Accurate prediction of micro-pKa values is crucial for understanding and modulating the acidity and basicity of organic molecules, with applications in drug discovery, materials science, and environmental chemistry. This work introduces QupKake, a novel workflow that combines graph neural network (GNN) models with semiempirical quantum mechanical (QM) features to achieve exceptional accu- racy and generalization in micro-pKa prediction. QupKake outperforms state-of-the-art models on a variety of benchmark datasets, with root mean square errors (RMSEs) between 0.5-0.8 pKa units on five external test sets. Feature importance analysis reveals the crucial role of QM features in both the reaction site enumeration and micro-pKa prediction models. QupKake represents a significant advancement in micro-pKa prediction, offering a powerful tool for various applications in chemistry and beyond.
@article{Abarbanel_Hutchison_2023,
title = {QupKake: Integrating Machine Learning and Quantum Chemistry for micro-pKa Predictions},
doi = {10.26434/chemrxiv-2023-gxplb},
journal = {ChemRxiv},
author = {Abarbanel, Omri and Hutchison, Geoffrey},
year = {2023},
}Organic π-conjugated polymers with a triplet ground state have been the focus of recent research for their interesting and unique electronic properties, arising from the presence of the two unpaired electrons. These compounds are usually built from alternating electron-donating and electron-accepting monomer pairs which lower the HOMO–LUMO gap and yield a triplet state instead of the typical singlet ground state. In this paper, we use density functional theory calculations to explore the design rules that govern the creation of a ground-state triplet conjugated polymer and find that a small HOMO–LUMO gap in the singlet state is the best predictor for the existence of a triplet ground state, compared to previous use of a pro-quinoidal bonding character. This work can accelerate the discovery of new stable triplet materials by reducing the computational resources needed for electronic-state calculations and the number of potential candidates for synthesis.
@article{doi:10.1021/acs.jpclett.2c00509,
author = {Abarbanel, Omri D. and Rozon, Julisa and Hutchison, Geoffrey R.},
title = {Strategies for Computer-Aided Discovery of Novel Open-Shell Polymers},
journal = {The Journal of Physical Chemistry Letters},
volume = {13},
number = {9},
pages = {2158-2164},
year = {2022},
doi = {10.1021/acs.jpclett.2c00509},
note = {PMID: 35226497},
}Stable ground-state triplet π-conjugated copolymers have many interesting electronic and optoelectronic properties. However, the large number of potential monomer combinations makes it impractical to synthesize or even just use density functional theory (DFT) to calculate their triplet ground-state stability. Here, we present a genetic algorithm implementation that uses the semi-empirical GFN2- xTB to find ground-state triplet polymer candidates. We find over 1400 polymer candidates with a triplet ground-state stability of up to 4 eV versus the singlet. Additionally, we explore the properties of the monomers of those candidates in order to understand the design rules which promote the formation of a stable ground-state triplet in π-conjugated polymers.
@article{abarbanelUsingGeneticAlgorithms2022,
title = {Using Genetic Algorithms to Discover Novel Ground- State Triplet Conjugated Polymers},
author = {Abarbanel, Omri D and Hutchison and R, Geoffrey},
year = {2022},
month = jul,
doi = {10.26434/CHEMRXIV-2022-G5QFR},
}Understanding and predicting the charge transport properties of π-conjugated materials is an important challenge for designing new organic electronic devices, such as solar cells, plastic transistors, light-emitting devices, and chemical sensors. A key component of the hopping mechanism of charge transfer in these materials is the Marcus reorganization energy which serves as an activation barrier to hole or electron transfer. While modern density functional methods have proven to accurately predict trends in intramolecular reorganization energy, such calculations are computationally expensive. In this work, we outline active machine learning methods to predict computed intramolecular reorganization energies of a wide range of polythiophenes and their use toward screening new compounds with low internal reorganization energies. Our models have an overall root mean square error (RMSE) of ±0.113 eV, but a much smaller RMSE of only ±0.036 eV on the new screening set. Since the larger error derives from high-reorganization energy compounds, the new method is highly effective to screen for compounds with potentially efficient charge transport parameters.
@article{doi:10.1063/5.0059682,
author = {Abarbanel, Omri D. and Hutchison, Geoffrey R.},
title = {Machine learning to accelerate screening for Marcus reorganization energies},
journal = {The Journal of Chemical Physics},
volume = {155},
number = {5},
pages = {054106},
year = {2021},
doi = {10.1063/5.0059682},
}