Biomedical subjects
Publications and source records attributed to Gisbert Schneider.
SOMMER is a publicly available, Java-based toolbox for training and visualizing two- and three-dimensional unsupervised self-organizing maps (SOMs). Various map topologies are implemented for planar rectangular, toroidal, cubic-surface and spherical projections. The software allows for visualization of the training process, which has been shown to be particularly valuable for teaching purposes.
BACKGROUND: Particle Swarm Optimization (PSO) is an established method for parameter optimization. It represents a population-based adaptive optimization technique that is influenced by several "strategy parameters". Choosing reasonable parameter values for the PSO is crucial for its convergence behavior, and depends on the optimization task. We present a method for parameter meta-optimization based on PSO and its application to neural network training. The concept of the Optimized Particle Swarm Optimization (OPSO) is to optimize the free parameters of the PSO by having swarms within a swarm. We assessed the performance of the OPSO method on a set of five artificial fitness functions and compared it to the performance of two popular PSO implementations. RESULTS: Our results indicate that PSO performance can be improved if meta-optimized parameter sets are applied. In addition, we could improve optimization speed and quality on the other PSO methods in the majority of our experiments. We applied the OPSO method to neural network training with the aim to build a quantitative model for predicting blood-brain barrier permeation of small organic molecules. On average, training time decreased by a factor of four and two in comparison to the other PSO methods, respectively. By applying the OPSO method, a prediction model showing good correlation with training-, test- and validation data was obtained. CONCLUSION: Optimizing the free parameters of the PSO method can result in performance gain. The OPSO approach yields parameter combinations improving overall optimization performance. Its conceptual simplicity makes implementing the method a straightforward task.
Explore the source record for details and available documents.
Explore the source record for details and available documents.
Explore the source record for details and available documents.
A virtual screening method is presented that is grounded on a receptor-derived pharmacophore model termed "virtual ligand" or "pseudo-ligand". The model represents an idealized constellation of potential ligand sites that interact with residues of the binding pocket. For rapid virtual screening of compound libraries the potential pharmacophore points of the virtual ligand are encoded as an alignment-free correlation vector, avoiding spatial alignment of pharmacophore features between the pharmacophore query (i.e., the virtual ligand) and the candidate molecule. The method was successfully applied to retrieving factor Xa inhibitors from a Ugi three-component combinatorial library, and yielded high enrichment of actives in a retrospective search for cyclooxygenase-2 (COX-2) inhibitors. The approach provides a concept for "de-orphanizing" potential drug targets and identifying ligands for hitherto unexplored or allosteric binding pockets.
Support vector machines (SVM) were trained to predict cyclooxygenase 2 (COX-2) and thrombin inhibitors. The classifiers were obtained using sets of known COX-2 and thrombin inhibitors as "positive examples" and a large collection of screening compounds as "negative examples". Molecules were encoded by topological pharmacophore-point triangles. In retrospective virtual screening, 50-90% of the known active compounds were listed within the first 0.1% of the ranked database. To check the validity of the constructed classifiers, we developed a method for feature extraction and visualization using SVM. As a result, potential pharmacophore points were weighted according to their importance for COX-2 and thrombin inhibition. Known thrombin and COX-2 pharmacophore points were correctly recognized by the machine learning system. In a prospective virtual screening study, several potential COX-2 inhibitors were predicted and tested in a cellular activity assay. A benzimidazole derivative exhibited significant inhibitory activity with an IC(50) of 0.2 microM, which is better than Celecoxib in our assay. It was demonstrated that the SVM machine-learning method can be used in virtual screening and be analyzed in a human-interpretable way that results in a set of rules for designing novel molecules.
5-Lipoxygenase (5-LO) is a tightly regulated enzyme in the synthesis of bioactive lipids from arachidonic acid. Here, we demonstrate that 5-LO is regulated by caspases, which are signaling molecules that control critical biological processes by means of specific limited proteolysis. Cell splitting of the Epstein-Barr virus-transformed B lymphocytic cell line BL41-E95-A caused a pronounced, but transient, reduction of functional 5-LO protein, accompanied by the appearance of a 62-kDa 5-LO cleavage product. In parallel, splitting of BL41-E95-A cells induced activation of caspase-6 (casp-6) and casp-8. Caspase activation and 5-LO degradation were blocked by the protein-synthesis inhibitor cycloheximide, and cell-permeable peptide inhibitors of casp-6 and casp-8 prevented 5-LO cleavage. Activation of casp-6 and casp-8 was connected to subsequent enhancement of cell proliferation, whereas selective caspase inhibition blocked cell growth. Last, isolated human 5-LO was cleaved by recombinant casp-6 in vitro to a 58-kDa fragment. Based on site-directed mutagenesis studies, 5-LO is cleaved by casp-6 after Asp-170, which in a homology-based 3D model of 5-LO is located on the enzyme periphery. We suggest that splitting of BL41-E95-A cells induces de novo synthesis of a protein involved in the activation of casp-6, which cleaves 5-LO.
Explore the source record for details and available documents.
TAR RNA is a potential target for AIDS therapy. Ligand-based virtual screening was performed to retrieve novel scaffolds for RNA-binding molecules capable of inhibiting the Tat-TAR interaction, which is essential for HIV replication. We used a "fuzzy" pharmacophore approach (SQUID) and an alignment-free pharmacophore method (CATS3D) to carry out virtual screening of a vendor database of small molecules and to perform "scaffold-hopping". A small subset of 19 candidate molecules were experimentally tested for TAR RNA binding in a fluorescence resonance energy transfer (FRET) assay. Both methods retrieved molecules that exhibited activities comparable to those of the reference molecules acetylpromazine and chlorpromazine, with the best molecule showing ten times better binding behavior (IC50 = 46 microM). The hits had molecular scaffolds different from those of the reference molecules.
Explore the source record for details and available documents.
A classification of molecules depends on the descriptor set which is used to represent the compounds, and each descriptor could be regarded as one perception of a molecule. In this study we show that a combination of several classifiers that are grounded on separate descriptor sets can be superior to a single classifier that was built using all available descriptors. The task of predicting ligands of G-protein coupled receptors (GPCR) served as an example application. The perceptron, multilayer neural networks, and radial basis function (RBF) networks were employed for prediction. We developed classifiers with and without descriptor selection. Prediction accuracy was assessed by the area under the receiver operating characteristic (ROC) curve. In the case with descriptor selection both the selection and the rank order of the descriptors depended on the type and topology of the neural networks. We demonstrate that the overall prediction accuracy of the system can be improved by joining neural network classifiers of different type and topology using a "jury network" that is trained to evaluate the predictions from the individual classifiers. Seventy-one percent correct prediction of GPCR ligands was obtained.
Ever since the first automated de novo design techniques were conceived only 15 years ago, the computer-based design of hit and lead structure candidates has emerged as a complementary approach to high-throughput screening. Although many challenges remain, de novo design supports drug discovery projects by generating novel pharmaceutically active agents with desired properties in a cost- and time-efficient manner. In this review, we outline the various design concepts and highlight current developments in computer-based de novo design.
A pharmacophore-based approach for compiling focused screening libraries is presented. It integrates information from three-dimensional molecular alignments into correlation vector-based database screening. The pharmacophore model is represented by a number of spheres of Gaussian-distributed feature densities. Different degrees of "fuzziness" can be introduced to influence the model's resolution. Transformation of this pharmacophore representation into a correlation vector results in a vector of feature probabilities which can be utilized for rapid virtual screening of compound databases or virtual libraries. The approach was validated by retrospective screening for cyclooxygenase 2 (COX-2) and thrombin ligands. A variety of models with different degrees of fuzziness were calculated and tested for both classes of molecules. Best performance was obtained with pharmacophore models reflecting an intermediate degree of fuzziness, yielding an enrichment factor of up to 39 for the first 1% of the ranked database. Appropriately weighted fuzzy pharmacophore models performed better in retrospective screening than similarity searching using only a single query molecule. The new pharmacophore method was shown to complement existing approaches.
The influence of preprocessing of molecular descriptor vectors for solving classification tasks was analyzed for drug/nondrug classification by artificial neural networks. Molecular properties were used to form descriptor vectors. Two types of neural networks were used, supervised multilayer neural nets trained with the back-propagation algorithm, and unsupervised self-organizing maps (Kohonen maps). Data were preprocessed by logistic scaling and histogram equalization. For both types of neural networks, the preprocessing step significantly improved classification compared to nonstandardized data. Classification accuracy was measured as prediction mean square error and Matthews correlation coefficient in the case of supervised learning, and quantization error in the case of unsupervised learning. The results demonstrate that appropriate data preprocessing is an essential step in solving classification tasks.
Explore the source record for details and available documents.
Enlarged sets of reference data and special machine learning approaches have improved the accuracy of the prediction of protein subcellular localization. Recent approaches report over 95% correct predictions with low fractions of false-positives for secretory proteins. A clear trend is to develop specifically tailored organism- and organelle-specific prediction tools rather than using one general method. Focus of the review is on machine learning systems, highlighting four concepts: the artificial neural feed-forward network, the self-organizing map (SOM), the Hidden-Markov-Model (HMM), and the support vector machine (SVM).
Besides the choice of an automated software method for selecting 'maximally diverse' compounds from a large pool of molecules, it is the implementation of the algorithm that critically determines the usefulness of the approach. The speed of execution of two implementations of the Maxmin algorithm is compared for the selection of maximally diverse subsets of large compound collections. Different versions of the software are compared using various C compiler options and Java virtual machines. The analysis shows that the Maxmin algorithm can be implemented in both languages yielding sufficient speed of execution. For large compound libraries the Java version outperformes the C version. While the Java version selects the same compounds independent of the virtual machine used, the C version produces slightly different subsets depending on the compiler and on the optimization settings.