Informatic tools for predicting an ordinal response for high-dimensional data
Results from NIH/National Library of Medicine funded project
R01-LM011169
Kellie J. Archer, PI
-
Software developments:
- Link to glmnetcr package available from the Comprehensive R Archive Network
- Link to glmpathcr package available from the Comprehensive R Archive Network
- Link to ordinalgmifs package available from the Comprehensive R Archive Network for fitting cumulative, adjacent category, forward and backward continuation ratio, and stereotype ordinal response models for the high-dimensional data setting.
- Download ordinalgmifs vignette that described usage.
- Invited presentation: Kellie J. Archer. “Identifying Genes for Establishing a Multigenic Test for HCC Surveillance in HCV+ Cirrhotic Patients” Virginia State University, Petersburg, Virginia, March 1, 2013.
- Invited plenary keynote speaker: Kellie J. Archer. “Penalized ordinal response models for high-dimensional datasets.” Math Awareness SIAM Conference, Old Dominion University, Norfolk, Virginia, April 13, 2013.
- Kellie J. Archer and Andre AA Williams. Feature selection among ordinal classes for high-throughput genomic data. 2013 Eastern North American Region (ENAR) of the International Biometric Society Meeting, Orlando, FL, March 10, 2013 (contributed poster).
- Kellie J. Archer and Jiayi Hou. 2014 Eastern North American Region of the International Biometric Society Meeting, Baltimore, MD. Generalized incremental forward stagewise ordinal models: Application predicting stage of Alzheimer's disease. Poster presentation.
- Qing Zhou and Kellie J. Archer. “Penalized sterotype logit model for high-dimensional datasets.” Virginia Academy of Science: Statistics, Virginia Commonwealth University, Richmond, VA, May 15, 2014.
- Kyle Ferber. “Modeling Censored Discrete Survival Time in High-Dimensional Settings.” The Forty-Second Annual John C. Forbes. Graduate Student Honors Colloquium, Virginia Commonwealth University, Richmond, VA, March 12, 2015.
- Kyle Ferber and Kellie J. Archer. “Modeling censored discrete survival time in high- dimensional settings.” Virginia Academy of Science: Statistics, James Madison University, Harrisonburg, VA, May 22, 2015.
- Invited presentation: Kellie J. Archer. “Identifying factors related to micronuclei frequency in women with breast cancer.” Cancer Cell Biology Program, West Virginia University, Morgantown, WV, April 1, 2015.
- Kellie J. Archer, Jiayi Hou, Qing Zhou, Kyle Ferber, John G. Layne, Amanda Elswick Gentry. ordinalgmifs: An R package for ordinal regression in high-dimensional data settings. Cancer Informatics 13:187-95, 2014
- Kellie J. Archer, Jiayi Hou, Andre A.A. Williams. Classifying Normal, Nevus, and Malignant Melanoma Skin Samples using Penalized Ordinal Regression. Invited chapter in monograph, New Frontiers of Multidisciplinary Research in STEAM-H (Science, Technology, Engineering, Agriculture, Mathematics and Health) Springer Proceedings in Mathematics & Statistics, edited by Bourama Toni, pp. 111-133, 2014.
- Kyle Ferber and Kellie J. Archer. Modeling discrete survival time using genomic feature data. Cancer Informatics, Mar 2;14(Suppl 2):37-43, 2015.
- Amanda Elswick Gentry, Colleen Jackson-Cook, Debra Lyon, Kellie J. Archer. Penalized Ordinal Regression Methods for Predicting Stage of Cancer in High-Dimensional Covariate Spaces. Cancer Informatics, May 27;14(Suppl 2):201-8, 2015.
- Mateusz Makowski and Kellie J. Archer. Generalized monotone incremental forward stagewise method for modeling count data: Application predicting micronuclei frequency. Cancer Informatics, Apr 29;14(Suppl 2):97-105, 2015.
Presentations:
Publications
- We have developed ordinal support vector machine and random forest R code and plan to make it publicly available after testing.
- We have developed an R package to invoke the MIXOR Fortran stand-alone program.
Link to mixor R package
that includes a vignette illustrating usage.
-
Presentations
- Archer KJ. Invited presentation: Ordinal Response Models for Modeling Longitudinal High-Dimensional Genomic Feature Data. Current Topic Workshop: Molecular to Systems Physiology, Mathematical Biosciences Institute, The Ohio State University, Columbus, OH, May 7, 2014.
- Jiayi Hou and Kellie J Archer. Regularization methods for predicting an ordinal response using longitudinal high-dimensional genomic data. Joint Statistical Meetings, Boston, MA, August 6, 2014.
- Archer KJ. Invited presentation: Extending the Generalized Monotone Incremental Forward Stagewise Method for Modeling Longitudinal High-Dimensional Genomic Feature Data. Institute for Applied Statistics Sri Lanka, Colombo, Sri Lanka, December 28-30, 2014.
- Jiayi Hou and Kellie J. Archer. Regularization method for predicting an ordinal response using longitudinal high-dimensional genomic data. Statistical Applications in Genetics and Molecular Biology 14(1):93-111, 2015.
- Qing Zhou, Colleen Jackson-Cook, Debra Lyon, Robert Perera, Kellie J. Archer. Identifying molecular features associated with psychoneurological symptoms in women with breast cancer using multivariate mixed models. Cancer Informatics, May 7;14(Suppl 2):139-45, 2015.
Publications