Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 8, 2025BloodOpen Access

Machine learning-powered integration of global proteomics and ex vivo sensitivity unveils a protein signature predictive of treatment success to AML therapy: Validation in patients treated with FHD-286, a SMARCA2/4 dual inhibitor

View Full Paper
Ask AI
Bookmark
Share

Authors

JSJames T. SorrentinoAKAntonius KollerAKAlexis Khalil

Discussion

Loading...

Member takes

Overview

Deep learning models predictive of AML treatment outcomes using proteomics and dose-response data, highlighting B-cell receptor signaling biomarkers.

Key Points

  • To develop a predictive model for acute myeloid leukemia treatment success using proteomics and machine learning.
  • Generated quantitative proteomics and therapeutic response data from AML samples.
  • Employed deep learning to integrate global proteomics and dose-response data.
  • Used >200 patient samples and >90 patient-derived cell lines for model training.
  • Identified a 5-protein signature that predicts treatment response to FHD-286 with 100% accuracy.
  • The protein signature classified patient responses into treatment failure, stable disease, and complete response.
  • Utilized transfer learning for enhanced model training and robustness.

Cite This Study

Sorrentino et al. (2025) studied this question.

synapsesocial.com/papers/69362f574fa91c937236d9fchttps://doi.org/10.1182/blood-2025-3498
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Multi-drug algorithm to accurately predict best first-line treatments in newly-diagnosed acute myeloid leukemia (AML).2024
  2. 2Machine Learning for Predicting Therapeutic Outcomes in Acute Myeloid Leukemia Patients2024 · 2 citations
  3. 3Longitudinal single-cell spatial proteomics reveals predictive immune and stem cell signatures in Relapsed/Refractory AML2025
  4. 4PREDICT-AML: personalized response via drug interaction with cellular traits for acute myeloid leukemia2026
  5. 5Abstract 4413: Identifying genome-wide histone profiles in patient derived models of AML for predictive biomarker development2024