LUADpp: an effective prediction model on prognosis of lung adenocarcinomas based on somatic mutational features

Abstract

BackgroundLung adenocarcinoma is the most common type of lung cancers. Whole-genome sequencing studies disclosed the genomic landscape of lung adenocarcinomas. however, it remains unclear if the genetic alternations could guide prognosis prediction. Effective genetic markers and their based prediction models are also at a lack for prognosis evaluation.MethodsWe obtained the somatic mutation data and clinical data for 371 lung adenocarcinoma cases from The Cancer Genome Atlas. The cases were classified into two prognostic groups (3-year survival), and a comparison was performed between the groups for the somatic mutation frequencies of genes, followed by development of computational models to discrete the different prognosis.ResultsGenes were found with higher mutation rates in good (≥ 3-year survival) than in poor (< 3-year survival) prognosis group of lung adenocarcinoma patients. Genes participating in cell-cell adhesion and motility were significantly enriched in the top gene list with mutation rate difference between the good and poor prognosis group. Support Vector Machine models with the gene somatic mutation features could well predict prognosis, and the performance improved as feature size increased. An 85-gene model reached an average cross-validated accuracy of 81% and an Area Under the Curve (AUC) of 0.896 for the Receiver Operating Characteristic (ROC) curves. The model also exhibited good inter-stage prognosis prediction performance, with an average AUC of 0.846 for the ROC curves.ConclusionThe prognosis of lung adenocarcinomas is related with somatic gene mutations. The genetic markers could be used for prognosis prediction and furthermore provide guidance for personal medicine.Electronic supplementary materialThe online version of this article (10.1186/s12885-019-5433-7) contains supplementary material, which is available to authorized users.

A Multi-Gene Model Effectively Predicts the Overall Prognosis of Stomach Adenocarcinomas With Large Genetic Heterogeneity Using Somatic Mutation Features

“…It was noted that all the 52 genes with most significant difference showed higher mutation rates in the good prognosis group of TCGA cases stratified by the median survival time (Figure 2A). It was consistent with previous findings in lung adenocarcinomas (Yu et al, 2019). Recently, a study identified the association between higher MUC16 gene mutation rate and better prognosis of STADs.…”

“…For a variety of tumors, prognosis has been reported to be associated with somatic gene mutations ( Loi et al, 2013 ; Lee et al, 2017 ; Zhang et al, 2017 ; Cho et al, 2018 ; Yu et al, 2019 ). Despite the large heterogeneity of STADs, common genetic factors (e.g., BRCA2 and MUC16) were still identified and reported to be associated with the prognosis ( Chen et al, 2015 ; Li et al, 2018 ).…”

The Role of Artificial Intelligence in the Diagnosis and Prognosis of Renal Cell Tumors

“…To increase the accuracy of predictions in prognosis, data on mutations have been integrated with those of gene expression [ 91 , 92 , 93 ]. However, it is difficult to train an expert system to consider the mutation load of a sample since the effect of a mutation depends on the function of the gene and its position along the gene [ 94 ].…”

Novel strategies in immune checkpoint inhibitor drug development: How far are we from the paradigm shift?

“…Finally, there has been increasing development and integration of novel computational omics methods into the IO clinical arena, particularly pertaining to artificial intelligence (AI). Machine learning (ML) is an AI tool that can process enormous amounts of imported data, enabling classification with predictive capabilities, as it has been shown to predict genotypes associated with poor prognosis 150 . AI may be applied to cellular phenotype detection and classification to determine the presence of a particular disease or its outcome.…”