Supervised clustering of high-dimensional data using regularized mixture modeling

Abstract

Identifying relationships between genetic variations and their clinical presentations has been challenged by the heterogeneous causes of a disease. It is imperative to unveil the relationship between the high-dimensional genetic manifestations and the clinical presentations, while taking into account the possible heterogeneity of the study subjects.We proposed a novel supervised clustering algorithm using penalized mixture regression model, called component-wise sparse mixture regression (CSMR), to deal with the challenges in studying the heterogeneous relationships between high-dimensional genetic features and a phenotype. The algorithm was adapted from the classification expectation maximization algorithm, which offers a novel supervised solution to the clustering problem, with substantial improvement on both the computational efficiency and biological interpretability. Experimental evaluation on simulated benchmark datasets demonstrated that the CSMR can accurately identify the subspaces on which subset of features are explanatory to the response variables, and it outperformed the baseline methods. Application of CSMR on a drug sensitivity dataset again demonstrated the superior performance of CSMR over the others, where CSMR is powerful in recapitulating the distinct subgroups hidden in the pool of cell lines with regards to their coping mechanisms to different drugs. CSMR represents a big data analysis tool with the potential to resolve the complexity of translating the clinical representations of the disease to the real causes underpinning it. We believe that it will bring new understanding to the molecular basis of a disease and could be of special relevance in the growing field of personalized medicine.

Keywords: disease heterogeneity; mixture modeling; supervised learning.

Figure 1

The motivation of CSMR. Under the same treatment, some patients acquired one mechanism to deal with the drug, (blue), while others picked up another (pink), resulting in different prognoses for the same treatment. The motivation of CSMR is to cluster the patients in a supervised fashion and examine what are the genes (yellow) that are selected in tumor progression that lead to the different drug resistance subtypes of patients, and their functions (network).

Figure 2

Time consumption of CSMR, and ICC on simulation data for (left) and (right), and over 100 repetitions; error bars indicate standard deviations.

Figure 3

The distributions of the RMSE over 100 repetitions for the five methods, for the 24 drugs. The lower the RMSE value, the better the performance. ‘C’,‘I’,‘A’,‘G’ and ‘F’ stand for ‘CSMR’,‘ICC’,‘LASSO’,‘RIDGE’ and ‘Random Forest’.

Figure 4

For each drug, the Venn diagram of the selected genes for different mixing components is shown. The numbers show the size of overlap among the gene sets.