Li Guo
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
Research Interests
Li Guo has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoxia Li
State Key Laboratory of Multiphase Complex Systems, Institute of Process Engineering, Chinese Academy of Sciences, Beijing 100190, P. R. China
5 shared publications Leming Shi
State Key Laboratory of Genetic Engineering, Human Phenome Institute, School of Life Sciences, and Shanghai Cancer Center, Fudan University
3 shared publicationsYunjin Wang
Department of Breast Surgery, Precision Cancer Medicine Center, Key Laboratory of Breast Cancer in Shanghai, Fudan University Shanghai Cancer Center
3 shared publications- Chunxing Ren
State Key Laboratory of Multiphase Complex Systems, Institute of Process Engineering, Chinese Academy of Sciences, Beijing 100190, P. R. China
2 shared publications - Haolei Zhang2 shared publications
Jinghai Li
2 shared publications
Latest Publications
- Open Access
- 6 August 2026
- Published by Elsevier in Engineering
From Data-Driven to Physically Constrained Modeling: Artificial Intelligence Based on the Principle of Compromise in Competition
- 6 August 2026
- Published by Elsevier in Engineering
Open AccessFrom Data-Driven to Physically Constrained Modeling: Artificial Intelligence Based on the Principle of Compromise in Competition
- 8 June 2025
- Published by Elsevier in Chemical Engineering Science
- Vol. 316
Accelerating gas-solid flow simulations with a physics-informed transformer-based neural network
- 8 June 2025
- Published by Elsevier in Chemical Engineering Science
- Vol. 316
Accelerating gas-solid flow simulations with a physics-informed transformer-based neural network
- 14 September 2024
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 63 (38) , 16598-16608
A Neural Network Method for Characterizing Particle Clusters in Gas–Solid Fluidized Beds
- 14 September 2024
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 63 (38) , 16598-16608
A Neural Network Method for Characterizing Particle Clusters in Gas–Solid Fluidized Beds
- 1 May 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (5)
Coupling numerical simulation and artificial intelligence prediction: A computational fluid dynamics–discrete element method and deep learning approach to gas–solid flows
With the development of computing technology and numerical methods, a coupling discrete element method (DEM) with computational fluid dynamics (CFD) is becoming an effective simulation method for deeper understanding of large-scale gas–solid flow systems. Traditionally, the computational cost of the DEM part is usually much higher than the CFD part due to explicitly tracking much more solid particles than the CFD grids. However, with coarse-graining and high-performance computing, the CFD part is actually the wall-time bottleneck in many cases. To mitigate this problem, a deep-learning-based fluid-dynamics prediction method (FPM) is proposed to replace or accelerate the CFD. Accurate CFD–DEM simulation results provide the dataset for deep learning using the artificial neural network (ANN) and UNet architecture, with time-series of local, neighboring, and global information of the gas–solid flow to consider its critical spatiotemporal heterogeneity feature. The FPM can be incorporated into CFD–DEM (FPM–CFD–DEM) or simply replace the CFD (FPM–DEM). Simulations have demonstrated that FPM–DEM can be 10-fold faster than original CFD–DEM under similar accuracy, while FPM–CFD–DEM can only double the speed of CFD–DEM but predict reasonable gas–solid dynamics for much longer time. Future work may exploit remarkable potential of artificial intelligence techniques in developing efficient simulation methods of the gas–solid or other multiphase system.
- 1 May 2024
- Published by AIP Publishing in Physics of Fluids
- Vol. 37 (5)
Coupling numerical simulation and artificial intelligence prediction: A computational fluid dynamics–discrete element method and deep learning approach to gas–solid flows
With the development of computing technology and numerical methods, a coupling discrete element method (DEM) with computational fluid dynamics (CFD) is becoming an effective simulation method for deeper understanding of large-scale gas–solid flow systems. Traditionally, the computational cost of the DEM part is usually much higher than the CFD part due to explicitly tracking much more solid particles than the CFD grids. However, with coarse-graining and high-performance computing, the CFD part is actually the wall-time bottleneck in many cases. To mitigate this problem, a deep-learning-based fluid-dynamics prediction method (FPM) is proposed to replace or accelerate the CFD. Accurate CFD–DEM simulation results provide the dataset for deep learning using the artificial neural network (ANN) and UNet architecture, with time-series of local, neighboring, and global information of the gas–solid flow to consider its critical spatiotemporal heterogeneity feature. The FPM can be incorporated into CFD–DEM (FPM–CFD–DEM) or simply replace the CFD (FPM–DEM). Simulations have demonstrated that FPM–DEM can be 10-fold faster than original CFD–DEM under similar accuracy, while FPM–CFD–DEM can only double the speed of CFD–DEM but predict reasonable gas–solid dynamics for much longer time. Future work may exploit remarkable potential of artificial intelligence techniques in developing efficient simulation methods of the gas–solid or other multiphase system.
- 1 April 2024
- Published by Bentham Science Publishers Ltd. in Current Chinese Science
- Vol. 4 (2) , 135-144
Recent Patents for Optical Alignment
Background: The installation of optical devices is a necessary operation before their use. Therefore, the configuration of the optical system affects the performance of the whole optical system. However, in the process of optical system installation, there are still some technical breakthroughs to be made in order to better carry out optical system installation in the future. Objective: Through the introduction and discussion of the devices, methods and patent features of optical alignment testing in recent years, some valuable conclusions are summarized, and future research and development are prospected. Methods: The patents of optical system assembly were studied, and the patents and research progress of optical alignment were summarized. Results: With the development of optical technology, optical alignment has become more and more important, so optical alignment is needed to realize the design of optical systems. Conclusion: It is concluded that there is still a large space for the development of optical alignment, and the main development trend is towards high precision and large caliber.
- 1 April 2024
- Published by Bentham Science Publishers Ltd. in Current Chinese Science
- Vol. 4 (2) , 135-144
Recent Patents for Optical Alignment
Background: The installation of optical devices is a necessary operation before their use. Therefore, the configuration of the optical system affects the performance of the whole optical system. However, in the process of optical system installation, there are still some technical breakthroughs to be made in order to better carry out optical system installation in the future. Objective: Through the introduction and discussion of the devices, methods and patent features of optical alignment testing in recent years, some valuable conclusions are summarized, and future research and development are prospected. Methods: The patents of optical system assembly were studied, and the patents and research progress of optical alignment were summarized. Results: With the development of optical technology, optical alignment has become more and more important, so optical alignment is needed to realize the design of optical systems. Conclusion: It is concluded that there is still a large space for the development of optical alignment, and the main development trend is towards high precision and large caliber.
- 4 March 2024
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 63 (10) , 4631-4646
Machine Learning Assisted Characterization of Local Bubble Properties and Its Coupling with the EMMS Bubbling Drag
- 4 March 2024
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 63 (10) , 4631-4646
Machine Learning Assisted Characterization of Local Bubble Properties and Its Coupling with the EMMS Bubbling Drag
- Open Access
A comprehensive personal omics clinical interpreter based on genomic and transcriptomic profiles
Advances in precision medicine rely on the accurate identification and analysis of molecular alterations for personalized diagnostic, prognostic, and therapeutic decision-making. A critical obstacle is the integration of heterogeneous interpretations of clinically actionable alterations from various knowledgebases. Here, we present the Personal Omics Interpreter (POI), a web-based application engineered to aggregate and interpret therapeutic options, including targeted, immunological, and chemotherapeutic agents, by leveraging personal genomic and transcriptomic profiles. POI employs the Precision Medicine Knowledgebase (PreMedKB), an updated harmonized resource we previously reported, to annotate the clinically actionable somatic variants. It further incorporates a predictive algorithm to broaden therapeutic options according to established gene-gene interactions and offers insights into phenotypic responses of chemotherapeutic agents through phasing germline diplotypes. Validated against three cohort datasets encompassing over 22,000 cancer patients, POI demonstrates consistently high matching rates (94.7 ∼ 95.6%) between patients and suggested therapies, highlighting its potential in supporting precision-driven informed treatment strategies.
Open AccessA comprehensive personal omics clinical interpreter based on genomic and transcriptomic profiles
Advances in precision medicine rely on the accurate identification and analysis of molecular alterations for personalized diagnostic, prognostic, and therapeutic decision-making. A critical obstacle is the integration of heterogeneous interpretations of clinically actionable alterations from various knowledgebases. Here, we present the Personal Omics Interpreter (POI), a web-based application engineered to aggregate and interpret therapeutic options, including targeted, immunological, and chemotherapeutic agents, by leveraging personal genomic and transcriptomic profiles. POI employs the Precision Medicine Knowledgebase (PreMedKB), an updated harmonized resource we previously reported, to annotate the clinically actionable somatic variants. It further incorporates a predictive algorithm to broaden therapeutic options according to established gene-gene interactions and offers insights into phenotypic responses of chemotherapeutic agents through phasing germline diplotypes. Validated against three cohort datasets encompassing over 22,000 cancer patients, POI demonstrates consistently high matching rates (94.7 ∼ 95.6%) between patients and suggested therapies, highlighting its potential in supporting precision-driven informed treatment strategies.
- 8 February 2024
- Published by American Chemical Society (ACS) in Energy & Fuels
- Vol. 38 (5) , 4594-4612
Creating a Reaction Data Set Labeled with Reaction Class for Automated Reaction Classification for ReaxFF Molecular Dynamics Simulations of Realistic Fuel Pyrolysis
- 8 February 2024
- Published by American Chemical Society (ACS) in Energy & Fuels
- Vol. 38 (5) , 4594-4612
Creating a Reaction Data Set Labeled with Reaction Class for Automated Reaction Classification for ReaxFF Molecular Dynamics Simulations of Realistic Fuel Pyrolysis
- Open Access
- 19 January 2024
- Published by Elsevier in Engineering
- Vol. 39, 84-93
A Case Study Applying Mesoscience to Deep Learning
- 19 January 2024
- Published by Elsevier in Engineering
- Vol. 39, 84-93
Open AccessA Case Study Applying Mesoscience to Deep Learning
- 16 January 2024
- Published by Royal Society of Chemistry (RSC) in Physical Chemistry Chemical Physics
- Vol. 26 (6) , 5649-5668
Generating a skeleton reaction network for reactions of large-scale ReaxFF MD pyrolysis simulations based on a machine learning predicted reaction class
The reactive molecular dynamics using ReaxFF provides an effective means to generate global reactions for pyrolysis of realistic fuel mixtures. The reactions from large-scale pyrolysis simulations of a fuel mixture may be characterized by multiple reaction sites, explosion of intermediate species structures, and scattered contribution of diversified pathways to product species. This work proposes an approach of SRG-Reax aiming at generating skeleton reaction networks based on reaction patterns or classes of reaction centers from huge reactions obtained from ReaxFF MD simulations of realistic fuel pyrolysis. SRG-Reax (Skeleton Reaction network Generation for ReaxFF MD) is implemented through building a semi-supervised machine learning model of tri-training for predicting the reaction classes of pyrolysis reactions based on an extended reaction center. Three different reaction center descriptions of reaction features and reaction transformation fingerprints are employed as inputs for developing the tri-training classifier. Major reaction pathways can be identified based on reaction class ratios and product species ratios calculated by merging reaction pathways of the same reaction class. The SRG-Reax approach was applied in skeleton reaction network generation for RP-3 pyrolysis based on the ReaxFF MD simulations of a high-fidelity 45-component RP-3 fuel model. The skeleton reaction networks for n-paraffins, iso-paraffins, cycloparaffins, olefins, and aromatics in RP-3 pyrolysis were obtained. The reaction class ratios and product species ratios in the obtained skeleton reaction network provide comprehensive intuitive insight into global pyrolysis chemistry. SRG-Reax has the potential to obtain relatively complete skeleton reaction networks for the pyrolysis of hydrocarbon fuel, polymers, biomass, coal, and more.
- 16 January 2024
- Published by Royal Society of Chemistry (RSC) in Physical Chemistry Chemical Physics
- Vol. 26 (6) , 5649-5668
Generating a skeleton reaction network for reactions of large-scale ReaxFF MD pyrolysis simulations based on a machine learning predicted reaction class
The reactive molecular dynamics using ReaxFF provides an effective means to generate global reactions for pyrolysis of realistic fuel mixtures. The reactions from large-scale pyrolysis simulations of a fuel mixture may be characterized by multiple reaction sites, explosion of intermediate species structures, and scattered contribution of diversified pathways to product species. This work proposes an approach of SRG-Reax aiming at generating skeleton reaction networks based on reaction patterns or classes of reaction centers from huge reactions obtained from ReaxFF MD simulations of realistic fuel pyrolysis. SRG-Reax (Skeleton Reaction network Generation for ReaxFF MD) is implemented through building a semi-supervised machine learning model of tri-training for predicting the reaction classes of pyrolysis reactions based on an extended reaction center. Three different reaction center descriptions of reaction features and reaction transformation fingerprints are employed as inputs for developing the tri-training classifier. Major reaction pathways can be identified based on reaction class ratios and product species ratios calculated by merging reaction pathways of the same reaction class. The SRG-Reax approach was applied in skeleton reaction network generation for RP-3 pyrolysis based on the ReaxFF MD simulations of a high-fidelity 45-component RP-3 fuel model. The skeleton reaction networks for n-paraffins, iso-paraffins, cycloparaffins, olefins, and aromatics in RP-3 pyrolysis were obtained. The reaction class ratios and product species ratios in the obtained skeleton reaction network provide comprehensive intuitive insight into global pyrolysis chemistry. SRG-Reax has the potential to obtain relatively complete skeleton reaction networks for the pyrolysis of hydrocarbon fuel, polymers, biomass, coal, and more.