Machine Learning for Future Subtyping of the Tumor Microenvironment of Gastro-Esophageal Adenocarcinomas

Klein, Sebastian; Duda, Dan G.

doi:10.3390/cancers13194919

Cited by 5 publications

(3 citation statements)

References 198 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tumor microenvironment (TME), consisting of a vast variety of innate and adaptive immune cells and non-immune stromal cells such as endothelial cells and mesenchymal cells, profoundly influences cancer progression and therapeutic responses. [9][10][11] Currently, immunotherapy has made revolutionary breakthroughs in the treatment of cancer. However, immunotherapy faces many problems, for example, limited number of patients achieve survival benefits from it in clinic, and treatment resistance.…”

Section: Introductionmentioning

confidence: 99%

AGT May Serve as a Prognostic Biomarker and Correlated with Immune Infiltration in Gastric Cancer

Wu¹,

Zhang²,

Wang³

et al. 2022

IJGM

View full text Add to dashboard Cite

Angiotensinogen (AGT), as a component of the renin-angiotensin system (RAS), is associated with multiple risk factors for gastric cancer (GC). However, the relationship between AGT and tumor-infiltrating lymphocytes in GC remains elusive. Methods: AGT expression was analyzed based on the Cancer Genome Atlas (TCGA) dataset. Kaplan-Meier curve was employed to assess the role of AGT expression in gastric patients' prognosis. The association between AGT expression and tumor immune infiltration was further evaluated via exploring Tumour Immune Estimation Resource (TIMER) and The Gene Expression Profiling Interactive Analysis (GEPIA). We also used multiple public databases to analyse the aberrant methylation of AGT, construct proteinprotein interaction (PPI) and gene ontology (GO) analyses. Results: AGT was overexpressed in GC tissues compared with normal gastric tissues (P<0.05). High AGT expression related with poorer overall survival of patients with GC, especially in advanced GC patients. Immune infiltration analysis revealed that AGT was associated with several immune cells (including B cells, CD4+ T cells, macrophages), and AGT expression was also associated with the markers of NK cells, TAMs, Tregs, and so on (all P<0.05). Methylation analysis indicated that hypomethylation may lead to abnormal upregulation of the AGT. GO analysis showed that AGT and its related genes were enriched in systemic arterial blood pressure by hormone, regulation of blood volume by renin-angiotensin, NIK/NF-kappaB signaling, ficolin-1-rich granule and so on. Conclusion: AGT could act as a promising biomarker for prognosis and immune infiltration in GC.

show abstract

Section: Introductionmentioning

confidence: 99%

AGT May Serve as a Prognostic Biomarker and Correlated with Immune Infiltration in Gastric Cancer

Wu¹,

Zhang²,

Wang³

et al. 2022

IJGM

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence (AI)-based systems are increasingly getting better at optimizing treatment decision making for cancer patients [6,[12][13][14][15]. Machine learning (ML), in particular deep learning (DL) techniques can process large-scale data to learn biologically relevant 1 https://www.cancer.gov/about-cancer/understanding/statistics 2 A collection of biomolecules inside living organisms, e.g., genomics, metabolomics, and proteomics patterns, by addressing issues such as the curse of dimensionality and heterogeneity [6].…”

Section: Introductionmentioning

confidence: 99%

Adversary-Aware Multimodal Neural Networks for Cancer Susceptibility Prediction From Multiomics Data

et al. 2022

View full text Add to dashboard Cite

Artificial intelligence (AI) systems are increasingly used in health and personalized care. However, the adoption of data-driven approaches in many clinical settings has been hampered due to their inability to perform in a reliable and safe manner to leverage accurate and trustworthy diagnoses. A critical and challenging usage scenario for AI is aiding the treatment of cancerous conditions. Providing accurate diagnosis for cancer is a challenging problem in precision oncology. Although machine learning (ML)-based approaches are very effective at cancer susceptibility prediction and subsequent treatment recommendations, ML models can be vulnerable to adversarial attacks. Since adversarially weak models can lead to wrong clinical recommendations, such vulnerabilities is more critical -especially when AI-guided systems are used to aid medical doctors. Therefore, it is indispensable that healthcare professionals employ trustworthy AI tools for predicting and assessing disease risks and progression. In this paper, we propose an adversaryaware multimodal convolutional autoencoder (MCAE) model for cancer susceptibility prediction from multi-omics data consisting of copy number variations (CNVs), miRNA expression, and gene expression (GE). Based on different representational learning techniques, the MCAE model learns multimodal feature representations from multi-omics data, followed by classifying the patient cohorts into different cancer types on multimodal embedding space that exhibit similar characteristics in end-to-end setting. To make the MCAE model robust to adversaries and to provide consistent diagnosis, we formulate robustness as a property, such that predictions remain stable with regard to small variations in the input. We study different adversarial attacks scenarios and take both proactive and reactive measures (e.g., adversarial retraining and identification of adversarial inputs). Experiment results show that the MCAE model based on latent representation concatenation (LRC) exhibits high confidence at predicting cancer types, giving an average precision and Matthews correlation coefficient (MCC) scores of 0.9625 and 0.8453, respectively and shows higher robustness when compared and tested with state-of-the-art approaches against different attack scenarios w.r.t. ERM and CLEVER scores. Overall, our study suggests that a well-fitted and adversarially robust model can provide consistent and reliable diagnosis for cancer.

show abstract

“…TME includes immune cells, fibroblasts, endothelial cells, perivascular cells, neurons, and extracellular matrix. There is increasing evidence that TME plays an important role in cell proliferation, cell survival, epithelial–mesenchymal transition (EMT), angiogenesis/lymphangiogenesis immunosuppression, invasion, and metastasis ( 8 , 9 ). TME is a dynamic environment constantly reshaped by tumor and tumor-associated cells to make tumor cells survive well ( 10 ).…”

Section: Introductionmentioning

confidence: 99%

The Role of Tumor Microenvironment in Invasion and Metastasis of Esophageal Squamous Cell Carcinoma

2022

View full text Add to dashboard Cite

Esophageal squamous cell carcinoma (ESCC) is one of the most common cancers in the world, with a high rate of morbidity. The invasion and metastasis of ESCC is the main reason for high mortality. More and more evidence suggests that metastasized cancer cells require cellular elements that contribute to ESCC tumor microenvironment (TME) formation. TME contains many immune cells and stromal components, which are critical to epithelial–mesenchymal transition, immune escape, angiogenesis/lymphangiogenesis, metastasis niche formation, and invasion/metastasis. In this review, we will focus on the mechanism of different microenvironment cellular elements in ESCC invasion and metastasis and discuss recent therapeutic attempts to restore the tumor-suppressing function of cells within the TME. It will represent the whole picture of TME in the metastasis and invasion process of ESCC.

show abstract

Machine Learning for Future Subtyping of the Tumor Microenvironment of Gastro-Esophageal Adenocarcinomas

Cited by 5 publications

References 198 publications

AGT May Serve as a Prognostic Biomarker and Correlated with Immune Infiltration in Gastric Cancer

AGT May Serve as a Prognostic Biomarker and Correlated with Immune Infiltration in Gastric Cancer

Adversary-Aware Multimodal Neural Networks for Cancer Susceptibility Prediction From Multiomics Data

The Role of Tumor Microenvironment in Invasion and Metastasis of Esophageal Squamous Cell Carcinoma

Contact Info

Product

Resources

About