The role of tumor microenvironment in drug resistance: emerging technologies to unravel breast cancer heterogeneity

Frontiers in Oncology, Journal Year: 2023, Volume and Issue: 13

Published: May 17, 2023

Breast cancer is a highly heterogeneous disease, at both inter- and intra-tumor levels, this heterogeneity crucial determinant of malignant progression response to treatments. In addition genetic diversity plasticity cells, the tumor microenvironment contributes shaping physical biological surroundings tumor. The activity certain types immune, endothelial or mesenchymal cells in can change effectiveness therapies via plethora different mechanisms. Therefore, deciphering interactions between distinct cell types, their spatial organization specific contribution growth drug sensitivity still major challenge. Dissecting currently an urgent need better define breast biology develop therapeutic strategies targeting as helpful tools for combined personalized treatment. review, we analyze mechanisms by which affects characteristics that ultimately result resistance, outline state art preclinical models emerging technologies will be instrumental unraveling impact on resistance therapies.

Language: Английский

---

Artificial Intelligence and Machine Learning Technologies in Cancer Care: Addressing Disparities, Bias, and Data Diversity

Cancer Discovery, Journal Year: 2022, Volume and Issue: 12(6), P. 1423 - 1427

Published: June 2, 2022

Summary: Artificial intelligence (AI) and machine learning (ML) technologies have not only tremendous potential to augment clinical decision-making enhance quality care precision medicine efforts, but also the worsen existing health disparities without a thoughtful, transparent, inclusive approach that includes addressing bias in their design implementation along cancer discovery continuum. We discuss applications of AI/ML tools provide recommendations for mitigating with AI ML while promoting equity.

Language: Английский

---

Deep learning facilitates multi-data type analysis and predictive biomarker discovery in cancer precision medicine

Computational and Structural Biotechnology Journal, Journal Year: 2023, Volume and Issue: 21, P. 1372 - 1382

Published: Jan. 1, 2023

Cancer progression is linked to gene-environment interactions that alter cellular homeostasis. The use of biomarkers as early indicators disease manifestation and can substantially improve diagnosis treatment. Large omics datasets generated by high-throughput profiling technologies, such microarrays, RNA sequencing, whole-genome shotgun nuclear magnetic resonance, mass spectrometry, have enabled data-driven biomarker discoveries. identification differentially expressed traits molecular markers has traditionally relied on statistical techniques are often limited linear parametric modeling. heterogeneity, epigenetic changes, high degree polymorphism observed in oncogenes demand biomarker-assisted personalized medication schemes. Deep learning (DL), a major subunit machine (ML), been increasingly utilized recent years investigate various diseases. combination ML/DL approaches for performance optimization across multi-omics produces robust ensemble-learning prediction models, which becoming useful precision medicine. This review focuses the development methods provide integrative solutions discovering cancer-related biomarkers, their utilization

Language: Английский

---

An Integrated Multi-Omics and Artificial Intelligence Framework for Advance Plant Phenotyping in Horticulture

Biology, Journal Year: 2023, Volume and Issue: 12(10), P. 1298 - 1298

Published: Sept. 30, 2023

This review discusses the transformative potential of integrating multi-omics data and artificial intelligence (AI) in advancing horticultural research, specifically plant phenotyping. The traditional methods phenotyping, while valuable, are limited their ability to capture complexity biology. advent (meta-)genomics, (meta-)transcriptomics, proteomics, metabolomics has provided an opportunity for a more comprehensive analysis. AI machine learning (ML) techniques can effectively handle volume data, providing meaningful interpretations predictions. Reflecting multidisciplinary nature this area review, readers will find collection state-of-the-art solutions that key integration phenotyping experiments horticulture, including experimental design considerations with several technical non-technical challenges, which discussed along solutions. future prospects include precision predictive breeding, improved disease stress response management, sustainable crop exploration biodiversity. holds immense promise revolutionizing research applications, heralding new era

Language: Английский

---

Integrating Molecular Perspectives: Strategies for Comprehensive Multi-Omics Integrative Data Analysis and Machine Learning Applications in Transcriptomics, Proteomics, and Metabolomics

Biology, Journal Year: 2024, Volume and Issue: 13(11), P. 848 - 848

Published: Oct. 22, 2024

With the advent of high-throughput technologies, field omics has made significant strides in characterizing biological systems at various levels complexity. Transcriptomics, proteomics, and metabolomics are three most widely used each providing unique insights into different layers a system. However, analyzing data set separately may not provide comprehensive understanding subject under study. Therefore, integrating multi-omics become increasingly important bioinformatics research. In this article, we review strategies for transcriptomics, data, including co-expression analysis, metabolite-gene networks, constraint-based models, pathway enrichment interactome analysis. We discuss combined integration approaches, correlation-based strategies, machine learning techniques that utilize one or more types data. By presenting these methods, aim to researchers with better how integrate gain view system, facilitating identification complex patterns interactions might be missed by single-omics analyses.

Language: Английский

---

A machine learning and deep learning-based integrated multi-omics technique for leukemia prediction

Heliyon, Journal Year: 2024, Volume and Issue: 10(3), P. e25369 - e25369

Published: Feb. 1, 2024

In recent years, scientific data on cancer has expanded, providing potential for a better understanding of malignancies and improved tailored care. Advances in Artificial Intelligence (AI) processing power algorithmic development position Machine Learning (ML) Deep (DL) as crucial players predicting Leukemia, blood cancer, using integrated multi-omics technology. However, realizing these goals demands novel approaches to harness this deluge. This study introduces Leukemia diagnosis approach, analyzing accuracy ML DL algorithms. techniques, including Random Forest (RF), Naive Bayes (NB), Decision Tree (DT), Logistic Regression (LR), Gradient Boosting (GB), methods such Recurrent Neural Networks (RNN) Feedforward (FNN) are compared. GB achieved 97 % ML, while RNN outperformed by achieving 98 DL. approach filters unclassified effectively, demonstrating the significance leukemia prediction. The testing validation was based 17 different features patient age, sex, mutation type, treatment methods, chromosomes, others. Our compares techniques chooses best technique that gives optimum results. emphasizes implications high-throughput technology healthcare, offering

Language: Английский

---

Enhancing pancreatic cancer diagnostics: Ensemble-based model for automated urine biomarker classification

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 189, P. 109997 - 109997

Published: March 10, 2025

Language: Английский

---

Multi-omics Data Integration Model Based on UMAP Embedding and Convolutional Neural Network

Cancer Informatics, Journal Year: 2022, Volume and Issue: 21, P. 117693512211242 - 117693512211242

Published: Jan. 1, 2022

Multi-omics data integration facilitates collecting richer understanding and perceptions than separate omics data. Various promising integrative approaches have been utilized to analyze multi-omics for biomedical applications, including disease prediction subtypes, biomarker prediction, others.In this paper, we introduce a method that is constructed using the combination of gene similarity network (GSN) based on uniform manifold approximation projection (UMAP) convolutional neural networks (CNNs). The utilizes UMAP embed expression, DNA methylation, copy number alteration (CNA) lower dimension creating two-dimensional RGB images. Gene expression used as reference construct GSN then integrate other with better prediction. We CNNs predict Gleason score levels prostate cancer patients tumor stage in breast patients.The model proposed near perfection accuracy above 99% all performance measurements at same level. outperformed state-of-art iSOM-GSN constructs map self-organizing map.The results show an embedding technique can maps into SOM. also be applied build types cancer.

Language: Английский

---

Automated classification of urine biomarkers to diagnose pancreatic cancer using 1-D convolutional neural networks

Journal of Biological Engineering, Journal Year: 2023, Volume and Issue: 17(1)

Published: April 17, 2023

Abstract Background Early diagnosis of Pancreatic Ductal Adenocarcinoma (PDAC) is the main key to surviving cancer patients. Urine proteomic biomarkers which are creatinine, LYVE1, REG1B, and TFF1 present a promising non-invasive inexpensive diagnostic method PDAC. Recent utilization both microfluidics technology artificial intelligence techniques enables accurate detection analysis these biomarkers. This paper proposes new deep-learning model identify urine for automated pancreatic cancers. The proposed composed one-dimensional convolutional neural networks (1D-CNNs) long short-term memory (LSTM). It can categorize patients into healthy pancreas, benign hepatobiliary disease, PDAC cases automatically. Results Experiments evaluations have been successfully done on public dataset 590 samples three classes, 183 pancreas samples, 208 disease 199 samples. results demonstrated that our 1-D CNN + LSTM achieved best accuracy score 97% area under curve (AUC) 98% versus state-of-the-art models diagnose cancers using Conclusion A efficient 1D CNN-LSTM has developed early four TFF1. showed superior performance other machine learning classifiers in previous studies. prospect this study laboratory realization deep classifier urinary biomarker panels assisting procedures

Language: Английский

---

Machine learning and multi-omics data in chronic lymphocytic leukemia: the future of precision medicine?

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

Published: Jan. 12, 2024

Chronic lymphocytic leukemia is a complex and heterogeneous hematological malignancy. The advance of high-throughput multi-omics technologies has significantly influenced chronic research paved the way for precision medicine approaches. In this review, we explore role machine learning in analysis data We discuss recent literature on different models applied to single omic studies leukemia, with special focus potential contributions medicine. Finally, highlight recently published applications area as well their limitations.

Language: Английский

---