5 papers · ranked by Valyu relevance
Linde Schoenmaker, Olivier Béquignon, Willem Jespers, Gerard van Westen
Generative deep learning models have emerged as a powerful approach for de novo drug design, as they aid researchers in finding new molecules with desired properties. Despite continuous improvements in the field, a subset of the outputs that sequence-based de novo generators produce cannot be progressed due to errors.…
Omer Markovitch, Juntian Wu, Otto Sijbren
Copying information is vital for life's propagation. Current life forms maintain a low error rate in replication using complex machinery to prevent and correct errors. However, primitive life had to deal with higher error rates, limiting its ability to evolve. Discovering mechanisms to reduce errors would alleviate…
Authors not listed
Bayesian optimization (BO) has become increasingly important for experimental optimization across scientific domains, yet implementing BO pipelines requires significant programming expertise and familiarity with specialized frameworks. This creates a barrier for domain experts who could benefit from BO but lack the…
Niraj Pangeni, Chandra Shahi, John P. Perdew, Vishal Subramanian + 3 more
Unusually large energy errors of semi-local density functional approximations (DFAs) for molecules are often strongly reduced by using the Hartree–Fock (HF) electron density instead of the selfconsistent DFA density. For reaction barriers and water clusters, some of us earlier found that HF-DFT succeeds not because the…
Authors not listed
Development of meta-generalized gradient approximations (meta-GGAs) has generally led to more accurate density-functional approximations, albeit ones that have more stringent requirements for the quadrature grids that are used to evaluate the exchange-correlation energy. Here, we demonstrate that grid-induced errors…