TBMaLT, a flexible toolkit for combining tight-binding and machine learning.

Tight-binding approaches, especially the Density Functional Tight-Binding (DFTB) and the extended tight-binding schemes, allow for efficient quantum mechanical simulations of large systems and long-time scales. They are derived from ab initio density functional theory using pragmatic approximations and some empirical terms, ensuring a fine balance between speed and accuracy. Their accuracy can be improved by tuning the empirical parameters using machine learning techniques, especially when information about the local environment of the atoms is incorporated. As the significant quantum mechanical contributions are still provided by the tight-binding models, and only short-ranged corrections are fitted, the learning procedure is typically shorter and more transferable as it were with predicting the quantum mechanical properties directly with machine learning without an underlying physically motivated model. As a further advantage, derived quantum mechanical quantities can be calculated based on the tight-binding model without the need for additional learning. We have developed the open-source framework-Tight-Binding Machine Learning Toolkit-which allows the easy implementation of such combined approaches. The toolkit currently contains layers for the DFTB method and an interface to the GFN1-xTB Hamiltonian, but due to its modular structure and its well-defined interfaces, additional atom-based schemes can be implemented easily. We are discussing the general structure of the framework, some essential implementation details, and several proof-of-concept applications demonstrating the perspectives of the combined methods and the functionality of the toolkit.

A deep neural network for molecular wave functions in quasi-atomic minimal basis representation.

The emergence of machine learning methods in quantum chemistry provides new methods to revisit an old problem: Can the predictive accuracy of electronic structure calculations be decoupled from their numerical bottlenecks? Previous attempts to answer this question have, among other methods, given rise to semi-empirical quantum chemistry in minimal basis representation. We present an adaptation of the recently proposed SchNet for Orbitals (SchNOrb) deep convolutional neural network model [K. T. Schütt et al., Nat. Commun. 10, 5024 (2019)] for electronic wave functions in an optimized quasi-atomic minimal basis representation. For five organic molecules ranging from 5 to 13 heavy atoms, the model accurately predicts molecular orbital energies and wave functions and provides access to derived properties for chemical bonding analysis. Particularly for larger molecules, the model outperforms the original atomic-orbital-based SchNOrb method in terms of accuracy and scaling. We conclude by discussing the future potential of this approach in quantum chemical workflows.

Challenging anaesthetic management of captive reindeer (Rangifer tarandus): Report of 4 cases.

INTRODUCTION: Four captive reindeer underwent anaesthesia to allow dehorning or drainage of lymph nodes abscessation. Premedication was based on xylazine (dose range: 0.075- 0.5 mg/kg, IM or IV), with or without ketamine (dose range: 1-2 mg/kg, IM or IV), all of which failed to produce effective sedation without side effects. During anaesthesia, 2 reindeer experienced severe hypoxaemia and hypoventilation. Recovery was smooth in 3 out 4 animals, but delayed in one reindeer sedated with 0.5 mg/kg of xylazine IV; this patient required repeated atipamezole administrations (0.01 mg/kg IM given 3 times) to regain normal locomotion. Anaesthesia of reindeer is challenging and useful dose ranges for safe and effective anaesthesia are mostly unknown.

INTRODUCTION: Quatre rennes détenus en captivité ont été anesthésiés pour procéder à un écornage et pour le drainage d'un ganglion lymphatique abcédé. Une prémédication à base de xylazine (dosage allant de 0.075 à 0.5 mg/kg, IM ou IV), seule ou en combinaison avec de la kétamine (dosage de 1 à 2 mg/kg, IM ou IV), n'a pas conduit, dans différents dosages et voies d'application, à une sédation satisfaisante et indemne d'effets secondaires. L'induction de la narcose avec de la kétamine par voie intraveineuse suivie d'une intubation endotrachéale s'est faite sans problème. Durant la narcose, deux animaux ont montré une grave hypoxémie et une hypoventilation. Trois des quatre rennes ont présenté une phase de réveil satisfaisante et calme. Chez le quatrième animal, qui avait été prémédiqué avec de la xylazine par voie intraveineuse (0.5 mg/kg), la phase de réveil a été prolongé et une application répétée d'atipamezol (trois fois 0.01mg/kg IM) a été nécessaire jusqu'à ce qu'il puisse de nouveau marcher normalement. La narcose des rennes représente un défi particulier car le dosage sûr et efficace des anesthésiques et trop peu connu.