properties of G-protein-coupled receptors and GPCR ligands. The technique of mutual information (MI) is able to reveal statistical inter-dependence between variations in amino acid residues on the one hand and variations in ligand molecular descriptors on the other. Although this MI analysis uses novel information that differs from the results of known site-directed mutagenesis studies or published GPCR crystal structures, the method is capable of identifying the well-known common ligand binding region of GPCRs between the upper part of the seven transmembrane helices and the second extracellular loop. The analysis shows amino acid positions that are sensitive to either stimulating (agonistic) or inhibitory (antagonistic) ligand effects or both. It appears that amino acid positions for antagonistic and agonistic effects are both concentrated around the extracellular region, but selective agonistic effects are cumulated between transmembrane helices (TMHs) 2, 3, and ECL2, while selective residues for antagonistic effects are located at the top of helices 5 and 6. Above all, the MI analysis provides detailed indications about amino acids located in the transmembrane region of these receptors that determine G-protein signalling pathway preferences.

A maximum common subgraph kernel method for predicting the chromosome aberration test.

The chromosome aberration test is frequently used for the assessment of the potential of chemicals and drugs to elicit genetic damage in mammalian cells in vitro. Due to the limitations of experimental genotoxicity testing in early drug discovery phases, a model to predict the chromosome aberration test yielding high accuracy and providing guidance for structure optimization is urgently needed. In this paper, we describe a machine learning approach for predicting the outcome of this assay based on the structure of the investigated compound. The novelty of the proposed method consists in combining a maximum common subgraph kernel for measuring the similarity of two chemical graphs with the potential support vector machine for classification. In contrast to standard support vector machine classifiers, the proposed approach does not provide a black box model but rather allows to visualize structural elements with high positive or negative contribution to the class decision. In order to compare the performance of different methods for predicting the outcome of the chromosome aberration test, we compiled a large data set exhibiting high quality, reliability, and consistency from public sources and configured a fixed cross-validation protocol, which we make publicly available. In a comparison to standard methods currently used in pharmaceutical industry as well as to other graph kernel approaches, the proposed method achieved significantly better performance.

Benchmark data set for in silico prediction of Ames mutagenicity.

Up to now, publicly available data sets to build and evaluate Ames mutagenicity prediction tools have been very limited in terms of size and chemical space covered. In this report we describe a new unique public Ames mutagenicity data set comprising about 6500 nonconfidential compounds (available as SMILES strings and SDF) together with their biological activity. Three commercial tools (DEREK, MultiCASE, and an off-the-shelf Bayesian machine learner in Pipeline Pilot) are compared with four noncommercial machine learning implementations (Support Vector Machines, Random Forests, k-Nearest Neighbors, and Gaussian Processes) on the new benchmark data set.

A probabilistic approach to classifying metabolic stability.

Metabolic stability is an important property of drug molecules that should-optimally-be taken into account early on in the drug design process. Along with numerous medium- or high-throughput assays being implemented in early drug discovery, a prediction tool for this property could be of high value. However, metabolic stability is inherently difficult to predict, and no commercial tools are available for this purpose. In this work, we present a machine learning approach to predicting metabolic stability that is tailored to compounds from the drug development process at Bayer Schering Pharma. For four different in vitro assays, we develop Bayesian classification models to predict the probability of a compound being metabolically stable. The chosen approach implicitly takes the "domain of applicability" into account. The developed models were validated on recent project data at Bayer Schering Pharma, showing that the predictions are highly accurate and the domain of applicability is estimated correctly. Furthermore, we evaluate the modeling method on a set of publicly available data.

Estimating the domain of applicability for machine learning QSAR models: a study on aqueous solubility of drug discovery molecules.

We investigate the use of different Machine Learning methods to construct models for aqueous solubility. Models are based on about 4000 compounds, including an in-house set of 632 drug discovery molecules of Bayer Schering Pharma. For each method, we also consider an appropriate method to obtain error bars, in order to estimate the domain of applicability (DOA) for each model. Here, we investigate error bars from a Bayesian model (Gaussian Process (GP)), an ensemble based approach (Random Forest), and approaches based on the Mahalanobis distance to training data (for Support Vector Machine and Ridge Regression models). We evaluate all approaches in terms of their prediction accuracy (in cross-validation, and on an external validation set of 536 molecules) and in how far the individual error bars can faithfully represent the actual prediction error.

Machine learning models for lipophilicity and their domain of applicability.

Unfavorable lipophilicity and water solubility cause many drug failures; therefore these properties have to be taken into account early on in lead discovery. Commercial tools for predicting lipophilicity usually have been trained on small and neutral molecules, and are thus often unable to accurately predict in-house data. Using a modern Bayesian machine learning algorithm--a Gaussian process model--this study constructs a log D7 model based on 14,556 drug discovery compounds of Bayer Schering Pharma. Performance is compared with support vector machines, decision trees, ridge regression, and four commercial tools. In a blind test on 7013 new measurements from the last months (including compounds from new projects) 81% were predicted correctly within 1 log unit, compared to only 44% achieved by commercial software. Additional evaluations using public data are presented. We consider error bars for each method (model based error bars, ensemble based, and distance based approaches), and investigate how well they quantify the domain of applicability of each model.

Estimating the domain of applicability for machine learning QSAR models: a study on aqueous solubility of drug discovery molecules.

We investigate the use of different Machine Learning methods to construct models for aqueous solubility. Models are based on about 4000 compounds, including an in-house set of 632 drug discovery molecules of Bayer Schering Pharma. For each method, we also consider an appropriate method to obtain error bars, in order to estimate the domain of applicability (DOA) for each model. Here, we investigate error bars from a Bayesian model (Gaussian Process (GP)), an ensemble based approach (Random Forest), and approaches based on the Mahalanobis distance to training data (for Support Vector Machine and Ridge Regression models). We evaluate all approaches in terms of their prediction accuracy (in cross-validation, and on an external validation set of 536 molecules) and in how far the individual error bars can faithfully represent the actual prediction error.

Accurate solubility prediction with error bars for electrolytes: a machine learning approach.

Accurate in silico models for predicting aqueous solubility are needed in drug design and discovery and many other areas of chemical research. We present a statistical modeling of aqueous solubility based on measured data, using a Gaussian Process nonlinear regression model (GPsol). We compare our results with those of 14 scientific studies and 6 commercial tools. This shows that the developed model achieves much higher accuracy than available commercial tools for the prediction of solubility of electrolytes. On top of the high accuracy, the proposed machine learning model also provides error bars for each individual prediction.

Computational prediction of the chromosome-damaging potential of chemicals.

We report on the generation of computer-based models for the prediction of the chromosome-damaging potential of chemicals as assessed in the in vitro chromosome aberration (CA) test. On the basis of publicly available CA-test results of more than 650 chemical substances, half of which are drug-like compounds, we generated two different computational models. The first model was realized using the (Q)SAR tool MCASE. Results obtained with this model indicate a limited performance (53%) for the assessment of a chromosome-damaging potential (sensitivity), whereas CA-test negative compounds were correctly predicted with a specificity of 75%. The low sensitivity of this model might be explained by the fact that the underlying 2D-structural descriptors only describe part of the molecular mechanism leading to the induction of chromosome aberrations, that is, direct drug-DNA interactions. The second model was constructed with a more sophisticated machine learning approach and generated a classification model based on 14 molecular descriptors, which were obtained after feature selection. The performance of this model was superior to the MCASE model, primarily because of an improved sensitivity, suggesting that the more complex molecular descriptors in combination with statistical learning approaches are better suited to model the complex nature of mechanisms leading to a positive effect in the CA-test. An analysis of misclassified pharmaceuticals by this model showed that a large part of the false-negative predicted compounds were uniquely positive in the CA-test but lacked a genotoxic potential in other mutagenicity tests of the regulatory testing battery, suggesting that biologically nonsignificant mechanisms could be responsible for the observed positive CA-test result. Since such mechanisms are not amenable to modeling approaches it is suggested that a positive prediction made by the model reflects a biologically significant genotoxic potential. An integration of the machine-learning model as a screening tool in early discovery phases of drug development is proposed.

Classifying 'drug-likeness' with kernel-based learning methods.

In this article we report about a successful application of modern machine learning technology, namely Support Vector Machines, to the problem of assessing the 'drug-likeness' of a chemical from a given set of descriptors of the substance. We were able to drastically improve the recent result by Byvatov et al. (2003) on this task and achieved an error rate of about 7% on unseen compounds using Support Vector Machines. We see a very high potential of such machine learning techniques for a variety of computational chemistry problems that occur in the drug discovery and drug design process.

Characterization of new estrogen receptor destabilizing compounds: effects on estrogen-sensitive and tamoxifen-resistant breast cancer.

BACKGROUND: Antiestrogens of the selective estrogen receptor modulator (SERM) type, such as tamoxifen, have two major limitations: their mixed agonist and antagonist profile and the development of tumor resistance. We characterized two new pure antiestrogens-ZK-703 and ZK-253-that belong to the class of specific estrogen receptor destabilizers (SERDs), which includes fulvestrant, and compared their activity with that of fulvestrant and tamoxifen. METHODS: Effects of antiestrogens on the growth of estrogen-dependent breast tumors in vivo were determined using several mouse xenograft models (including the tamoxifen-sensitive tumors MCF7, T47D, and MV3366 and the tamoxifen-resistant tumors ZR75-1 and MCF7/TAM) and chemically induced (nitrosomethyl urea [NMU] and dimethylbenzanthracene [DMBA]) rat breast cancer models (groups of 10 animals). We determined the initial response and effects on hormone receptor levels and the time to relapse after treatment (i.e., time to reach a predetermined tumor size threshold). Estrogen receptor (ER) levels were determined by immunoassay. RESULTS: ZK-703 (administered subcutaneously) and ZK-253 (administered orally) were more effective than tamoxifen or fulvestrant at inhibiting the growth of ER-positive breast cancer in all xenograft models. For example, MCF7 tumors relapsed (i.e., reached the size threshold) in 10 weeks in mice treated with tamoxifen but in 30 weeks in mice treated with ZK-703. ZK-703 and ZK-253 also prevented further tumor progression in tamoxifen-resistant breast cancer models to a similar extent (more than 30 weeks in mice with ZR75-1 and MCF7/TAM tumors). In the chemically induced rat breast cancer models, orally administered ZK-703 and ZK-253 caused a nearly complete (>80%) inhibition of tumor growth. ER levels were dramatically reduced in MCF7 tumors after 5 weeks of ZK-703 treatment compared with ER levels in vehicle-treated tumors; by contrast, ER levels in tamoxifen-treated tumors were higher than those in control tumors. CONCLUSION: ZK-703 and ZK-253 are potent, long-term inhibitors of growth in both tamoxifen-sensitive and tamoxifen-resistant breast cancer models.

Mindo/3 and mndo calculations of closed- and open-shell cations containing C, H, N, and O.

Heats of formation of 119 closed- and open-shell carbocations calculated by the semiempirical quantum chemical methods MINDO/3 and MNDO are reported and compared with experimental data. With proper consideration of failures in specific areas, both methods can be used for the thermodynamics of carbocations containing C, H, N, and O. MINDO/3 predicts unrealistic values for nitrogen containing cations with nitrogen multiple bonds and is not suited for closed-shell cations containing oxygen. Saturated acyclic hydrocarbon radical cations often are computed with abnormally long CC bonds by MNDO. Otherwise, the standard deviation of the two methods is not very different, being in the range of ±13 kcal/mol. MINDO/3 tends to overestimate the cation stabilities, whereas MNDO calculates cations usually too high in energy. Some of the errors which were found in the calculations of the ions are related to the computed values for the parent neutral structures, but others are not.