Deep neural network affinity model for BACE inhibitors in D3R Grand Challenge 4

Drug Design Data Resource (D3R) Grand Challenge 4 (GC4) offered a unique opportunity for designing and testing novel methodology for accurate docking and affinity prediction of ligands in an open and blinded manner. We participated in the beta-secretase 1 (BACE) Subchallenge which is comprised of cross-docking and redocking of 20 macrocyclic ligands to BACE and predicting binding affinity for 154 macrocyclic ligands. For this challenge, we developed machine learning models trained specifically on BACE. We developed a deep neural network (DNN) model that used a combination of both structure and ligand-based features that outperformed simpler machine learning models. According to the results released by D3R, we achieved a Spearman's rank correlation coefficient of 0.43(7) for predicting the affinity of 154 ligands. We describe the formulation of our machine learning strategy in detail. We compared the performance of DNN with linear regression, random forest, and support vector machines using ligand-based, structure-based, and combining both ligand and structure-based features. We compared different structures for our DNN and found that performance was highly dependent on fine optimization of the L2 regularization hyperparameter, alpha. We also developed a novel metric of ligand three-dimensional similarity inspired by crystallographic difference density maps to match ligands without crystal structures to similar ligands with known crystal structures. This report demonstrates that detailed parameterization, careful data training and implementation, and extensive feature analysis are necessary to obtain strong performance with more complex machine learning methods. Post hoc analysis shows that scoring functions based only on ligand features are competitive with those also using structural features. Our DNN approach tied for fifth in predicting BACE-ligand binding affinities.

     

Electrochemical characterization and determination of N-acetylpenicillamine thionitrite

Square-wave voltammetry and cyclic voltammetry are used to investigate the electrochemistry of N-acetylpenicillamine thionitrate. Thionitrites have been proposed as intracellular intermediates in organic nitrate-induced mammalian vasodilatation. Although these intermediates have been demonstrated indirectly, no sensitive direct determinations have been developed. The electrochemical behavior of this thionitrite at mercury and vitreous carbon electrodes in buffered aqueous media is here described. At mercury, below pH 6.0 one reversible anodic wave and one irreversible cathodic wave are seen. On solid electrodes, only the irreversible wave is present. A determination for thionitrite based on the irreversible cathodic wave is presented. When square-wave voltammetry is used, the current response is linear with concentration in the range of 1–200 μg l^?1 (40 μM?1.5 mM). N-Acetylpenicillamine does not interfere.     

Cyclometalated Platinum(II) Complexes with Donor-Acceptor-Containing Bidentate Ligands and Their Application Studies as Organic Resistive Memories

A series of heteroleptic cyclometalated platinum(II) complexes, [Pt(C^N)(O^O)], ( 1 – 10 ) with various donors and acceptors has been synthesized and characterized by ¹H NMR spectroscopy, elemental analyses, infrared spectroscopy and mass spectrometry. The X-ray structure of 2 has also been determined. The electrochemical and photophysical properties of the platinum(II) complexes were studied. These experimental results have been supported by computational studies. Furthermore, two of the complexes have been employed as the active material in the fabrication of resistive memory devices, exhibiting stable binary memory performance with low operating voltage, high ON/OFF ratio and long retention time.