Towards Exploring Large Molecular Space: An Efficient Chemical Genetic Algorithm

Generating molecules with desired properties is an important task in chemistry and pharmacy. An efficient method may have a positive impact on finding drugs to treat diseases like COVID-19. Data mining and artificial intelligence may be good ways to find an efficient method. Recently, both the generative models based on deep learning and the work based on genetic algorithms have made some progress in generating molecules and optimizing the molecule's properties. However, existing methods need to be improved in efficiency and performance. To solve these problems, we propose a method named the Chemical Genetic Algorithm for Large Molecular Space (CALM). Specifically, CALM employs a scalable and efficient molecular representation called molecular matrix. Then, we design corresponding crossover, mutation, and mask operators inspired by domain knowledge and previous studies. We apply our genetic algorithm to several tasks related to molecular property optimization and constraint molecular optimization. The results of these tasks show that our approach outperforms the other state-of-the-art deep learning and genetic algorithm methods, where the z tests performed on the results of several experiments show that our method is more than 99% likely to be significant. At the same time, based on the experimental results, we point out the insufficiency in the experimental evaluation standard which affects the fair evaluation of previous work. Supplementary Information The online version contains supplementary material available at 10.1007/s11390-021-0970-3.

Named Entity Recognition of Traditional Chinese Medicine Patents Based on BiLSTM-CRF

With the growing popularity of traditional Chinese medicine (TCM) in the world and the increasing awareness of intellectual property protection, the number of TCM patent application is growing year by year. TCM patents contain rich medical, legal, and economic information. Effective text mining of TCM patents is of great theoretical and practical significance (e.g., the R&D of new medicines, patent infringement litigation, and patent acquisition). Named entity recognition (NER) is a fundamental task in natural language processing and a crucial step before indepth analysis of TCM patent. In this paper, a method combining Bidirectional Long Short-Term Memory neural network with Conditional Random Field (BiLSTM-CRF) is proposed to automatically recognize entities of interest (i.e., herb names, disease names, symptoms, and therapeutic effects) from the abstract texts of TCM patents. By virtue of the capabilities of deep learning methods, the semantic information in the context can be learned without feature engineering. Experiments show that the BiLSTM-CRF-based method provides superior performance in comparison with various baseline methods.

Enhancing the performance of paper-based electrochemical impedance spectroscopy nanobiosensors: An experimental approach.

Accurate, rapid, and low-cost molecular diagnostics is essential in managing outbreaks of infectious diseases, such as the pandemic of coronavirus disease 2019 (COVID-19). Accordingly, microfluidic paper-based analytical devices (µPADs) have emerged as promising diagnostic tools. Among the extensive efforts to improve the performance and usability of diagnostic tools, biosensing mechanisms based on electrochemical impedance spectroscopy (EIS) have shown great promise because of their label-free operation and high sensitivity. However, the method to improve EIS biosensing on µPADs is less explored. Here, we present an experimental approach to enhancing the performance of paper-based EIS biosensors featuring zinc oxide nanowires (ZnO NWs) directly grown on working electrodes (WEs). Through a comparison of different EIS settings and an examination of ZnO-NW effects on EIS measurements, we show that ZnO-NW-enhanced WEs function reliably with Faradaic processes utilizing iron-based electron mediators. We calibrate paper-based EIS biosensors with different morphologies of ZnO NWs and achieve a low limit of detection (0.4 pg ml-1) in detecting p24 antigen as a marker for human immunodeficiency virus (HIV). Through microscopic imaging and electrochemical characterization, we reveal that the morphological and the electrochemical surface areas of ZnO-NW-enhanced WEs indicate the sensitivities and sensing ranges of the EIS nanobiosensors. Finally, we report that the EIS nanobiosensors are capable of differentiating the concentrations (blank, 10 ng ml-1, 100 ng ml-1, and 1 µg ml-1) of IgG antibody (CR3022) to SARS-CoV-2 in human serum samples, demonstrating the efficacy of these devices for COVID-19 diagnosis. This work provides a methodology for the rational design of high-performance EIS µPADs and has the potential to facilitate diagnosis in pandemics.