DeepAC – conditional transformer-based chemical language model for the prediction of activity cliffs formed by bioactive compounds
Hengwei Chen, Martin Vogt, Jürgen Bajorath
Abstract
Activity cliffs (ACs) are formed by pairs of structurally similar or analogous active small molecules with large differences in potency.
Topics & Concepts
TransformerComputer scienceNatural language processingArtificial intelligenceChemistryEngineeringElectrical engineeringVoltageComputational Drug Discovery MethodsMachine Learning in Materials ScienceBioinformatics and Genomic Networks