A new research paper was published in Oncotarget on July 19, 2022, entitled “Predicting the Cancer Immunotherapy Response of Intestinal Microbiomes Using Machine Learning Models”.
“In the last decade, the use of cancer immunotherapy aimed at immune checkpoint inhibitors (ICIs) to increase T-cell-mediated cancer cell clearance has significantly improved patient survival. with cancer “.
Cancer immunotherapy has significantly improved patient survival. However, half of the patients do not respond to immunotherapy. Intestinal microbiomes have been linked to the clinical response of patients with melanoma in immunotherapies; however, different taxa have been associated with response status with inconsistent taxa involved between studies.
In this new study, conducted by Hai Liang, Jay-Hyun Jo, Zhiwei Zhang, Margaret A. MacGibeny, Jungmin Han, Diana M. Proctor, Monica E. Taylor, You Che, Paul Juneau, Andrea B. Apolo, John A. McCulloch, Diwakar Davar, Hassane M. Zarour, Amiran K. Dzutsev, Isaac Brownell, Giorgio Trinchieri, James L. Gulley and Heidi H. Kong of the National Institutes of Health Library, National Cancer Institute, National Human Genome Research Institute, West Virginia University, Zimmerman Associates Inc. and the University of Pittsburgh, the researchers used an agnostic approach to the tumor to find common features of the intestinal microbiome response among immunotherapy patients with different advanced cancers.
“Using the combined dataset, we trained and validated models with machine learning algorithms to predict patients’ clinical responses, followed by validation of cross-sequencing platforms using shotgun metagenomic sequencing data.”
A combined meta-analysis of 16S rRNA gene sequencing data from a cohort of mixed tumors and three published immunotherapy gut microbiome data sets from different cohorts of melanoma patients found certain intestinal bacterial taxa correlated with response status. in immunotherapy regardless of tumor type.
Using multivariate selbal analysis, the researchers identified two separate groups of bacterial genera associated with those who respond versus those who do not respond. Statistical models of intestinal microbiome community characteristics showed an accurate prediction of the immunotherapy response in amplicon sequencing data sets and in the validation of cross-sequencing platforms with metagenomic data sets. shotgun.
The results suggest that the initial characteristics of the intestinal microbiome may be predictive of clinical outcomes in cancer patients with immunotherapies, and some of these characteristics may be generalizable to different types of tumors, patient cohorts, and sequencing platforms. The findings show how machine learning models can reveal microbiome-immunotherapy interactions that can ultimately improve the outcomes of cancer patients.
“In conclusion, analyzes of our cohort and the combined microbiome dataset have provided a robust assessment of the intestinal microbiomes of immunotherapy patients. The development of reliable models offers an additional opportunity to distinguish and predict those responding to immunotherapy. However, the interactions between the keys Microbial taxa and host immunity have yet to be elucidated.Lastly, this research will help identify microbial biomarkers or new therapeutic targets to improve outcomes. of immunotherapy and the overall survival of cancer patients “.
Source:
Magazine reference:
Liang, H., et al. (2022) Prediction of the cancer immunotherapy response of intestinal microbiomes using machine learning models. Oncotarget. doi.org/10.18632/oncotarget.28252