Dataset Information

Identification of combinations of somatic mutations that predict cancer survival and immunotherapy benefit.

ABSTRACT: Cancer evolves through the accumulation of somatic mutations over time. Although several methods have been developed to characterize mutational processes in cancers, these have not been specifically designed to identify mutational patterns that predict patient prognosis. Here we present CLICnet, a method that utilizes mutational data to cluster patients by survival rate. CLICnet employs Restricted Boltzmann Machines, a type of generative neural network, which allows for the capture of complex mutational patterns associated with patient survival in different cancer types. For some cancer types, clustering produced by CLICnet also predicts benefit from anti-PD1 immune checkpoint blockade therapy, whereas for other cancer types, the mutational processes associated with survival are different from those associated with the improved anti-PD1 survival benefit. Thus, CLICnet has the ability to systematically identify and catalogue combinations of mutations that predict cancer survival, unveiling intricate associations between mutations, survival, and immunotherapy benefit.

SUBMITTER: Gussow AB

PROVIDER: S-EPMC8127965 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundGastric cancer (GC) ranks as the fifth most prevalent malignancy and the second leading cause of oncologic mortality globally. Despite staging guidelines and standard treatment protocols, significant heterogeneity exists in patient survival and response to therapy for GC. Thus, an increasing number of research have examined prognostic models recently for screening high-risk GC patients.MethodsWe studied DEGs between GC tissues and adjacent non-tumor tissues in GEO and TCGA datasets. Then the candidate DEGs were further screened in TCGA cohort through univariate Cox regression analyses. Following this, LASSO regression was utilized to generate prognostic model of DEGs. We used the ROC curve, Kaplan-Meier curve, and risk score plot to evaluate the signature's performance and prognostic power. ESTIMATE, xCell, and TIDE algorithm were used to explore the relationship between the risk score and immune landscape relationship. As a final step, nomogram was developed in this study, utilizing both clinical characteristics and a prognostic model.ResultsThere were 3211 DEGs in TCGA, 2371 DEGs in GSE54129, 627 DEGs in GSE66229, and 329 DEGs in GSE64951 selected as candidate genes and intersected with to obtain DEGs. In total, the 208 DEGs were further screened in TCGA cohort through univariate Cox regression analyses. Following this, LASSO regression was utilized to generate prognostic model of 6 DEGs. External validation showed favorable predictive efficacy. We studied interaction between risk models, immunoscores, and immune cell infiltrate based on six-gene signature. The high-risk group exhibited significantly elevated ESTIMATE score, immunescore, and stromal score relative to low-risk group. The proportions of CD4+ memory T cells, CD8+ naive T cells, common lymphoid progenitor, plasmacytoid dentritic cell, gamma delta T cell, and B cell plasma were significantly enriched in low-risk group. According to TIDE, the TIDE scores, exclusion scores and dysfunction scores for low-risk group were lower than those for high-risk group. As a final step, nomogram was developed in this study, utilizing both clinical characteristics and a prognostic model.ConclusionIn conclusion, we discovered a 6 gene signature to forecast GC patients' OS. This risk signature proves to be a valuable clinical predictive tool for guiding clinical practice.

Dataset Information

Identification of combinations of somatic mutations that predict cancer survival and immunotherapy benefit.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets