Jianjun Hu

University of South Carolina

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Shaobo Li

Guizhou University

Edirisuriya M. Dilanga Siriwardane

University of Colombo

Rongzhi Dong

University of South Carolina

Yong Zhao

Southwest Jiaotong University

Ming Hu

University of South Carolina

Nihang Fu

University of South Carolina

Sadman Sadeed Omee

University of South Carolina

Erik D. Goodman

Michigan State University

Yuqi Song

Australian Regenerative Medicine Institute

Alireza Nasiri

New York Structural Biology Center

Cooperative Institutions

University of South Carolina

Guizhou University

Chinese Academy of Sciences

Ministry of Agriculture and Rural Affairs

Henan Agricultural University

University of Chinese Academy of Sciences

Shanghai Jiao Tong University

Dalian University of Technology

Huazhong University of Science and Technology

Harbin Institute of Technology

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Predicting Elastic Properties of Materials from Electronic Charge Density Using 3D Deep Convolutional Neural Networks

The Journal of Physical Chemistry C (2020)

Yong Zhao Kunpeng Yuan Yinqiao Liu Steph-Yves Louis Ming Hu

Materials representation plays a key role in machine learning based prediction of materials properties and new materials discovery. Currently both graph and 3D voxel representation methods are based on the heterogeneous elements of the crystal structures. Here, we propose to use electronic charge density (ECD) as a generic unified 3D descriptor for materials property prediction with the advantage of possessing close relation with the physical and chemical properties of materials. We developed an ECD based 3D convolutional neural networks (CNNs) for predicting elastic properties of materials, in which CNNs can learn effective hierarchical features with multiple convolving and pooling operations. Extensive benchmark experiments over 2,170 Fm-3m face-centered-cubic (FCC) materials show that our ECD based CNNs can achieve good performance for elasticity prediction. Especially, our CNN models based on the fusion of elemental Magpie features and ECD descriptors achieved the best 5-fold cross-validation performance. More importantly, we showed that our ECD based CNN models can achieve significantly better extrapolation performance when evaluated over non-redundant datasets where there are few neighbor training samples around test samples. As additional validation, we evaluated the predictive performance of our models on 329 materials of space group Fm-3m by comparing to DFT calculated values, which shows better prediction power of our model for bulk modulus than shear modulus. Due to the unified representation power of ECD, it is expected that our ECD based CNN approach can also be applied to predict other physical and chemical properties of crystalline materials.

Pooling

Representation

Inductive bias

10.1021/acs.jpcc.0c02348

Cite

Citations (32)

Physics guided deep learning for generative design of crystal materials with symmetry constraints

npj Computational Materials (2023)

Yong Zhao Edirisuriya M. Dilanga Siriwardane Zhenyao Wu Nihang Fu Mohammed Al‐Fahdi

Abstract Discovering new materials is a challenging task in materials science crucial to the progress of human society. Conventional approaches based on experiments and simulations are labor-intensive or costly with success heavily depending on experts’ heuristic knowledge. Here, we propose a deep learning based Physics Guided Crystal Generative Model (PGCGM) for efficient crystal material design with high structural diversity and symmetry. Our model increases the generation validity by more than 700% compared to FTCP, one of the latest structure generators and by more than 45% compared to our previous CubicGAN model. Density Functional Theory (DFT) calculations are used to validate the generated structures with 1869 materials out of 2000 are successfully optimized and deposited into the Carolina Materials Database www.carolinamatdb.org , of which 39.6% have negative formation energy and 5.3% have energy-above-hull less than 0.25 eV/atom, indicating their thermodynamic stability and potential synthesizability.

Crystal (programming language)

Generative model

10.1038/s41524-023-00987-9

Cite

Citations (54)

Proteomic characterization of Her2/neu‐overexpressing breast cancer cells

PROTEOMICS (2010)

Hexin Chen Genaro Pimienta Yiben Gu Xu Sun Jianjun Hu

The receptor tyrosine kinase HER2 is an oncogene amplified in invasive breast cancer and its overexpression in mammary epithelial cell lines is a strong determinant of a tumorigenic phenotype. Accordingly, HER2-overexpressing mammary tumors are commonly indicative of a poor prognosis in patients. Several quantitative proteomic studies have employed two-dimensional gel electrophoresis in combination with MS/MS, which provides only limited information about the molecular mechanisms underlying HER2/neu signaling. In the present study, we used a SILAC-based approach to compare the proteomic profile of normal breast epithelial cells with that of Her2/neu-overexpressing mammary epithelial cells, isolated from primary mammary tumors arising in mouse mammary tumor virus-Her2/neu transgenic mice. We identified 23 proteins with relevant annotated functions in breast cancer, showing a substantial differential expression. This included overexpression of creatine kinase, retinol-binding protein 1, thymosin 4 and tumor protein D52, which correlated with the tumorigenic phenotype of Her2-overexpressing cells. The differential expression pattern of two genes, gelsolin and retinol binding protein 1, was further validated in normal and tumor tissues. Finally, an in silico analysis of published cancer microarray data sets revealed a 23-gene signature, which can be used to predict the probability of metastasis-free survival in breast cancer patients.

HER2/neu

10.1002/pmic.201000297

Cite

Citations (37)

Design of control system for high intensity proton RFQ based on redundancy technology

Nuclear Instruments and Methods in Physics Research Section B Beam Interactions with Materials and Atoms (2014)

Chunlei Yu Zheng Yawei Yuhui Guo Yuan He Haitao Liu

Intensity

Source

Cite

Citations (1)

Active vibration suppression for integrated electric drive systems based on the CNN-LSTM considering dead zone

Mechanical Systems and Signal Processing (2024)

Zhicheng Sun Jianjun Hu Zutang Yao

Dead zone

10.1016/j.ymssp.2024.112153

Cite

Citations (0)

Contact map based crystal structure prediction using global optimization

CrystEngComm (2021)

Jianjun Hu Wenhui Yang Rongzhi Dong Yuxin Li Li Xiang

Crystal structure prediction is now playing an increasingly important role in the discovery of new materials or crystal engineering.

Crystal Structure Prediction

Crystal (programming language)

10.1039/d0ce01714k

Cite

Citations (21)

Volatilization Behavior and Mechanisms of Arsenic, Sulfur and Carbon in the Refractory Gold Concentrate

Springer eBooks (2015)

Hou Li-chen Qian Li Jianjun Hu Yongbin Yang Bing Xu

Roasting

Volatilisation

Oxidizing agent

Carbon fibers

10.1007/978-3-319-48217-0_21

Cite

Citations (2)

Automating the Hierarchical Synthesis of MEMS Using Evolutionary Approaches

Springer eBooks (2006)

Zhun Fan Jiachuan Wang Kisung Seo Jianjun Hu Ronald Rosenberg

10.1007/3-540-32364-3_6

Cite

Citations (2)

Establishment and Application of Matter Element Model for Comprehensive Evaluation of Tobacco Quality by Its Chemical Components

Tobacco Science & Technology (2003)

Jingyun Chen Jianjun Hu

The conception of matter element evaluation model was briefly introduced. In order to evaluate the quality of tobacco leaf by its chemical composition, the quality grade, quality index and chemical compositions of tobacco leaf were used as matter elements, the evaluated grades and tested data were normalized to obtain the sutra field, controlled field, weighting coefficient, and degree of correlation, and establish the matter element model. The quality of several Virginia tobacco and burley tobacco samples was evaluated with the model. It was found that the model was a suitable and simple method for comprehensive evaluation of tobacco quality by its chemical composition.

Tobacco leaf

Curing of tobacco

Source

Cite

Citations (0)

Nuclear localization signal prediction based on sequential pattern mining

Jhih-Rong Lin Jianjun Hu

Nuclear Localization Signals (NLS) are the most direct evidence for nuclear localization of proteins. Despite a couple of NLS prediction methods have been developed, the prediction performance is far from being satisfactory. In this study we proposed a sequential pattern mining based algorithm for identifying NLSs from protein sequences. The experiment results showed that our method can achieve better or comparable prediction performance than existing NLS prediction methods, which indicates that the motif residues discovered by our algorithm are effective features for predicting NLS.

NLS

SIGNAL (programming language)

10.1145/2382936.2383013

Cite

Citations (0)