Random Forest Modelling of High-Dimensional Mixed-Type Data for Breast Cancer Classification
Open Access
Abstract
Advances in high-throughput technologies encourage the generation of large amounts of multiomics data to investigate complex diseases, including breast cancer. Given that the aetiologies of such diseases extend beyond a single biological entity, and that essential biological information can be carried by all data regardless of data type, integrative analyses are needed to identify clinically relevant patterns. To facilitate such analyses, we present a permutation-based framework for random forest methods which simultaneously allows the unbiased integration of mixed-type data and assessment of relative feature importance. Through simulation studies and machine learning datasets, the performance of the approach was evaluated. The results showed minimal multicollinearity and limited overfitting. To further assess the performance, the permutation-based framework was applied to high-dimensional mixed-type data from two independent breast cancer cohorts. Reproducibility and robustness of our approach was demonstrated by the concordance in relative feature importance between the cohorts, along with consistencies in clustering profiles. One of the identified clusters was shown to be prognostic for clinical outcome after standard-of-care adjuvant chemotherapy and outperformed current intrinsic molecular breast cancer classifications.Keywords
Funding Information
- Breast Cancer Now (KCL-BCN-Q3)
- Cancer Research UK (C604/A25135)
This publication has 45 references indexed in Scilit:
- Whole-genome sequencing of triple-negative breast cancers in a population-based clinical studyNature Medicine, 2019
- Mechanism of tandem duplication formation in BRCA1-mutant cellsNature, 2017
- HRDetect is a predictor of BRCA1 and BRCA2 deficiency based on mutational signaturesNature Medicine, 2017
- Landscape of somatic mutations in 560 breast cancer whole-genome sequencesNature, 2016
- Prediction of Late Distant Recurrence After 5 Years of Endocrine Treatment: A Combined Analysis of Patients From the Austrian Breast and Colorectal Cancer Study Group 8 and Arimidex, Tamoxifen Alone or in Combination Randomized Trials Using the PAM50 Risk of Recurrence ScoreJournal of Clinical Oncology, 2015
- Comprehensive molecular portraits of human breast tumoursNature, 2012
- The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroupsNature, 2012
- Supervised Risk Predictor of Breast Cancer Based on Intrinsic SubtypesJournal of Clinical Oncology, 2009
- Gene expression patterns of breast carcinomas distinguish tumor subclasses with clinical implicationsProceedings of the National Academy of Sciences, 2001
- Molecular portraits of human breast tumoursNature, 2000