Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Machine Learning Signal Enrichment for Ultrasensitive Plasma Tumor Burden Monitoring

ABSTRACT: In solid tumor oncology, circulating tumor DNA (ctDNA) is poised to transform care through accurate assessment of minimal residual disease (MRD) and therapeutic response monitoring. To overcome the sparsity of ctDNA fragments in low tumor fraction (TF) settings and increase MRD sensitivity, we previously leveraged genome-wide mutational integration through plasma whole genome sequencing (WGS). We now introduce MRD-EDGE, a composite machine learning-guided WGS ctDNA single nucleotide variant (SNV) and copy number variant (CNV) detection platform designed to increase signal enrichment. MRD-EDGESNV uses deep learning and a ctDNA-specific feature space to increase SNV signal-to-noise enrichment in WGS by 300X compared to previous WGS error suppression. MRD-EDGECNV also reduces the degree of aneuploidy needed for ultrasensitive CNV detection through WGS from 1 Gb to 200 Mb, thereby expanding its applicability to a wider range of solid tumors. We harness the improved performance to identify MRD following surgery in multiple cancer types, track changes in tumor burden in response to neoadjuvant immunotherapy in non-small cell lung cancer (NSCLC) and demonstrate ctDNA shedding in precancerous colorectal adenomas. Finally, the radical signal-to-noise enrichment in MRD-EDGESNV enables de novo mutation calling in melanoma and small cell lung cancer (SCLC) without matched tumor, yielding clinically informative TF monitoring for patients on immune checkpoint inhibition (ICI).

PROVIDER: EGAS00001007451 | EGA |

REPOSITORIES: EGA

ACCESS DATA

Json Xml

Similar Datasets

Machine learning guided signal enrichment for ultrasensitive plasma tumor burden monitoring

Project description:In solid tumor oncology, circulating tumor DNA (ctDNA) is poised to transform care through accurate assessment of minimal residual disease (MRD) and therapeutic response monitoring. To overcome the sparsity of ctDNA fragments in low tumor fraction (TF) settings and increase MRD sensitivity, we previously leveraged genome-wide mutational integration through plasma whole genome sequencing (WGS). We now introduce MRD-EDGE, a composite machine learning-guided WGS ctDNA single nucleotide variant (SNV) and copy number variant (CNV) detection platform designed to increase signal enrichment. MRD-EDGESNV uses deep learning and a ctDNA-specific feature space to increase SNV signal-to-noise enrichment in WGS by 300X compared to previous WGS error suppression. MRD-EDGECNV also reduces the degree of aneuploidy needed for ultrasensitive CNV detection through WGS from 1 Gb to 200 Mb, thereby expanding its applicability to a wider range of solid tumors. We harness the improved performance to identify MRD following surgery in multiple cancer types, track changes in tumor burden in response to neoadjuvant immunotherapy in non-small cell lung cancer (NSCLC) and demonstrate ctDNA shedding in precancerous colorectal adenomas. Finally, the radical signal-to-noise enrichment in MRD-EDGESNV enables de novo mutation calling in melanoma and small cell lung cancer (SCLC) without matched tumor, yielding clinically informative TF monitoring for patients on immune checkpoint inhibition (ICI).

| EGAS00001007545 | EGA

Optimization of transcription factor binding map accuracy by utilizing their knockout-mouse models

Project description:Genome-wide assessment of protein-DNA interactions binding by ChIP-seq is a key technology to study transcription factor (TF) localization and regulation of gene-expression. In ChIP-seq, signal-to-noise-ratio as well as signal specificity depend on many variables including antibody quality, and efforts to improve ChIP-seq data thus far focused mostly on generating better reagents. Here we introduce KOIN (KO implemented normalization) as a novel strategy to increase signal specificity and reduce noise by using TF knockout-mice as a critical control for ChIP-seq. We tested our new peak calling strategy (KO implemented normalization = KOIN) on different ChIP-seq datasets to increase signal specificity and reduce noise.

2014-07-17 | E-GEOD-55317 | biostudies-arrayexpress

Optimization of transcription factor binding map accuracy by utilizing their knockout-mouse models

2014-07-17 | GSE55317 | GEO

Detecting cell-of-origin and cancer-specific methylation features of cell-free DNA from Nanopore sequencing

Project description:The Oxford Nanopore (ONT) platform provides portable and rapid genome sequencing, and its ability to natively profile DNA methylation without complex sample processing is attractive for clinical sequencing. We recently demonstrated ONT shallow whole-genome sequencing to detect copy number alterations (CNA) from the circulating tumor DNA (ctDNA) of cancer patients. Here, we show that cell-type and cancer-specific methylation changes can also be detected, as well as cancer-associated fragmentation signatures. This feasibility study suggests that ONT shallow WGS could be a powerful tool for liquid biopsy, especially real-time medical applications.

2022-04-27 | GSE185307 | GEO

Reliable tumor detection using cerebrospinal fluid cell-free DNA methylomes in pediatric medulloblastoma

Project description:Medulloblastoma (MB) is an embryonal tumor of the cerebellum and a highly malignant childhood brain tumor. Cell-free circulating tumor DNA (ctDNA) from the cerebrospinal fluid (CSF) of patients with brain tumors faithfully represent genomic alterations of brain tumors. Distinct epigenetic signatures among subgroups of MB allow us to detect epigenetic alterations in CSF to aid classify and guide therapy of MB tumors. Here, we evaluate DNA methylation and hydroxymethylation of ctDNA derived from small amount of CSF (200 µL) and matched tumor DNA from 3 MB patients. We find highly concordance of DNA methylation and hydroxymethylation between CSF ctDNA and tumor DNA, especially in CpG islands. Importantly, CSF ctDNA can mostly recapitulate the dynamic changes of DNA methylation and hydroxymehtylation in tumor species compared to healthy cerebellums. Those MB tumor signature CpGs’ DNA methylation status are recovered in CSF ctDNA can clearly distinguish MB subgroups by utilizing public large cohort data. We further identified potential diagnostic and prognostic DNA methylation markers in CSF ctDNA. Our results show that CSF ctNDA methylation and hydroxymethylation can be a minimal invasive method to assess epigenetic alterations of MB, which is complementary to current diagnoses of MB tumors.

2020-10-28 | GSE142241 | GEO

Project description:Signal and Noise in Metabarcoding Data

| PRJNA966238 | ENA

MYC drives temporal evolution of small cell lung cancer subtypes by reprogramming neuroendocrine fate [WGS data]

Project description:Distinct SCLC molecular subtypes have been defined based on expression of lineage-related transcription factors: ASCL1, NEUROD1, POU2F3 or YAP1, but their origins remain unknown. To study transcriptional dynamics of MYC-driven tumor evolution and compare transcriptional states to human SCLC tumors, we performed bulk and single-cell RNA-sequencing on various timepoints of Rb1/Trp53/MycT58A (RPM) tumor cells (from Ad-Cgrp-Cre infected mice) as they progress in culture, and on RPM bulk tumors. Here, to complement these analyses we performed ~30X whole-genome sequencing (WGS) of early (day 4) and late (day 23) time-point RPM tumor cells from culture, along with a matching normal blood control to confirm complete loss of expected regions of Rb1 and Trp53. WGS analyses revealed no detectable copy number variations (CNVs), and SNV analysis suggests that minimal clonal and subclonal evolution occurs in vitro. Together, these data ultimately reveal that MYC drives the dynamic evolution of SCLC subtypes. We find that MYC promotes a temporal shift from an ASCL1-to-NEUROD1-to-YAP1+ state from a neuroendocrine cell of origin. MYC activates Notch signaling to dedifferentiate tumor cells to non-neuroendocrine fates. These findings support our overall conclusions that genetics, cell of origin, and tumor cell plasticity determine SCLC subtype.

2020-05-28 | GSE149444 | GEO

CAPEOX vs Observation in Colorectal Cancer Patients With Positive MRD

Project description:Patients with stage Ⅰ colorectal cancer or stage Ⅱ colon cancer usually have a good prognosis and are not recommended to receive adjuvant chemotherapy after radical surgery. With the advances in liquid biopsy technology, detection of circulating tumor DNA (ctDNA) can effectively identify early-stage cancer patients with minimal residual disease (MRD) after surgery. According to the growing number of MRD studies in solid tumor, colorectal cancer patients with ctDNA-MRD detection have a poor clinical outcome and are likely to relapse within two years. This study aims to assess the efficacy of adjuvant chemotherapy with capecitabine plus oxaliplatin (CAPEOX) compared with conventional observation in MRD-positive patients with stage I colorectal cancer and clinically low-risk stage II colon cancer.

| 6161 | ecrin-mdr-crc

SpiDe-Sr: blind super-resolution network for precise cell segmentation and clustering in spatial proteomics imaging

Project description:Spatial proteomics elucidates cellular biochemical changes with unprecedented topological level. Imaging mass cytometry (IMC) is a high-dimensional single-cell resolution platform for targeted spatial proteomics. However, the precision of subsequent clinical analysis is constrained by imaging noise and resolution. Here, we propose SpiDe-Sr, a super-resolution network embedded with a denoising module for IMC spatial resolution enhancement. SpiDe-Sr effectively resists noise and improves resolution by 4 times. We demonstrate SpiDe-Sr respectively with cells, mouse and human tissues, resulting 18.95%/ 27.27%/ 21.16% increase in peak signal-to-noise ratio and 15.95%/ 31.63%/ 15.52% increase in cell extraction accuracy. We further apply SpiDe-Sr to study the tumor microenvironment of a 20-patient clinical breast cancer cohort with 269,556 single cells, and discover the invasion of Gram-negative bacteria is positively correlated with carcinogenesis markers and negatively correlated with immunological markers. Additionally, SpiDe-Sr is also compatible with fluorescence microscopy imaging, suggesting SpiDe-Sr an alternative tool for microscopy image super-resolution.

2024-02-25 | PXD050123 |

Circulating tumor DNA for monitoring classic Hodgkin lymphoma patients: correlation with FDG-PET/CT

Project description:Circulating tumor DNA (ctDNA) as a biomarker of disease activity in classic Hodgkin lymphoma (cHL) patients are still not well-defined. By profiling primary tumors and ctDNA, we identified common variants between primary tumors and longitudinal plasma samples in most of the cases, confirming high PBatial and temporal heterogeneity. Though ctDNA analyses mirrored HRS cell genetics overall, the prevalence of variants shows that none of them can be used as a single biomarker. Conversely, the estimation of hGE/mL, based in total ctDNA quantification, reflects disease activity and is almost perfectly correlated with standard parameters such as PET/CT that are associated with refractoriness.

2023-12-18 | GSE244989 | GEO

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data