Ameet Soni

Ameet Soni

Assistant Professor
Computer Science Department
Swarthmore College
500 College Ave
Swarthmore, PA 19081
phone: (610) 957-6288
office: 253 Science Center

I am currently an Assistant Professor of Computer Science at Swarthmore College. I received my Ph.D. in Computer Science in August 2011 from the University of Wisconsin where I was advised by Professor Jude Shavlik. My general research interests are in the areas of machine learning and computational biology.

Current Semester

Fall 2014 Schedule
  CS68   Bioinformatics
          Lecture   1:15-2:30pm Tuesday, Thursday 183 Sci Ctr
          Lab A   1:15-2:45pm Monday 240 Sci Ctr
          Lab B   3:00-4:30pm Monday 240 Sci Ctr
  Office Hours   10:00am-noon Friday,  and by appointment 253 Sci Ctr
  Prep time (limited availability)   10:00am-noon Monday; 10pm-noon, Tuesday, Thursday 253 Sci Ctr
  Research Hours   1:00pm-4pm Wednesday, Friday  

Past Courses Taught:

Research Interests

Projects

Most recently, I have begun researching several different computational problems in the area of MRI braining imaging. Specifically, I seek to apply probabilistic methods to improve the ability to diagnose onset of Alzheimer's disease and other cognitive impairments. Currently, my group is pursuing methods for segmenting anatomical regions of the brain using graph-based methods as well intuit anatomical relationships between patients in the larger ADNI study.

Previously, I worked on ACMI (Automated Crystallographic Map Interpretation). The task of determining protein structures has been a central one to the biological community for several decades. The structure allows biologists to extract information about the underlying biology of a protein, and has implications for various applications such as disease treatment, drug design, and protein design. The most popular method for producing protein structures is by interpreting an electron-density map - a three-dimensional image of a molecule produced through X-ray crystallography. This process, however, remains a resource- intensive and time-consuming task, stunting basic biological research. Thus, the main objective of the project is:

Given the electron-density map (3D image) and a primary sequence of a target protein, produce a three- dimensional, physically-feasible, all-atom model of the target protein's structure.

The result of our group's efforts is ACMI, a probabilistic technique for determining protein structures. Prior to ACMI, techniques failed when trying to interpret low-quality images. With ACMI, crystallographers can now obtain complete and accurate structures from these difficult proteins instead of scrapping the project or dedicating months of effort.

Publications

Supervised students are underlined

A Graphical Model Approach to ATLAS-free Mining of MRI Images.
Chris S. Magnano, Ameet Soni, Sriraam Natarajan, and Gautam Kunapuli.
In the Proceedings of the 2014 SIAM International Conference on Data Mining (SDM '14), 2014.

Conditional Random Fields for Brain Tissue Segmentation.
Chris S. Magnano, Ameet Soni, Sriraam Natarajan, and Gautam Kunapuli.
Presented at the Workshop on Machine Learning and Interpretation in NeuroImaging (MLINI) at NIPS, 2013.
This is a shortened version of the SDM 2014 paper.
Poster

A Support Program for Introductory CS Courses that Improves Student Performance and Retains Students from Underrepresented Groups.
Tia Newhall, Lisa Meeden, Andrew Danner, Ameet Soni, Frances Ruiz, Richard Wicentowski.
In the Proceedings of the ACM Technical Symposium on Computer Science Education (SIGCSE), 2014.

Probabilistic Ensembles for Improved Inference in Protein-Structure Determination.
Ameet Soni, Jude Shavlik.
Journal of Bioinformatics and Computational Biology, 10(1), 2012.
doi: http://dx.doi.org/10.1142/S0219720012400094
An extended version of this paper can be found here.
Abstract.

Techniques for Improved Probabilistic Inference In Protein-Structure Determination via X-Ray Crystallography
Ameet Soni
PhD Thesis, Department of Computer Sciences, University of Wisconsin-Madison, 2011.
Also appears as UW Technical Report CS-TR-11-1703
Slides (PPT/PPTX).

ACM DL Author-ize service Probabilistic ensembles for improved inference in protein-structure determination
Ameet Soni, Jude Shavlik
In the Proceedings of the 2nd ACM Conference on Bioinformatics, Computational Biology and Biomedicine (ACM-BCB '11), 2011
Slides (PPT/PPTX). Abstract.

Structural characterization of human Uch37.
E. Sethe Burgie, Craig Bingman, S. Leigh Grundhoefer, Ameet Soni, George Phillips
Proteins: Structure, Function, and Bioinformatics, 80: 649-654, 2011.
doi:10.1002/prot.23147

ACM DL Author-ize service Guiding belief propagation using domain knowledge for protein-structure determination
Ameet Soni, Craig Bingman, Jude Shavlik
In the Proceedings of the First ACM International Conference on Bioinformatics and Computational Biology (ACM-BCB '10), 2010
Slides (PPT/PPTX). Abstract.

Spherical-Harmonic Decomposition for Molecular Recognition in Electron-Density Maps.
Frank DiMaio, Ameet Soni, George Phillips, Jude Shavlik.
International Journal of Data Mining and Bioinformatics, 3: 205-227, 2009.
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.

Machine Learning in Structural Biology: Interpreting 3D Protein Images.
Frank DiMaio, Ameet Soni, Jude Shavlik.
In S. Mitra, S. Datta, T. Perkins & G. Michailidis, editors,
Introduction to Machine Learning and Bioinformatics, 237-276, 2008. Chapman & Hall/CRC Press
Abstract.

Creating Protein Models from Electron-Density Maps using Particle-Filtering Methods.
Frank DiMaio, Dmitry Kondrashov, Eduard Bitto, Ameet Soni, Craig Bingman, George Phillips, Jude Shavlik.
Bioinformatics, 23: 2851-2858, 2007.
doi: 10.1093/bioinformatics/btm480; PMCID: PMC2567142
Abstract.

Improved Methods for Template-Matching in Electron-Density Maps Using Spherical Harmonics.
Frank DiMaio, Ameet Soni, George Phillips, and Jude Shavlik.
In the Proceedings of the First IEEE International Conference on Bioinformatics and Biomedicine (BIBM '07), 2007
Code. Data. Abstract.

Research Students

Previous Current