Reaction classification and yield prediction using the differential reaction fingerprint DRFP
Daniel Probst, Philippe Schwaller, Jean‐Louis Reymond
Abstract
performs better than DFT-based fingerprints in reaction yield prediction and other structure-based fingerprints in reaction classification, reaching the performance of state-of-the-art learned fingerprints in both tasks while being data-independent.
Topics & Concepts
Fingerprint (computing)Yield (engineering)Differential (mechanical device)Artificial intelligencePattern recognition (psychology)Computer scienceMaterials scienceEngineeringMetallurgyAerospace engineeringComputational Drug Discovery MethodsMachine Learning in Materials ScienceChemical Synthesis and Analysis