Dataset Information

Building predictive disease models using extracellular vesicle microscale flow cytometry and machine learning.

ABSTRACT: Extracellular vesicles (EVs) are highly abundant in human biofluids, containing a repertoire of macromolecules and biomarkers representative of the tissue of origin. EVs released by tumours can communicate key signals both locally and to distant sites to promote growth and survival or impact invasive and metastatic progression. Microscale flow cytometry of circulating EVs is an emerging technology that is a promising alternative to biopsy for disease diagnosis. However, biofluid-derived EVs are highly heterogeneous in size and composition, making their analysis complex. To address this, we developed a machine learning approach combined with EV microscale cytometry using tissue- and disease-specific biomarkers to generate predictive models. We demonstrate the utility of this novel extracellular vesicle machine learning analysis platform (EVMAP) to predict disease from patient samples by developing a blood test to identify high-grade prostate cancer and validate its performance in a prospective 215 patient cohort. Models generated using the EVMAP approach significantly improved the prediction of high-risk prostate cancer, highlighting the clinical utility of this diagnostic platform for improved cancer prediction from a blood test.

SUBMITTER: Paproski RJ

PROVIDER: S-EPMC9980304 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Building predictive disease models using extracellular vesicle microscale flow cytometry and machine learning.

Paproski Robert J RJ Pink Desmond D Sosnowski Deborah L DL Vasquez Catalina C Lewis John D JD

Molecular oncology 20221229 3

Extracellular vesicles (EVs) are highly abundant in human biofluids, containing a repertoire of macromolecules and biomarkers representative of the tissue of origin. EVs released by tumours can communicate key signals both locally and to distant sites to promote growth and survival or impact invasive and metastatic progression. Microscale flow cytometry of circulating EVs is an emerging technology that is a promising alternative to biopsy for disease diagnosis. However, biofluid-derived EVs are ...[more]

PMID: 36520580

Similar Datasets

Project description:Extracellular vesicles (EVs) are small, heterogeneous and difficult to measure. Flow cytometry (FC) is a key technology for the measurement of individual particles, but its application to the analysis of EVs and other submicron particles has presented many challenges and has produced a number of controversial results, in part due to limitations of instrument detection, lack of robust methods and ambiguities in how data should be interpreted. These complications are exacerbated by the field's lack of a robust reporting framework, and many EV-FC manuscripts include incomplete descriptions of methods and results, contain artefacts stemming from an insufficient instrument sensitivity and inappropriate experimental design and lack appropriate calibration and standardization. To address these issues, a working group (WG) of EV-FC researchers from ISEV, ISAC and ISTH, worked together as an EV-FC WG and developed a consensus framework for the minimum information that should be provided regarding EV-FC. This framework incorporates the existing Minimum Information for Studies of EVs (MISEV) guidelines and Minimum Information about a FC experiment (MIFlowCyt) standard in an EV-FC-specific reporting framework (MIFlowCyt-EV) that supports reporting of critical information related to sample staining, EV detection and measurement and experimental design in manuscripts that report EV-FC data. MIFlowCyt-EV provides a structure for sharing EV-FC results, but it does not prescribe specific protocols, as there will continue to be rapid evolution of instruments and methods for the foreseeable future. MIFlowCyt-EV accommodates this evolution, while providing information needed to evaluate and compare different approaches. Because MIFlowCyt-EV will ensure consistency in the manner of reporting of EV-FC studies, over time we expect that adoption of MIFlowCyt-EV as a standard for reporting EV- FC studies will improve the ability to quantitatively compare results from different laboratories and to support the development of new instruments and assays for improved measurement of EVs.

Dataset Information

Building predictive disease models using extracellular vesicle microscale flow cytometry and machine learning.

Publications

Building predictive disease models using extracellular vesicle microscale flow cytometry and machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets