Designing new molecules with a set of predefined properties is a core problem in modern drug discovery and development. There is a growing need for de-novo design methods that would address this problem. We present MolecularRNN, the graph recurrent generative model for molecular structures. Our model generates diverse realistic molecular graphs after likelihood pretraining on a big database of molecules. We perform an analysis of our pretrained models on large-scale generated datasets of 1 million samples. Further, the model is tuned with policy gradient algorithm, provided a critic that estimates the reward for the property of interest. We show a significant distribution shift to the desired range for lipophilicity, drug-likeness, and melting point outperforming state-of-the-art works. With the use of rejection sampling based on valency constraints, our model yields 100% validity. Moreover, we show that invalid molecules provide a rich signal to the model through the use of structure penalty in our reinforcement learning pipeline.Preprint. Under review.

An 8 × 7 × 2 (112 element) dual-polarized end-£re tapered-slot phased array has been designed, fabricated and tested. We demonstrate a step towards cost effectiveness without sacri£cing much of array performance. The measured mutual coupling coef£cients and the scan blindness predicted by numerical in£nite array analysis are presented. Since the antenna is entirely made out of solid aluminium, no plated-through vias are required to eliminate in-band impedance anomalies in contrast to printed bilateral Tapered Slot Antennas (TSAs). The array has been designed to operate from 0.5 to 1.5 GHz. Despite that the electrical size of the prototype array is only 5λ × 5λ (at 1.5 GHz), the location of the impedance anomalies are predicted well.

Deep learning models have demonstrated outstanding results in many data-rich areas of research, such as computer vision and natural language processing. Currently, there is a rise of deep learning in computational chemistry and materials informatics, where deep learning could be effectively applied in modeling the relationship between chemical structures and their properties. With the immense growth of chemical and materials data, deep learning models can begin to outperform conventional machine learning techniques such as random forest, support vector machines, nearest neighbor, etc. Herein, we introduce OpenChem, a PyTorch-based deep learning toolkit for computational chemistry and drug design. OpenChem offers easy and fast model development, modular software design, and several data preprocessing modules. It is freely available via the GitHub repository.

No abstract

No abstract