Blackburn Bjerrum (canadacoat9)

Predicting accurate protein-ligand binding affinities is an important task in drug discovery but remains a challenge even with computationally expensive biophysics-based energy scoring methods and state-of-the-art deep learning approaches. Despite the recent advances in the application of deep convolutional and graph neural network-based approaches, it remains unclear what the relative advantages of each approach are and how they compare with physics-based methodologies that have found more mainstream success in virtual screening pipelines. We present fusion models that combine features and inference from complementary representations to improve binding affinity prediction. This, to our knowledge, is the first comprehensive study that uses a common series of evaluations to directly compare the performance of three-dimensional (3D)-convolutional neural networks (3D-CNNs), spatial graph neural networks (SG-CNNs), and their fusion. We use temporal and structure-based splits to assess performance on novel protein targets. To test the practical applicability of our models, we examine their performance in cases that assume that the crystal structure is not available. In these cases, binding free energies are predicted using docking pose coordinates as the inputs to each model. In addition, we compare these deep learning approaches to predictions based on docking scores and molecular mechanic/generalized Born surface area (MM/GBSA) calculations. Our results show that the fusion models make more accurate predictions than their constituent neural network models as well as docking scoring and MM/GBSA rescoring, with the benefit of greater computational efficiency than the MM/GBSA method. Finally, we provide the code to reproduce our results and the parameter files of the trained models used in this work. The software is available as open source at https//github.com/llnl/fast. Model parameter files are available at ftp//gdo-bioinformatics.ucllnl.org/fast/pdbbind2016_model_checkpoints/.Sodium niobate (NaNbO3) attracts attention for its great potential in a variety of applications, for instance, due to its unique optical properties. Still, optimization of its synthetic procedures is hard due to the lack of understanding of the formation mechanism under hydrothermal conditions. Through in situ X-ray diffraction, hydrothermal synthesis of NaNbO3 was observed in real time, enabling the investigation of the reaction kinetics and mechanisms with respect to temperature and NaOH concentration and the resulting effect on the product crystallite size and structure. Several intermediate phases were observed, and the relationship between them, depending on temperature, time, and NaOH concentration, was established. The reaction mechanism involved a gradual change of the local structure of the solid Nb2O5 precursor upon suspending it in NaOH solutions. Heating gave a full transformation of the precursor to HNa7Nb6O19·15H2O, which destabilized before new polyoxoniobates appeared, whose structure depended on the NaOH concentration. Following these polyoxoniobates, Na2Nb2O6·H2O formed, which dehydrated at temperatures ≥285 °C, before converting to the final phase, NaNbO3. The total reaction rate increased with decreasing NaOH concentration and increasing temperature. Two distinctly different growth regimes for NaNbO3 were observed, depending on the observed phase evolution, for temperatures below and above ≈285 °C. Below this temperature, the growth of NaNbO3 was independent of the reaction temperature and the NaOH concentration, while for temperatures ≥285 °C, the temperature-dependent crystallite size showed the characteristics of a typical dissolution-precipitation mechanism.Lysophospholipids are bioactive signaling molecules derived from cell membrane glycerophospholipids or sphingolipids and are highly regulated under normal physiological conditions. Lysophosphatidic acids (LPAs) are a class of lysophospholipids that act on G-protein-coupled recep