Integration of Cancer Genomics Data for Tree‐based Dimensionality Reduction and Cancer Outcome Prediction

Abstract

Accurate outcome prediction is crucial for precision medicine and personalized treatment of cancer. Researchers have found that multi‐dimensional cancer omics studies outperform each data type (mRNA, microRNA, methylation or somatic copy number alteration) study in human disease research. Existing methods leveraging multiple level of molecular data often suffer from various limitations, e. g., heterogeneity, poor robustness or loss of generality. To overcome these limitations, we presented the tree‐based dimensionality reduction approach for the identification of smooth tree graph and developed accurate predictive model for clinical outcome prediction. We demonstrated that 1) Discriminative Dimensionality Reduction via learning a Tree (DDRTree) achieved reduced dimension space tree with statistical significance; 2) Tree based support vector machine (SVM) classifier improved prediction performance of cancer recurrence as compared to t‐test based SVM classifier; 3) Tree based SVM classifier was robust with regard to the different number of multi‐markers; 4) Combining multiple omics data improved prediction performance of cancer recurrence as compared to a single‐omics data; and 5) Tree based SVM classifier achieved similar or better prediction performance when compared to the features from state‐of‐the‐art feature selection methods. Our results demonstrated great potential of the tree‐based dimensionality reduction approach based clinical outcome prediction.

SCInter: A comprehensive single-cell transcriptome integration database for human and mouse

“…To study and simulate the dynamic biological processes of cells, SCInter adopted the popular software Monocle to produce a trajectory of cell's development [38] , [39] . Firstly, we used DDRTree to reduce the dimensionality of the dataset [40] . The orderCells function of Monocle was then performed to re-order the cells.…”

Deciphering the tumour microenvironment of clear cell renal cell carcinoma: Prognostic insights from programmed death genes using machine learning

“…This sophisticated tool relies on gene counts and expressions to infer the trajectory of cellular differentiation. Employing the DDRTree method, we skillfully selected differentially expressed genes (DEGs) 23 within the clustered results while simultaneously reducing the dimensionality of the data. To delve into intercellular communication networks, we availed ourselves of the rich resource known as the CellChatDB.human database.…”

Intratumoral Microbiota-Host Interactions Shape the Variability of Lung Adenocarcinoma and Lung Squamous Cell Carcinoma in Recurrence and Metastasis

“…Besides, with the development of sequencing technology, there have been several studies using machine learning models combined with multi-omics data to predict recurrence or metastasis in LUSC patients. Shi et al predicted recurrence or metastasis in LUSC patients by integrating information on mRNA, microRNA (miRNA), methylation, and copy number variation in LUSC patients in combination with the support vector machines (SVM) classifier ( 29 ). In addition, Yang et al used SVM with decision tree models to predict tumor recurrence in LUSC patients by integrating clinical data and information on mutations and copy number variants in 15 genes in LUSC patients ( 10 ).…”