MoGCN: A Multi-Omics Integration Method Based on Graph Convolutional Network for Cancer Subtype Analysis

Frontiers in Genetics, Journal Year: 2022, Volume and Issue: 13

Published: Feb. 2, 2022

In light of the rapid accumulation large-scale omics datasets, numerous studies have attempted to characterize molecular and clinical features cancers from a multi-omics perspective. However, there are great challenges in integrating using machine learning methods for cancer subtype classification. this study, MoGCN, integration model based on graph convolutional network (GCN) was developed classification analysis. Genomics, transcriptomics proteomics datasets 511 breast invasive carcinoma (BRCA) samples were downloaded Cancer Genome Atlas (TCGA). The autoencoder (AE) similarity fusion (SNF) used reduce dimensionality construct patient (PSN), respectively. Then vector PSN input into GCN training testing. Feature extraction visualization further biological knowledge discovery analysis multi-dimensional data BRCA TCGA, MoGCN achieved highest accuracy compared with several popular algorithms. Moreover, can extract most significant each layer provide candidate functional molecules their effects. And showed that could make clinically intuitive diagnosis. generality proven TCGA pan-kidney datasets. public available at https://github.com/Lifoof/MoGCN. Our study shows performs well heterogeneous interpretability results, which confers potential applications biomarker identification

Language: Английский

---

A benchmark study of deep learning-based multi-omics data fusion methods for cancer

Genome biology, Journal Year: 2022, Volume and Issue: 23(1)

Published: Aug. 9, 2022

A fused method using a combination of multi-omics data enables comprehensive study complex biological processes and highlights the interrelationship relevant biomolecules their functions. Driven by high-throughput sequencing technologies, several promising deep learning methods have been proposed for fusing generated from large number samples.

Language: Английский

---

Multi-OMICS approaches in cancer biology: New era in cancer therapy

Biochimica et Biophysica Acta (BBA) - Molecular Basis of Disease, Journal Year: 2024, Volume and Issue: 1870(5), P. 167120 - 167120

Published: March 13, 2024

Language: Английский

---

Glioblastoma: An Update in Pathology, Molecular Mechanisms and Biomarkers

International Journal of Molecular Sciences, Journal Year: 2024, Volume and Issue: 25(5), P. 3040 - 3040

Published: March 6, 2024

Glioblastoma multiforme (GBM) is the most common and malignant type of primary brain tumor in adults. Despite important advances understanding molecular pathogenesis biology this past decade, prognosis for GBM patients remains poor. characterized by aggressive biological behavior high degrees inter-tumor intra-tumor heterogeneity. Increased cellular heterogeneity may not only help more accurately define specific subgroups precise diagnosis but also lay groundwork successful implementation targeted therapy. Herein, we systematically review key achievements pathogenesis, mechanisms, biomarkers decade. We discuss pathology GBM, including genetics, epigenetics, transcriptomics, signaling pathways. that have potential clinical roles. Finally, new strategies, current challenges, future directions discovering therapeutic targets will be discussed.

Language: Английский

---

Advancements and challenges in triple-negative breast cancer: a comprehensive review of therapeutic and diagnostic strategies

Frontiers in Oncology, Journal Year: 2024, Volume and Issue: 14

Published: May 28, 2024

Triple-negative breast cancer (TNBC) poses significant challenges in oncology due to its aggressive nature, limited treatment options, and poorer prognosis compared other subtypes. This comprehensive review examines the therapeutic diagnostic landscape of TNBC, highlighting current strategies, emerging therapies, future directions. Targeted including PARP inhibitors, immune checkpoint EGFR hold promise for personalized approaches. Challenges identifying novel targets, exploring combination developing predictive biomarkers must be addressed optimize targeted therapy TNBC. Immunotherapy represents a transformative approach TNBC treatment, yet biomarker identification, overcoming resistance persist. Precision medicine approaches offer opportunities tailored based on tumor biology, but integration multi-omics data clinical implementation present requiring innovative solutions. Despite these challenges, ongoing research efforts collaborative initiatives hope improving outcomes advancing strategies By addressing complexities biology effective approaches, treatments can realized, ultimately enhancing lives patients. Continued research, trials, interdisciplinary collaborations are essential realizing this vision making meaningful progress management.

Language: Английский

---

A multimodal graph neural network framework for cancer molecular subtype classification

BMC Bioinformatics, Journal Year: 2024, Volume and Issue: 25(1)

Published: Jan. 15, 2024

Abstract Background The recent development of high-throughput sequencing has created a large collection multi-omics data, which enables researchers to better investigate cancer molecular profiles and taxonomy based on subtypes. Integrating data been proven be effective for building more precise classification models. Most current integrative models use either an early fusion in the form concatenation or late with separate feature extractor each omic, are mainly deep neural networks. Due nature biological systems, graphs structural representation bio-medical data. Although few graph network (GNN) methods have proposed, they suffer from three common disadvantages. One is most them only one type connection, inter-omics intra-omic connection; second, consider kind GNN layer, convolution (GCN) attention (GAT); third, these not tested complex task, such as Results In this study, we propose novel end-to-end framework accurate robust subtype classification. proposed model utilizes heterogeneous multi-layer graphs, combine both connections established knowledge. incorporates learned features global genome We Cancer Genome Atlas (TCGA) Pan-cancer dataset TCGA breast invasive carcinoma (BRCA) classification, respectively. shows superior performance compared four state-of-the-art baseline terms accuracy, F1 score, precision, recall. comparative analysis GAT-based GCN-based reveals that preferred smaller less information larger extra information.

Language: Английский

---

A comprehensive review of machine learning techniques for multi-omics data integration: challenges and applications in precision oncology

Briefings in Functional Genomics, Journal Year: 2024, Volume and Issue: 23(5), P. 549 - 560

Published: April 10, 2024

Multi-omics data play a crucial role in precision medicine, mainly to understand the diverse biological interaction between different omics. Machine learning approaches have been extensively employed this context over years. This review aims comprehensively summarize and categorize these advancements, focusing on integration of multi-omics data, which includes genomics, transcriptomics, proteomics metabolomics, alongside clinical data. We discuss various machine techniques computational methodologies used for integrating distinct omics datasets provide valuable insights into their application. The emphasizes both challenges opportunities present integration, medicine patient stratification, offering practical recommendations method selection scenarios. Recent advances deep network-based are also explored, highlighting potential harmonize information layers. Additionally, we roadmap oncology, outlining advantages, implementation difficulties. Hence offers thorough overview current literature, providing researchers with particularly oncology. Contact: [email protected].

Language: Английский

---

Advanced Biomaterials and Biomedical Devices for Studying Tumor-Associated Fibroblasts: Current Trends, Innovations, and Future Prospects

Deleted Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 19, 2025

Language: Английский

---

ACVIMconsensus statement guidelines on diagnosing and distinguishing low‐grade neoplastic from inflammatory lymphocytic chronic enteropathies in cats

Journal of Veterinary Internal Medicine, Journal Year: 2023, Volume and Issue: 37(3), P. 794 - 816

Published: May 1, 2023

Lymphoplasmacytic enteritis (LPE) and low-grade intestinal T cell lymphoma (LGITL) are common diseases in older cats, but their diagnosis differentiation remain challenging.

Language: Английский

---

Artificial intelligence (AI) and machine learning (ML) in precision oncology: a review on enhancing discoverability through multiomics integration

British Journal of Radiology, Journal Year: 2023, Volume and Issue: 96(1150)

Published: Sept. 3, 2023

Multiomics data including imaging radiomics and various types of molecular biomarkers have been increasingly investigated for better diagnosis therapy in the era precision oncology. Artificial intelligence (AI) machine learning (ML) deep (DL) techniques combined with exponential growth multiomics may great potential to revolutionize cancer subtyping, risk stratification, prognostication, prediction clinical decision-making. In this article, we first present different categories their roles therapy. Second, AI-based fusion methods modeling as well validation schemes are illustrated. Third, applications examples research oncology demonstrated. Finally, challenges regarding heterogeneity set, availability omics data, discussed. The transition real clinics still requires consistent efforts standardizing collection analysis, building computational infrastructure sharing storing, developing advanced improve interpretability, ultimately, conducting large-scale prospective trials fill gap between study findings benefits.

Language: Английский

---