Cancer driven recognition based on functional regions of protein sequence

Abstract

Identifying cancer drivers is a key challenge in explaining the mechanisms of cancer development and achieving precision medicine. Many ways are provided to identify cancer drivers based on a single mutation site or an entire gene, but a lot of medium-sized functional elements are ignored. The fact that mutations which occur in different regions of a protein sequence have different effects on cancer progression is hypothesized. The invention develops a new function-driven region (frDriver) recognition method based on Bayesian probability and multiple linear regression models to identify protein regions which can regulate gene expression levels and have high functional impact potential. By combining gene expression data and somatic mutation data with functional impact scores (SIFT, PROVEAN)as prior knowledge, we identified cancer-driving regions with the most accurate prediction of gene expression levels. We evaluated the performance of frDriver on TCGA's BRCA and GBM datasets. The results indicate that frDriver identifies known cancer drivers and outperforms the other three state-of-the-art methods (eDriver, ActiveDriver and OncodriveCLUST).

Description

technical field [0001] The invention relates to data mining in bioinformatics, in particular to mining of cancer bioinformatics data. Specifically, it relates to a method for identifying novel functionally driven cancer region correlations based on protein sequence functional regions through Bayesian probability and multiple linear regression models. Background technique [0002] Identification of cancer drivers is a key challenge in explaining cancer mechanisms and enabling precision medicine. There are many approaches to identify cancer drivers based on single mutation sites or entire genes. But they omit a large number of medium-sized functional elements. [0003] Mutations can affect cellular regulatory processes, signaling processes, and more. Due to the complexity of the mutations, different functional effects resulted. Compared with germline cells, somatic cells acquire mutations faster, tens to hundreds of times faster than primary cells. However, only a small s...

AI Technical Summary

Problems solved by technology

[0006] In summary, existing methods do not fully consider the role of a large number of intermediate-sized functional elements in identifying cancer drivers, and rarely estimate the impact of amino acid sequence changes on protein function from comparing individual amino acids and calculate their functional impact scores This direction identifies cancer driver regions

Images