A5026643759- Computational Drug Discovery Methods
- Bioinformatics and Genomic Networks
- Machine Learning in Materials Science
- Metabolomics and Mass Spectrometry Studies
- Cell Image Analysis Techniques
- Protein Structure and Dynamics
- Chemical Synthesis and Analysis
- Pharmacogenetics and Drug Metabolism
- Microbial Natural Products and Biosynthesis
- Receptor Mechanisms and Signaling
- Machine Learning in Bioinformatics
- Synthesis and biological activity
- Analytical Chemistry and Chromatography
- Genetics, Bioinformatics, and Biomedical Research
- Gene expression and cancer classification
- Click Chemistry and Applications
- Viral Infectious Diseases and Gene Expression in Insects
- Molecular Biology Techniques and Applications
- Gene Regulatory Network Analysis
- vaccines and immunoinformatics approaches
- Drug Transport and Resistance Mechanisms
- Animal testing and alternatives
- Synthesis and Biological Evaluation
- HIV/AIDS drug development and treatment
- Phosphodiesterase function and regulation
Ludwig-Maximilians-Universität München
2023-2025
University of Cambridge
2015-2024
LMU Klinikum
2023-2024
Babeș-Bolyai University
2024
AstraZeneca (United Kingdom)
2020-2024
Broad Institute
2009-2024
Bridge University
2024
Munich Center for Machine Learning
2023
Nuvisan (Germany)
2021
Unilever (United Kingdom)
2005-2016
The Online Chemical Modeling Environment is a web-based platform that aims to automate and simplify the typical steps required for QSAR modeling. consists of two major subsystems: database experimental measurements modeling framework. A user-contributed contains set tools easy input, search modification thousands records. OCHEM based on wiki principle focuses primarily quality verifiability data. tightly integrated with framework, which supports all create predictive model: data search,...
While drug combination therapies are a well-established concept in cancer treatment, identifying novel synergistic combinations is challenging due to the size of combinatorial space. However, computational approaches have emerged as time- and cost-efficient way prioritize test, based on recently available large-scale screening data. Recently, Deep Learning has had an impact many research areas by achieving new state-of-the-art model performance. not yet been applied synergy prediction, which...
Preclinical Safety Pharmacology (PSP) attempts to anticipate adverse drug reactions (ADRs) during early phases of discovery by testing compounds in simple, vitro binding assays (that is, preclinical profiling). The selection PSP targets is based largely on circumstantial evidence their contribution known clinical ADRs, inferred from findings trials, animal experiments, and molecular studies going back more than forty years. In this work we explore chemical space its relevance for the...
Different molecular descriptors capture different aspects of structures, but this effect has not yet been quantified systematically on a large scale. In work, we calculate the similarity 37 by repeatedly selecting query compounds and ranking rest database. Euclidean distances between rank-ordering are calculated to determine descriptor (as opposed compound) similarity, followed PCA for visualization. Four broad classes identified, which circular fingerprints; fingerprints considering counts;...
Drug-induced cardiotoxicity (DICT) is a major concern in drug development, accounting for 10-14% of postmarket withdrawals. In this study, we explored the capabilities chemical and biological data to predict cardiotoxicity, using recently released DICTrank set from United States FDA. We found that such data, including protein targets, especially those related ion channels (e.g., hERG), physicochemical properties electrotopological state), peak concentration plasma offer strong predictive...
A molecular similarity searching technique based on atom environments, information-gain-based feature selection, and the naive Bayesian classifier has been applied to a series of diverse datasets its performance compared those alternative methods. Atom environments are count vectors heavy atoms present at topological distance from each structure. In this application, using recently published dataset more than 100000 molecules MDL Drug Data Report database, environment approach appears...
A novel technique for similarity searching is introduced. Molecules are represented by atom environments, which fed into an information-gain-based feature selection. naïve Bayesian classifier then employed compound classification. The new method tested its ability to retrieve five sets of active molecules seeded in the MDL Drug Data Report (MDDR). In comparison experiments, algorithm outperforms all current retrieval methods assessed here using two- and three-dimensional descriptors offers...
Bridging chemical and biological space is the key to drug discovery development. Typically, cheminformatics methods operate under assumption that similar chemicals have activity. Ideally then, one could predict a drug's function(s) given only its structure by similarity searching in libraries of compounds with known activities. In practice, effectively choosing metric case dependent. This work compares both 2D 3D descriptors as tools for predicting targets ligand probes, on basis their...
This study describes a method for mining and modeling binding data obtained from large panel of targets (in vitro safety pharmacology) to distinguish differences between promiscuous selective compounds. Two naïve Bayes models promiscuity selectivity were generated validated on test set as well publicly available drug databases. The model shows higher score (lower promiscuity) marketed drugs than compounds in early development or that failed during clinical development. Such can be used...
We have applied the k-nearest neighbor (kNN) modeling technique to prediction of melting points. A data set 4119 diverse organic molecules (data 1) and an additional 277 drugs 2) were used compare performance in different regions chemical space, we investigated influence number nearest neighbors using types molecular descriptors. To compute on basis temperatures neighbors, four methods (arithmetic geometric average, inverse distance weighting, exponential weighting), which weighting scheme...