8 Hits in 1.2 sec

ATOM3D: Tasks On Molecules in Three Dimensions [article]

Raphael J.L. Townshend, Martin Vögele, Patricia Suriana, Alexander Derry, Alexander Powers, Yianni Laloudakis, Sidhika Balachandar, Bowen Jing, Brandon Anderson, Stephan Eismann, Risi Kondor, Russ B. Altman (+1 others)
2022 arXiv   pre-print
Computational methods that operate on three-dimensional molecular structure have the potential to solve important questions in biology and chemistry.  ...  We implement several classes of three-dimensional molecular learning methods for each of these tasks and show that they consistently improve performance relative to methods based on one- and two-dimensional  ...  F.6 LEP We train DeepDTA [Öztürk et al., 2018] 10 (with the same hyperparameters as in the original paper) on the LEP dataset as baseline.  ... 
arXiv:2012.04035v4 fatcat:5uvarnqwpjaxdei4hxa3d6gxku

COLLAPSE: A representation learning framework for identification and characterization of protein structural sites [article]

Alexander Derry, Russ B Altman
2022 bioRxiv   pre-print
Our representations generalize across disparate tasks in a transfer learning context, achieving state-of-the-art performance on standardized benchmarks (protein-protein interactions and mutation stability  ...  ) and on the prediction of functional sites from the PROSITE database.  ...  Benchmarking on ATOM3D tasks We evaluate COLLAPSE on two ATOM3D tasks concerned with local sites in one or more protein structures: protein interface prediction (PIP), and mutation stability prediction  ... 
doi:10.1101/2022.07.20.500713 fatcat:t4h5hw2ds5alfkvgdqunrjuf5i

Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphs [article]

Zhao Xu, Youzhi Luo, Xuan Zhang, Xinyi Xu, Yaochen Xie, Meng Liu, Kaleb Dickerson, Cheng Deng, Maho Nakata, Shuiwang Ji
2021 arXiv   pre-print
Recent studies show that when 3D molecular geometries, such as bond lengths and angles, are available, molecular property prediction tasks can be made more accurate.  ...  We implement two baseline methods that either predict the pairwise distance between atoms or atom coordinates in 3D space.  ...  Acknowledgments and Disclosure of Funding This work was supported in part by National Science Foundation grants IIS-1908198 and IIS-1908220.  ... 
arXiv:2110.01717v1 fatcat:jsh353cvdvd5nevzm4ncqoumwm

Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching [article]

Shengchao Liu, Hongyu Guo, Jian Tang
2022 arXiv   pre-print
Pretraining molecular representations is critical in a variety of applications in drug and material discovery due to the limited number of labeled molecules, yet most of existing work focuses on pretraining  ...  Leveraging a SE(3)-invariant score matching method, we propose SE(3)-DDM where the coordinate denoising proxy task is effectively boiled down to the denoising of the pairwise atomic distances in a molecule  ...  Downstream Tasks on Binding Affinity Prediction Atom3D [61] is a recently published dataset. It gathers several core tasks for 3D molecules, including binding affinity.  ... 
arXiv:2206.13602v1 fatcat:xxvhqv3tezcfzhgn6eut24iqxi

Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs [article]

Fang Wu, Qiang Zhang, Dragomir Radev, Jiyu Cui, Wen Zhang, Huabin Xing, Ningyu Zhang, Huajun Chen
2022 arXiv   pre-print
The research to date mainly focuses on atom-level homogeneous molecular graphs, ignoring the rich information in subgraphs or motifs.  ...  Procuring expressive molecular representations underpins AI-driven molecule design and scientific discovery.  ...  Experiments We conduct extensive experiments on 7 datasets about both small molecules and large protein molecules from three different domains, including quantum chemistry, physiology, and biophysics.  ... 
arXiv:2110.01191v5 fatcat:faaetbdesjb5djy7vknczwrc7e

Pre-training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug Binding [article]

Fang Wu, Yinghui Jiang, Shuting Jin, Xurui Jin, Xiangrong Liu, Zhangming Niu, Qiang Zhang, Stan Z. Li
2022 arXiv   pre-print
learning tasks: an atom-level prompt-based denoising generative task and a conformation-level snapshot ordering task to seize the flexibility information inside MD trajectories with very fine temporal  ...  Nonetheless, remarkable changes in associated atomic sites and binding pose can provide vital information in understanding the process of drug binding.  ...  Acknowledgments This work is supported in part by the Science and Technology Innovation 2030 -Major Project (No. 2021ZD0150100) and National Natural Science Foundation of China (No. U21A20427).  ... 
arXiv:2204.08663v3 fatcat:ps3eakq5rbcfla3eolh4av4zu4

Training data composition affects performance of protein structure analysis algorithms [article]

Alexander Derry, Kristy A. Carpenter, Russ B. Altman
2021 bioRxiv   pre-print
Importantly, we show that including all three types of structures in the training set does not degrade test performance on X-ray structures, and in some cases even increases it.  ...  In this work, we evaluate the magnitude of this effect across three distinct tasks: estimation of model accuracy, protein sequence design, and catalytic residue prediction.  ...  Most of the computing for this project was performed on the Sherlock cluster; we would like to thank Stanford University and the Stanford Research Computing Center for providing computational resources  ... 
doi:10.1101/2021.09.30.462647 fatcat:4z5zlpsje5bbdnlrzveac3iyqm

Precise determination of object position in 1D optical lattice

Tomáš Čizmár, Martin Šiler, Mojmír Šerý, Pavel Zemánek, Kishan Dholakia, Gabriel C. Spalding
2006 Optical Trapping and Optical Micromanipulation III  
The algorithm was used in a standing wave optical trap for determination of the trap properties and particle behavior even in the standing wave in motion.  ...  Particle movement with respect to the interference structure of illumination is followed by changes in the light field scattered by the particle.  ...  two dimensions because they can be tracked in complex environment.  ... 
doi:10.1117/12.680563 fatcat:rwfumm4zcbemfdosngrjaxul6a