Pattern Recognition Receptor based Prognostic Biomarkers for predicting Survival of Uterine Corpus Endometrial Cancer Patients
Kaur, D.; Arora, C.; Raghava, G. P. S.
Show abstract
In this study, we attempted to identify prognostic biomarkers for predicting survival risk of uterine corpus endometrial cancer (UCEC) patients from the gene expression profile of pattern recognition receptors (PRRs). A wide range of feature selection techniques have been tried, including network-based methods to identify a small number of genes from 331 PRR genes. Firstly, a risk stratification model has been developed using biomarker genes selected using a network-based approach and achieved HR=1.37 with p=0.294. Secondly, we developed a risk stratification model using biomarker of seven genes obtained from clustering and achieved HR=9.14 and p= 1.49x10-12. Finally, we developed various combinatorial models using biomarker of 15 PRR genes that were significantly associated with UCEC survival. We found that a multiple genes-based risk stratification model using nine genes (CLEC1B, CLEC3A, IRF7, CTSB, FCN1, RIPK2, NLRP10, NLRP9 and SARM1) gave the best result (HR=10.70, p=1.1x10-12, C=0.76, log-rank-p=8.15x10-14). The performance of this model improved significantly when we used the clinical stage of patients in combination with the expression of nine genes and achieved HR=15.23 (p=2.21x10-7, C=0.78, log-rank-p=2.76x10-17). We also developed classification models that can classify high-risk patients (survive [≤] 4.3 years) and low-risk patients (survive > 4.3 years) and achieved AUROC of 0.86. It was observed that specific genes are positively correlated with overall survival of UCEC patients. Based on these observations, we identified potential immunotherapeutic agents for treating UCEC patients.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Machine learning based prediction of recurrence after curative resection for rectal cancer 96%
- Prognostic Biomarkers for Predicting Papillary Thyroid Carcinoma Patients at High Risk Using Nine Genes of Apoptotic Pathway 95%
- Classification of early and late stage Liver Hepatocellular Carcinoma patients from their genomics and epigenomics profiles. 95%
Similar papers in this journal
- Classification models for Invasive Ductal Carcinoma Progression, based on gene expression data-trained supervised machine learning 97%
- Discovering Key Transcriptomic Regulators in Pancreatic Ductal Adenocarcinoma using Dirichlet Process Gaussian Mixture Model 95%
- Machine learning prediction of antiviral-HPV protein interactions for anti-HPV pharmacotherapy 95%
Similar papers in this journal
- Risk assessment of cancer patients based on HLA-I alleles, neobinders and expression of cytokines 95%
- Development of an absolute assignment predictor for triple-negative breast cancer subtyping using machine learning approaches 95%
- Unsupervised Discovery of Risk Profiles on Negative and Positive COVID-19 Hospitalized Patients 95%
Similar papers in this journal
- Gene expression profiles and pathway enrichment analysis to identification of differentially expressed gene and signaling pathways in epithelial ovarian cancer based on high-throughput RNA-seq data 95%
- Development and validation of a six-RNA binding proteins prognostic signature and candidate drugs for prostate cancer 94%
- PanClassif: Improving pan cancer classification of single cell RNA-seq using machine learning 93%
Similar papers in this journal
- Systems biomedicine of primary and metastatic colorectal cancer reveals potential therapeutic targets 96%
- Patient stratification of clear cell renal cell carcinoma using the global transcription factor activity landscape derived from RNA-seq data 96%
- Absence of Glutathione S-Transferase Theta 1 Gene is Significantly Associated with Breast Cancer Susceptibility in Pakistani Population and Poor Overall Survival in Breast Cancer Patients: A Case-Control and Case Series Analysis 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.