Optimized Binary and Multi-Class Classification With Biomarker Detection in Brain Cancer Gene Expression DOI

Abioye Abiodun Oluwasegun,

Olalekan J. Awujoola, Muhammad Nazeer Musa

et al.

Advances in medical diagnosis, treatment, and care (AMDTC) book series, Journal Year: 2024, Volume and Issue: unknown, P. 315 - 360

Published: Dec. 17, 2024

This chapter presents a comprehensive analysis of brain cancer gene expression datasets through binary and multi-class classification using the CatBoostClassifier, enhanced by Principal Component Analysis (PCA) for dimensionality reduction. The result discussion section elucidates key findings, trends, efficacy methodologies employed. Utilizing Volcano Plots, we identified significant biomarkers that differentiate between cancerous normal tissues, facilitating discovery potential diagnostic targets. In classification, model effectively distinguished various types, including ependymoma, glioblastoma, medulloblastoma, pilocytic astrocytoma, achieving an overall accuracy 87%. Conversely, exhibited remarkable performance, attaining 100% accuracy, precision, recall, F1-score in distinguishing tumors from samples. underscores machine learning techniques advancing diagnostics improving patient outcomes.

Language: Английский

Spatial Transcriptomic and Metabolomic Landscapes of Oral Submucous Fibrosis‐Derived Oral Squamous Cell Carcinoma and its Tumor Microenvironment DOI Creative Commons
Yuan Zhi, Qian Wang,

Moxin Zi

et al.

Advanced Science, Journal Year: 2024, Volume and Issue: 11(12)

Published: Jan. 16, 2024

Abstract In South and Southeast Asia, the habit of chewing betel nuts is prevalent, which leads to oral submucous fibrosis (OSF). OSF a well‐established precancerous lesion, portion cases eventually progress squamous cell carcinoma (OSCC). However, specific molecular mechanisms underlying malignant transformation OSCC from are poorly understood. this study, leading‐edge techniques Spatial Transcriptomics (ST) Metabolomics (SM) integrated obtain spatial location information cancer cells, fibroblasts, immune as well transcriptomic metabolomic landscapes in OSF‐derived tissues. This work reveals for first time that some cells undergo partial epithelial–mesenchymal transition (pEMT) within situ (ISC) region, acquiring fibroblast‐like phenotypes participating collagen deposition. Complex interactions among epithelial tumor microenvironment demonstrated. Most importantly, significant metabolic reprogramming OSCC, including abnormal polyamine metabolism, potentially playing pivotal role promoting tumorigenesis evasion discovered. The ST SM data study shed new light on deciphering OSCC. also offers invaluable clues prevention treatment

Language: Английский

Citations

23

Tumor battlefield within inflamed, excluded or desert immune phenotypes: the mechanisms and strategies DOI Creative Commons
Siwei Zheng,

Wenwen Wang,

Lesang Shen

et al.

Experimental Hematology and Oncology, Journal Year: 2024, Volume and Issue: 13(1)

Published: Aug. 6, 2024

Abstract The tumor microenvironment demonstrates great immunophenotypic heterogeneity, which has been leveraged in traditional immune-hot/cold categorization based on the abundance of intra-tumoral immune cells. By incorporating spatial contexture, immunophenotype was further elaborated into immune-inflamed, immune-excluded, and immune-desert. However, mechanisms underlying these different phenotypes are yet to be comprehensively elucidated. In this review, we discuss how cells interact collectively shape landscape from perspectives cells, extracellular matrix, cancer metabolism, summarize potential therapeutic options according distinct immunophenotypes for personalized precision medicine.

Language: Английский

Citations

18

Advancements in single-cell RNA sequencing and spatial transcriptomics: transforming biomedical research DOI Creative Commons

Getnet Molla Desta,

Alemayehu Godana Birhanu

Acta Biochimica Polonica, Journal Year: 2025, Volume and Issue: 72

Published: Feb. 5, 2025

In recent years, significant advancements in biochemistry, materials science, engineering, and computer-aided testing have driven the development of high-throughput tools for profiling genetic information. Single-cell RNA sequencing (scRNA-seq) technologies established themselves as key dissecting sequences at level single cells. These reveal cellular diversity allow exploration cell states transformations with exceptional resolution. Unlike bulk sequencing, which provides population-averaged data, scRNA-seq can detect subtypes or gene expression variations that would otherwise be overlooked. However, a limitation is its inability to preserve spatial information about transcriptome, process requires tissue dissociation isolation. Spatial transcriptomics pivotal advancement medical biotechnology, facilitating identification molecules such their original context within sections single-cell level. This capability offers substantial advantage over traditional techniques. valuable insights into wide range biomedical fields, including neurology, embryology, cancer research, immunology, histology. review highlights approaches, technological developments, associated challenges, various techniques data analysis, applications disciplines microbiology, neuroscience, reproductive biology, immunology. It critical role characterizing dynamic nature individual

Language: Английский

Citations

6

THItoGene: a deep learning method for predicting spatial transcriptomics from histological images DOI Creative Commons

Yuran Jia,

Junliang Liu, Li Chen

et al.

Briefings in Bioinformatics, Journal Year: 2023, Volume and Issue: 25(1)

Published: Nov. 22, 2023

Abstract Spatial transcriptomics unveils the complex dynamics of cell regulation and transcriptomes, but it is typically cost-prohibitive. Predicting spatial gene expression from histological images via artificial intelligence offers a more affordable option, yet existing methods fall short in extracting deep-level information pathological images. In this paper, we present THItoGene, hybrid neural network that utilizes dynamic convolutional capsule networks to adaptively sense potential molecular signals for exploring relationship between high-resolution pathology image phenotypes expression. A comprehensive benchmark evaluation using datasets human breast cancer cutaneous squamous carcinoma has demonstrated superior performance THItoGene prediction. Moreover, its capacity decipher both context enrichment within specific tissue regions. can be freely accessed at https://github.com/yrjia1015/THItoGene.

Language: Английский

Citations

30

Spatially Resolved Transcriptomics Technology Facilitates Cancer Research DOI Creative Commons
Qian Wang, Yuan Zhi,

Moxin Zi

et al.

Advanced Science, Journal Year: 2023, Volume and Issue: 10(30)

Published: Aug. 26, 2023

Single cell RNA sequencing (scRNA-seq) provides a great convenience for studying tumor occurrence and development its ability to study gene expression at the individual level. However, patient-derived tissues are composed of multiple types cells including adjacent non-malignant such as stromal immune cells. The spatial locations various in situ plays pivotal role tumors, which cannot be elucidated by scRNA-seq alone. Spatially resolved transcriptomics (SRT) technology emerges timely explore unrecognized relationship between background particular functions, is increasingly used cancer research. This review systematic overview SRT technologies that developed, more widely cutting-edge based on next-generation (NGS). In addition, main achievements precisely unveiling underappreciated function with unprecedented high-resolution research emphasized, aim developing effective clinical therapeutics oriented deeper understanding interaction surrounding

Language: Английский

Citations

21

Cellular Dynamics of Tumor Microenvironment Driving Immunotherapy Resistance in Non-Small-Cell Lung Carcinoma DOI
Shujie Huang, Jeff Yat‐Fai Chung, Chunjie Li

et al.

Cancer Letters, Journal Year: 2024, Volume and Issue: unknown, P. 217272 - 217272

Published: Sept. 1, 2024

Language: Английский

Citations

8

Single-cell RNA sequencing to map tumor heterogeneity in gastric carcinogenesis paving roads to individualized therapy DOI Creative Commons
Jiao Xu,

Bixin Yu,

Fan Wang

et al.

Cancer Immunology Immunotherapy, Journal Year: 2024, Volume and Issue: 73(11)

Published: Sept. 13, 2024

Gastric cancer (GC) is a highly heterogeneous disease with complex tumor microenvironment (TME) that encompasses multiple cell types including cells, immune stromal and so on. Cancer-associated cells could remodel the TME influence progression of GC therapeutic response. Single-cell RNA sequencing (scRNA-seq), as an emerging technology, has provided unprecedented insights into complicated biological composition characteristics at molecular, cellular, immunological resolutions, offering new idea for studies. In this review, we discuss novel findings from scRNA-seq datasets revealing origin evolution GC, powerful tool investigating transcriptional dynamics intratumor heterogeneity (ITH) in GC. Meanwhile, demonstrate vital within TME, T B macrophages, play important role progression. Additionally, also overview how facilitates our understanding about effects on individualized therapy patients. Spatial transcriptomes (ST) have been designed to determine spatial distribution capture local intercellular communication networks, enabling further relationship between background particular its functions. summary, other single-cell technologies provide valuable perspective molecular pathological hold promise advancing basic research clinical practice

Language: Английский

Citations

6

Neutrophils Recruited by NKX2‐1 Suppression via Activation of CXCLs/CXCR2 Axis Promote Lung Adenocarcinoma Progression DOI Creative Commons

Anita Silas La’ah,

Ping‐Hsing Tsai,

Aliaksandr A. Yarmishyn

et al.

Advanced Science, Journal Year: 2024, Volume and Issue: 11(38)

Published: Aug. 7, 2024

NK2 Homeobox 1 (NKX2-1) is a well-characterized pathological marker that delineates lung adenocarcinoma (LUAD) progression. The advancement of LUAD influenced by the immune tumor microenvironment through paracrine signaling. However, involvement NKX2-1 in modeling still unclear. Here, downregulation observed high-grade LUAD. Meanwhile, single-cell RNA sequencing and Visium situ capturing profiling revealed recruitment infiltration neutrophils orthotopic syngeneic tumors exhibiting strong cell-cell communication activation CXCLs/CXCR2 depletion triggered expression secretion CXCL1, CXCL2, CXCL3, CXCL5 cells. Chemokine analyzed chemokine array validated qRT-PCR. ATAC-seq restrictive regulation on promoters genes. This phenomenon led to increased growth, conversely, growth decreased when inhibited CXCR2 antagonist SB225002. study unveils how modulates tumor-promoting inhibiting CXCLs/CXCR2-dependent mechanisms. Hence, targeting NKX2-1-low potential antitumor therapy may improve patient outcomes.

Language: Английский

Citations

5

Emerging ctDNA detection strategies in clinical cancer theranostics DOI Creative Commons
Kexin Yi, Xiaoju Wang, Sergey K. Filippov

et al.

Smart Medicine, Journal Year: 2023, Volume and Issue: 2(4)

Published: Nov. 1, 2023

Abstract Circulating tumor DNA (ctDNA) is naked molecules shed from the cells into peripheral blood circulation. They contain tumor‐specific gene mutations and other valuable information. ctDNA considered to be one of most significant analytes in liquid biopsies. Over past decades, numerous researchers have developed various detection strategies perform quantitative or qualitative analysis, including PCR‐based sequencing‐based detection. More more studies illustrated great value as a biomarker diagnosis, prognosis heterogeneity tumor. In this review, we first outlined development digital PCR (dPCR)‐based next generation sequencing (NGS)‐based systems. Besides, presented introduction emerging analysis based on biosensors, such electrochemical fluorescent surface plasmon resonance Raman spectroscopy, well their applications field biomedicine. Finally, summarized essentials preceding discussions, existing challenges prospects for future are also involved.

Language: Английский

Citations

12

Defining precancer: a grand challenge for the cancer community DOI
Jessica M. Faupel‐Badger, Indu Kohaar, Manisha Bahl

et al.

Nature reviews. Cancer, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 1, 2024

Language: Английский

Citations

4