A. K. Sehgal,
S. Das,
K. Noto,
M. H. Saier, Jr.
and C. Elkan.
Identifying Relevant Data for a Biological Database: Handcrafted Rules Versus Machine Learning.
In IEEE/ACM Transactions on Computational Biology and Bioinformatics (to appear, 2009)
Presentations and Posters
Paper presentation,
2008 Conference on Uncertainty in Artificial Intelligence (UAI) in Helsinki, Finland.
Invited speaker,
National Library of Medicine (NLM) Informatics Training Conference 2006, hosted by Vanderbilt University.
Paper presentation,
2006 European Conference on Computational Biology (ECCB) in Eilat, Israel.
K. Noto and M. Craven,
Poster: A Specialized Learner for Inferring Structured cis-Regulatory Modules.
2005 International Conference on Intelligent Systems for Molecular Biology (ISMB) in Detroit, MI.
Paper presentation,
RECOMB 2004 Workshop on Regulatory Genomics, hosted by the University of California—San Diego.
Research Experience
(The following briefly highlights my research interests and experience.
Please see my research statement for details.)
Research Interests
Machine learning algorithm development and application.
Applying machine learning to biological domains (bioinformatics).
Development of software beyond research level to create real-world tools.
Research Projects
Inferring gene regulatory networks from differential gene expression (microarray) and cellular conditions
(RECOMB workshop 2004).
Discovering modules of transcription factor binding sites,
including spatial and logical relationships between sites,
primarily from sequence and expression data
(ECCB 2006,
BMC Bioinformatics 2006).
Adapting a sequence classification algorithm
for regression tasks using hidden Markov models
(UAI 2008)
and support vector machines
(2009;in preparation).
Introduction to Artificial Intelligence
(Fall 2002, Prof. Jude Shavlik).
Co-Mentor of an undergraduate student for the
Computational Biology and Biostatistics (CBB) summer research program
at the University of Wisconsin—Madison, June-August, 2006.
Designed a two-month computational biology project for the student.
Advised on all aspects of the project: Code design, computational experiments, analysis of results and a final report.
I served on an NSF grant review panel
in the area of robust intelligence
in 2009.
Awards
Computation and Informatics in Biology and Medicine (CIBM) fellowship, April 2003-2006
(http://www.cibm.wisc.edu).
CIBM fellowship (second award), April 2006-2007
Travel fellowship award for ECCB 2006 from Biosapiens, funded by the EU.
Travel fellowship award for the RECOMB 2004 workshop.
Distinctive scholastic achievement (top 20% of graduating class),
B.A. from the University of Wisconsin—Madison, 1998.
Software
Rupa (Regression Using Path Aggregation),
a package for learning a regression model (based on hidden Markov models)
from the real-valued response associated with each of a set of training sequences
(written in C and Python)
(http://www.cs.ucsd.edu/~knoto/rupa).
Scrm (Structured cis-Regulatory Modules, versions 1 and 2), packages for learning
the arrangements of multiple DNA-binding sites from sequence data
(written in C++)
(http://pages.cs.wisc.edu/~noto/crm).
Previous Employment
September 1998 - January 2002: Software engineer,
Legislative Technology Services Bureau (Wisconsin state government).
Developed software
used by the
Wisconsin state representatives, senators and staff,
including several features of the Assembly and Senate voting systems.
Developed software that communicates with
Wisconsin's "InSession" sites.
Prof. Mark Craven (Ph.D. advisor)
University of Wisconsin—Madison, Dept. of Biostatistics and Medical Informatics
1300 University Avenue #6730 MSC, Madison WI 53706
E-mail: cravenbiostat.wisc.edu
Phone: (608) 265-6181
Prof. Charles Elkan (Postdoc Mentor)
University of California at San Diego, Dept. of Computer Science and Engineering
9500 Gilman Drive (EBU3B, MC0404), La Jolla, CA 92093
E-mail: elkancs.ucsd.edu
Phone: (858) 534-8897
Prof. Milton H. Saier, Jr.
University of California at San Diego, Dept. of Biology
9500 Gilman Drive, La Jolla, CA 92093
E-mail: saierbiomail.ucsd.edu
Phone: (858) 534-4084
Prof. Jude Shavlik
University of Wisconsin—Madison, Dept. of Computer Sciences
1210 West Dayton Street, Madison WI 53706
E-mail: shavlikcs.wisc.edu
Phone: (608) 263-7625
Prof. David Page
University of Wisconsin—Madison, Dept. of Biostatistics and Medical Informatics
1300 University Avenue #6743 MSC, Madison WI 53706
E-mail: pagebiostat.wisc.edu
Phone: (608) 265-6186
Jeffrey Ylvisaker
Director, Legislative Technology Services Bureau (Wisconsin)
17 W. Main St. Suite 200, Madison WI 53703
E-mail: jeff.ylvisakerlegis.state.wi.us
Phone: (608) 267-9528