Recognizing Pattern and Rule of Mutation Signatures Corresponding to Cancer Types.

Lei Chen,Zhaoyuan Fang,Xiaoyong Pan,Tao Zeng,Xianchao Zhou,Yu-Hang Zhang,Yu-Dong Cai,Tao Huang

doi:10.3389/fcell.2021.712931

Abstract

Cancer has been generally defined as a cluster of systematic malignant pathogenesis involving abnormal cell growth. Genetic mutations derived from environmental factors and inherited genetics trigger the initiation and progression of cancers. Although several well-known factors affect cancer, mutation features and rules that affect cancers are relatively unknown due to limited related studies. In this study, a computational investigation on mutation profiles of cancer samples in 27 types was given. These profiles were first analyzed by the Monte Carlo Feature Selection (MCFS) method. A feature list was thus obtained. Then, the incremental feature selection (IFS) method adopted such list to extract essential mutation features related to 27 cancer types, find out 207 mutation rules and construct efficient classifiers. The top 37 mutation features corresponding to different cancer types were discussed. All the qualitatively analyzed gene mutation features contribute to the distinction of different types of cancers, and most of such mutation rules are supported by recent literature. Therefore, our computational investigation could identify potential biomarkers and prediction rules for cancers in the mutation signature level.

Highlights

Cancer is generally defined as a systematic disease with abnormal cell proliferation and invasion potentials
All mutation features were used in this case, indicating that each mutation type gave less or more contributions to the distinction of different cancer types
The repeated incremental pruning to produce error reduction (RIPPER) classifier was much better in this regard because it can learn some classification rules for explaining and understanding particular cancer differences

Summary

Introduction

Cancer is generally defined as a systematic disease with abnormal cell proliferation and invasion potentials. The general symptoms of cancer include cough, weight loss, lump, and abnormal bleeding, depending on the pathological regions of cancer. Such symptoms are common but not specific in cancers, which may be shared in other diseases. Genetic factors from either noxious environmental factors or inherited variations trigger the initiation and progression of cancers (Anand et al, 2008; Tang et al, 2018). The regulation and functioning of genetic alterations vary at different omics levels with alternative pathological potentials.

Methods

Results

Discussion

Conclusion