Know-GRRF: Domain-Knowledge Informed Biomarker Discovery with Random Forests

Due to its robustness and built-in feature selection capability, random forest is frequently employed in omics studies for biomarker discovery and predictive modeling. However, random forest assumes equal importance of all features, while in reality domain knowledge may justify the prioritization of more relevant features. Furthermore, it has been shown that an antecedent feature selection step can improve the performance of random forest by reducing noises and search space. In this paper, we present a novel Know-guided regularized random forest (Know-GRRF) method that incorporates domain knowledge in a random forest framework for feature selection. Via rigorous simulations, we show that Know-GRRF outperforms existing methods by correctly identifying informative features and improving the accuracy of subsequent predictive models. Know-GRRF is responsive to a wide range of tuning parameters that help to better differentiate candidate features. Know-GRRF is also stable from run to run, making it robust to noises. We further proved that Know-GRRF is a generalized form of existing methods, RRF and GRRF. We applied Known-GRRF to a real world radiation biodosimetry study that uses non-human primate data to discover biomarkers for human applications. By using cross-species correlation as domain knowledge, Know-GRRF was able to identify three gene markers that significantly improved the cross-species prediction accuracy. We implemented Know-GRRF as an R package that is available through the CRAN archive.

[1]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[2]  D. Felsher,et al.  MYC as a regulator of ribosome biogenesis and protein synthesis , 2010, Nature Reviews Cancer.

[3]  Michael C Joiner,et al.  Accurate gene expression-based biodosimetry using a minimal set of human gene transcripts. , 2014, International journal of radiation oncology, biology, physics.

[4]  Chris H. Q. Ding,et al.  Minimum Redundancy Feature Selection from Microarray Gene Expression Data , 2005, J. Bioinform. Comput. Biol..

[5]  Victor L. Brailovsky,et al.  On domain knowledge and feature selection using a support vector machine , 1999, Pattern Recognit. Lett..

[6]  Joshua LaBaer,et al.  Developing Human Radiation Biodosimetry Models: Testing Cross-Species Conversion Approaches Using an Ex Vivo Model System , 2017, Radiation Research.

[7]  Hongyi Zhou,et al.  A knowledge-based approach for predicting gene-disease associations , 2016, Bioinform..

[8]  Y. Benjamini,et al.  Controlling the false discovery rate: a practical and powerful approach to multiple testing , 1995 .

[9]  V. Meineke,et al.  Gene Expression Comparisons Performed for Biodosimetry Purposes on In Vitro Peripheral Blood Cellular Subsets and Irradiated Individuals , 2012, Radiation research.

[10]  Håkon Reikvam,et al.  Expression of the potential therapeutic target CXXC5 in primary acute myeloid leukemia cells - high expression is associated with adverse prognosis as well as altered intracellular signaling and transcriptional regulation , 2014, Oncotarget.

[11]  George C. Runger,et al.  Gene selection with guided regularized random forest , 2012, Pattern Recognit..

[12]  Verónica Bolón-Canedo,et al.  A review of feature selection methods on synthetic data , 2013, Knowledge and Information Systems.

[13]  Suzanne L Wolden,et al.  Prediction of In Vivo Radiation Dose Status in Radiotherapy Patients using Ex Vivo and In Vivo Gene Expression Signatures , 2011, Radiation research.

[14]  Verónica Bolón-Canedo,et al.  A review of microarray datasets and applied feature selection methods , 2014, Inf. Sci..

[15]  J. Mesirov,et al.  Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. , 1999, Science.

[16]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[17]  Satoru Miyano,et al.  Interaction-Based Feature Selection for Uncovering Cancer Driver Genes Through Copy Number-Driven Expression Level , 2017, J. Comput. Biol..

[18]  Matthew A. Coleman,et al.  Candidate protein biodosimeters of human exposure to ionizing radiation , 2006, International journal of radiation biology.