Machine learning-based analysis identifies and validates serum exosomal proteomic signatures for the diagnosis of colorectal cancer

Quick Facts

  • Publication title: Machine learning-based analysis identifies and validates serum exosomal proteomic signatures for the diagnosis of colorectal cancer
  • Journal: Cell Rep Med
  • Year: 2024
  • DOI: 10.1016/j.xcrm.2024.101689
  • PMID/PMCID: 39168094; PMC11384723

Research overview

Collectively, our study identified the crucial proteomic signatures in serum EVs and established a promising EV-related RF model for CRC diagnosis in the clinic. Additionally, multi-omics approaches were employed to predict the functions and potential sources of serum EV-derived proteins.

Key findings

The potential of serum extracellular vesicles (EVs) as non-invasive biomarkers for diagnosing colorectal cancer (CRC) remains elusive.

We employed an in-depth 4D-DIA proteomics and machine learning (ML) pipeline to identify key proteins, PF4 and AACT, for CRC diagnosis in serum EV samples from a discovery cohort of 37 cases.

PF4 and AACT outperform traditional biomarkers, CEA and CA19-9, detected by ELISA in 912 individuals.

963 in the train and test sets, respectively.

Echo Biotech Role

Echo Biotech contributed EV isolation and purification; the study also used or cited Exosupur®.

Related platforms: Exoomics®, Research Reagents & Tools

Related services and capabilities: Biofluid EV Isolation & Purification, Research Reagent / Product Supply

Related products or reagents: Exosupur® EV Isolation/Purification Kit

References

Original publication: Machine learning-based analysis identifies and validates serum exosomal proteomic signatures for the diagnosis of colorectal cancer Cell reports. Medicine. 2024. DOI: 10.1016/j.xcrm.2024.101689. PMID/PMCID: 39168094; PMC11384723.