23 Papers
46 Citations
Jie Li is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Computer science & Chemistry. The author has an hindex of 6, co-authored 11 publications. Previous affiliations of Jie Li include Fudan University.
Chat about Author
Papers
AutoDetect-mNP: An Unsupervised Machine Learning Algorithm for Automated Analysis of Transmission Electron Microscope Images of Metal Nanoparticles
Xingzhi Wang,Xingzhi Wang,Jie Li,Hyun Dong Ha,Hyun Dong Ha,Jakob C. Dahl,Jakob C. Dahl,Justin C. Ondry,Ivan A. Moreno-Hernandez,Teresa Head-Gordon,A. Paul Alivisatos +10 more
TL;DR: In this article, an unsupervised algorithm AutoDetect-mNP was developed for automated analysis of TEM images that objectively extracts morphological information on convex mNPs from TEM image based on their shape attributes, requiring little to no human input in the process.
Multiresolution 3D-DenseNet for Chemical Shift Prediction in NMR Crystallography
Shuai Liu,Jie Li,Kochise Bennett,Brad Ganoe,Tim Stauch,Martin Head-Gordon,Alexander Hexemer,Daniela Ushizima,Teresa Head-Gordon +8 more
TL;DR: In this article, a 3D-DenseNet was proposed for chemical shift prediction for atoms in molecular crystals that utilizes an atom-centered Gaussian density model for the 3D data representation of a molecule.
•Posted Content
NewtonNet: A Newtonian message passing network for deep learning of interatomic potentials and forces
Mojtaba Haghighatlari,Jie Li,Xingyi Guan,Oufan Zhang,Akshaya K. Das,Christopher J. Stein,Farnaz Heidar-Zadeh,Meili Liu,Martin Head-Gordon,Luke W. Bertels,Hongxia Hao,Itai Leven,Teresa Head-Gordon +12 more
TL;DR: NewmanNet as mentioned in this paper takes inspiration from Newton's equations of motion to learn interatomic potentials and forces and achieves state-of-the-art performance on energy and force prediction.
26
Functionality proportion and corresponding stability study of multivariate metal-organic frameworks
TL;DR: In this paper, a multivariate metal-organic frameworks (MTV-MOFs) with different ratios of terephthalate linker and amino-benzenedicarboxylate (BDC-NH2) linker were synthesized through both direct synthesis from linker mixture and linker exchange of activated single-linker MOFs.
22
Learning to evolve structural ensembles of unfolded and disordered proteins using experimental solution data.
Oufan Zhang,Mojtaba Haghighatlari,Jie Li,Ziqing Liu,Ashley Namini,João M.C. Teixeira,Julie D. Forman-Kay,Teresa Head-Gordon +7 more
TL;DR: This work develops a GRNN that learns the probability of the next residue torsions X i +1 from the previous residue in the sequence X i to generate new IDP conformations and shows that updating the generative model parameters according to the reward feedback on the basis of the agreement between structures and data improves upon existing approaches.
18