Sie sind hier:UHH > MIN-Fakultät > ZBH > Forschung > Angewandte Chemieinformatik und molekulares Design > News: Angewandte Chemieinformatik und molekulares Design > Hit Dexter: A Machine-Learning Model for the Prediction of Frequent Hitters

Hit Dexter: A Machine-Learning Model for the Prediction of Frequent Hitters

2. Februar 2018

False-positive assay signals triggered by badly behaving compounds continue to pose a major challenge to experimental screening. A free web service developed by scientists of the Kirchmair lab, called Hit Dexter, is able to identify such compounds with high accuracy, enabling chemists to make better-informed decisions on their hit compounds.

The method has been published as a Very Important Paper in ChemMedChem. The free web service is accessible here.

Weitere Meldungen

27.03.2018|New Paper

How Diverse Are the Protein-Bound Conformations of Small-Molecule Drugs and Cofactors?

Nils-Ole Friedrich, Méliné Simsir and Johannes Kirchmair from the Junior Research Group for Applied Cheminformatics and Molecular Design have conducted a comprehensive study of protein-bound conformations of drugs and drug-like molecules.

Using an elaborate cheminformatics pipeline, which also...

24.10.2017|New Paper

Benchmarking Commercial Conformer Ensemble Generators

Three-dimensional approaches in computer-aided molecular design such as ligand docking, pharmacophore modeling and 3D QSAR rely on the accurate representation of the protein- bound conformations of small molecules. A common approach to covering the conformational space is to compute ensembles of...

Metanavigation

Suche

Inhalt

Hit Dexter: A Machine-Learning Model for the Prediction of Frequent Hitters

Weitere Meldungen