Analysis of Expression Pattern of snoRNAs in Different Cancer Types with Machine Learning Algorithms.

Xiaoyong Pan,Xiao-Hua Hu,Yu-Dong Cai,Lei Chen,Tao Huang,Kai-Yan Feng,Xiang-Yin Kong,Yu-Hang Zhang

doi:10.3390/ijms20092185

Abstract

Small nucleolar RNAs (snoRNAs) are a new type of functional small RNAs involved in the chemical modifications of rRNAs, tRNAs, and small nuclear RNAs. It is reported that they play important roles in tumorigenesis via various regulatory modes. snoRNAs can both participate in the regulation of methylation and pseudouridylation and regulate the expression pattern of their host genes. This research investigated the expression pattern of snoRNAs in eight major cancer types in TCGA via several machine learning algorithms. The expression levels of snoRNAs were first analyzed by a powerful feature selection method, Monte Carlo feature selection (MCFS). A feature list and some informative features were accessed. Then, the incremental feature selection (IFS) was applied to the feature list to extract optimal features/snoRNAs, which can make the support vector machine (SVM) yield best performance. The discriminative snoRNAs included HBII-52-14, HBII-336, SNORD123, HBII-85-29, HBII-420, U3, HBI-43, SNORD116, SNORA73B, SCARNA4, HBII-85-20, etc., on which the SVM can provide a Matthew’s correlation coefficient (MCC) of 0.881 for predicting these eight cancer types. On the other hand, the informative features were fed into the Johnson reducer and repeated incremental pruning to produce error reduction (RIPPER) algorithms to generate classification rules, which can clearly show different snoRNAs expression patterns in different cancer types. The analysis results indicated that extracted discriminative snoRNAs can be important for identifying cancer samples in different types and the expression pattern of snoRNAs in different cancer types can be partly uncovered by quantitative recognition rules.

Highlights

Small nucleolar RNAs are a group of functional small RNAs that mainly participate in the chemical modifications of other functional RNAs, such as rRNAs, tRNAs, and small nuclear RNAs [1,2,3]
On the basis of some machine learning methods, we identified a group of effective core regulatory snoRNAs that may participate in tumorigenesis and contribute to the distinction of the eight candidate tumor subtypes, but we set up a series of qualitative rules for the precise recognition of different subtypes according to the expression pattern of the optimal parameters
As we have mentioned above, snoRNAs are a group of small nucleolar RNAs that generally contribute to the regulation of RNA modifications

Summary

Introduction

Small nucleolar RNAs (snoRNAs) are a group of functional small RNAs that mainly participate in the chemical modifications of other functional RNAs, such as rRNAs, tRNAs, and small nuclear RNAs [1,2,3]. SnoRNAs interact with at least four protein molecules; snoRNAs form a complicated RNA/protein complex for further modification processes [6,7]. After the precise identification and localization processes mediated by this antisense element, the four interacted protein molecules around snoRNAs are located at the correct physical position and contribute to the chemical modification of the target bases [7]. The basic biological processes of snoRNAs are relatively similar based on the objective modification pattern of pre-rRNAs; snoRNAs can be classified into two major subtypes, namely, C/D and H/ACA boxes [9,10]. According to recent publications [11,12], the direct methylation modification sites of C/D snoRNAs are located precisely 5 bp upstream of the D box of snoRNPs, reflecting the accurate positioning and effective regulatory contribution of snoRNAs

Methods

Results

Conclusion