Explore the vast range of titles available.

Generative models are becoming a tool of choice for exploring the molecular space. These models learn on a large training dataset and produce novel molecular structures with similar properties. Generated structures can be utilized for virtual screening or training semi-supervized predictive models in the downstream tasks. While there are plenty of generative models, it is unclear how to compare and rank them. In this work, we introduce a benchmarking platform called Molecular Sets (MOSES) to standardize training and comparison of molecular generative models. MOSES provides training and testing datasets, and a set of metrics to evaluate the quality and diversity of generated structures. We have implemented and compared several molecular generation models and suggest to use our results as reference points for further advancements in generative chemistry research. The platform and source code are available at https://github.com/molecularsets/moses .

Generative models are becoming a tool of choice for exploring the molecular space. These models learn on a large training dataset and produce novel molecular structures with similar properties. Generated structures can be utilized for virtual screening or training semi-supervised predictive models in the downstream tasks. While there are plenty of generative models, it is unclear how to compare and rank them. In this work, we introduce a benchmarking platform called Molecular Sets (MOSES) to standardize training and comparison of molecular generative models. MOSES provides a training and testing datasets, and a set of metrics to evaluate the quality and diversity of generated structures. We have implemented and compared several molecular generation models and suggest to use our results as reference points for further advancements in generative chemistry research. The platform and source code are available at https://github.com/molecularsets/moses.

Unique observation of a long-lasting meteor trail of about half an hour duration is described. The trail resulted from a burning meteor from the Leonid storm flux in the middle latitudes over eastern Siberia. We describe three-dimensional morphological characteristics of both the meteor and the long-lasting trail using data from wide-angle CCD cameras. Additionally, we present the meteor and the trail radiolocation characteristics obtained with a meteor radar and ionosonde. The background dynamics of the upper atmosphere at the height where the long-lasting trail developed were observed using data from the meteor radar and Fabry-Perot interferometer. The obtained results allowed the conclusion that the dynamics of a long-lasting trail are conditioned by the wind. However, during the first minutes of trail development, it is possible that a high-speed component is present, resulting from explosion of the meteor body in the atmosphere. A primitive spectral analysis of the long-lasting trail’s optical emissions and earlier studies point to hydroxyl molecules as a possible source of the glow. We believe the enhanced hydroxyl emission could be related to interaction of excited O(1D) oxygen atoms with meteor body water in the Earth’s upper atmosphere.