A5039926688- Computational Drug Discovery Methods
- Microbial Natural Products and Biosynthesis
- Machine Learning in Materials Science
- Metabolomics and Mass Spectrometry Studies
- Analytical Chemistry and Chromatography
- Chemical Synthesis and Analysis
- Bioinformatics and Genomic Networks
- Protein Structure and Dynamics
- Synthesis and biological activity
- Click Chemistry and Applications
- Plant biochemistry and biosynthesis
- Monoclonal and Polyclonal Antibodies Research
- Genetics, Bioinformatics, and Biomedical Research
- Cholinesterase and Neurodegenerative Diseases
- Chemistry and Chemical Engineering
- Pharmacogenetics and Drug Metabolism
- Glycosylation and Glycoproteins Research
- Receptor Mechanisms and Signaling
- Immune Cell Function and Interaction
- Various Chemistry Research Topics
- T-cell and B-cell Immunology
- Peptidase Inhibition and Analysis
- Enzyme Structure and Function
- Melanoma and MAPK Pathways
- Protease and Inhibitor Mechanisms
Lamarr Institute for Machine Learning and Artificial Intelligence
2023-2025
University of Bonn
2016-2025
Fraunhofer Society
2023-2024
University of Bologna
2023-2024
Bonn Aachen International Center for Information Technology
2013-2023
Novartis (Switzerland)
2022
Novartis Institutes for BioMedical Research
2022
Purdue University West Lafayette
2022
Schiller International University
2010-2021
GTx (United States)
2017-2020
Current success in organ transplantation is dependent upon the use of calcineurin-inhibitor-based im-munosuppressive regimens. Unfortunately, current immunotherapy targets molecules with ubiquitous ex-pression resulting devastating non-immune side effects. T-cell costimulation has been identified as a new potential immunosuppressive target. The best characterized pathway includes CD28, its homologue CTLA4 and their ligands CD80 CD86. While an im-munoglobulin fusion protein construct...
Similarity is a subjective and multifaceted concept, regardless of whether compounds or any other objects are considered. Despite its intrinsically nature, attempts to quantify the similarity have long history in chemical informatics drug discovery. Many computational methods employ measures identify new for pharmaceutical research. However, chemoinformaticians medicinal chemists typically perceive different ways. numerical readouts calculations probably among most misunderstood approaches...
Abstract Difficulties in interpreting machine learning (ML) models and their predictions limit the practical applicability of confidence ML pharmaceutical research. There is a need for agnostic approaches aiding interpretation regardless complexity that also applicable to deep neural network (DNN) architectures model ensembles. To these ends, SHapley Additive exPlanations (SHAP) methodology has recently been introduced. The SHAP approach enables identification prioritization features...
Abstract A major challenge in computational chemistry is the generation of novel molecular structures with desirable pharmacological and physiochemical properties. In this work, we investigate potential use autoencoder, a deep learning methodology, for de novo design. Various generative autoencoders were used to map molecule into continuous latent space vice versa their performance as structure generator was assessed. Our results show that preserves chemical similarity principle thus can be...
ADVERTISEMENT RETURN TO ISSUEPREVPerspectiveNEXTExploring Activity Cliffs in Medicinal ChemistryMiniperspectiveDagmar Stumpfe and Jürgen Bajorath*View Author Information Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology Chemistry, Rheinische Friedrich-Wilhelms-Universität, Dahlmannstrasse 2, D-53113 Bonn, Germany*Phone: +49-228-2699-306. Fax: +49-228-2699-341. E-mail: [email protected]Cite this: J. Med. Chem. 2012, 55, 7, 2932–2942Publication Date...
In qualitative or quantitative studies of structure-activity relationships (SARs), machine learning (ML) models are trained to recognize structural patterns that differentiate between active and inactive compounds. Understanding model decisions is challenging but critical importance guide compound design. Moreover, the interpretation ML results provides an additional level validation based on expert knowledge. A number complex approaches, especially deep (DL) architectures, have distinctive...
Scaffold hopping refers to the computer-aided search for active compounds containing different core structures, which is a topic of high interest in medicinal chemistry. Herein foundations and caveats scaffold approaches are discussed recent methodological developments analyzed. Despite conceptual prevalence pharmacophore methods hopping, variety computational have been successfully applied. In years, calculations increasingly carried out at level scaffolds rather than compounds, queries...
Abstract The support vector machine (SVM) algorithm is one of the most widely used learning (ML) methods for predicting active compounds and molecular properties. In chemoinformatics drug discovery, SVM has been a state-of-the-art ML approach more than decade. A unique attribute that it operates in feature spaces increasing dimensionality. Hence, conceptually departs from paradigm low dimensionality applies to many other chemical space navigation. applicable compound classification, ranking,...
B7-H1 and B7-DC are ligands for PD-1, a receptor implicated in negative regulation of T B cell functions. These ligands, however, also costimulate responses. It remains elusive whether or not costimulation is mediated through PD-1. By comparative molecular modeling site-directed mutagenesis, we found that nonconserved residues between these on the A′GFCC′C′′ face mediate interaction with This indicates significant structural heterogeneity interactions PD-1 its ligands. Importantly, ligand...
T cell surface receptors CD28 and CTLA-4 are homologous members of the immunoglobulin superfamily (IgSF), each comprising a single V-like extracellular domain. bind to B7-1 B7-2 counter-receptors on antigen presenting cells (APCs), thereby triggering costimulatory pathway important for optimal activation in vitro vivo. Soluble forms which domains were fused Ig constant (CD28Ig CTLA4Ig), have been used study their interactions with B7-2, CTLA4Ig binding more strongly than CD28Ig...
T lymphocyte receptors CD28 and CTLA-4 bind costimulatory molecules CD80 (B7-1) CD86 (B7-2) on antigen-presenting cells regulate cell activation. While distinct functional roles have been ascribed to each of these molecules, little is known about how they interact. To better characterize interactions, we used surface plasmon resonance perform equilibrium kinetic binding analyses extracellular fragments CD28/CTLA-4/CD80/CD86. We show that are both characterized by rapid on-rates dissociation...