Generative Models for Molecular Design

Livestream sales prediction based on an interpretable deep-learning model

Although live streaming is indispensable, live-streaming e-business requires accurate and timely sales-volume prediction to ensure a healthy supply-demand balance for companies. Practically, because various factors can significantly impact sales results, the development of a powerful, interpretable model is crucial for accurate sales prediction. In this study, we propose SaleNet, a deep-learning model designed for sales-volume prediction. Our model achieved correct prediction results on our private, real operating data. The mean absolute percentage error (MAPE) of our model's performance fell as low as 11.47% for a + 1.5-days forecast. Even for a 1-week forecast (+ 6 days), the MAPE was only 19.79%, meeting actual business needs and practical requirements. Notably, our model demonstrated robust interpretability, as evidenced by the feature contribution results which are consistent with prevailing research findings and industry expertise. Our findings provided a theoretical foundation for predicting shopping behavior in live-broadcast e-commerce and offered valuable insights for designing live-broadcast content and optimizing the user experience.

A compact review of progress and prospects of deep learning in drug discovery

BACKGROUND

Drug discovery processes, such as new drug development, drug synergy, and drug repurposing, consume significant yearly resources. Computer-aided drug discovery can effectively improve the efficiency of drug discovery. Traditional computer methods such as virtual screening and molecular docking have achieved many gratifying results in drug development. However, with the rapid growth of computer science, data structures have changed considerably; with more extensive and dimensional data and more significant amounts of data, traditional computer methods can no longer be applied well. Deep learning methods are based on deep neural network structures that can handle high-dimensional data very well, so they are used in current drug development.

RESULTS

This review summarized the applications of deep learning methods in drug discovery, such as drug target discovery, drug de novo design, drug recommendation, drug synergy, and drug response prediction. While applying deep learning methods to drug discovery suffers from a lack of data, transfer learning is an excellent solution to this problem. Furthermore, deep learning methods can extract deeper features and have higher predictive power than other machine learning methods. Deep learning methods have great potential in drug discovery and are expected to facilitate drug discovery development.

Computational medicinal chemistry role in clinical pharmacy education: Ingavirin for coronavirus disease 2019 (COVID-19) discovery model

Objective

Given the major shift to patient-directed education, novel coronavirus (nCoV) provides a live example on how medicinal chemistry could be a key science to teach pharmacy students. In this paper, students and clinical pharmacy practitioners will find a stepwise primer on identifying new potential nCoV treatments mechanistically modulated through angiotensin-converting enzyme 2 (ACE2).

Methods

First, we identified the maximum common pharmacophore between carnosine and melatonin as background ACE2 inhibitors. Second, we performed a similarity search to spot out structures containing the pharmacophore. Third, molinspiration bioactivity scoring enabled us to promote one of the newly identified molecules as the best next candidate for nCoV. Preliminary docking in SwissDock and visualization through University of California San Francisco (UCSF) chimera made it possible to qualify one of them for further detailed docking and experimental validation.

Results

Ingavirin had the best docking results with full fitness of -3347.15 kcal/mol and estimated ΔG of -8.53 kcal/mol compared with melatonin (-6.57 kcal/mol) and carnosine (-6.29 kcal/mol). UCSF chimera showed viral spike protein elements binding to ACE2 retained in the best ingavirin pose in SwissDock at 1.75 Angstroms.

Conclusion

Ingavirin has a promising inhibitory potential to host (ACE2 and nCoV spike protein) recognition, and hence could offer the next best mitigating effect against the current coronavirus disease (COVID-19) pandemic.

Advances and Challenges in De Novo Drug Design Using Three-Dimensional Deep Generative Models

A persistent goal for de novo drug design is to generate novel chemical compounds with desirable properties in a labor-, time-, and cost-efficient manner. Deep generative models provide alternative routes to this goal. Numerous model architectures and optimization strategies have been explored in recent years, most of which have been developed to generate two-dimensional molecular structures. Some generative models aiming at three-dimensional (3D) molecule generation have also been proposed, gaining attention for their unique advantages and potential to directly design drug-like molecules in a target-conditioning manner. This review highlights current developments in 3D molecular generative models combined with deep learning and discusses future directions for de novo drug design.

Effective Reaction-Based De Novo Strategy for Kinase Targets: A Case Study on MERTK Inhibitors

Reaction-based de novo design is the computational generation of novel molecular structures by linking building blocks using reaction vectors derived from chemistry knowledge. In this work, we first adopted a recurrent neural network (RNN) model to generate three groups of building blocks with different functional groups and then constructed an in silico target-focused combinatorial library based on chemical reaction rules. Mer tyrosine kinase (MERTK) was used as a study case. Combined with a scaffold enrichment analysis, 15 novel MERTK inhibitors covering four scaffolds were achieved. Among them, compound 5a obtained an IC₅₀ value of 53.4 nM against MERTK without any further optimization. The efficiency of hit identification could be significantly improved by shrinking the compound library with the fragment iterative optimization strategy and enriching the dominant scaffold in the hinge region. We hope that this strategy can provide new insights for accelerating the drug discovery process.

Data-Driven Methods for Accelerating Polymer Design

Optimal design of polymers is a challenging task due to their enormous chemical and configurational space. Recent advances in computations, machine learning, and increasing trends in data and software availability can potentially address this problem and accelerate the molecular-scale design of polymers. Here, the central problem of polymer design is reviewed, and the general ideas of data-driven methods and their working principles in the context of polymer design are discussed. This Review provides a historical perspective and a summary of current trends and outlines future scopes of data-driven methods for polymer research. A few representative case studies on the use of such data-driven methods for discovering new polymers with exceptional properties are presented. Moreover, attempts are made to highlight how data-driven strategies aid in establishing new correlations and advancing the fundamental understanding of polymers. This Review posits that the combination of machine learning, rapid computational characterization of polymers, and availability of large open-sourced homogeneous data will transform polymer research and development over the coming decades. It is hoped that this Review will serve as a useful reference to researchers who wish to develop and deploy data-driven methods for polymer research and education.

Molecular Conditional Generation and Property Analysis of Non-Fullerene Acceptors with Deep Learning

The proposition of non-fullerene acceptors (NFAs) in organic solar cells has made great progress in the raise of power conversion efficiency, and it also broadens the ways for searching and designing new acceptor molecules. In this work, the design of novel NFAs with required properties is performed with the conditional generative model constructed from a convolutional neural network (CNN). The temporal CNN is firstly trained to be a good string-based molecular conditional generative model to directly generate the desired molecules. The reliability of generated molecular properties is then demonstrated by a graph-based prediction model and evaluated with quantum chemical calculations. Specifically, the global attention mechanism is incorporated in the prediction model to pool the extracted information of molecular structures and provide interpretability. By combining the generative and prediction models, thousands of NFAs with required frontier molecular orbital energies are generated. The generated new molecules essentially explore the chemical space and enrich the database of transformation rules for molecular design. The conditional generation model can also be trained to generate the molecules from molecular fragments, and the contribution of molecular fragments to the properties is subsequently predicted by the prediction model.