Plasma Cell‐Free DNA Concentration and Fragmentomes Predict Neoadjuvant Chemotherapy Response in Cervical Cancer Patients DOI Creative Commons
Ting Peng, Haiqiang Zhang,

Lingguo Li

et al.

Advanced Science, Journal Year: 2024, Volume and Issue: 11(43)

Published: Sept. 25, 2024

Abstract Cervical cancer remains one of the most lethal gynecological malignancies. However, biomarkers for more precise patient care are an unmet need. Herein, concentration 285 plasma cell‐free DNA (cfDNA) samples analyzed from 84 cervical patients and clinical significance cfDNA fragmentomic characteristics across neoadjuvant chemotherapy (NACT) treatment. Patients with poor NACT response exhibit a significantly greater escalation in levels following initial cycle treatment, comparison to favorable response. Distinctive end motif profiles promoter coverages observed between differing responses. Notably, DNASE1L3 analysis further demonstrates intrinsic association resistance. The ratios show good discriminative capacity predicting non‐responders responders (area under curve (AUC) > 0.8). In addition, transcriptional start sites (TSS) around promoters discern alteration biological processes associated resistance reflect potential value These findings predictive may optimize treatment selection, minimize unnecessary assist establishing personalized strategies patients.

Language: Английский

A deep-learning model for quantifying circulating tumour DNA from the density distribution of DNA-fragment lengths DOI
Guanhua Zhu, Chowdhury Rafeed Rahman,

Victor Getty

et al.

Nature Biomedical Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: March 7, 2025

Language: Английский

Citations

2
Artificial intelligence and machine learning in cell-free-DNA-based diagnostics DOI

WY Tsui,

Spencer C Ding, Peiyong Jiang

et al.

Genome Research, Journal Year: 2025, Volume and Issue: 35(1), P. 1 - 19

Published: Jan. 1, 2025

The discovery of circulating fetal and tumor cell-free DNA (cfDNA) molecules in plasma has opened up tremendous opportunities noninvasive diagnostics such as the detection chromosomal aneuploidies cancers posttransplantation monitoring. advent high-throughput sequencing technologies makes it possible to scrutinize characteristics cfDNA molecules, opening fields genetics, epigenetics, transcriptomics, fragmentomics, providing a plethora biomarkers. Machine learning (ML) and/or artificial intelligence (AI) that are known for their ability integrate high-dimensional features have recently been applied field liquid biopsy. In this review, we highlight various AI ML approaches cfDNA-based diagnostics. We first introduce biology basic concepts technologies. then discuss selected examples ML- or AI-based applications prenatal testing cancer These include deduction fraction, tissue mapping, localization. Finally, offer perspectives on future direction using leverage fragmentation patterns terms methylomic transcriptional investigations.

Language: Английский

Citations

1
Examining cellular heterogeneity in human DNA methylation studies: Overview and recommendations DOI Creative Commons
Maggie P. Fu, Sarah M. Merrill, Keegan Korthauer

et al.

STAR Protocols, Journal Year: 2025, Volume and Issue: 6(1), P. 103638 - 103638

Published: Feb. 12, 2025

Language: Английский

Citations

1
Benchmarking of methods for DNA methylome deconvolution DOI Creative Commons
Kobe De Ridder, Huiwen Che, Kaat Leroy

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: May 16, 2024

Abstract Defining the number and abundance of different cell types in tissues is important for understanding disease mechanisms as well diagnostic prognostic purposes. Typically, this achieved by immunohistological analyses, sorting, or single-cell RNA-sequencing. Alternatively, cell-specific DNA methylome information can be leveraged to deconvolve fractions from a bulk mixture. However, comprehensive benchmarking deconvolution methods modalities was not yet performed. Here we evaluate 16 algorithms, developed either specifically data more generically. We assess performance these effect normalization methods, while modeling variables that impact performance, including abundance, type similarity, reference panel size, method profiling (array sequencing), technical variation. observe differences algorithm depending on each variables, emphasizing need tailoring analyses. The complexity reference, marker selection method, loci and, sequencing-based assays, sequencing depth have marked influence performance. By developing handles select optimal analysis configuration, provide valuable source studies aiming array- methylation data.

Language: Английский

Citations

7
Circulating tumor DNA methylation detection as biomarker and its application in tumor liquid biopsy: advances and challenges DOI Creative Commons
Lingyu Li, Yingli Sun

MedComm, Journal Year: 2024, Volume and Issue: 5(11)

Published: Nov. 1, 2024

Abstract Circulating tumor DNA (ctDNA) methylation, an innovative liquid biopsy biomarker, has emerged as a promising tool in early cancer diagnosis, monitoring, and prognosis prediction. As noninvasive approach, overcomes the limitations of traditional tissue biopsy. Among various biomarkers, ctDNA methylation garnered significant attention due to its high specificity detection capability across diverse types. Despite immense potential, clinical application faces substantial challenges pertaining sensitivity, specificity, standardization. In this review, we begin by introducing basic biology common techniques methylation. We then explore recent advancements faced biopsies. This includes progress screening identification molecular subtypes, monitoring recurrence minimal residual disease (MRD), prediction treatment response prognosis, assessment burden, determination origin. Finally, discuss future perspectives applications. comprehensive overview underscores vital role enhancing diagnostic accuracy, personalizing treatments, effectively progression, providing valuable insights for research practice.

Language: Английский

Citations

7
CpGPT: a Foundation Model for DNA Methylation DOI Creative Commons
Lucas Paulo de Lima Camillo, Raghav Sehgal, Judith Armstrong

et al.

Published: Oct. 29, 2024

Abstract DNA methylation is a critical epigenetic modification that regulates gene expression and plays significant role in development disease processes. Here, we present the Cytosine-phosphate-Guanine Pretrained Transformer (CpGPT), novel foundation model pretrained on over 1,500 datasets encompassing 100,000 samples from diverse tissues conditions. CpGPT leverages an improved transformer architecture to learn comprehensive representations of patterns, allowing it impute reconstruct genome-wide profiles limited input data. By capturing sequence, positional, contexts, outperforms specialized models when finetuned for aging-related tasks, including chronological age prediction, mortality risk, morbidity assessments. The highly adaptable across different platforms tissue types. Furthermore, analysis sample-specific attention weights enables identification most influential CpG sites individual predictions. As model, sets new benchmark analysis, achieving strong performance Biomarkers Aging Challenge, where placed second overall estimation first public leaderboard methylation-based prediction. Highlights 100,000+ samples. demonstrates zero-shot tasks imputation, array conversion, reference mapping. achieves state-of-the-art results prediction estimation. Sample-specific interpretability enabled through weights.

Language: Английский

Citations

6
Epitranscriptomic rRNA fingerprinting reveals tissue-of-origin and tumor-specific signatures DOI
Ivan Milenkovic, Sonia Cruciani, Laia Llovera

et al.

Molecular Cell, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 1, 2024

Language: Английский

Citations

6
Cell-free DNA methylation in the clinical management of lung cancer DOI
Mark O. Ezegbogu, E. J. Wilkinson, Glen Reid

et al.

Trends in Molecular Medicine, Journal Year: 2024, Volume and Issue: 30(5), P. 499 - 515

Published: April 5, 2024

Language: Английский

Citations

5
CelFiE-ISH: a probabilistic model for multi-cell type deconvolution from single-molecule DNA methylation haplotypes DOI Creative Commons
Irene Unterman,

Dana Avrahami,

Efrat Katsman

et al.

Genome biology, Journal Year: 2024, Volume and Issue: 25(1)

Published: June 10, 2024

Language: Английский

Citations

4
A Novel Tissue-Free Method to Estimate Tumor-Derived Cell-Free DNA Quantity Using Tumor Methylation Patterns DOI Open Access

Collin Melton,

Peter Freese,

Yifan Zhou

et al.

Cancers, Journal Year: 2023, Volume and Issue: 16(1), P. 82 - 82

Published: Dec. 23, 2023

Estimating the abundance of cell-free DNA (cfDNA) fragments shed from a tumor (i.e., circulating (ctDNA)) can approximate burden, which has numerous clinical applications. We derived novel, broadly applicable statistical method to quantify cancer-indicative methylation patterns within cfDNA estimate ctDNA abundance, even at low levels. Our algorithm identified differentially methylated regions (DMRs) between reference database cancer tissue biopsy samples and individuals without cancer. Then, utilizing matched biopsy, counts matching hyper/hypo-methylated DMRs were used determine fraction (TMeF; methylation-based quantification allele abundance) for plasma samples. TMeF small variant (SVAF) estimates same correlated (Spearman’s correlation coefficient: 0.73), synthetic dilutions expected 10−3 10−4 had estimated two-fold 95% 77% samples, respectively. increased with stage size inversely survival probability. Therefore, tumor-derived in patients be leveraged need may provide non-invasive approximations burden.

Language: Английский

Citations

10