Development and Clinical Validation of a Seven-Gene Prognostic Signature Based on Multiple Machine Learning Algorithms in Kidney Cancer

Identification of a signature of histone modifiers in kidney renal clear cell carcinoma

Kidney renal clear cell carcinoma (KIRC) is a cancer that is closely associated with epigenetic alterations, and histone modifiers (HMs) are closely related to epigenetic regulation. Therefore, this study aimed to comprehensively explore the function and prognostic value of HMs-based signature in KIRC. HMs were first obtained from top journal. Then, the mRNA expression profiles and clinical information in KIRC samples were downloaded from The Cancer Genome Atlas (TCGA) database and Gene Expression Omnibus (GEO) datasets. Cox regression analysis and least absolute shrinkage and selection operator (Lasso) analysis were implemented to find prognosis-related HMs and construct a risk model related to the prognosis in KIRC. Kaplan-Meier analysis was used to determine prognostic differences between high- and low-risk groups. Immune infiltration and drug sensitivity analysis were also performed between high- and low-risk groups. Eventually, 8 HMs were successfully identified for the construction of a risk model in KIRC. The results of the correlation analysis between risk signature and the prognosis showed HMs-based signature has good prognostic value in KIRC. Results of immune analysis of risk models showed there were significant differences in the level of immune cell infiltration and expression of immune checkpoints between high- and low-risk groups. The results of the drug sensitivity analysis showed that the high-risk group was more sensitive to several chemotherapeutic agents such as Sunitinib, Tipifarnib, Nilotinib and Bosutinib than the low-risk group. In conclusion, we successfully constructed HMs-based prognostic signature that can predict the prognosis of KIRC.

Comprehensive prognostic assessment in kidney cancer: A multidimensional approach analyzing Fufang Sanling granules, genetic variants, and immune infiltration

This study delves into the potential therapeutic benefits of Fufang Sanling Granules for kidney cancer, focusing on their active components and the underlying mechanisms of their interaction with cancer-related targets. By constructing a drug-active component-target network based on eight herbs, key active compounds such as kaempferol, quercetin, and linolenic acid were identified, suggesting their pivotal roles in modulating immune responses and cellular signaling pathways relevant to cancer progression. The research further identified 51 central drug-disease genes through comprehensive bioinformatics analyses, implicating their involvement in crucial biological processes and pathways. A novel risk score model, encompassing six genes with significant prognostic value for renal cancer, was established and validated, showcasing its effectiveness in predicting patient outcomes through mutation analysis and survival studies. The model's predictive power was further confirmed by its ability to stratify patients into distinct risk groups with significant survival differences, highlighting its potential as a prognostic tool. Additionally, the study explored the relationship between gene expression within the identified black module and the risk score, uncovering significant associations with the extracellular matrix and immune infiltration patterns. This reveals the complex interplay between the tumor microenvironment and cancer progression. The integration of the risk score with clinical parameters through a nomogram significantly improved the model's predictive accuracy, offering a more comprehensive tool for predicting kidney cancer prognosis. In summary, by combining detailed molecular analyses with clinical insights, this study presents a robust framework for understanding the therapeutic potential of Fufang Sanling Granules in kidney cancer. It not only sheds light on the active components and their interactions with cancer-related genes but also introduces a reliable risk score model, paving the way for personalized treatment strategies and improved patient management in the future.

Early prediction of growth patterns after pediatric kidney transplantation based on height-related single-nucleotide polymorphisms

BACKGROUND

Growth retardation is a common complication of chronic kidney disease in children, which can be partially relieved after renal transplantation. This study aimed to develop and validate a predictive model for growth patterns of children with end-stage renal disease (ESRD) after kidney transplantation using machine learning algorithms based on genomic and clinical variables.

METHODS

A retrospective cohort of 110 children who received kidney transplants between May 2013 and September 2021 at the First Affiliated Hospital of Zhengzhou University were recruited for whole-exome sequencing (WES), and another 39 children who underwent transplant from October 2021 to March 2022 were enrolled for external validation. Based on previous studies, we comprehensively collected 729 height-related single-nucleotide polymorphisms (SNPs) in exon regions. Seven machine learning algorithms and 10-fold cross-validation analysis were employed for model construction.

RESULTS

The 110 children were divided into two groups according to change in height-for-age Z -score. After univariate analysis, age and 19 SNPs were incorporated into the model and validated. The random forest model showed the best prediction efficacy with an accuracy of 0.8125 and an area under curve (AUC) of 0.924, and also performed well in the external validation cohort (accuracy, 0.7949; AUC, 0.796).

CONCLUSIONS

A model with good performance for predicting post-transplant growth patterns in children based on SNPs and clinical variables was constructed and validated using machine learning algorithms. The model is expected to guide clinicians in the management of children after renal transplantation, including the use of growth hormone, glucocorticoid withdrawal, and nutritional supplementation, to alleviate growth retardation in children with ESRD.

Quantitative proteomics reveals pregnancy prognosis signature of polycystic ovary syndrome women based on machine learning

OBJECTIVE

We aimed to screen and construct a predictive model for pregnancy loss in polycystic ovary syndrome (PCOS) patients through machine learning methods.

METHODS

We obtained the endometrial samples from 33 PCOS patients and 7 healthy controls at the Reproductive Center of the Second Hospital of Lanzhou University from September 2019 to September 2020. Liquid chromatography tandem mass spectrometry (LCMS/MS) was conducted to identify the differentially expressed proteins (DEPs) of the two groups. Gene Ontology (GO) as well as Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis were performed to analyze the related pathways and functions of the DEPs. Then, we used machine learning methods to screen the feature proteins. Multivariate Cox regression analysis was also conducted to establish the prognostic models. The performance of the prognostic model was then evaluated by the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA). In addition, the Bootstrap method was conducted to verify the generalization ability of the model. Finally, linear correlation analysis was performed to figure out the correlation between the feature proteins and clinical data.

RESULTS

Four hundred and fifty DEPs in PCOS and controls were screened out, and we obtained some pathways and functions. A prognostic model for the pregnancy loss of PCOS was established, which has good discrimination and generalization ability based on two feature proteins (TIA1, COL5A1). Strong correlation between clinical data and proteins were identified to predict the reproductive outcome in PCOS.

CONCLUSION

The model based on the TIA1 and COL5A1 protein could effectively predict the occurrence of pregnancy loss in PCOS patients and provide a good theoretical foundation for subsequent research.

Multi-center validation of an immune-related lncRNA signature for predicting survival and immune status of patients with renal cell carcinoma: an integrating machine learning-derived study

BACKGROUND

Long noncoding RNAs (lncRNAs) have been reported to play an important role in tumor immune modification. Nonetheless, the clinical implication of immune-associated lncRNAs in renal cell carcinoma (RCC) remains to be further explored.

METHODS

76 combinations of machine learning algorithms were integrated to develop and validate a machine learning-derived immune-related lncRNA signature (MDILS) in five independent cohorts (n = 801). We collected 28 published signatures and collated clinical variables for comparison with MDILS to verify its efficacy. Subsequently, molecular mechanisms, immune status, mutation landscape, and pharmacological profile were further investigated in different stratified patients.

RESULTS

Patients with high MDILS displayed worse overall survival than those with low MDILS. The MDILS could independently predict overall survival and convey robust performance across five cohorts. MDILS has a significantly better performance compared with traditional clinical variables and 28 published signatures. Patients with low MDILS exhibited more abundant immune infiltration and higher potency of immunotherapeutic response, while patients with high MDILS might be more sensitive to multiple chemotherapeutic drugs (e.g., sunitinib and axitinib).

CONCLUSION

MDILS is a robust and promising tool to facilitate clinical decision-making and precision treatment of RCC.

Micro-inflammation related gene signatures are associated with clinical features and immune status of fibromyalgia

BACKGROUND

Fibromyalgia (FM) is a multifaceted disease. Along with the genetic, environmental and neuro-hormonal factors, inflammation has been assumed to have role in the pathogenesis of FM. The aim of the present study was to explore the differences in clinical features and pathophysiology of FM patients under different inflammatory status.

METHODS

The peripheral blood gene expression profile of FM patients in the Gene Expression Omnibus database was downloaded. Differentially expressed inflammatory genes were identified, and two molecular subtypes were constructed according to these genes used unsupervised clustering analysis. The clinical characteristics, immune features and pathways activities were compared further between the two subtypes. Then machine learning was used to perform the feature selection and construct a classification model.

RESULTS

The patients with FM were divided into micro-inflammation and non-inflammation subtypes according to 54 differentially expressed inflammatory genes. The micro-inflammation group was characterized by more major depression (p = 0.049), higher BMI (p = 0.021), more active dendritic cells (p = 0.010) and neutrophils. Functional enrichment analysis showed that innate immune response and antibacterial response were significantly enriched in micro-inflammation subtype (p < 0.050). Then 5 hub genes (MMP8, ENPP3, MAP2K3, HGF, YES1) were screened thought three feature selection algorithms, an accurate classifier based on the 5 hub DEIGs and 2 clinical parameters were constructed using support vector machine model. Model scoring indicators such as AUC (0.945), accuracy (0.936), F1 score (0.941), Brier score (0.079) and Hosmer-Lemeshow goodness-of-fit test (χ2 = 4.274, p = 0.832) proved that this SVM-based classifier was highly reliable.

CONCLUSION

Micro-inflammation status in FM was significantly associated with the occurrence of depression and activated innate immune response. Our study calls attention to the pathogenesis of different subtypes of FM.

Artificial Intelligence in Urooncology: What We Have and What We Expect

INTRODUCTION

Artificial intelligence is transforming healthcare by driving innovation, automation, and optimization across various fields of medicine. The aim of this study was to determine whether artificial intelligence (AI) techniques can be used in the diagnosis, treatment planning, and monitoring of urological cancers.

METHODOLOGY

We conducted a thorough search for original and review articles published until 31 May 2022 in the PUBMED/Scopus database. Our search included several terms related to AI and urooncology. Articles were selected with the consensus of all authors.

RESULTS

Several types of AI can be used in the medical field. The most common forms of AI are machine learning (ML), deep learning (DL), neural networks (NNs), natural language processing (NLP) systems, and computer vision. AI can improve various domains related to the management of urologic cancers, such as imaging, grading, and nodal staging. AI can also help identify appropriate diagnoses, treatment options, and even biomarkers. In the majority of these instances, AI is as accurate as or sometimes even superior to medical doctors.

CONCLUSIONS

AI techniques have the potential to revolutionize the diagnosis, treatment, and monitoring of urologic cancers. The use of AI in urooncology care is expected to increase in the future, leading to improved patient outcomes and better overall management of these tumors.

A comprehensive analysis of the FOX family for predicting kidney renal clear cell carcinoma prognosis and the oncogenic role of FOXG1

Previous studies have confirmed that the forkhead box (FOX) superfamily of transcription factors regulates tumor progression and metastasis in multiple cancer. The purpose of this study was to develop a model based on FOX family genes for predicting kidney renal clear cell carcinom (KIRC) prognosis. We downloaded the transcriptional profiles and clinical data of KIRC patients from the Cancer Genome Atlas (TCGA) and International Cancer Genome Consortium (ICGC) datasets. To build a new prognosis model, we screened prognosis-related FOX family genes using Lasso regression and Multivariate Cox regression analyses. Receiver operating characteristic (ROC) curves were used to evaluate model performance. Additionally, a prognostic nomogram was developed using clinical information and selected genes to improve the accuracy of prognostic prediction. We also investigated whether prognosis-related FOX family genes are related to the immune response in KIRC. Finally, we validated the oncogenic role of FOXG1 in KIRC using an in vitro tumor function assay. Six prognosis-related FOX family genes were screened: FOXO1, FOXM1, FOXK2, FOXG1, FOXA1, and FOXD1. The ROC curves indicated that our model was capable of making accurate predictions for 1-, 3-, and 5-year overall survival (OS). The nomogram further improved the accuracy of prognostic predictions. In addition, compared to those in patients with low-risk scores, high-risk scores predicted a decreased level of immune cell infiltration and a lower immune response rate. Moreover, the results of in vitro studies confirmed that FOXG1 supports the proliferation and invasion of KIRC.

Prognostic value of dysadherin in cancer: A systematic review and meta-analysis

Cancer is a leading cause of death worldwide and novel prognostic factors are reported with increasing numbers. Systematic reviews and meta-analyses on cumulative research data are crucial in estimating the true prognostic value of proposed factors. Dysadherin (FXYD Domain Containing Ion Transport Regulator 5; FXYD5) is a cell membrane glycoprotein that modulates Na+, K+-ATPase activity and cell-cell adhesion. It is abundantly expressed in a variety of cancer cells, but only in a limited number of normal cells and its levels are increased in many different tumor types. The expression or level of dysadherin has been suggested as an independent predictor for metastasis and poor prognosis by number of studies, yet we lack a definitive answer. In this study, we systematically evaluated the prognostic value of dysadherin in cancer and summarized the current knowledge on the subject. PubMed, Scopus, Web of Science and relevant clinical trial and preprint databases were searched for relevant publications and PRISMA and REMARK guidelines were applied in the process. After a careful review, a total of 23 original research articles were included. In each study, dysadherin was pointed as a marker for poor prognosis. Meta-analyses revealed 3- and 1.5-fold increases in the risk of death (fixed effects HR 3.08, 95% CI 1.88-5.06, RR 1.47, 95% CI 1.06-2.05 on overall survival, respectively) for patients with high (>50%) tumoral FXYD5 level. In many studies, a connection between dysadherin expression or level and metastatic behavior of the cancer as well as inverse correlation with E-cadherin level were reported. Thus, we conclude that dysadherin might be a useful prognostic biomarker in the assessment of disease survival of patients with solid tumors.

Ensemble classification based signature discovery for cancer diagnosis in RNA expression profiles across different platforms

Molecular signatures have been excessively reported for diagnosis of many cancers during the last 20 years. However, false-positive signatures are always found using statistical methods or machine learning approaches, and that makes subsequent biological experiments fail. Therefore, signature discovery has gradually become a non-mainstream work in bioinformatics. Actually, there are three critical weaknesses that make the identified signature unreliable. First of all, a signature is wrongly thought to be a gene set, each component of which keeps differential expressions between or among sample groups. Second, there may be many false-positive genes expressed differentially found, even if samples derived from cancer or normal group can be separated in one-dimensional space. Third, cross-platform validation results of a discovered signature are always poor. In order to solve these problems, we propose a new feature selection framework based on ensemble classification to discover signatures for cancer diagnosis. Meanwhile, a procedure for data transform among different expression profiles across different platforms is also designed. Signatures are found on simulation and real data representing different carcinomas across different platforms. Besides, false positives are suppressed. The experimental results demonstrate the effectiveness of our method.

Identification and validation of an immune-related gene pairs signature for three urologic cancers

Reliable biomarkers are needed to recognize urologic cancer patients at high risk for recurrence. In this study, we built a novel immune-related gene pairs signature to simultaneously predict recurrence for three urologic cancers. We gathered 14 publicly available gene expression profiles including bladder, prostate and kidney cancer. A total of 2,700 samples were classified into the training set (n = 1,622) and validation set (n = 1,078). The 25 immune-related gene pairs signature consisting of 41 unique genes was developed by the least absolute shrinkage and selection operator regression analysis and Cox regression model. The signature stratified patients into high- and low-risk groups with significantly different relapse-free survival in the meta-training set and its subpopulations, and was an independent prognostic factor of urologic cancers. This signature showed a robust ability in the meta-validation and multiple independent validation cohorts. Immune and inflammatory response, chemotaxis and cytokine activity were enriched with genes relevant to the signature. A significantly higher infiltration level of M1 macrophages was found in the high-risk group versus the low-risk group. In conclusion, our signature is a promising prognostic biomarker for predicting relapse-free survival in patients with urologic cancer.