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 Experiment Video

Updated: Jun 27, 2026

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors
11:15

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors

Published on: September 20, 2016

Mutational Signatures and Machine Learning for Risk Stratification of Acute Myeloid Leukaemia Based on Targeted

Heba Elhaddad1,2,3, Claudia Chiriches1,2, Shuvro Prokash Nandi4,5

  • 1Division of Cancer and Genetics, Section of Haematology, School of Medicine, Cardiff University, Cardiff CF14 4XN, UK.

Cancers
|June 26, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Combining Quizartinib with intensive chemotherapy in older patients with newly diagnosed AML: results of the UK NCRI AML18 Trial.

Blood·2026
Same author

Genetic liability to psoriasis predicts severe disease outcomes.

Genome medicine·2025
Same author

The Skin Genetics Consortium.

The British journal of dermatology·2025
Same author

Acute myeloid leukaemia cells express high levels of androgen receptor but do not depend on androgen signaling for survival.

Leukemia·2025
Same author

Multimodal and Data-Driven Assessment of Myeloid Neoplasms Refines Classification across Disease States.

Blood cancer discovery·2025
Same author

Self-amplifying NRF2-EZH2 epigenetic loop converts KRAS-initiated progenitors to invasive pancreatic cancer.

Nature cancer·2025

Machine learning accurately predicts acute myeloid leukaemia (AML) treatment response using targeted sequencing data. This approach identifies key mutational patterns, improving risk stratification for personalized AML therapy.

Area of Science:

  • Genomics
  • Bioinformatics
  • Machine Learning

Background:

  • Accurate prediction of acute myeloid leukaemia (AML) patient response to induction chemotherapy (CTX) is lacking.
  • Current AML risk assessment relies on complex cytogenetic and molecular abnormalities, focusing on key leukaemogenesis genes.

Purpose of the Study:

  • To develop a validated scoring system for predicting AML patient response to induction chemotherapy.
  • To identify novel mutational patterns and risk-defining signatures using bioinformatic analysis of targeted sequencing data.

Main Methods:

  • Bioinformatic analysis of targeted sequencing (TS) data from 1552 AML patients.
  • Non-negative matrix factorization (NNMF) to extract recursive signatures (RSs) and distinguish responders from non-responders.
  • Random Forest (RF) models, Synthetic Minority Over-sampling Technique (SMOTE), and incorporation of germline variants to improve predictive performance.
Keywords:
Random ForestSMOTE balancingacute myeloid leukaemiabioinformaticsinduction chemotherapymachine learningrisk assessment

More Related Videos

Characterizing Mutational Load and Clonal Composition of Human Blood
07:58

Characterizing Mutational Load and Clonal Composition of Human Blood

Published on: July 11, 2019

Comparative Lesions Analysis Through a Targeted Sequencing Approach
08:16

Comparative Lesions Analysis Through a Targeted Sequencing Approach

Published on: November 5, 2019

Related Experiment Videos

Last Updated: Jun 27, 2026

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors
11:15

Next Generation Sequencing for the Detection of Actionable Mutations in Solid and Liquid Tumors

Published on: September 20, 2016

Characterizing Mutational Load and Clonal Composition of Human Blood
07:58

Characterizing Mutational Load and Clonal Composition of Human Blood

Published on: July 11, 2019

Comparative Lesions Analysis Through a Targeted Sequencing Approach
08:16

Comparative Lesions Analysis Through a Targeted Sequencing Approach

Published on: November 5, 2019

Main Results:

  • NNMF-derived RSs effectively clustered AML patients based on treatment response, indicating diagnostic TS data's predictive potential.
  • RF models incorporating balanced data and germline variations showed improved predictive performance over somatic-only models.
  • The study successfully identified clinically relevant mutational structures for AML risk stratification.

Conclusions:

  • Machine learning applied to TS data can extract informative mutational structures for improved AML risk stratification.
  • This approach holds potential for integration into precision medicine decision-making for AML patients.
  • The findings support the use of genomic data and machine learning for personalized AML treatment strategies.