AUTHOR=Keshavarz-Rahaghi Faeze , Pleasance Erin , Kolisnik Tyler , Jones Steven J. M. 

TITLE=A p53 transcriptional signature in primary and metastatic cancers derived using machine learning

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.987238

DOI=10.3389/fgene.2022.987238

ISSN=1664-8021

ABSTRACT=The tumor suppressor gene, TP53, has the highest rate of mutation among all genes in human cancer. This transcription factor plays an essential role in the regulation of many cellular processes. Mutations in TP53 result in loss of wild type p53 function in a dominant negative manner. Although TP53 is a well-studied gene, the transcriptome modifications caused by the mutations in this gene have not yet been explored in a pan-cancer study using both primary and metastatic samples. In this work, we used a random forest model to stratify tumor samples based on TP53 mutational status and detected a p53 transcriptional signature. We hypothesize that the existence of this signature is due to the loss of wild type p53 function which is universal across primary and metastatic tumors as well as different tumor types. Additionally, we showed that the algorithm successfully detected this signature in samples with silent mutations that affect correct mRNA splicing. Furthermore, we observed that most of the top important genes in classification extracted from the random forest have known associations with p53 in literature. We suggest the other genes found in this list including GPSM2, OR4N2, CTSL2, SPERT, and RPE65 protein coding genes have a link to p53 which is yet to be uncovered. Our analysis of time on different therapies also revealed that this signature is more effective in detecting patients who can benefit from platinum therapies and taxanes. Our findings delineate a p53 transcriptional signature, and expand knowledge of p53 biology and the genes important in p53 pathways.