The PulseCalendarExplorerLongevity Clinics MapLongevity Investors MapWearables & Nearables MapAcademyCoursesMy LearningHealth AuditAbout

Back to Longevity News

Longevity News

Machine learning-guided discovery of natural anti-inflammatory agents targeting NF-κB p65

Source: Nature - Biotechnology • Published: 28 Aug 2026, 00:00

Machine learning-guided discovery of natural anti-inflammatory agents targeting NF-κB p65

Examination of a machine learning pipeline that predicted natural compounds inhibiting NF-κB p65 and validated top candidates experimentally.

Key Takeaways
  • XGBoost model achieved a Pearson correlation of 0.893 on a 179,771 IC50 dataset
  • Model screened 101 natural products and ranked luteolin as the strongest inhibitor after a positive control
  • Experimental assays confirmed luteolin reduced p65 activation and lowered IL6, TNF, IL1B, and CXCL8 expression
Read Original Source

Continue exploring

Related longevity signals

Frontiers - HealthPrediction of benign paroxysmal positional vertigo recurrence in postmenopausal women: a machine learning-based clinical studyExamines machine learning models to predict recurrence risk of positional vertigo specifically in postmenopausal women, comparing algorithms and interpreting key predictors.Frontiers - HealthMachine Learning-Based Assessment of Tumor-Infiltrating Lymphocytes in Breast Cancer Histopathology: A Systematic Review and Evidence-Gap Analysis of Translational ReadinessAssessments of tumor-infiltrating lymphocytes in breast cancer using machine learning are reviewed and mapped for translational readiness and methodological gaps.Frontiers - HealthPredicting Unfavorable Response to Initial Radioactive Iodine Therapy in Differentiated Thyroid Cancer: An Explainable Machine Learning and Survival Analysis ApproachAssessment of combining pre-therapy and early post-therapy clinical data with machine learning to predict poor responses after initial radioactive iodine treatment for differentiated thyroid cancer.Nature - BiotechnologyMechanistic machine learning for prediction of prime editing outcomesAn explanation of a mechanism-informed machine learning model that predicts prime editing efficiencies by modeling biochemical steps and training across diverse datasets.