scholarly journals Landscape of Immune Microenvironment in Epithelial Ovarian Cancer and Establishing Risk Model by Machine Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Shi-yi Liu ◽  
Rong-hui Zhu ◽  
Zi-tao Wang ◽  
Wei Tan ◽  
Li Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ovarian Cancer ◽  
Epithelial Ovarian Cancer ◽  
Immune Cells ◽  
Risk Model ◽  
Dominant Role ◽  
Immune Checkpoints ◽  
Support Vector ◽  
Lasso Regression ◽  
High Infiltration

Background. Epithelial ovarian cancer (EOC) is an extremely lethal gynecological malignancy and has the potential to benefit from the immune checkpoint blockade (ICB) therapy, whose efficacy highly depends on the complex tumor microenvironment (TME). Method and Result. We comprehensively analyze the landscape of TME and its prognostic value through immune infiltration analysis, somatic mutation analysis, and survival analysis. The results showed that high infiltration of immune cells predicts favorable clinical outcomes in EOC. Then, the detailed TME landscape of the EOC had been investigated through “xCell” algorithm, Gene set variation analysis (GSVA), cytokines expression analysis, and correlation analysis. It is observed that EOC patients with high infiltrating immune cells have an antitumor phenotype and are highly correlated with immune checkpoints. We further found that dendritic cells (DCs) may play a dominant role in promoting the infiltration of immune cells into TME and forming an antitumor immune phenotype. Finally, we conducted machine-learning Lasso regression, support vector machines (SVMs), and random forest, identifying six DC-related prognostic genes (CXCL9, VSIG4, ALOX5AP, TGFBI, UBD, and CXCL11). And DC-related risk stratify model had been well established and validated. Conclusion. High infiltration of immune cells predicted a better outcome and an antitumor phenotype in EOC, and the DCs might play a dominant role in the initiation of antitumor immune cells. The well-established risk model can be used for prognostic prediction in EOC.

scholarly journals Value of radiomics in differential diagnosis of chromophobe renal cell carcinoma and renal oncocytoma

2019 ◽  
Vol 45 (10) ◽  
pp. 3193-3201 ◽  
Author(s):  
Yajuan Li ◽  
Xialing Huang ◽  
Yuwei Xia ◽  
Liling Long
Keyword(s):  
Machine Learning ◽  
Differential Diagnosis ◽  
Cell Carcinoma ◽  
Area Under The Curve ◽  
Image Features ◽  
Renal Tumors ◽  
Support Vector ◽  
Svm Classifier ◽  
Renal Oncocytoma ◽  
Lasso Regression

Abstract Purpose To explore the value of CT-enhanced quantitative features combined with machine learning for differential diagnosis of renal chromophobe cell carcinoma (chRCC) and renal oncocytoma (RO). Methods Sixty-one cases of renal tumors (chRCC = 44; RO = 17) that were pathologically confirmed at our hospital between 2008 and 2018 were retrospectively analyzed. All patients had undergone preoperative enhanced CT scans including the corticomedullary (CMP), nephrographic (NP), and excretory phases (EP) of contrast enhancement. Volumes of interest (VOIs), including lesions on the images, were manually delineated using the RadCloud platform. A LASSO regression algorithm was used to screen the image features extracted from all VOIs. Five machine learning classifications were trained to distinguish chRCC from RO by using a fivefold cross-validation strategy. The performance of the classifier was mainly evaluated by areas under the receiver operating characteristic (ROC) curve and accuracy. Results In total, 1029 features were extracted from CMP, NP, and EP. The LASSO regression algorithm was used to screen out the four, four, and six best features, respectively, and eight features were selected when CMP and NP were combined. All five classifiers had good diagnostic performance, with area under the curve (AUC) values greater than 0.850, and support vector machine (SVM) classifier showed a diagnostic accuracy of 0.945 (AUC 0.964 ± 0.054; sensitivity 0.999; specificity 0.800), showing the best performance. Conclusions Accurate preoperative differential diagnosis of chRCC and RO can be facilitated by a combination of CT-enhanced quantitative features and machine learning.

scholarly journals The Tumor Microenvironment of Epithelial Ovarian Cancer and Its Influence on Response to Immunotherapy

Cancers ◽  
2018 ◽  
Vol 10 (8) ◽  
pp. 242 ◽  
Author(s):  
Galaxia Rodriguez ◽  
Kristianne Galpin ◽  
Curtis McCloskey ◽  
Barbara Vanderhyden
Keyword(s):  
Ovarian Cancer ◽  
Tumor Microenvironment ◽  
Epithelial Ovarian Cancer ◽  
B Lymphocytes ◽  
Immune Cells ◽  
Ovarian Cancer Cell ◽  
Cell Types ◽  
Therapeutic Approaches ◽  
Mutational Burden ◽  
Tumor Mutational Burden

Immunotherapy as a treatment for cancer is a growing field of endeavor but reports of success have been limited for epithelial ovarian cancer. Overcoming the challenges to developing more effective therapeutic approaches lies in a better understanding of the factors in cancer cells and the surrounding tumor microenvironment that limit response to immunotherapies. This article provides an overview of some ovarian cancer cell features such as tumor-associated antigens, ovarian cancer-derived exosomes, tumor mutational burden and overexpression of immunoinhibitory molecules. Moreover, we describe relevant cell types found in epithelial ovarian tumors including immune cells (T and B lymphocytes, Tregs, NK cells, TAMs, MDSCs) and other components found in the tumor microenvironment including fibroblasts and the adipocytes in the omentum. We focus on how those components may influence responses to standard treatments or immunotherapies.

Immune cells of the epithelial ovarian cancer microenvironment

2021 ◽  
pp. 67-78
Author(s):  
Varvara Nikolaevna Zhurman ◽  
Natalia Gennadevna Plekhova ◽  
Ekaterina Valeryevna Eliseeva
Keyword(s):  
Ovarian Cancer ◽  
Epithelial Ovarian Cancer ◽  
Immune Cells ◽  
Ovarian Tumor ◽  
Biologically Active ◽  
Cancer Microenvironment ◽  
Review Of The Literature ◽  
Prognostic Role ◽  
Active Substances

The article is a review of the literature, which analyzes the data on the role of cells of the immune system, cytokines and other biologically active substances secreted by them in the interstitial space of an ovarian tumor. The emphasis is made on the mechanism of realization by immune cells of the stimulating and suppressing action on the development of the tumor. Considerable attention is paid to the prognostic role of immune cells in the development of epithelial ovarian cancer.

scholarly journals Association of Soluble B7-H4 and Circulating Tumor Cells in Blood of Advanced Epithelial Ovarian Cancer Patients

2021 ◽  
Vol 11 ◽  
Author(s):  
Pawel Mach ◽  
Rainer Kimmig ◽  
Sabine Kasimir-Bauer ◽  
Paul Buderath
Keyword(s):  
Ovarian Cancer ◽  
Epithelial Ovarian Cancer ◽  
Tumor Cells ◽  
Circulating Tumor Cells ◽  
Survival Data ◽  
Liquid Biopsy ◽  
Therapy Response ◽  
Predictive Biomarkers ◽  
Prognostic Biomarkers ◽  
Immune Checkpoints

IntroductionEpithelial ovarian cancer (EOC) is the deadliest gynecologic malignancy worldwide. Reliable predictive biomarkers are urgently needed to estimate the risk of relapse and to improve treatment management. Soluble immune-checkpoints in EOC are promising molecules serving as prognostic biomarkers accessible via liquid biopsy. We thus, aimed at elucidating the role of sB7-H4 in EOC.Material and MethodsWe analyzed soluble serum B7-H4 (sB7-H4) using ELISA and circulating tumor cells (CTCs) in blood applying the AdnaTest OvarianCancer in 85 patients suffering from advanced EOC. Findings were correlated with clinical parameters as well as survival data.ResultssB7-H4 was detectable in 14.1% patients, CTCs in 32.9% patients and simultaneous presence of CTCs and sB7-H4 was found in 7% patients, respectively. Although no association between sB7-H4 and CTC could be documented, each of them served as independent predictive factors for overall survival (OS).ConclusionsB7-H4 and CTCs are independent prognostic biomarkers for impaired survival in EOC. As they are easily accessible via liquid biopsy, they may be of potential benefit for the prediction of therapy response and survival for EOC patients.

scholarly journals What’s in a Trauma? Using Machine Learning to Unpack What Makes an Event Traumatic

2021 ◽  
Author(s):  
Payton J. Jones
Keyword(s):  
Machine Learning ◽  
Empirical Work ◽  
Ensemble Classifier ◽  
Political Orientation ◽  
Support Vector ◽  
Physical Injury ◽  
Lasso Regression ◽  
Interaction Terms ◽  
Out Of Sample ◽  
And Gender

What differentiates a trauma from an event that is merely upsetting? Wildly different definitions of trauma have been used across various settings. Yet there is a dearth of empirical work examining the features of events that individuals use to define an event as a ‘trauma’. First, a group of qualitative coders classified features (e.g., actual physical injury, loss of possessions) of 600 event descriptions (e.g., “was verbally harassed by a boss”, “watched a video of an adult being shot and killed”). Next, across two studies, machine learning was used to predict whether individuals rated event descriptions as ‘trauma’ or ‘traumatic’ in over 100,000 judgment tasks. In Study 1, examining continuous ratings, a cross-validated LASSO regression with interaction terms provided the best out-of-sample predictions (r2 = 0.76), outperforming ridge regression, support vector regression, and linear regression. In Study 2, using binary judgments, a random forest model accurately predicted out-of-sample individual responses (AUC = 0.96), outperform-ing a neural network and an AdaBoost ensemble classifier. The most important event features across the two studies were actual death, threat of death, and the presence of a human perpetrator. The most important human features in predicting judgments were political orientation and gender.

Meta-analysis of Cellular Toxicity for Graphene via Data-Mining the Literature and Machine Learning

2021 ◽  
Author(s):  
Ying Ma ◽  
Jianli Wang ◽  
Jingying Wu ◽  
Chuxuan Tong ◽  
Ting Zhang
Keyword(s):  
Machine Learning ◽  
Detection Method ◽  
Meta Analysis ◽  
Analysis Approach ◽  
Support Vector ◽  
Learning Tools ◽  
Lasso Regression ◽  
Data Set ◽  
Cellular Toxicity ◽  
Published Evidence

Abstract Background: Due to graphene is currently incorporated into various consumer product and numerous new applications, determining the relationships between physicochemical properties of graphene and their toxicity is a prominent concern for environmental and health risk analysis. Data from the literatures suggested that graphene exposure may resulted in cytotoxicity, however, the toxicity data of graphene is still insufficient to point out its side because of the complexity and heterogeneity of available data on potential risks of graphene. Methods and Results: Here, we developed a meta-analysis approach for assembling published evidence on cytotoxicity based on 792 related publications, 986 cell survival rate samples, 762 IC50 samples, and 100 LDH release samples. In this study, among corresponding attributes, we proved that the cytotoxicity of graphene assessed in the form of cell viability, IC50 and LDH can be primarily predicted from exposure dose and detection method, diameter and surface modification, detection method and organ source, respectively. Furthermore, this paper provides guidance regarding three optional data sets for above-mentioned three endpoints that are chiefly related to cellular toxicity for future studies and cross-validation studies based on machine learning tools including Random Forests (RFs), Support Vector Machine (SVM), LASSO regression, and Elastic Net were conducted for result verification. Conclusions: In summary, our study indicates that following rigorous methodological experimental and extract approaches accompanied with suitable machine learning tools, in parallel to continuous addition to reliable data set developed using our meta-analysis approach, will offer higher predictive power and accuracy, and also help to provide effective information on designing safe graphene.

scholarly journals Machine learning for ovarian cancer: lasso regression-based predictive model of early mortality in patients with stage I and stage II ovarian cancer

2020 ◽  
Author(s):  
Robert Chen
Keyword(s):  
Machine Learning ◽  
Ovarian Cancer ◽  
Predictive Model ◽  
Learning Algorithm ◽  
Malignant Neoplasm ◽  
Mortality Prediction ◽  
Stage I ◽  
Lasso Regression ◽  
Left Testis ◽  
Prediction Of Mortality

ABSTRACTWhile machine learning has shown promise in prediction of mortality in situations such as intensive care units, there is limited evidence of its application towards ovarian cancer.In this study, we extracted clinical covariates from a cohort of 273 patients with stage I and II ovarian cancer, and trained a machine learning algorithm, L2-regularized logistic regression, on the set of patients in prediction problem for mortality less than 20 months, representing the 25th percentile of overall survival.Our model achieves an AUC of 0.621, accuracy 0.761, sensitivity 0.130, positive predictive value 0.659, and F1 score 0.216. This study serves as a proof of concept for a predictive model customized towards mortality prediction for malignant neoplasm of the left testis, and can be adapted and generalized to related tumors such as spermatic cord and scrotal tumor types.

scholarly journals The Heterogeneity of Infiltrating Macrophages in Metastatic Osteosarcoma and Its Correlation with Immunotherapy

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Zhanchao Wang ◽  
Huiqiao Wu ◽  
Yu Chen ◽  
Huajiang Chen ◽  
Wen Yuan ◽  
...  
Keyword(s):  
Immune Cells ◽  
Risk Model ◽  
Disease Free Survival ◽  
Immune Checkpoints ◽  
Free Survival ◽  
Primary Osteosarcoma ◽  
Kaplan Meier ◽  
Metastatic Osteosarcoma ◽  
Related Risk ◽  
Disease Free

Background. Metastatic osteosarcoma is a common and fatal bone tumor. Several studies have found that tumor-infiltrating immune cells play pivotal roles in the progression of metastatic osteosarcoma. However, the heterogeneity of infiltrating immune cells across metastatic and primary osteosarcoma remains unclear. Methods. Immune infiltration analysis was carried out via the “ESTIMATE” and “xCell” algorithms in primary and metastatic osteosarcoma. Then, we evaluated the prognostic value of infiltrating immune cells in 85 osteosarcomas through the Kaplan–Meier (K-M) and receiver operating characteristic (ROC) curve. Infiltrations of macrophage M1 and M2 were evaluated in metastatic osteosarcoma, as well as their correlation with immune checkpoints. Macrophage-related prognostic genes were identified through Weighted Gene Coexpression Network Analysis (WGCNA), Lasso analysis, and Random Forest algorithm. Finally, a macrophage-related risk model had been constructed and validated. Results. Macrophages, especially the macrophage M1, sparingly infiltrated in metastatic compared with the primary osteosarcoma and predicted the worse overall survival (OS) and disease-free survival (DFS). Macrophage M1 was positively correlated with immune checkpoints PDCD1, CD274 (PD-L1), PDCD1LG2, CTLA4, and TIGIT. In addition, four macrophage-related prognostic genes (IL10, VAV1, CD14, and CCL2) had been identified, and the macrophage-related risk model had been validated to be reliable for evaluating prognosis in osteosarcoma. Simultaneously, the risk score showed a strong correlation with several immune checkpoints. Conclusion. Macrophages potentially contribute to the regulation of osteosarcoma metastasis. It can be used as a candidate marker for metastatic osteosarcoma’ prognosis and immune checkpoints blockades (ICBs) therapy. We constructed a macrophage-related risk model through machine-learning, which might help us evaluate patients’ prognosis and response to ICBs therapy.

Sign in / Sign up

Export Citation Format

Share Document