University of Wisconsin Computer Sciences Header Map (repeated with
textual links if page includes departmental footer)

Machine Learning and Visualization in Structural Biology

Research

Our research aims to develop computational tools that assist X-ray crystallographers in rapidly determining the three-dimensional structure of a protein from X-ray reflection data. More specifically, we address the following task: given a 3D electron-density map and the primary sequence of the protein that produced it, find the most likely layout (i.e, "trace") of the protein structure. We develop both automated methods based on statistical machine-learning and computer-vision techniques, as well as visualization tools that support humans doing this layout. Our methods are especially well-suited to high-throughput, protein-structure determination; being able to accurately interpret lower-quality X-ray data promises to allow higher-throughput structure determination at lower cost.

Funding

Our work is funded by grant 5-R01-LM008796-03 from the National Library of Medicine.

Downloads

Our research has developed ACMI (Automatic Crystallographic Map Interpretation), a probabilistic method for automatically interpreting low-resolution electron-density maps. ACMI is available for download here.

Publications

A. Soni, C. Bingman & J. Shavlik (2010).
Guiding Belief Propagation using Domain Knowledge for Protein-Structure Determination. Proceedings of the ACM International Conference on Bioinformatics and Computational Biology 2010 (ACM-BCB 2010), Niagara Falls, New York.
Slides (PPT/PPTX). Abstract.
F. DiMaio, A. Soni, G. Phillips & J. Shavlik (2009).
Spherical-Harmonic Decomposition for Molecular Recognition in Electron-Density Maps. International Journal of Data Mining and Bioinformatics, 3, pp. 205-227. doi: 10.1504/IJDMB.2009.024852 NIHMSID: NIHMS68171 PMCID: PMC2696052
(The paper is in pre-publication form. It is an extension to: DiMaio et al. (BIBM 2007))
Abstract.
Frank DiMaio, Ameet Soni & Jude Shavlik (2008).
Machine Learning in Structural Biology: Interpreting 3D Protein Images. In S. Mitra, S. Datta, T. Perkins & G. Michailidis, editors, Introduction to Machine Learning and Bioinformatics, pp. 237-276. Chapman & Hall/CRC Press.
(The on-line version is a pre-publication version of the chapter)
Abstract.
Frank DiMaio (2007).
Probabilistic Methods for Interpreting Electron-Density Maps. PhD thesis, Department of Computer Sciences, University of Wisconsin-Madison.
(Also appears as UW Technical Report CS-TR-07-1617)
Slides (PPT/PPTX).
F. DiMaio, D. Kondrashov, E. Bitto, A. Soni, C. Bingman, G. Phillips & J. Shavlik (2007).
Creating Protein Models from Electron-Density Maps using Particle-Filtering Methods. Bioinformatics, 23, pp. 2851-2858. doi: 10.1093/bioinformatics/btm480 PMCID: PMC2567142
Abstract.
F. DiMaio, A. Soni, G. Phillips & J. Shavlik (2007).
Improved Methods for Template-Matching in Electron-Density Maps Using Spherical Harmonics. Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM'07), Fremont, CA.
Code. Data. Abstract.
F. DiMaio, J. Shavlik & G. Phillips (2006).
A Probabilistic Approach to Protein Backbone Tracing in Electron Density Maps. Bioinformatics, Special Issue Based on the Papers Presented at the Fourteenth International Conference on Intelligent Systems for Molecular Biology (ISMB-06), Fortaleza, Brazil, 22, pp. e81-e89.
Slides (PPT/PPTX). Abstract.
F. DiMaio & J. Shavlik (2006).
Belief Propagation in Large, Highly Connected Graphs for 3D Part-Based Object Recognition. Proceedings of the Sixth IEEE International Conference on Data Mining (ICDM'06), pp. 845-850, Hong Kong.
Slides (PPT/PPTX). Abstract.
F. DiMaio & J. Shavlik (2006).
Improving the Efficiency of Belief Propagation in Large Highly Connected Graphs. Department of Computer Sciences, University of Wisconsin, Machine Learning Research Group Working Paper 06-1.
Abstract.

Posters and Workshops

A. Bryden, G. Phillips, and M. Gleicher (2009).
Automated Illustration of Molecular Flexibility. In Poster Proceedings at: IEEE Visualization 2009, Atlantic City, New Jersey, USA
A. Bryden, G. Phillips, and M. Gleicher (2008).
Interactive Exploration of Protein Flexibility Using Coarse Grained Normal Modes. In Poster Proceedings at: IEEE Visualization 2008, Columbus, Ohio, USA also presented at doctoral colloquium for: IEEE Visualization 2008, Columbus, Ohio, USA.
F. DiMaio (2007).
Guiding particle filtering with marginal approximations: An application in protein image interpretation. The Learning Workshop, San Juan, Puerto Rico.
F. DiMaio (2007).
New approaches to automatic fitting of electron density maps. PSI Protein Production and Crystallization Workshop, Bethesda, Maryland.
F. DiMaio (2006).
Modeling protein backbones with pairwise Markov fields. ISMB Satellite Meeting on Structural Bioinformatics and Computational Biophysics (3Dsig), Fortaleza, Brazil.
F. DiMaio (2006).
Tracing protein backbones in electron density maps using a Markov random field model. Snowbird Learning Workshop, Snowbird, Utah.

This page was created by shavlik@cs.wisc.edu

Computer Sciences Department
College of Letters and Science
University of Wisconsin - Madison

INFORMATION ~ PEOPLE ~ GRADS ~ UNDERGRADS ~ RESEARCH ~ RESOURCES

5355a Computer Sciences and Statistics ~ 1210 West Dayton Street, Madison, WI 53706
cs@cs.wisc.edu ~ voice: 608-262-1204 ~ fax: 608-262-9777