Dhammika Amaratunga

Short courses

My co-author and I have offered a few short courses on microarray data analysis. The latest version of my slides for the course are available here.

Software for the course is available at DNAMR.

[Where short courses have been given: ICSA (2011, New York), ASA's San Francisco Bay Area Chapter (2010), International Society of Clinical Biostatistics (2009, Prague), ASA's Biopharmaceutical Section webinar series (2009), ASA's New York City Chapter (2007), ASA's New Jersey Chapter(2004), and at ASA's Joint Statistical Meetings (2003).] 

Books and associated material

(1) D. Amaratunga and J. Cabrera (2003), Exploration and Analysis of DNA Microarray and Protein Array Data, New York: John Wiley (avaialable on Amazon).

Companion software: DNAMR

Datasets: E5, E7, and MUS are available as comma-separated text files.

Updates: Errata, Supplementary exercises.

Trivia: This is the first fully-authored book on microarray data analysis. We also gave the first talk on microarrays at a JSM (in 1999).

(2) D. Lin, Z. Shkedy, D. Yekutieli, D. Amaratunga and L. Bijnens (editors) (2012) Modeling Dose-Response Microarray Data in Early Drug Development Experiments using R, Springer (will be available on Amazon in Feb 2012)

(3) D. Amaratunga, J. Cabrera, L.Fernholz and S. Morgenthaler (2012) Exploratory Data Analysis, New York: John Wiley (in preparation)

Selected publications

D. Amaratunga, J. Cabrera, Y. Cherkas and Y. S. Lee (2011). Ensemble classifiers, in IMS Collection Volume 8, Contemporary Developments in Bayesian Analysis and Statistical Decision Theory : A Festschrift for William E. Strawderman.

N. Raghavan, A. Nie, M. McMillian and D. Amaratunga (2011). A linear prediction rule based on ensemble classifiers for non-genotoxic carcinogenicity, Statistics in Biopharmaceutical Research: Special Issue on Nonclinical Biopharmaceutical Statistics .

J. Kasturi, J. G. Geisler, J. Liu, T. Kirchner, D. Amaratunga, and M. Lubomirski (2011) IRINI: Efficient group allocation of multiple prognostic factors, Contemporary Clinical Trials.

K. R. D. De Silva, R. Silva, D. Amaratunga, W. S. L. Gunasekera, and R. W. Jayesekera (2011). Types of the cerebral arterial circle (circle of Willis) in a Sri Lankan Population, BMC Neurology, 11:5.

W. Talloen, S. Hochreiter, L. Bijnens, A. Kasim, Z.Shkedy, D. Amaratunga, and H. Göhlmann (2010)  Filtering data from high-throughput experiments based on measurement reliability, PNAS 107 (46) E173-E174.

D. Amaratunga and J. Cabrera (2010). DNA microarray data, prepared by invitation for Wiley Interdisciplinary Reviews: Computational Statistics edited by E. Wegman, Y. Said, and D. Scott.

D. Amaratunga, J. Cabrera and Y. S. Lee (2010). Ensemble classifiers, in review.

D. Amaratunga and J. Cabrera (2009). A conditional t suite of tests for identifying differentially expressed genes in a DNA microarray experiment with little replication,
Statistics in Biopharmaceutical Research (new ASA journal), 1:26-38. [PDF]

J. M. Dixon, M. Lubomirski, D. Amaratunga, and S. E. Ilyin (2009). An exercise in evaluating a new genomics technology: analyzing data from a pilot High-Density RT-PCR experiment, BioTechniques, 46:ii-viii.[PDF]

A. Kasim, D. Lin, S. Van Sanden, D. Clevert, L. Bijnens, H. Göhlmann, D. Amaratunga, S. Hochreiter, Z. Shkedy, and W. Talloen (2009). Informative or noninformative calls for gene expression: a latent variable approach, to appear in Statistical Applications in Genetics and Molecular Biology.

D. Amaratunga, J. Cabrera and Y. S. Lee (2008). Enriched random forests, Bioinformatics, 24:2010-2014.[PDF]

D. Amaratunga, J. Cabrera and V. Kovtun (2008). Microarray learning with ABC,
Biostatistics, 9:128-136.[PDF]

M. Tuefferd, A. De Bondt, I. Van Den Wyngaert, W. Talloen, T. Verbeke, B. Carvalho, D. A. Clevert, M. Alifano, N. Raghavan, D. Amaratunga, H. Gohlmann, P. Broet and S. Camilleri-Broet(2008) Genome-wide copy number alterations detection in fresh frozen and matched ffpe samples using SNP 6.0 arrays. Genes, Chromosomes and Cancer, 47:957-64.

M. McMillian, A. Nie, N. Raghavan, D. Amaratunga, and P. Lord (2008). Predictive toxicogenomics approaches to non-genotoxic carcinogens, Abstracts: Toxicology Letters, 180S, S14.

N. Raghavan, A De Bondt, W. Talloen, D. Moechars, H. Gohlmann and D. Amaratunga (2007). The high-level similarity of some disparate gene expression measures, Bioinformatics, 23:3032-3038.[PDF]

W. Talloen, D. Clevert, H. Gohlmann, S. Hochreiter, D. Amaratunga, L. Bijnens (2007). Gene selection: filtering microarray probesets based on probe level consistency, Bioinformatics,  23: 2897 - 2902.[PDF]

M. Lubomirski, M. R. D'Andrea, S. M. Belkowski, J. Cabrera, J. M. Dixon, and D. Amaratunga (2007), A consolidated approach to analyzing data from high throughput protein microarrays with an application to immune response profiling in humans. Journal of Computational Biology, 14:96-105.[PDF]

D. Amaratunga, H. Gohlmann and P. Peeters (2007), DNA microarrays for drug target research, in Comprehensive Medicinal Chemistry II (edited by D. J. Triggle and J. B Taylor), Oxford: Elsevier.

D. Amaratunga, J. Cabrera and V. Kovtun (2007), Towards superior classifications with ABC dissimilarities, Proceedings of the 2007 Joint Statistical Meetings: Biopharmaceutical Section.

N. Raghavan, D. Amaratunga, J. Cabrera, A. Nie, Q. Jie and M.McMillian (2007), Gene signatures for non-genotoxic carcinogenicity, Proceedings of the 2007 Joint Statistical Meetings: Biopharmaceutical Section.

N. Raghavan, D. Amaratunga, J. Cabrera, A. Nie, Q. Jie and M.McMillian (2006), On methods for gene function scoring as a means of facilitating the interpretation of microarray results, Journal of Computational Biology, 13: 798-809. [PDF]

D. Amaratunga and PhRMA's Statistics Expert Team for Pharmacogenomics (2006), Bias and variation considerations in gene expression microarray experiments and methods for data preprocessing, unpublished white paper. [PDF]

N. Raghavan, D. Amaratunga, A. Nie and M.McMillian (2005), Class prediction in toxicogenomics, Journal of Biopharmaceutical Statistics, 15:327-341. [PDF]

D. Amaratunga and J. Cabrera (2004), Mining data to find subsets of high activity, Journal of Statistical Planning and Inference, 122: 23-41. [PDF]

D. Amaratunga and J. Cabrera (2001), Statistical analysis of viral microchip data, Journal of the American Statistical Association, 96: 1161-1170.

D. Amaratunga (2001), How to assess simple screening strategies, Drug Information Journal, 35: 413-418.

H. Nguyen and D. Amaratunga (2001), Analysis of pharmacokinetic data, in Applied Statistics in the Pharmaceutical Industry with Case Studies using S-PLUS, S. Millard and A. Krause, editors, Springer.

D. Amaratunga and J. Cabrera (2001), Outlier resistance, standardization and modeling issues for DNA microarray data, in Statistics in the Sciences, L. Fernholz, S. Morgenthaler, E. Ronchetti, W. Stahel, editors, Birkhauser-Verlag.

D. Amaratunga (1999), Searching for the right sample size, The American Statistician, 53: 52-55. [PDF]

D. Amaratunga and N. Ge (1998), Step-down trend tests to determine a minimum effective dose, Journal of Biopharmaceutical Statistics, 8:145-156.

D. Amaratunga (1997), Reference ranges for screening preclinical drug safety data, Journal of Biopharmaceutical Statistics, 7:417-422.

D. Amaratunga (1997), Errors-in-variables regression estimators that have high breakdown and high Gaussian efficiency, in The Practice of Data Analysis: Essays in Honor of John W. Tukey, edited by D. R. Brillinger, L. T. Fernholz and S. Morgenthaler, Princeton University Press.

D. Amaratunga, Pushing back coefficients and orthogonal sampling in regression, my Ph.D. thesis!.
 

Software

The R function QuickSize.Fisher implements the QuickSize method (fast sample size determinations for complex problems described in my 1999 American Statistician paper) for the Fisher Exact Test.

The R package, ARF, for finding active regions in multidimensional space (based on our 2004 JSPI paper) can be downloaded from here (ARF) or from my co-author's website (ARF).

The R library for microarray data analysis, DNAMR, can be downloaded from here (DNAMR) or from my co-author's website (DNAMR).

The R function f.ABC implements the ABC learning (clustering) procedure. This requires DNAMR.

The R library ERF implements the Enriched Random Forest procedure for supervised classification. This requires DNAMR.

The R library Eclass implements the Ensemble Classifier procedure for supervised classification. This requires DNAMR.