Discovery of Cancer Subtypes Based on Stacked Autoencoder

2020 ◽  
pp. 447-454
Author(s):  
Bo Zhang ◽  
Rui-Fen Cao ◽  
Jing Wang ◽  
Chun-Hou Zheng
Keyword(s):  
Cancer Subtypes ◽  
Stacked Autoencoder

scholarly journals A hierarchical integration deep flexible neural forest framework for cancer subtype classification by integrating multi-omics data

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Jing Xu ◽  
Peng Wu ◽  
Yuehui Chen ◽  
Qingfang Meng ◽  
Hussain Dawood ◽  
...  
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
High Throughput Sequencing ◽  
Omics Data ◽  
Expression Data ◽  
Cancer Subtypes ◽  
Stacked Autoencoder ◽  
Subtype Classification ◽  
Sequencing Technologies ◽  
Cancer Subtype

Abstract Background Cancer subtype classification attains the great importance for accurate diagnosis and personalized treatment of cancer. Latest developments in high-throughput sequencing technologies have rapidly produced multi-omics data of the same cancer sample. Many computational methods have been proposed to classify cancer subtypes, however most of them generate the model by only employing gene expression data. It has been shown that integration of multi-omics data contributes to cancer subtype classification. Results A new hierarchical integration deep flexible neural forest framework is proposed to integrate multi-omics data for cancer subtype classification named as HI-DFNForest. Stacked autoencoder (SAE) is used to learn high-level representations in each omics data, then the complex representations are learned by integrating all learned representations into a layer of autoencoder. Final learned data representations (from the stacked autoencoder) are used to classify patients into different cancer subtypes using deep flexible neural forest (DFNForest) model.Cancer subtype classification is verified on BRCA, GBM and OV data sets from TCGA by integrating gene expression, miRNA expression and DNA methylation data. These results demonstrated that integrating multiple omics data improves the accuracy of cancer subtype classification than only using gene expression data and the proposed framework has achieved better performance compared with other conventional methods. Conclusion The new hierarchical integration deep flexible neural forest framework(HI-DFNForest) is an effective method to integrate multi-omics data to classify cancer subtypes.

Identification of new therapeutic leads for triple negative breast cancer subtypes

Planta Medica ◽  
2015 ◽  
Vol 81 (11) ◽  
Author(s):  
AJ Robles ◽  
L Du ◽  
S Cai ◽  
RH Cichewicz ◽  
SL Mooberry
Keyword(s):  
Breast Cancer ◽  
Triple Negative Breast Cancer ◽  
Triple Negative ◽  
Breast Cancer Subtypes ◽  
Cancer Subtypes ◽  
Therapeutic Leads

Pursuit of the Abscopal Effect

2020 ◽  
Vol 04 (04) ◽  
pp. 369-372
Author(s):  
Paul B. Romesser ◽  
Christopher H. Crane
Keyword(s):  
Tumor Immunology ◽  
Antitumor Immunity ◽  
Clinical Success ◽  
Immune Recognition ◽  
Immune Modulators ◽  
Cancer Subtypes ◽  
The Past ◽  
Tumor Irradiation ◽  
Wide Range ◽  
Tumor Recognition

AbstractEvasion of immune recognition is a hallmark of cancer that facilitates tumorigenesis, maintenance, and progression. Systemic immune activation can incite tumor recognition and stimulate potent antitumor responses. While the concept of antitumor immunity is not new, there is renewed interest in tumor immunology given the clinical success of immune modulators in a wide range of cancer subtypes over the past decade. One particularly interesting, yet exceedingly rare phenomenon, is the abscopal response, characterized by a potent systemic antitumor response following localized tumor irradiation presumably attributed to reactivation of antitumor immunity.

scholarly journals DNA Methylation Based Molecular Subtypes Predict Prognosis in Breast Cancer Patients

2021 ◽  
Vol 28 ◽  
pp. 107327482098851
Author(s):  
Zeng-Hong Wu ◽  
Yun Tang ◽  
Yan Zhou
Keyword(s):  
Breast Cancer ◽  
Dna Methylation ◽  
Molecular Subtypes ◽  
Methylation Status ◽  
The Cancer Genome Atlas ◽  
Training Dataset ◽  
Consensus Clustering ◽  
Breast Cancer Patients ◽  
Cancer Subtypes ◽  
Novel Biomarkers

Background: Epigenetic changes are tightly linked to tumorigenesis development and malignant transformation’ However, DNA methylation occurs earlier and is constant during tumorigenesis. It plays an important role in controlling gene expression in cancer cells. Methods: In this study, we determining the prognostic value of molecular subtypes based on DNA methylation status in breast cancer samples obtained from The Cancer Genome Atlas database (TCGA). Results: Seven clusters and 204 corresponding promoter genes were identified based on consensus clustering using 166 CpG sites that significantly influenced survival outcomes. The overall survival (OS) analysis showed a significant prognostic difference among the 7 groups (p<0.05). Finally, a prognostic model was used to estimate the results of patients on the testing set based on the classification findings of a training dataset DNA methylation subgroups. Conclusions: The model was found to be important in the identification of novel biomarkers and could be of help to patients with different breast cancer subtypes when predicting prognosis, clinical diagnosis and management.

scholarly journals The Ability of Metabolomics to Discriminate Non-Small-Cell Lung Cancer Subtypes Depends on the Stage of the Disease and the Type of Material Studied

Cancers ◽  
2021 ◽  
Vol 13 (13) ◽  
pp. 3314
Author(s):  
Tomasz Kowalczyk ◽  
Joanna Kisluk ◽  
Karolina Pietrowska ◽  
Joanna Godzien ◽  
Miroslaw Kozlowski ◽  
...  
Keyword(s):  
Metabolic Pathways ◽  
Early Stage ◽  
Chronic Obstructive ◽  
Liquid Chromatography Mass Spectrometry ◽  
Obstructive Pulmonary Disease ◽  
Cell Lung Carcinoma ◽  
Cancer Subtypes ◽  
Inflammatory State ◽  
Nsclc Patients

Identification of the NSCLC subtype at an early stage is still quite sophisticated. Metabolomics analysis of tissue and plasma of NSCLC patients may indicate new, and yet unknown, metabolic pathways active in the NSCLC. Our research characterized the metabolomics profile of tissue and plasma of patients with early and advanced NSCLC stage. Samples were subjected to thorough metabolomics analyses using liquid chromatography-mass spectrometry (LC-MS) technique. Tissue and/or plasma samples from 137 NSCLC patients were analyzed. Based on the early stage tissue analysis, more than 200 metabolites differentiating adenocarcinoma (ADC) and squamous cell lung carcinoma (SCC) subtypes as well as normal tissue, were identified. Most of the identified metabolites were amino acids, fatty acids, carnitines, lysoglycerophospholipids, sphingomyelins, plasmalogens and glycerophospholipids. Moreover, metabolites related to N-acyl ethanolamine (NAE) biosynthesis, namely glycerophospho (N-acyl) ethanolamines (GP-NAE), which discriminated early-stage SCC from ADC, have also been identified. On the other hand, the analysis of plasma of chronic obstructive pulmonary disease (COPD) and NSCLC patients allowed exclusion of the metabolites related to the inflammatory state in lungs and the identification of compounds (lysoglycerophospholipids, glycerophospholipids and sphingomyelins) truly characteristic to cancer. Our results, among already known, showed novel, thus far not described, metabolites discriminating NSCLC subtypes, especially in the early stage of cancer. Moreover, the presented results also indicated the activity of new metabolic pathways in NSCLC. Further investigations on the role of NAE biosynthesis pathways in the early stage of NSCLC may reveal new prognostic and diagnostic targets.

scholarly journals Cancer, Retrogenes, and Evolution

Life ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 72
Author(s):  
Klaudia Staszak ◽  
Izabela Makałowska
Keyword(s):  
Specific Resistance ◽  
Neoplastic Transformation ◽  
Resistance Mechanisms ◽  
Response To Therapy ◽  
Additional Gene ◽  
Cancer Subtypes ◽  
Gene Copies ◽  
Specific Cancer ◽  
Evolution Of Genomes

This review summarizes the knowledge about retrogenes in the context of cancer and evolution. The retroposition, in which the processed mRNA from parental genes undergoes reverse transcription and the resulting cDNA is integrated back into the genome, results in additional copies of existing genes. Despite the initial misconception, retroposition-derived copies can become functional, and due to their role in the molecular evolution of genomes, they have been named the “seeds of evolution”. It is convincing that retrogenes, as important elements involved in the evolution of species, also take part in the evolution of neoplastic tumors at the cell and species levels. The occurrence of specific “resistance mechanisms” to neoplastic transformation in some species has been noted. This phenomenon has been related to additional gene copies, including retrogenes. In addition, the role of retrogenes in the evolution of tumors has been described. Retrogene expression correlates with the occurrence of specific cancer subtypes, their stages, and their response to therapy. Phylogenetic insights into retrogenes show that most cancer-related retrocopies arose in the lineage of primates, and the number of identified cancer-related retrogenes demonstrates that these duplicates are quite important players in human carcinogenesis.

Sign in / Sign up

Export Citation Format

Share Document