Litcius/Paper detail

Leveraging DFT and Molecular Fragmentation for Chemically Accurate p<i>K</i><sub>a</sub> Prediction Using Machine Learning

Alec J. Sanchez, Sarah Maier, Krishnan Raghavachari

2024Journal of Chemical Information and Modeling11 citationsDOI

Abstract

s of complex organic molecules using inexpensive density functional theory (DFT) calculations. By including physics-based features from low-level DFT calculations and structural features from our connectivity-based hierarchy (CBH) fragmentation protocol, we can correct the systematic error associated with DFT. The generalizability and performance of our model are evaluated on two benchmark sets (SAMPL6 and Novartis). We believe the carefully curated input of physics-based features lessens the model's data dependence and need for complex deep learning architectures, without compromising the accuracy of the test sets. As a point of novelty, our work extends the applicability of CBH, employing it for the generation of viable molecular descriptors for ML.

Topics & Concepts

Generalizability theoryDensity functional theoryComputer scienceRandom forestBenchmark (surveying)Quantum chemicalArtificial intelligenceNoveltyMachine learningMoleculeBiological systemAlgorithmComputational chemistryChemistryPhysicsMathematicsQuantum mechanicsStatisticsGeographyTheologyBiologyPhilosophyGeodesyComputational Drug Discovery MethodsMachine Learning in Materials ScienceFree Radicals and Antioxidants