A5018827857- Computational Drug Discovery Methods
- Pharmacogenetics and Drug Metabolism
- Metabolomics and Mass Spectrometry Studies
- Cell Image Analysis Techniques
- Analytical Chemistry and Chromatography
- Pharmacological Effects and Toxicity Studies
- Genetics, Bioinformatics, and Biomedical Research
- Machine Learning in Materials Science
- Drug Transport and Resistance Mechanisms
- Pesticide Exposure and Toxicity
- Carcinogens and Genotoxicity Assessment
- Spectroscopy Techniques in Biomedical and Chemical Research
- Cholinesterase and Neurodegenerative Diseases
- Various Chemistry Research Topics
- HIV/AIDS drug development and treatment
BASF (Germany)
2024
University of Vienna
2019-2020
Over the last few years more and organ idiosyncratic toxicities were linked to mitochondrial toxicity. Despite well-established assays, such as seahorse Glucose/Galactose assay, an in silico approach toxicity is still feasible, particularly when it comes assessment of large compound libraries. Therefore, approaches could be very beneficial indicate hazards early drug development pipeline. By combining multiple endpoints, we derived largest so far published dataset on A thorough data analysis...
Abstract Training neural networks with small and imbalanced datasets often leads to overfitting disregard of the minority class. For predictive toxicology, however, models a good balance between sensitivity specificity are needed. In this paper we introduce conformational oversampling as means oversample for prediction toxicity. Conformational enhances dataset by generation multiple conformations molecule. These can be used balance, well dataset, thereby increasing size without need...
The open-source package scikit-learn provides various machine learning algorithms and data processing tools, including the Pipeline class, which allows users to prepend custom transformation steps model. We introduce MolPipeline package, extends this concept chemoinformatics by wrapping default functionalities of RDKit, such as reading writing SMILES strings or calculating molecular descriptors from a molecule object. aimed build an easy-to-use Python create completely automated end-to-end...
The open-source package scikit-learn provides various machine learning algorithms and data processing tools, including the Pipeline class, which allows users to prepend custom transformation steps model. We introduce MolPipeline package, extends this concept cheminformatics by wrapping standard RDKit functionality, such as reading writing SMILES strings or calculating molecular descriptors from a molecule object. aimed build an easy-to-use Python create completely automated end-to-end...
The drugs we use to cure our diseases can cause damage the liver as it is primary organ responsible for metabolism of environmental chemicals and drugs. To identify eliminate potentially problematic drug candidates in early stages discovery, silico techniques provide quick practical solutions toxicity determination. Deep learning has emerged one recent years field pharmaceutical chemistry. Generally, case small data sets used toxicology, these data-hungry algorithms are prone overfitting. We...
Abstract The activity and potency of a drug is inherently affected by the metabolic state its target cell. Solute Carriers (SLCs) represent largest family transmembrane transporters in humans constitute major determinants cellular metabolism. Several SLCs have been shown to be required for uptake individual chemical compounds into systems, but systematic surveys transporter-drug relationships human cells are currently lacking. We performed series genetic screens haploid cell line HAP1 using...
In human health risk assessment of chemicals and pharmaceuticals, identification genotoxicity hazard usually starts with a standard battery in vitro tests, which is needed to cover all endpoints. The individual tests included the are not designed pick up This explains why resulting data can appear contradictory, thereby complicating accurate interpretation findings. Such could be improved through application mathematical modeling. One advantages modeling that strengths weaknesses each test...