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
  1. Home
  3. Systemic Immunometabolic Profiling Classifies Cisplatin Sensitivity States Using Interpretable Machine Learning.
  1. Home
  3. Systemic Immunometabolic Profiling Classifies Cisplatin Sensitivity States Using Interpretable Machine Learning.

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

Flood-induced microbial contaminants and quantitative microbial risk assessment over a riverine environment of the mid-Brahmaputra valley, India.

Environmental monitoring and assessment·2026
Same author

Laser-Assisted Drug Delivery of 5-Fluorouracil and Triamcinolone vs. Triamcinolone Monotherapy Does Not Lead to Different Outcomes in the Treatment of Burn Hypertrophic Scars.

Dermatologic surgery : official publication for American Society for Dermatologic Surgery [et al.]·2026
Same author

Sleep apnea and the ageing brain: bridging mechanisms and clinical outcomes.

The American journal of medicine·2026
Same author

The Tryptophan Paradox: From Microbiome-Mediated Homeostasis to Tumor-Driven Immune Escape.

International journal of molecular sciences·2026
Same author

Tumor cell specific total mRNA expression informed neural networks predicts cancer progression.

bioRxiv : the preprint server for biology·2026
Same author

Multimodal Free-Water Imaging Links Cardiometabolic Risk to Periarterial Dysfunction and Amyloid Accumulation in Early Alzheimer's.

Research square·2026
Same journal

The WEE1 inhibitor azenosertib broadly enhances efficacy of antibody-drug conjugates with topoisomerase I and microtubule inhibitor payloads.

iScience·2026
Same journal

Na<sub>2</sub>CO<sub>3</sub>-assisted oxygen-alkali recyclable cellulose separation/pulping technology of straw and silicon controllable migration.

iScience·2026
Same journal

Local global feature enhanced transformer with attention pruning for precise medical image segmentation.

iScience·2026
Same journal

hSpindly dynamics modulate spindle assembly checkpoint signaling, promoting resistance to mitotic inhibitors.

iScience·2026
Same journal

Naive CD4<sup>+</sup> T cells synthesize a hyaluronan-rich glycocalyx that is diminished following activation.

iScience·2026
Same journal

STRAP promotes hepatocellular carcinoma progression through activation of an STRAP/Wnt-β-catenin/STRAP positive feedback loop.

iScience·2026
See all related articles

Related Experiment Video

Mass Cytometry Analysis of Systemic and Local Immune Responses in Hepatocellular Carcinoma
08:25

Mass Cytometry Analysis of Systemic and Local Immune Responses in Hepatocellular Carcinoma

Published on: April 25, 2025

908

Systemic immunometabolic profiling classifies cisplatin sensitivity states using interpretable machine learning.

Emily Y Kim1,2,3,4, Diane C Lim1,2,5,6, Yujie Wang7

  • 1Research Services, Miami VA Healthcare System, Miami, FL 33125, USA.

Iscience
|March 19, 2026

View abstract on PubMed

Summary
This summary is machine-generated.

We developed a new diagnostic tool, ImmunoMetabolic Profiling Analysis and Classification Tool (IMPACT), to predict cisplatin sensitivity in lung adenocarcinoma. This machine learning approach accurately distinguishes between sensitive and resistant tumors using immunometabolic markers.

Keywords:
Computing methodologyMachine learningMetabolomics

More Related Videos

Evaluating the Effectiveness of Cancer Drug Sensitization In Vitro and In Vivo
09:19

Evaluating the Effectiveness of Cancer Drug Sensitization In Vitro and In Vivo

Published on: February 6, 2015

9.2K
Predictive Immune Modeling of Solid Tumors
08:50

Predictive Immune Modeling of Solid Tumors

Published on: February 25, 2020

7.6K

Related Experiment Videos

Mass Cytometry Analysis of Systemic and Local Immune Responses in Hepatocellular Carcinoma
08:25

Mass Cytometry Analysis of Systemic and Local Immune Responses in Hepatocellular Carcinoma

Published on: April 25, 2025

908
Evaluating the Effectiveness of Cancer Drug Sensitization In Vitro and In Vivo
09:19

Evaluating the Effectiveness of Cancer Drug Sensitization In Vitro and In Vivo

Published on: February 6, 2015

9.2K
Predictive Immune Modeling of Solid Tumors
08:50

Predictive Immune Modeling of Solid Tumors

Published on: February 25, 2020

7.6K

Area of Science:

  • Oncology
  • Immunology
  • Computational Biology

Background:

  • Cisplatin resistance is a major challenge in lung adenocarcinoma treatment.
  • Lack of practical systemic diagnostics for cisplatin sensitivity hinders effective patient stratification.

Purpose of the Study:

  • To develop and validate an interpretable machine learning pipeline, IMPACT, for predicting cisplatin sensitivity in lung adenocarcinoma.
  • To identify key immunometabolic features associated with cisplatin sensitivity and resistance.

Main Methods:

  • Quantified serum amino acids and immune cell populations in a syngeneic orthotopic model.
  • Utilized recursive feature elimination within IMPACT to identify minimal, mechanistically informative feature sets.
  • Employed machine learning to classify cisplatin-sensitive vs. cisplatin-resistant tumors and cancer vs. control groups.

Main Results:

  • IMPACT achieved high accuracy (AUC = 0.950) in classifying cisplatin-sensitive vs. cisplatin-resistant lung adenocarcinoma.
  • Bone marrow myeloid-derived suppressor cells (MDSCs) and serum glutamine were key predictors of cisplatin sensitivity.
  • The framework also accurately classified cancer vs. control groups (AUC = 0.955), with lung MDSCs and phosphoserine as top features.

Conclusions:

  • IMPACT provides a promising, accurate, and interpretable method for assessing cisplatin sensitivity in lung adenocarcinoma.
  • Systemic immunometabolic profiling, particularly bone marrow MDSCs and serum glutamine, offers valuable insights into platinum-based chemotherapy response.
  • This approach has potential for clinical application in stratifying lung adenocarcinoma patients for chemotherapy.