Archive

Author Archive

Local false discovery rate software

5 November 2008 Leave a comment

Zahra Montazeri and David Bickel developed empiricalBayes, an R software bundle that provides a simple solution to the extreme multiple testing problem. It contains two packages:

  • localFDR estimates local false discovery rates given a vector of p-values.
  • HighProbability determines which p-values are low enough that their alternative hypotheses can be considered highly probable.
Categories: software, trainee author

Conference on statistics in biology

6 September 2008 Leave a comment

The Department of Statistics at Iowa State University is pleased to host an ASA and IMS co-sponsored conference on statistics in biology. The conference will feature a series of talks and posters on statistical theory, methods, and applications motivated by problems from the biological sciences. Contributed talks or posters by students expecting a Ph.D. in 2009 or new researchers who have received Ph.D. degrees in 2007 or 2008 are especially welcome. Limited financial support is available for such participants.

Categories: Fragments

On statisticians and men

22 July 2008 Leave a comment
Categories: Fragments

Bioinformatics graduate program

26 June 2008 1 comment
Categories: applications welcome

Application: cis- & trans-effects on gene expression

4 April 2008 Leave a comment

M. Guo, S. Yang, M. Rupe, B. Hu, D. R. Bickel, L. Arthur, and O. Smith, “Genome-wide allele-specific expression analysis using Massively Parallel Signature Sequencing (MPSS) reveals cis- and trans-effects on gene expression in maize hybrid meristem tissue,” Plant Molecular Biology 66, 551-563 (2008).

Estimating levels of differential gene expression

10 March 2008 Leave a comment

D. R. Bickel, “Correcting the estimated level of differential expression for gene selection bias: Application to a microarray study,” Statistical Applications in Genetics and Molecular Biology 7 (1) 10, http://www.bepress.com/sagmb/vol7/iss1/art10 (2008).

Postdoctoral Training in Statistical Genomics

13 February 2008 Leave a comment

Scientific breakthroughs from genome-sequencing projects brought the realization that reliable interpretation of the resulting information makes unprecedented demands for contemporaneous advances in computation and mathematical modeling. As the complexity of genomic data sets drives innovative statistics research, the new Statistical Inference and Computation in Genomics (Statomics) Lab of the Ottawa Institute of Systems Biology seeks a postdoctoral researcher who will collaboratively develop and apply statistical methods to solve current problems in analyzing and integrating gene-expression, proteomics, metabolomics, SNP, ChIP-chip, and/or clinical data. The lab is presently targeting inference in genome-wide association studies, bias reduction in estimated levels of gene expression, and validation of microarray predictions and will attack similar statistical and computational challenges of importance to genetics and functional genomics. The researcher’s background will complement that of any students and any postdoctoral researcher to be recruited to the Statomics Lab from the biomedical and computer science communities, creating an interdisciplinary environment for high impact on the biological sciences as well as on statistics.

Scientific creativity and a thorough knowledge of either Bayesian statistics or another likelihood-based inferential framework are essential, as is the demonstrated ability to quickly and accurately implement likelihood-based methods in software. Strong initiative, excellent communication skills, and reception of a PhD in statistics or a closely related field within the four years prior to the start date are also absolutely necessary. The following qualities are desirable but not required: exposure to the law of likelihood; knowledge of biology; familiarly with BUGS, R, S-PLUS, C, Fortran, and/or LaTeX; experience in a UNIX or Linux environment.

To apply, send a PDF CV that has contact information of three references to dbickel0@uottawa.ca (without the zero), with “likelihood postdoc” and the year of your graduation or anticipated graduation in the Subject line of the message; in the plaintext message body, concisely include evidence that you meet each requirement for the position and a description of your most significant papers and software packages with an explanation of your own contributions to them. Only those applicants selected for further consideration will receive a response.

Graduate Student Stipends

25 January 2008 1 comment

Scientific breakthroughs from genome-sequencing projects brought the realization that reliable interpretation of the resulting information makes unprecedented demands for contemporaneous advances in computation and mathematical modeling. As the complexity of genomic data sets drives innovative statistics research, the new Statistical Inference and Computation in Genomics (Statomics) Lab of the Ottawa Institute of Systems Biology seeks MSc and PhD students who will develop and apply novel methodology and algorithms to solve current problems in analyzing gene-expression, proteomics, metabolomics, SNP, ChIP-chip, and/or phenotypic data. The lab is presently targeting inference in genome-wide association studies, estimation of levels of gene expression, and improvements in the repeatability of microarray results and will attack similar statistical and computational challenges of importance to genetics and functional genomics.

The OISB provides a highly collaborative research environment with ample opportunities to interact with leading experimental and computational biologists. In addition, each student’s background will complement that of any students and any postdoctoral researchers to be recruited to the Statomics Lab from the statistics, bioinformatics, and computer science communities, creating interdisciplinary synergism for making unique contributions to science.

Intellectual curiosity and high mathematical aptitude are essential, as is the ability to quickly code and debug computer programs. Canadian citizenship or permanent resident status, strong initiative, good communication skills, and a degree in bioinformatics, computer science, mathematics, physics, statistics, any field of engineering, or an equally quantitative field are also absolutely necessary. The following qualities are desirable but not required: coursework in computer science, numerical methods, numerical analysis, software engineering, statistics, and/or biology; familiarly with BUGS, R, S-PLUS, C, Fortran, and/or LaTeX; experience with UNIX or Linux.

Send a PDF CV that has your GPA and contact information of two references to dbickel0@uottawa.ca (without the zero) with “statistical bioinformatics graduate student” in the Subject line of the message and with your preferred graduate program (Biochemistry, Mathematics & Statistics, or Computer Science) and the degree sought (MSc or PhD) in the message body. Only those students selected for further consideration will receive a response.

Mode estimation

25 January 2008 Leave a comment

Paul Poncet’s modeest package implements the half-range mode, the half-sample mode, and the mode-based skewness of D. R. Bickel, “Robust estimators of the mode and skewness of continuous data,” Computational Statistics and Data Analysis 39, 153-163 (2002).

More mode estimation software

Categories: software

Undergraduate research opportunity

21 January 2008 Leave a comment

Ideal for a fourth-year project or summer internship

THE EDGE. Acquire a statistical bioinformatics skill set by developing novel scientific software in the frontiers of post-genomic biology for high impact on medical science.
THE LAB. Scientific breakthroughs from genome-sequencing projects brought the realization that reliable interpretation of the resulting information makes unprecedented demands for contemporaneous advances in computation and mathematical modeling. As the complexity of genomic data sets drives innovative statistics research, the new Statistical Machine Learning in Functional Genomics (Statomics) Lab of the Ottawa Institute of Systems Biology aims to develop and apply novel methodology and algorithms to solve current problems in analyzing gene-expression, proteomics, metabolomics, SNP, ChIP-chip, and/or clinical data. The lab is presently targeting the inference of degrees of differential gene expression and improvements in the repeatability of microarray results and will attack similar statistics and machine learning challenges of importance to functional genomics.
THE STUDENT. Learn to analyze genomics data with newly created statistical methods. Make breakthrough bioinformatics software accessible worldwide by improving the usability and functionality of the lab’s data analysis code and by adding documentation. Providing scientists with these reliable biostatistical tools can advance medical research by improving the accuracy of conclusions drawn from genomics and clinical data.

Send your cover letter and CV or resume, including your GPA, to dbickel0@uottawa.ca (without the zero).

Categories: applications welcome