Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Cancers Originate from Somatic Mutations in a Single Cell02:21

Cancers Originate from Somatic Mutations in a Single Cell

13.2K
Cancer arises from mutations in the critical genes that allow healthy cells to escape cell cycle regulation and acquire the ability to proliferate indefinitely. Though originating from a single mutation event in one of the originator cells, cancer progresses when the mutant cell lines continue to gain more and more mutations, and finally, become malignant. For example, chronic myelogenous leukemia (CML) develops initially as a non-lethal increase in white blood cells, which progressively...
13.2K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Author Correction: Single-cell multi-omic detection of DNA methylation and histone modifications reconstructs the dynamics of epigenomic maintenance.

Nature methods·2026
Same author

Regulatory grammar in human promoters uncovered by MPRA-based deep learning.

Nature·2026
Same author

A computational framework to dissect imputation strategies for single-cell histone modification data.

NAR genomics and bioinformatics·2025
Same author

Author Correction: Single-cell multi-omic detection of DNA methylation and histone modifications reconstructs the dynamics of epigenomic maintenance.

Nature methods·2025
Same author

Single-cell multi-omic detection of DNA methylation and histone modifications reconstructs the dynamics of epigenomic maintenance.

Nature methods·2025
Same author

Predicting gene expression from DNA sequence using deep learning models.

Nature reviews. Genetics·2025

Related Experiment Video

Updated: Oct 6, 2025

Quantitative Mass Spectrometric Profiling of Cancer-cell Proteomes Derived From Liquid and Solid Tumors
08:08

Quantitative Mass Spectrometric Profiling of Cancer-cell Proteomes Derived From Liquid and Solid Tumors

Published on: February 27, 2015

16.5K

Cancer Type Classification in Liquid Biopsies Based on Sparse Mutational Profiles Enabled through Data Augmentation

Alexandra Danyi1, Myrthe Jager1,2, Jeroen de Ridder1,2

  • 1Center for Molecular Medicine, University Medical Center Utrecht, 3584 CX Utrecht, The Netherlands.

Life (Basel, Switzerland)
|January 21, 2022
PubMed
Summary

This study introduces a novel machine learning method to identify cancer

Keywords:
bioinformaticsdeep learninggenetic variabilitygenomics

More Related Videos

Detection of Cell-Free DNA in Blood Plasma Samples of Cancer Patients
08:25

Detection of Cell-Free DNA in Blood Plasma Samples of Cancer Patients

Published on: September 9, 2020

11.3K
Comparative Lesions Analysis Through a Targeted Sequencing Approach
08:16

Comparative Lesions Analysis Through a Targeted Sequencing Approach

Published on: November 5, 2019

6.9K

Related Experiment Videos

Last Updated: Oct 6, 2025

Quantitative Mass Spectrometric Profiling of Cancer-cell Proteomes Derived From Liquid and Solid Tumors
08:08

Quantitative Mass Spectrometric Profiling of Cancer-cell Proteomes Derived From Liquid and Solid Tumors

Published on: February 27, 2015

16.5K
Detection of Cell-Free DNA in Blood Plasma Samples of Cancer Patients
08:25

Detection of Cell-Free DNA in Blood Plasma Samples of Cancer Patients

Published on: September 9, 2020

11.3K
Comparative Lesions Analysis Through a Targeted Sequencing Approach
08:16

Comparative Lesions Analysis Through a Targeted Sequencing Approach

Published on: November 5, 2019

6.9K

Area of Science:

  • Oncology
  • Bioinformatics
  • Machine Learning

Background:

  • Identifying the cell of origin is crucial for effective cancer treatment.
  • Solid biopsies have limitations; liquid biopsies are promising but present data sparsity challenges for current machine learning models.
  • Somatic mutation profiles are sparse in liquid biopsies, hindering accurate cancer cell of origin classification.

Purpose of the Study:

  • To develop an improved machine learning method for classifying cancer cell of origin using sparse liquid biopsy data.
  • To enhance the robustness and accuracy of machine learning models in the context of limited somatic mutation data.

Main Methods:

  • Implemented data augmentation techniques to improve model performance on sparse liquid biopsy data.
  • Employed data integration by merging single nucleotide variant (SNV) density, SNVs in driver genes, and trinucleotide motifs.
  • Adapted existing machine learning models to effectively handle data sparsity.

Main Results:

  • Achieved an average accuracy of 0.88 with 70% SNV retention and 0.65 with 2% SNV retention.
  • Demonstrated superior performance compared to the original model, which achieved 0.83 and 0.41 accuracy, respectively, under the same data sparsity conditions.
  • The adapted method shows significant improvements in classifying cancer of origin from sparse liquid biopsy data.

Conclusions:

  • The proposed method effectively addresses data sparsity in liquid biopsies for cancer cell of origin detection.
  • This advancement enables the broader application of machine learning in liquid biopsy-based cancer diagnostics.
  • The findings pave the way for more accessible and less invasive cancer diagnostics.