Using Evolutionary Trees for the Colorectal Cancer Prognosis Prediction

Hung-Yu Yan,Dun-Wei Cheng,Meng-Ru Shen,Peng-Chan Lin,Sun-Yuan Hsieh,Hsin-Hung Chou

doi:10.11648/j.cbb.20210901.11

Abstract

The measurement of tree similarity based on structure comparison has been long used in diverse fields. We applied the evolutionary tree method to study the cancer genome. Cancer evolutionary trees, representing cancer diversity, provide information on the clonal evolution and the clinical outcome of cancer patients. This study considered 107 colorectal cancer (CRC) patients who received deep targeted sequencing of cancer tissues. The evolutionary trees of individual cancer patients were reconstructed from genome sequencing data based on variant allele frequencies (VAFs) of point mutations and small insertions or deletions (indels). The main purpose of this study was to predict cancer recurrence. We mapped the structure of a cancer evolutionary tree to a rooted tree and developed a canonical-form transformation for solving tree isomorphism to ensure that each patient has a unique tree structure. We proposed an algorithm for comparing tree similarity in terms of cost calculation between evolutionary structure trees. The cost was calculated using the node position, tree size (or number of nodes), tree height, node depth, number of descendants of the node (the size of the subtree with the node as a root), and relationship of the node with other nodes. After tree similarity comparison, the cancer patients were clustered into two groups through k-means clustering. The clustering information indicated that the evolutionary structure trees were associated with gender and tumor invasion stage. Several machine-learning strategies including random forest, support vector machine (SVM), bagging, and boosting were used to predict cancer recurrence in these patients. Our results revealed that combining the clustering information of evolutionary structure trees increased the prediction performance compared with using clinical information alone, and tree similarity comparison can help in the prognostic analysis of cancer patients.

Highlights

Cancer is a disease caused by the accumulation of somatic mutation
The cancer clonal theory states that most tumors originate in a single cell and that tumor progression and clonal expansions are caused by genetic variability; a tumor is the result of clonal evolution [1]
The tumor composition and evolutionary structure can be determined through somatic variant calling by using variant allele frequencies (VAFs) according to the read counts of the tumor and matched normal cell sequences in each patient

Summary

Introduction

Cancer is a disease caused by the accumulation of somatic mutation. Understanding the evolutionary history of tumor growth may provide valuable insights into tumor cell proliferation and survival [2]. Many studies have recently integrated evolutionary theory and genomic data into modern techniques for studying tumor growth and progression [3]. We used the evolutionary tree method to understand tumor progression. The tumor composition and evolutionary structure can be determined through somatic variant calling by using variant allele frequencies (VAFs) according to the read counts of the tumor and matched normal cell sequences in each patient. The VAFs of somatic variants can be used to reconstruct the cancer evolutionary histories as a cancer evolutionary tree, which reflects the somatic variant accumulation in each patient [4, 5]

Objectives

Methods

Results

Conclusion