News
200921: AMD Provides Computing Resources To Support COVID-19 Research at Xu Lab
200609: Our lab is awarded an NIH NIGMS R01 grant for developing novel methods for improving structural discrimination in cryo-electron tomography.
200530: Our lab is awarded an NSF IIS grant for developing novel methods for improving automation and speed of macromolecule recognition and localization in cryo-electron tomography using unsupervised deep learning.
200320: Our lab is awarded an NSF IIBR grant for developping novel methods to significantly reduce the amount of annotations for supervised deep learning based cryo-electron tomography analysis.
200224: Congratulations to Xiangrui Zeng for his first authored paper gets accepted by CVPR 2020, the best Computer Vision conference!
191218: Congratulations to Kai Wen Wang for Honorable Mention for the Computing Research Association's (CRA) Outstanding Undergraduate Researcher Award for 2020!
190519: Congratulations Yixiu Zhao for being awarded 2019 Elizabeth W. Jones Award for Excellence in Undergraduate Research in Experimental or Computational Biology.
190415: Congratulations Xiangrui Zeng for being awarded the CMLH fellowship!
181104: Congratulations Bo Zhou for having the following paper accepted by BIBM-MLHRM 2018: Feature Decomposition based Saliency Detection in Electron Cryo-Tomograms
180917: Congratulations Ran Li, Xiangrui Zeng and other students for having the following paper accepted by APBC2019: Automatic Localization and Identification of Mitochondria in Cellular Electron Cryo-Tomography using Faster-RCNN
180822: Our following paper got accepted by Structure. De novo structural pattern mining in cellular electron cryo-tomograms.
180702: Congratulations Chang Liu and other students for having following paper accepted: Liu C, Zeng X, Guo Q, Wang K, Xu M. Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography. British Machine Vision Conference (BMVC) 2018. arXiv:1805.06332
180702: Congratulations Kaiwen Wang and other students for having following paper accepted: Wang K, Zeng X, Liang X, Huo Z, Xing E, Xu M. Image-derived generative modeling of pseudo-macromolecular structures - towards statistical assessment of electron cryotomography template matching. British Machine Vision Conference (BMVC) 2018. arXiv:1805.04634
180525: Congratulations to Guannan Zhao, Bo Zhou and other students for having following paper accepted by MICCAI, a prestigious conference in biomedical image analysis! Zhao G, Zhou B, Wang K, Jiang R, Xu M. Respond-CAM: Analyzing Deep Models for 3D Imaging Data by Visualizations. Medical Image Computing and Computer Assisted Intervention (MICCAI) 2018. arXiv:1806.00102
180518: Congratulations to Chengqian Che and other students for having following paper accepted: Che C, Lin R, Zeng X, Elmaaroufi K, Galeotti J, Xu M. Improved deep learning based macromolecules structure classification from electron cryo tomograms. Machine Vision and Applications. arXiv:1707.04885
180516: Our new preliminary working report is online: Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography. arXiv:1805.06332
180515: Our new preliminary working report is online: Image-derived generative modeling of pseudo-macromolecular structures - towards statistical assessment of electron cryotomography template matching. arXiv:1805.04634
180504: Congratulations to Chang Liu and Xiangrui Zeng and other students for having following paper accepted: Deep learning based supervised semantic segmentation of Electron Cryo-Subtomograms. IEEE International Conference on Image Processing (ICIP) 2018. Preprint: arXiv:1802.04087
180402: Congratulations Yixiu Zhao and Xiangrui Zeng on their co-first authored paper being accepted by ISMB 2018! Title: An integration of fast alignment and maximum-likelihood methods for electron subtomogram averaging and classification.
180321: Congratulations Jialiang Guo and Bo Zhou for their paper being accepted by ICIAR!
180212: Our new preliminary working report is online: Deep learning based supervised semantic segmentation of Electron Cryo-Subtomograms
180131: Our new preliminary working report is online: Model compression for faster structural separation of macromolecules captured by Cellular Electron Cryo-Tomography
171227: Congratulations Xiangrui Zeng for his first authored paper being accepted by Journal of Structural Biology: A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation
170717: Our new preliminary working report is online: "Improved deep learning based macromolecules structure classification from electron cryo tomograms"
170616: Our new preliminary working report is online: "A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation"
170511: Kaiwen Wang just got awarded CMU Summer Undergraduate Research Apprenticeship on one of our collaborative research projects. Congratulations Kaiwen!
170406: Our manuscript entitled: "Deep learning based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms" will appear on ISMB 2017. Here is a preprint version.
170129: Our new manuscript is online: "Deep learning based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms"
Papers & Preprints
See here for the full list. See here for corresponding citations in latex bib format.
Cryo-ET analysis
Computer vision & Machine learning
Biomedical image analysis
Genomics
Computational biology
Group
Postdoctoral Associate
PhD students
Research assistants
Xiaoyu Zhu (LTI, MSAII)
Xindi Wu (RI, MSCV)
Gregory Howe (MLD, MSML)
Jeffery Chen (CSD, MSCS)
Saket Chaudhary (ECE, MSECE)
Xutong Ren (MLD, MSML)
Keting Zhao (ECE, MSECE)
Yicheng Bao (LTI, MSAI)
Ankita Mukherjea (BME, MSBE)
Students in collaboration
(Please see our publication)
Alumni
Yuchen Zeng (CBD)
Kai Wen Wang (ECE, CS)
Yixiu Zhao (CSD)
Bo Zhou (RI, MSCV)
Chang Liu (ECE)
About Min Xu
Min Xu, Ph.D.
Assistant Professor, Computational Biology Department
Training faculty, Master of Science in Computer Vision, Robotics Institute
School of Computer Science
Carnegie Mellon University
Office:
GHC 7709, 5000 Forbes Avenue, Pittsburgh, PA 15213
Email: mxu1 @ cs.cmu.edu
Curriculum Vitae,
Google Scholar, DBLP, Research Gate, and Linkedin pages.
Biography
Dr. Min Xu is an Assistant Professor at the Computational Biology Department in the School of Computer Science at Carnegie Mellon University. He serves as training faculty at the Joint CMU-Pitt Ph.D. Program in Computational Biology. He also serves as a training faculty Master of Science in Computer Vision Program at Robotics Institute. He is an investigator at the National Center for Multiscale Modeling of Biological Systems.
Dr. Xu’s career has centered on developing computational methods for the study of cellular systems using imaging and omics data. He started his research career in the field of Computational Biology and Bioinformatics since 2000. He developed machine learning methods for gene selection for classifying cancer samples, for cancer gene network module discovery, and for sample phenotype prediction through integration of hundreds of gene expression datasets. Since 2008, he started working in the field of computational analysis of Cellular Cryo-Electron Tomography (Cryo-ET) data. He designed structural pattern mining methods and first demonstrated the feasibility of De Novo extraction of structures and spatial organizations of macromolecular complexes in single cells using Cryo-ET data. His current research focus on Cryo-ET derived modelling of cellular organization at molecular resolution.
Dr. Xu has published over 60 research papers. He is currently serving in the editorial board of Statistical Methods in Medical Research.
Dr. Xu received an B.E. in Computer Science from the Beihang University, M.Sc from School of Computing at the National University of Singapore, M.A. in Applied Mathematics from the University of Southern California (USC), and Ph.D. in Computational Biology and Bioinformatics from USC.
He was a postdoctoral researcher at USC.
Dr. Xu does research for fun, and he enjoys working with highly talented and motivated students.
Positions
Software
The source code associated with our individual papers can be found at our papers page, following with each paper. All source code are deposited to our github portal. We are also in the process of integrating the algorithms into our AITom platform.
Research
The cell is the basic structural, functional, and biological unit of all known living organisms. It is a tiny but very complicated "living machine" that can do a lot of amazing things. However, so far we have very limited knowledge about its complicated molecular machinery due to lack of high resolution and systems level data of individual cells. Cellular Cryo-Electron Tomography is an emerging imaging technique that captures the 3D electron density distribution of cells at sub-molecular resolution and at close-to-native state. Our lab aims to use cutting-edge computation, mathematics and artificial intelligence techniques, particularly those related to computer vision, machine learning and big data, to build structural organization models using such imaging data. Such modeling would be useful for getting new insights into the machinery of cellular systems.
The figure above shows extracted structural patterns in cellular tomograms: (a) Slices of 3D tomogram images of two bacterial cells. Image data are from the Jensen Lab at Caltech. (b) Isosurfaces of instances of extracted structural patterns embedded into the original images. (c) Embedded instances, zooming in on a particular region. (d) Isosurfaces of one example structural pattern from each experiment. (e) Spatial distributions of instances of different structural patterns: left: the Ribosome like patterns distributed outside the nucleoid region; middle: patterns distributed on the nucleoid region; right: patterns distributed at the tip of the cell. For details, see our paper on Structure.