scholarly journals Deep learning-based tumor microenvironment segmentation is predictive of tumor mutations and patient survival in non-small-cell lung cancer

2021 ◽  
Author(s):  
Łukasz Rączkowski ◽  
Iwona Paśnik ◽  
Michał Kukiełka ◽  
Marcin Nicoś ◽  
Magdalena A Budzinska ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Tumor Microenvironment ◽  
Patient Survival ◽  
Digital Pathology ◽  
Gene Mutations ◽  
The Cancer Genome Atlas ◽  
Cancer Tissue ◽  
Segmented Images ◽  
Spatial Composition ◽  
Main Determinants

Despite the fact that tumor microenvironment (TME) and gene mutations are the main determinants of progression of the deadliest cancer in the world - lung cancer - their interrelations are not well understood. Digital pathology data provide a unique insight into the spatial composition of the TME. Here, we generated 23,199 image patches from 55 hematoxylin-and-eosin (H&E)-stained lung cancer tissue sections and annotated them into 9 different tissue classes. Using this dataset, we trained a deep neural network and used it to segment 467 lung cancer H&E images downloaded from The Cancer Genome Atlas (TCGA) database. We used the segmented images to compute human interpretable features reflecting the heterogeneous composition of the TME, and successfully utilized them to predict patient survival (c-index 0.723) and cancer gene mutations (largest AUC 73.5% for PDGFRB). Our approach can be generalized to different cancer types to inform precision medicine strategies.

scholarly journals p53 nuclear immunostaining and gene mutations in non-small-cell lung cancer and their effects on patient survival

1995 ◽  
Vol 6 ◽  
pp. S9-S13 ◽  
Author(s):  
T. Mitsudomi ◽  
T. Oyama ◽  
K. Nishida ◽  
A. Ogami ◽  
T. Osaki ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Cell Lung Cancer ◽  
Patient Survival ◽  
Gene Mutations ◽  
Small Cell ◽  
Small Cell Lung

scholarly journals Uncovering Prognosis-Related Genes and Pathways by Multi-Omics Analysis in Lung Cancer

Biomolecules ◽  
2020 ◽  
Vol 10 (4) ◽  
pp. 524 ◽  
Author(s):  
Ken Asada ◽  
Kazuma Kobayashi ◽  
Samuel Joutard ◽  
Masashi Tubaki ◽  
Satoshi Takahashi ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Patient Survival ◽  
Clinical Information ◽  
The Cancer Genome Atlas ◽  
Support Vector ◽  
Rna Expression ◽  
Bioinformatics Analyses ◽  
Expression Levels ◽  
Individual Level ◽  
Omics Analysis

Lung cancer is one of the leading causes of death worldwide. Therefore, understanding the factors linked to patient survival is essential. Recently, multi-omics analysis has emerged, allowing for patient groups to be classified according to prognosis and at a more individual level, to support the use of precision medicine. Here, we combined RNA expression and miRNA expression with clinical information, to conduct a multi-omics analysis, using publicly available datasets (the cancer genome atlas (TCGA) focusing on lung adenocarcinoma (LUAD)). We were able to successfully subclass patients according to survival. The classifiers we developed, using inferred labels obtained from patient subtypes showed that a support vector machine (SVM), gave the best classification results, with an accuracy of 0.82 with the test dataset. Using these subtypes, we ranked genes based on RNA expression levels. The top 25 genes were investigated, to elucidate the mechanisms that underlie patient prognosis. Bioinformatics analyses showed that the expression levels of six out of 25 genes (ERO1B, DPY19L1, NCAM1, RET, MARCH1, and SLC7A8) were associated with LUAD patient survival (p < 0.05), and pathway analyses indicated that major cancer signaling was altered in the subtypes.

scholarly journals Microbiome-TP53 Gene Interaction in Human Lung Cancer

2018 ◽  
Author(s):  
K. Leigh Greathouse ◽  
James R. White ◽  
Ashely J. Vargas ◽  
Valery V. Bliskovsky ◽  
Jessica A. Beck ◽  
...  
Keyword(s):  
Lung Cancer ◽  
16S Rrna ◽  
Cigarette Smoke ◽  
The Cancer Genome Atlas ◽  
Human Lung Cancer ◽  
Normal Lung ◽  
Diagnostic Tools ◽  
Cancer Tissue ◽  
Lung Carcinogenesis ◽  
Bacterial Gene

AbstractBackgroundLung cancer is the leading cancer diagnosis worldwide and the number one cause of cancer deaths. Exposure to cigarette smoke, the primary risk factor in lung cancer, reduces epithelial barrier integrity and increases susceptibility to infections. Herein, we hypothesized that somatic mutations together with cigarette smoke generate a dysbiotic microbiota that is associated with lung carcinogenesis. Using lung tissue from controls (n=33) and cancer cases (n=143), we conducted 16S rRNA bacterial gene sequencing, with RNA-seq data from lung cancer cases in The Cancer Genome Atlas (n=1112) serving as the validation cohort.ResultsOverall, we demonstrate a lower alpha diversity in normal lung as compared to non-tumor adjacent or tumor tissue. In squamous cell carcinoma (SCC) specifically, a separate group of taxa were identified, in which Acidovorax was enriched in smokers (P =0.0013). Acidovorax temporans was identified by fluorescent in situ hybridization within tumor sections, and confirmed by two separate 16S rRNA strategies. Further, these taxa, including Acidovorax, exhibited higher abundance among the subset of SCC cases with TP53 mutations, an association not seen in adenocarcinomas (AD).ConclusionsThe results of this comprehensive study show both a microbiome-gene and microbiome-exposure interactions in SCC lung cancer tissue. Specifically, tumors harboring TP53 mutations, which can damage epithelial function, have a unique bacterial consortia which is higher in relative abundance in smoking-associated SCC. Given the significant need for clinical diagnostic tools in lung cancer, this study may provide novel biomarkers for early detection.

scholarly journals Identification of Novel microRNA Prognostic Markers Using Cascaded Wx, a Neural Network-Based Framework, in Lung Adenocarcinoma Patients

Cancers ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 1890 ◽  
Author(s):  
Jeong Seon Kim ◽  
Sang Hoon Chun ◽  
Sungsoo Park ◽  
Sieun Lee ◽  
Sae Eun Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Cancer Cells ◽  
Epithelial To Mesenchymal Transition ◽  
Patient Survival ◽  
Survival Rates ◽  
The Cancer Genome Atlas ◽  
Lung Cancer Cells ◽  
Mesenchymal Transition ◽  
Next Generation Sequencing Technology

The evolution of next-generation sequencing technology has resulted in a generation of large amounts of cancer genomic data. Therefore, increasingly complex techniques are required to appropriately analyze this data in order to determine its clinical relevance. In this study, we applied a neural network-based technique to analyze data from The Cancer Genome Atlas and extract useful microRNA (miRNA) features for predicting the prognosis of patients with lung adenocarcinomas (LUAD). Using the Cascaded Wx platform, we identified and ranked miRNAs that affected LUAD patient survival and selected the two top-ranked miRNAs (miR-374a and miR-374b) for measurement of their expression levels in patient tumor tissues and in lung cancer cells exhibiting an altered epithelial-to-mesenchymal transition (EMT) status. Analysis of miRNA expression from tumor samples revealed that high miR-374a/b expression was associated with poor patient survival rates. In lung cancer cells, the EMT signal induced miR-374a/b expression, which, in turn, promoted EMT and invasiveness. These findings demonstrated that this approach enabled effective identification and validation of prognostic miRNA markers in LUAD, suggesting its potential efficacy for clinical use.

scholarly journals Identification of topological features in renal tumor microenvironment associated with patient survival

2017 ◽  
Vol 34 (6) ◽  
pp. 1024-1030 ◽  
Author(s):  
Jun Cheng ◽  
Xiaokui Mo ◽  
Xusheng Wang ◽  
Anil Parwani ◽  
Qianjin Feng ◽  
...  
Keyword(s):  
Tumor Microenvironment ◽  
Digital Pathology ◽  
Papillary Renal Cell Carcinoma ◽  
The Cancer Genome Atlas ◽  
Superior Performance ◽  
Supplementary Information ◽  
Topological Features ◽  
Unlimited Growth ◽  
Cell Patterns ◽  
Cancer Genome Atlas

Abstract Motivation As a highly heterogeneous disease, the progression of tumor is not only achieved by unlimited growth of the tumor cells, but also supported, stimulated, and nurtured by the microenvironment around it. However, traditional qualitative and/or semi-quantitative parameters obtained by pathologist’s visual examination have very limited capability to capture this interaction between tumor and its microenvironment. With the advent of digital pathology, computerized image analysis may provide a better tumor characterization and give new insights into this problem. Results We propose a novel bioimage informatics pipeline for automatically characterizing the topological organization of different cell patterns in the tumor microenvironment. We apply this pipeline to the only publicly available large histopathology image dataset for a cohort of 190 patients with papillary renal cell carcinoma obtained from The Cancer Genome Atlas project. Experimental results show that the proposed topological features can successfully stratify early- and middle-stage patients with distinct survival, and show superior performance to traditional clinical features and cellular morphological and intensity features. The proposed features not only provide new insights into the topological organizations of cancers, but also can be integrated with genomic data in future studies to develop new integrative biomarkers. Availability and implementation https://github.com/chengjun583/KIRP-topological-features Supplementary information Supplementary data are available atBioinformatics online.

scholarly journals TP53 Status, Patient Sex, and the Immune Response as Determinants of Lung Cancer Patient Survival

Cancers ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 1535 ◽  
Author(s):  
Donald Freudenstein ◽  
Cassandra Litchfield ◽  
Franco Caramia ◽  
Gavin Wright ◽  
Benjamin J. Solomon ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Transforming Growth Factor Beta ◽  
Transforming Growth Factor ◽  
Gene Mutations ◽  
Lung Squamous Cell Carcinoma ◽  
Tp53 Gene ◽  
Suppressor Gene ◽  
The Cancer Genome Atlas ◽  
Immune Signatures ◽  
Tp53 Gene Mutations

Lung cancer poses the greatest cancer-related death risk and males have poorer outcomes than females, for unknown reasons. Patient sex is not a biological variable considered in lung cancer standard of care. Correlating patient genetics with outcomes is predicted to open avenues for improved management. Using a bioinformatics approach across non-small cell lung cancer (NSCLC) subtypes, we identified where patient sex, mutation of the major tumor suppressor gene, Tumour protein P53 (TP53), and immune signatures stratified outcomes in lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC), among datasets of The Cancer Genome Atlas (TCGA). We exposed sex and TP53 gene mutations as prognostic for LUAD survival. Longest survival in LUAD occurred among females with wild-type (wt) TP53 genes, high levels of immune infiltration and enrichment for pathway signatures of Interferon Gamma (INF-γ), Tumour Necrosis Factor (TNF) and macrophages-monocytes. In contrast, poor survival in men with LUAD and wt TP53 genes corresponded with enrichment of Transforming Growth Factor Beta 1 (TGFB1, hereafter TGF-β) and wound healing signatures. In LUAD with wt TP53 genes, elevated gene expression of immune checkpoint CD274 (hereafter: PD-L1) and also protein 53 (p53) negative-regulators of the Mouse Double Minute (MDM)-family predict novel avenues for combined immunotherapies. LUSC is dominated by male smokers with TP53 gene mutations, while a minor population of TCGA LC patients with wt TP53 genes unexpectedly had the poorest survival, suggestive of a separate etiology. We conclude that advanced approaches to LUAD and LUSC therapy lie in the consideration of patient sex, TP53 gene mutation status and immune signatures.

Sign in / Sign up

Export Citation Format

Share Document