Postdoctoral fellowships in machine learning and computational biology
Seven postdoctoral fellowships in machine learning and computational
biology are available in the lab of William Stafford Noble in the
Department of Genome Sciences at the University of Washington,
Seattle, WA, USA.
Our research group develops and applies computational techniques for
modeling and understanding biological processes at the molecular
level. Our research emphasizes the application of statistical and
machine learning techniques, such as dynamic Bayesian networks and
support vector machines. We apply these techniques to various types of
biological data, including DNA and protein sequence data, shotgun
proteomics mass spectrometry data, and a variety of high-throughput
genomic data types. More information is available at
http://noble.gs.washington.edu.
The following projects are available:
o Structure of mammalian genomes: Last year, in collaboration with
Tony Blau’s lab, we published a detailed description of the
three-dimensional architecture of the yeast genome in vivo. We have
recently received NIH funding to continue this work in mammalian
systems. The postdoc involved in this project would work on
developing and applying statistical methods for interpreting the raw
sequencing data, for relating these data to known classes of
functional elements, and for improving our ability to infer 3D
structure from observed pairs of interactions.
o Clonal population of cancer: More recently, also in collaboration
with Tony Blau, we have been developing next generation sequencing
strategies for characterizing the population of clones in a single
cancer by assaying paired cancerous and non-cancerous samples. This
project will employ dynamic Bayesian network models to infer the
clonal population structure.
o Genomics and proteomics of Plasmodium: Our lab is about to embark in
a new research direction, focusing on analyses of Plasmodium
falciparum, the parasite responsible for the most lethal form of
malaria. In collaboration with Karine Le Roch’s lab at UC
Riverside, we will investigate local and global DNA structure, with
the goal of building a computational model of gene regulation in
this organism. We will also be applying our expertise in
interpreting shotgun proteomics data to help shed light on the
differences between RNA and protein expression.
o Local chromatin structure and gene regulation: This project involves
investigating the relationship between DNA sequence and chromatin
structure of the human genome. Computational models, such as
dynamic Bayesian networks or support vector machines, will be
employed to investigate the competitive binding of proteins to
nuclear DNA and to understand their collective influence on gene
regulation. This project is a collaboration with Prof. Zhiping Weng
at the University of Massachusetts Medical School.
o Integration of functional genomics data: This project will be
carried out in the context of the NIH ENCODE Consortium, the aim of
which is to discover all of the functional elements in the human
genome. Our lab’s role in this consortium is to develop
unsupervised and semi-supervised machine learning methods for
identifying new instances and new types of functional elements.
o Machine learning for mass spectrometry analysis: In collaboration
with Mike MacCoss’s lab here in Genome Sciences, as well as Jeff
Bilmes’ lab in Electrical Engineering, we have developed a series of
machine learning and statistical methods for interpreting shotgun
proteomics data sets. The postdoc working on this project will have
opportunities to develop new methods for quantifying proteins,
interpreting targeted proteomics data, identifying modified
proteins, etc.
o Genomics and proteomics of auditory pathways: Dr. Ed Rubel’s lab, in
the UW Department of Otalaryngology, studies auditory pathways in
the developing mouse brain. A collaboration involving Ed, Mike
MacCoss and our lab will collect a series of RNA and protein samples
from microdissected mouse brains at particular time points. These
samples will be subjected to shotgun proteomics and RNAseq analysis,
with the goal of identifying genes and proteins involved in
development of these pathways. The postdoc working on this project
would have the opportunity to work in any of the three collaborating
labs.
An ideal candidate would have training both in machine learning and
computational biology. However, talented individuals who lack
significant background in one of these two areas will also be
considered. Starting dates for most projects are flexible.
The Department of Genome Sciences was founded in September 2001 as the
fusion of the Departments of Genetics and Molecular Biotechnology.
Research in the department addresses leading edge questions in biology
and medicine by developing and applying genetic, genomic and
computational approaches that take advantage of genomic information
now available for humans, model organisms and a host of other species.
Nine faculty are members of the National Academy of Sciences,
including 2001 Nobel Prize winner Dr. Lee Hartwell. Five training
faculty are Howard Hughes Medical Institute Investigators. The
department moved into the new William H. Foege Building in 2006.
The University of Washington is consistently ranked as one of the top
research universities in the country and has more than 25,000
undergraduates and 9,000 others enrolled in its professional and
graduate programs. Seattle is considered one of the nation’s most
beautiful and livable cities, boasting an array of cultural
activities, parks, sports teams and restaurants, and serving as the
gateway to National Parks and Forests, as well as boating, skiing and
hiking areas.
The University of Washington is a culturally diverse community, and we
strongly encourage applications from women and minority
candidates. The University of Washington is an Affirmative
Action/Equal Opportunity Employer.
Applications will be accepted until the position is filled. Please
submit a CV, research statement and names of at least three references
to william-noble(at)uw.edu.
