HHHaoyang Hu

Haoyang Hu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Haoyang Hu has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Accelerated discovery of highly active enzyme nanohybrids with parallelized Bayesian optimization in hybrid space

    by Yu Liu, Haoyang Hu, Yueheng Han, Jia Song Deon Chon, Chin Lee Lo, Zhixuan Chen, Zheng Zhang, Zhihong Yuan, Jun Ge

    Artificial intelligence (AI) has significantly advanced protein engineering, enabling rapid enzyme evolution for diverse applications. However, the fragile nature of biomacromolecules requires enzyme immobilization to preserve catalytic activity under harsh industrial conditions, which often restricts substrate diffusion and reduces enzymatic activity. This challenge demands extensive trial-and-error experiments to optimize immobilized carriers with high activity for different enzymes. Here we show a machine-learning-guided workflow along with an algorithm named parallelized hybrid-space Bayesian optimization (PHBO) to accelerate the discovery of nanocarriers for specific enzymes and reactions. Leveraging prior knowledge, machine learning and iterative feedback, within limited number of experiments, this workflow explores the reaction space of over 10 7 experiments and achieves activity recovery of 100%, 90%, and 79% for glucose oxidase, catalase, and Candida Antarctica lipase B, respectively. These results demonstrate that data-efficient optimization can substantially accelerate the discovery of enzyme nanohybrids with high catalytic activity across diverse enzymatic systems.


  • Autonomous De Novo Lead Halide CsPbBr 3 Perovskite Quantum Dots Synthesis Platform With Transfer Learning Accelerated Bayesian Optimization

    by Haoyang Hu, Huiqing Wang, Xintong Huang, Yuhao Geng, Jianhong Xu, Zhihong Yuan

    Compared to traditional expert‐driven pattern, the emerging concept of self‐driving labs enabled by flow chemistry and artificial intelligence provides a new autonomous paradigm to significantly improve the R&D efficiency of functional material synthesis. In this work, focusing on on‐demand de novo synthesis of CsPbBr 3 quantum dots (QDs) by Ligand‐Assisted RePrecipitation (LARP) method, a micro TRansfer learning accelerated Bayesian Optimization driven reaction System (µTRBOS) is developed. Without any human supervision, µTRBOS can autonomously synthesize different types of high‐quality QDs, achieving user‐specified single‐peak fluorescent emission wavelengths between 455 and 505 nm with an error margin of less than 2 nm. These QDs exhibit particle sizes ranging from 2.5 to 7.4 nm. With knowledge transferred from existing experimental data, fewer than six experiments on average are required to optimize the synthetic conditions for each QD size. Additionally, the optimal synthetic conditions reveal the complex impact of temperature on LARP method.


  • CAPBO: A cost‐aware parallelized Bayesian optimization method for chemical reaction optimization

    by Runzhe Liang, Haoyang Hu, Yueheng Han, Bingzhen Chen, Zhihong Yuan

    Bayesian optimization employs probabilistic surrogate models to effectively address expensive and time‐consuming closed‐loop chemical experimental design. However, traditional Bayesian optimization focuses on reducing the number of iterations and follows an inherently sequential process (with one new data point sampled in each iteration), which is an inefficient means of exploiting and characterizing reactions using parallel microreactors. In this article, we present an approach that overcomes this issue by considering two essential factors: experimental cost sensitivity and parallelization. We propose a novel cost‐aware parallelized Bayesian optimization method (CAPBO) in which the goal is changed from reducing the number of iterations to reducing the experimental cost, with quantitative experimental speed‐up achieved through parallelization. The combination of these two items greatly fits the need of reaction optimization, leading to better optimization effects. Benchmarking and case studies demonstrate that the proposed method significantly outperforms traditional Bayesian optimization and considerably improves the optimization efficiency while maintaining the simplicity of the framework.


  • Synthesis of CsPbBr 3 in Micro Total Reaction System: Fast Operation Space Mapping and Subsecond Growth Process Monitoring

    by Yuhao Geng, Haoyang Hu, Yongqi Jia, Xintong Huang, Tian Yang, Runzhe Liang, Zhuo Chen, Zhihong Yuan, Jianhong Xu

    Lead halide perovskite nanocrystals (LHP NCs) have the characteristics of fast reaction kinetics and crystal instability due to the intrinsically highly ionic bonding between the respective ions, which bring challenges for revealing the growth kinetics and practical applications. Compared with conventional batch synthesis methods, the single‐function microreactor can achieve precise and stable control of the NCs synthesis process, but it still has the shortcoming of not being able to obtain information about the growth process. In this study, a micro Total Reaction System (μTRS) with remote control, online detection, and rapid data analysis functions is designed. μTRS can sample the photoluminescence information of CsPbBr 3 NCs growth in ligand‐assisted reprecipitation method. CsPbBr 3 NCs with an emission range of 435–492 nm are successfully detected, which breaks the record of the smallest size of CsPbBr 3 NCs synthesized directly from precursors. The real‐time feature of μTRS enables the construction of an automated close‐loop synthesis system. Besides, the rapid acquisition and timely processing of product information enable the rapid mapping of the operation space for CsPbBr 3 NCs preparation, which provides a reliable and learnable data set for designing a fully autonomous microreaction system capable of synthesizing NCs.


  • Open Access

    Efficacy and safety of inclisiran in stroke or cerebrovascular disease prevention: a systematic review and meta-analysis of randomized controlled trials

    by Min Luo, Yihan Liu, Xinyi Xu, Kai Liu, Chao Shen, Haoyang Hu, Zhiyao He, Fengbo Wu

    Aims: As the impact of inclisiran in stroke prevention in atherosclerotic cardiovascular disease (ASCVD) patients or those at high risk of ASCVD is still unclear, we conducted a systematic review and meta-analysis of randomized controlled trials (RCT) to quantify the effectiveness of inclisiran in stroke prevention in these patients.Methods: Literature research was conducted in four electronic databases (PubMed, EMBASE, Web of Science, CENTRAL) and two clinical trials registers (ClinicalTrials.gov, WHO ICTRP) from the inception of the study to 17 October 2022, and was updated by the end of the study on 5 January 2023. Two authors independently screened the studies, extracted the data, and assessed the bias. The risk of bias was assessed using the Cochrane risk-of-bias tool for randomized trials (RoB 2). The intervention effect was estimated by calculating risk ratio (RR), weighted mean difference (WMD), and 95% confidence interval (CI) with R 4.0.5. Sensitivity analysis by changing meta-analysis model was also performed to test the robustness of the pooled results. If this was not possible, a descriptive analysis was conducted.Results: Four RCTs (n = 3,713 patients) were rated as high-risk bias. Meta-analysis of three RCTs (ORION-9, ORION-10, and ORION-11) showed that inclisiran reduced myocardial infarction (MI) risk by 32% (RR = 0.68, 95%CI = 0.48–0.96) but did not reduce stroke (RR = 0.92, 95%CI = 0.54–1.58) and major cardiovascular events (MACE) (RR = 0.81, 95%CI = 0.65–1.02) risk. Sensitivity analysis results were stable. Safety was similar to the placebo group but had frequent injection-site reactions (RR = 6.56, 95%CI = 3.83–11.25), which were predominantly mild or moderate. A descriptive analysis of one RCT (ORION-5) was conducted due to different study designs, and suggested that inclisiran might be given semiannually from the beginning.Conclusion: Inclisiran is not beneficial for stroke or MACE prevention in ASCVD or patients at high risk of ASCVD but is associated with the reduction of MI. Given the limited number and quality of the available studies and the lack of a standardized definition for cardiovascular events, further studies are essential for confirming the results.


  • Open Access

    Microstructure engineering beyond SnSe1-xSx solid solution for high thermoelectric performance

    by Miaomiao Li, Hezhu Shao, Jingtao Xu, Qingsong Wu, Xiaojian Tan, Guoqiang Liu, Min Jin, Haoyang Hu, Huajie Huang, Jianfeng Zhang, et al.