Using Machine Learning Methods to Study Colorectal Cancer Tumor Micro-Environment and Its Biomarkers

Identification and validation of HOXC6 as a diagnostic biomarker for Ewing sarcoma: insights from machine learning algorithms and in vitro experiments

Introduction

Early diagnosis of Ewing sarcoma (ES) is critical for improving patient prognosis. However, the accurate diagnosis of ES remains challenging, underscoring the need for novel diagnostic biomarkers to enhance diagnostic precision and reliability. This study aimed to identify potential gene expression-based biomarkers for the diagnosis of ES.

Methods

We selected the GSE17679, GSE45544, and GSE68776 datasets from the Gene Expression Omnibus (GEO) database. After correcting for batch effects, we combined ES and normal tissue samples from the GSE17679 and GSE45544 datasets to create a combined cohort. Two-thirds of both the tumor and normal samples from the combined cohort were randomly selected for the training cohort, while the remaining one-third served as the internal validation cohort. Additionally, the GSE68776 dataset was used for external validation. To identify key diagnostic genes, we applied three machine learning algorithms: least absolute shrinkage and selection operator (LASSO), support vector machine recursive feature elimination (SVM-RFE), and random forest (RF).

Results

HOXC6 was identified as a key diagnostic biomarker for ES. It demonstrated strong diagnostic performance across all cohorts, with area under the curve (AUC) values of 0.956 (95% CI: 0.909-0.990) in the training cohort, 0.995 (95% CI: 0.977-1.000) in the internal validation cohort, and 0.966 (95% CI: 0.910-0.999) in the external validation cohort. Functional validation through HOXC6 knockdown in the RD-ES cell line revealed that its suppression significantly inhibited cell proliferation and migration. Furthermore, transcriptome sequencing suggested potential oncogenic mechanisms underlying HOXC6 function.

Discussion

These findings highlight HOXC6 as a promising diagnostic biomarker for ES, demonstrating robust performance across multiple datasets. Additionally, its functional role suggests potential as a therapeutic target.

Construction and Value Analysis of a Prognostic Assessment Model Based on Radiomics and Genetic Data for Colorectal Cancer

Aims/Background Colorectal cancer (CRC) is one of the major global health problems, with high morbidity and mortality, underscoring the need for new diagnostic and prognostic tools. Therefore, this study aims to evaluate the significance of integrating radiomics with genetic data in CRC prognostic assessment and improve the accuracy of prognosis prediction. Methods This study included computed tomography (CT) images from 225 CRC patients and RNA-seq information from 654 patients, obtained from the TICA database. Key radiomics features and genes were identified through radiomics feature extraction, least absolute shrinkage and selection operator (LASSO) regression analysis, and Kaplan-Meier survival analysis. Furthermore, a CRC prognostic model was constructed using these key genes and radiomics features. Results This study identified 170 key radiomics features. Out of them, five were significantly associated with CRC prognosis. Transcriptome data analysis identified 8 key genes, among which the high expressions of Inhibin Subunit Beta B (INHBB), Potassium Voltage-Gated Channel Subfamily Q Member 2 (KCNQ2), and Ubiquilin Like (UBQLNL) were significantly correlated with poor prognosis. Age, tumor stage, pathological T stage, and pathological N stage were determined as independent prognostic factors. Moreover, immune infiltration analysis demonstrated that the immune score of the low-risk group was higher than that of the high-risk group, with significant differences in some immune cells, and key genes were correlated with immune cells. Additionally, the constructed CRC prognostic model incorporating three genes, INHBB, KCNQ2, and UBQLNL, exhibited high prediction accuracy in the validation set, with area under the curve (AUC) values of 0.80, 0.87, and 0.84 at 1-year, 3-year, and 5-year, respectively, indicating good prediction performance and reliability of the model. Conclusion The multimodal data combining radiomics features and gene expression data can improve the accuracy of CRC prognostic assessment, providing a valuable prognostic prediction tool for clinical practice and helping to guide the selection and optimization of treatment regimens.

Multi-center study: ultrasound-based deep learning features for predicting Ki-67 expression in breast cancer

Applying deep learning algorithms to mine ultrasound features of breast cancer and construct a machine learning model that accurately predicts Ki-67 expression level. This multi-center retrospective study analyzed clinical and ultrasound data from 929 breast cancer patients. We integrated deep features from the tumor and peritumoral areas to build a fusion model for predicting Ki-67 expression. The model underwent performance validation on both internal and external test datasets. Its accuracy as well as clinical usefulness were evaluated by diverse statistical metrics. In the ultrasound depth feature model for the tumor area, the Support Vector Machine (SVM) algorithm achieved the highest performance, with an accuracy of 0.782, ROAUC of 0.771 (95% CI 0.704-0.838), sensitivity of 0.905, specificity of 0.543, and F1 score of 0.846. In the depth feature model for the peritumoral area, the Light Gradient Boosting Machine (LightGBM) algorithm demonstrated superior performance, achieving an accuracy of 0.728, ROAUC of 0.623 (95% CI 0.545-0.702), sensitivity of 0.892, specificity of 0.407, and F1 score of 0.813. The SVM algorithm exhibited superior performance in both internal and external test sets when validated the fusion model integrating depth features from tumor and peritumoral area. Internal test set validation in clinical application indicated significantly lower disease-free survival in the high Ki-67 expression group compared to the low expression group (P = 0.005). Through comprehensive analysis of breast cancer ultrasound images and the application of machine learning techniques, we developed a highly accurate model for predicting Ki-67 expression levels.

Predicting pathological response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer with two step feature selection and ensemble learning

Patients with locally advanced rectal cancer (LARC) show substantial individual variability and a pronounced imbalance in response distribution to neoadjuvant chemoradiotherapy (nCRT), posing significant challenges to treatment response prediction. This study aims to identify effective predictive biomarkers and develop an ensemble learning-based prediction model to assess the response of LARC patients to nCRT. A two-step feature selection method was developed to identify predictive biomarkers by deriving stable reversal gene pairs through within-sample relative expression orderings (REOs) from LARC patients undergoing nCRT. Preliminary screening utilized four methods-MDFS, Boruta, MCFS, and VSOLassoBag-to form a candidate feature set. Secondary screening ranked these features by permutation importance, applying Incremental Feature Selection (IFS) with an Extreme Gradient Boosting (XGBoost) to determine final predictive gene pairs. The ensemble model BoostForest, combining boosting and bagging, served as the predictive framework, with SHAP employed for interpretability. Through two-step feature selection, the 32-gene pair signature (32-GPS) was established as the final predictive biomarker. In the test set, the model achieved an area under the precision-recall curve (AUPRC) of 0.983 and an accuracy of 0.988. In the validation cohort, the AUPRC was 0.785, with an accuracy of 0.898, indicating strong model performance. The study further demonstrated that BoostForest achieved superior overall performance compared to Random Forest, Support Vector Machine (SVM), and XGBoost. To evaluate the effectiveness of the 32-GPS, its performance was compared with two alternative feature sets: the lasso-gene pair signature (lasso-GPS), derived through lasso regression, and the 15-shared gene pair signature (15-SGPS), consisting of gene pairs identified by all four feature selection methods. The 32-GPS demonstrated superior performance in both comparisons. The two-step feature selection method identified robust predictive biomarkers, and BoostForest outperformed Random Forest, Support Vector Machine, and XGBoost in classification performance and predictive capability.

Identification and Validation of the Potential Key Biomarkers for Atopic Dermatitis Mitochondrion by Learning Algorithms

Purpose

Atopic dermatitis (AD) is a common inflammatory skin condition characterized by erythema and pruritus. Its precise pathogenesis remains unclear, though factors such as genetic predisposition, autoantigen response, allergen exposure, infections, and skin barrier dysfunction are involved. Research suggests a correlation between AD and mitochondrial dysfunction, as well as oxidative stress in skin tissues.

Methods

 Skin sample datasets related to AD (GSE36842, GSE120721, GSE16161, and GSE121212) were retrieved from the GEO database. Differential gene analysis identified differentially expressed genes (DEGs) in AD. Three potential biomarkers-COX17, ACOX2, and ADH1B-were identified using LASSO and Support Vector Machine (SVM) algorithms. These biomarkers were validated through ROC curve analysis, nomogram modeling, calibration curves, and real-time PCR. Immune infiltration analysis assessed correlations of the biomarkers. Additionally, single-cell analysis of the GSE153760 dataset identified nine cell clusters and confirmed expression patterns of the three hub genes.

Results

Differential analysis identified 150 upregulated and 367 downregulated genes. Enrichment analysis revealed significant pathways related to mitochondrial function, oxidative stress, and energy metabolism in skin samples from AD patients. Area under the curve (AUC) values for biomarkers COX17, ACOX2, and ADH1B were 1.000, 0.928, and 0.895, respectively, indicating strong predictive capacity. qPCR results showed COX17 was highly expressed in AD lesions, while ACOX2 and ADH1B were higher in normal skin, consistent with previous findings. Correlation analysis indicated ACOX2 and ADH1B were positively correlated with resting mast cells but negatively with activated T cells and NK cells, while COX17 showed a positive correlation with activated T cells and a negative correlation with resting mast cells.

Conclusion

This study suggests that the hub genes COX17, ACOX2, and ADH1B may serve as potential biomarkers in the pathogenesis of AD. These findings could provide insights for the treatment and prognosis of AD and related inflammatory skin conditions.

Clinical Validation of a Machine Learning-Based Biomarker Signature to Predict Response to Cytotoxic Chemotherapy Alone or Combined with Targeted Therapy in Metastatic Colorectal Cancer Patients: A Study Protocol and Review

Metastatic colorectal cancer (mCRC) is a severe condition with high rates of illness and death. Current treatments are limited and not always effective because the cancer responds differently to drugs in different patients. This research aims to use artificial intelligence (AI) to improve treatment by predicting which therapies will work best for individual patients. By analyzing large sets of patient data and using machine learning, we hope to create a model that can identify which patients will respond to chemotherapy, either alone or combined with other targeted treatments. The study will involve dividing patients into training and validation sets to develop and test the models, avoiding overfitting. Various machine learning algorithms, like random survival forest and neural networks, will be integrated to develop a highly accurate and stable predictive model. The model's performance will be evaluated using statistical measures such as sensitivity, specificity, and the area under the curve (AUC). The aim is to personalize treatments, improve patient outcomes, reduce healthcare costs, and make the treatment process more efficient. If successful, this research could significantly impact the medical community by providing a new tool for better managing and treating mCRC, leading to more personalized and effective cancer care. In addition, we examine the applicability of learning methods to biomarker discovery and therapy prediction by considering recent narrative publications.

Machine Learning-Enabled Non-Invasive Screening of Tumor-Associated Circulating Transcripts for Early Detection of Colorectal Cancer

Colorectal cancer (CRC) is a major cause of cancer-related mortality, highlighting the need for accurate and non-invasive diagnostics. This study assessed the utility of tumor-associated circulating transcripts (TACTs) as biomarkers for CRC detection and integrated these markers into machine learning models to enhance diagnostic performance. We evaluated five models-Generalized Linear Model, Random Forest, Gradient Boosting Machine, Deep Neural Network (DNN), and AutoML-and identified the DNN model as optimal owing to its high sensitivity (85.7%) and specificity (90.9%) for CRC detection, particularly in early-stage cases. Our findings suggest that combining TACT markers with AI-based analysis provides a scalable and precise approach for CRC screening, offering significant advancements in non-invasive cancer diagnostics to improve early detection and patient outcomes.

Oral microbiota as a biomarker for predicting the risk of malignancy in indeterminate pulmonary nodules: a prospective multicenter study

BACKGROUND

Determining the benign or malignant status of indeterminate pulmonary nodules (IPN) with intermediate malignancy risk is a significant clinical challenge. Oral microbiota-lung cancer (LC) interactions have qualified oral microbiota as a promising non-invasive predictive biomarker in IPN.

MATERIALS AND METHODS

Prospectively collected saliva, throat swabs, and tongue coating samples from 1040 IPN patients and 70 healthy controls across three hospitals. Following up, the IPNs were diagnosed as benign (BPN) or malignant pulmonary nodules (MPN). Through 16S rRNA sequencing, bioinformatics analysis, fluorescence in situ hybridization (FISH), and seven machine learning algorithms (support vector machine, logistic regression, naïve Bayes, multi-layer perceptron, random forest, gradient-boosting decision tree, and LightGBM), we revealed the oral microbiota characteristics at different stages of HC-BPN-MPN, identified the sample types with the highest predictive potential, constructed and evaluated the optimal MPN prediction model for predictive efficacy, and determined microbial biomarkers. Additionally, based on the SHAP algorithm interpretation of the ML model's output, we have developed a visualized IPN risk prediction system on the web.

RESULTS

Saliva, tongue coating, and throat swab microbiotas exhibit site-specific characteristics, with saliva microbiota being the optimal sample type for disease prediction. The saliva-LightGBM model demonstrated the best predictive performance (AUC = 0.887, 95%CI: 0.865-0.918), and identified Actinomyces, Rothia, Streptococcus, Prevotella, Porphyromonas , and Veillonella as biomarkers for predicting MPN. FISH was used to confirm the presence of a microbiota within tumors, and external data from a LC cohort, along with three non-IPN disease cohorts, were employed to validate the specificity of the microbial biomarkers. Notably, coabundance analysis of the ecological network revealed that microbial biomarkers exhibit richer interspecies connections within the MPN, which may contribute to the pathogenesis of MPN.

CONCLUSION

This study presents a new predictive strategy for the clinic to determine MPNs from BPNs, which aids in the surgical decision-making for IPN.

Peripheral blood CD8 + CD28+ T cells as predictive biomarkers for treatment response in metastatic colorectal cancer

BACKGROUND

Colorectal cancer (CRC) is a substantial global health burden, with treatment outcomes significantly influenced by the interaction between the immune system and the tumor microenvironment.

OBJECTIVE

This study aims to investigate the role of peripheral blood immune cell subpopulations, particularly CD8+ CD28+ T cells, in predicting treatment response in metastatic CRC patients receiving bevacizumab combined with chemotherapy.

METHODS

A cohort of 45 CRC patients was analyzed. Flow cytometry was utilized to assess immune cell subpopulations.

RESULTS

Higher CD8+ CD28+ T cell counts were associated with better treatment responses, including improved objective response rates. In a murine CRC model, the combination therapy significantly inhibited tumor growth and enhanced immune cell function.

CONCLUSION

These findings highlight the importance of CD8+ CD28+ T cells as potential biomarkers for predicting treatment outcomes in CRC. They also suggest that bevacizumab, when combined with chemotherapy, can modulate immune function and improve clinical efficacy.

Co-expression network and survival analysis of breast cancer inflammation and immune system hallmark genes

The tertiary lymphoid structure (TLS) plays a central role in cancer immune response, and its gene expression pattern, called the TLS signature, has shown prognostic value in breast cancer. The formation of TLS and tumor-associated high endothelial venules (TA-HEVs), responsible for lymphocytic infiltration within the TLS, is associated with the expression of cancer hallmark genes (CHGs) related to immunity and inflammation. In this study, we performed co-expression network analysis of immune- and inflammation-related CHGs to identify predictive genes for breast cancer. In total, 382 immune- and inflammation-related CHGs with high expression variance were extracted from the GSE86166 microarray dataset of patients with breast cancer. CHGs were classified into five modules by applying weighted gene co-expression network analysis. The survival analysis results for each module showed that one module comprising 45 genes was statistically significant for relapse-free and overall survival. Four network properties identified key genes in this module with high prognostic prediction abilities: CD34, CXCL12, F2RL2, JAM2, PROS1, RAPGEF3, and SELP. The prognostic accuracy of the seven genes in breast cancer was synergistic and exceeded that of other predictors in both small and large public datasets. Enrichment analysis predicted that these genes had functions related to leukocyte infiltration of TA-HEVs. There was a positive correlation between key gene expression and the TLS signature, suggesting that gene expression levels are associated with TLS density. Co-expression network analysis of inflammation- and immune-related CHGs allowed us to identify genes that share a standard function in cancer immunity and have a high prognostic predictive value. This analytical approach may contribute to the identification of prognostic genes in TLS.

Identification of the m6A/m5C/m1A methylation modification genes in Alzheimer's disease based on bioinformatic analysis

BACKGROUND

As a progressive neurodegenerative disease, the comprehensive understanding of the pathogenesis of Alzheimer's disease (AD) is yet to be clarified. Modifications in RNA, including m6A/m5C/m1A, affect the onset and progression of many diseases. Consequently, this study focuses on the role of methylation modification in the pathogenesis of AD.

MATERIALS AND METHODS

Three AD-related datasets, namely GSE33000, GSE122063, and GSE44770, were acquired from GEO. Differential analysis of m6A/m5C/m1A regulator genes was conducted. Applying a consensus clustering approach, distinct subtypes within AD were identified as per the expression patterns of relevant differentially expressed genes. Machine learning models were constructed to identify five significant genes from the best model. The analysis of hub gene-based drug regulatory networks and ceRNA regulatory networks was conducted by Cytoscape.

RESULTS

In comparison to non-AD patients, 24 genes were identified as dysregulated in AD patients, and these genes were associated with various immunological characteristics. Two distinct clusters were successfully identified through consensus clustering, with cluster 2 demonstrating higher immune characteristics compared to cluster 1. The performance of four machine learning models was determined by conducting a receiver operating characteristic (ROC) analysis. The analysis revealed that the SVM model achieved the highest AUC value of 0.947. Five genes (YTHDF1, METTL3, DNMT1, DNMT3A, ALKBH1) were selected as the predicted genes. Finally, a hub gene-based Gene-Drug regulatory network and a ceRNA regulatory network were successfully developed.

CONCLUSIONS

The findings offered fresh perspectives on the molecular patterns and immune mechanisms underlying AD, contributing valuable insights into our understanding of this complex neurodegenerative disorder.

Identification of a disulfidptosis-related genes signature for diagnostic and immune infiltration characteristics in endometriosis

Endometriosis (EMs) is the prevalent gynecological disease with the typical features of intricate pathogenesis and immune-related factors. Currently, there is no effective therapeutic intervention for EMs. Disulfidptosis, the cell death pattern discovered recently, may show close relationships to immunity and EMs. In this study, bioinformatics analysis was used to investigate the role of disulfide breakdown related genes (DRGs) in EMs. The EMs gene expression matrix was subjected to differential analysis for identifying overlap between differentially expressed genes (DEGs) in EMs and genes associated with disulfide poisoning. Immunoinfiltration analysis was performed. In addition, the association of hub genes with immune cells was examined. Multiple machine learning methods were employed to identify hub genes, construction of predictive models, and validation using external datasets and clinical samples. Totally 15 overlapping genes were identified. Immune-correlation analysis showed that NK cells played a vital role, and these 15 genes were closely related to NK cells. PDLIM1 was further determined as the hub gene through machine learning techniques. Clinical samples and external datasets were adopted for validating the performance in diagnosis. According to the above findings, we built the predictive model, and calculated the AUCs obtained from three external validation datasets to demonstrate the model accuracy. RT-qPCR and IHC analyses were applied to confirm the results. Colony formation was used to verify the effect of PDLIM1 on the proliferation of primary EMs cells. A strong correlation between disulfidptosis and EMs was identified in this study, highlighting its close correlation with the immune microenvironment. Moreover, our results shed new lights on exploring biomarkers and potential therapeutic targets for EMs.

Integration of transcriptomics and machine learning for insights into breast cancer: exploring lipid metabolism and immune interactions

Background

Breast cancer (BRCA) represents a substantial global health challenge marked by inadequate early detection rates. The complex interplay between the tumor immune microenvironment and fatty acid metabolism in BRCA requires further investigation to elucidate the specific role of lipid metabolism in this disease.

Methods

We systematically integrated nine machine learning algorithms into 184 unique combinations to develop a consensus model for lipid metabolism-related prognostic genes (LMPGS). Additionally, transcriptomics analysis provided a comprehensive understanding of this prognostic signature. Using the ESTIMATE method, we evaluated immune infiltration among different risk subgroups and assessed their responsiveness to immunotherapy. Tailored treatments were screened for specific risk subgroups. Finally, we verified the expression of key genes through in vitro experiments.

Results

We identified 259 differentially expressed genes (DEGs) related to lipid metabolism through analysis of the cancer genome atlas program (TCGA) database. Subsequently, via univariate Cox regression analysis and C-index analysis, we developed an optimal machine learning algorithm to construct a 21-gene LMPGS model. We used optimal cutoff values to divide the lipid metabolism prognostic gene scores into two groups according to high and low scores. Our study revealed distinct biological functions and mutation landscapes between high-scoring and low-scoring patients. The low-scoring group presented a greater immune score, whereas the high-scoring group presented enhanced responses to both immunotherapy and chemotherapy drugs. Single-cell analysis highlighted significant upregulation of CPNE3 in epithelial cells. Moreover, by employing molecular docking, we identified niclosamide as a potential targeted therapeutic drug. Finally, our experiments demonstrated high expression of MTMR9 and CPNE3 in BRCA and their significant correlation with prognosis.

Conclusion

By employing bioinformatics and diverse machine learning algorithms, we successfully identified genes associated with lipid metabolism in BRCA and uncovered potential therapeutic agents, thereby offering novel insights into the mechanisms and treatment strategies for BRCA.

Identification and Analysis of Potential Biomarkers Associated with Neutrophil Extracellular Traps in Cervicitis

Early diagnosis of cervicitis is important. Previous studies have found that neutrophil extracellular traps (NETs) play pro-inflammatory and anti-inflammatory roles in many diseases, suggesting that they may be involved in the inflammation of the uterine cervix and NETs-related genes may serve as biomarkers of cervicitis. However, what NETs-related genes are associated with cervicitis remains to be determined. Transcriptome analysis was performed using samples of exfoliated cervical cells from 15 patients with cervicitis and 15 patients without cervicitis as the control group. First, the intersection of differentially expressed genes (DEGs) and neutrophil extracellular trap-related genes (NETRGs) were taken to obtain genes, followed by functional enrichment analysis. We obtained hub genes through two machine learning algorithms. We then performed Artificial Neural Network (ANN) and nomogram construction, confusion matrix, receiver operating characteristic (ROC), gene set enrichment analysis (GSEA), and immune cell infiltration analysis. Moreover, we constructed ceRNA network, mRNA-transcription factor (TF) network, and hub genes-drug network. We obtained 19 intersecting genes by intersecting 1398 DEGs and 136 NETRGs. 5 hub genes were obtained through 2 machine learning algorithms, namely PKM, ATG7, CTSG, RIPK3, and ENO1. Confusion matrix and ROC curve evaluation ANN model showed high accuracy and stability. A nomogram containing the 5 hub genes was established to assess the disease rate in patients. The correlation analysis revealed that the expression of ATG7 was synergistic with RIPK3. The GSEA showed that most of the hub genes were related to ECM receptor interactions. It was predicted that the ceRNA network contained 2 hub genes, 3 targeted miRNAs, and 27 targeted lnRNAs, and that 5 mRNAs were regulated by 28 TFs. In addition, 36 small molecule drugs that target hub genes may improve the treatment of cervicitis. In this study, five hub genes (PKM, ATG7, CTSG, RIPK3, ENO1) provided new directions for the diagnosis and treatment of patients with cervicitis.

Identifying Explainable Machine Learning Models and a Novel SFRP2+ Fibroblast Signature as Predictors for Precision Medicine in Ovarian Cancer

Ovarian cancer (OC) is a type of malignant tumor with a consistently high mortality rate. The diagnosis of early-stage OC and identification of functional subsets in the tumor microenvironment are essential to the development of patient management strategies. However, the development of robust models remains unsatisfactory. We aimed to utilize artificial intelligence and single-cell analysis to address this issue. Two independent datasets were screened from the Gene Expression Omnibus (GEO) database and processed to obtain overlapping differentially expressed genes (DEGs) in stage II-IV vs. stage I diseases. Three explainable machine learning algorithms were integrated to construct models that could determine the tumor stage and extract important characteristic genes as diagnostic biomarkers. Correlations between cancer-associated fibroblast (CAF) infiltration and characteristic gene expression were analyzed using TIMER2.0 and their relationship with survival rates was comprehensively explored via the Kaplan-Meier plotter (KM-plotter) online database. The specific expression of characteristic genes in fibroblast subsets was investigated through single-cell analysis. A novel fibroblast subset signature was explored to predict immune checkpoint inhibitor (ICI) response and oncogene mutation through Tumor Immune Dysfunction and Exclusion (TIDE) and artificial neural network algorithms, respectively. We found that Support Vector Machine-Shapley Additive Explanations (SVM-SHAP), Extreme Gradient Boosting (XGBoost), and Random Forest (RF) successfully diagnosed early-stage OC (stage I). The area under the receiver operating characteristic curves (AUCs) of these models exceeded 0.990. Their overlapping characteristic gene, secreted frizzled-related protein 2 (SFRP2), was a risk factor that affected the overall survival of OC patients with stage II-IV disease (log-rank test: p < 0.01) and was specifically expressed in a fibroblast subset. Finally, the SFRP2+ fibroblast signature served as a novel predictor in evaluating ICI response and exploring pan-cancer tumor protein P53 (TP53) mutation (AUC = 0.853, 95% confidence interval [CI]: 0.829-0.877). In conclusion, the models based on SVM-SHAP, XGBoost, and RF enabled the early detection of OC for clinical decision making, and SFRP2+ fibroblast signature used in diagnostic models can inform OC treatment selection and offer pan-cancer TP53 mutation detection.