Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 22, 2026Journal of Medicine and Life ScienceOpen Access

Machine learning framework for predicting DPP-4 inhibitory activity: a preliminary study on candidate screening and structural determinants

View Full Paper
Ask AI
Bookmark
Share

Authors

KKKwang Hyeon KimJCJae-Keun Cho

Discussion

Loading...

Member takes

Overview

Randomized trial identifies high-potential DPP-4 inhibitors, suggesting efficient candidate screening.

Key Points

  • This study aims to create a machine learning framework to predict the activity of DPP-4 inhibitors for type 2 diabetes.
  • Developed a dual-model random forest architecture with an 80/20 train-test split.
  • Used 2048-bit Morgan fingerprints to digitize chemical structures and retrieved bioactivity data from ChEMBL.
  • Evaluated model performance using ROC-AUC and SHAP analyses for predictive accuracy.
  • Achieved an ROC-AUC of 0.91 and overall accuracy of 91.17% for the random forest classifier.
  • Identified Candidate A with a predicted pIC50 of 6.4 and an 80.0% activity probability.
  • Validated drug-likeness of candidates using Lipinski's rule of five, enhancing bioavailability.

Cite This Study

Kim et al. (2026) studied this question.

synapsesocial.com/papers/6a0ff362d674f7c03778c08dhttps://doi.org/10.22730/jmls.2026.04.15
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. 1Modeling Structure-Activity Relationships with Machine Learning to Identify DPP4 Inhibitors as potential Therapeutics for Type 2 Diabetes2026
  2. 2AI/ML‐Driven DPP‐4 Inhibitor Predictor (d4p_v1) for Enhanced Type 2 Diabetes Mellitus Management: Insights Into Chemical Space, Fingerprints, and Electrostatic Potential Maps2025
  3. 3Machine Learning Exploration of Food-Derived Chemical Space for Potential Nutritional Metabolic Regulators Targeting Dipeptidyl Peptidase-42026
  4. 4Ensemble Machine Learning- and Deep Learning-Driven Identification and Validation of Sennidin B as a Novel Dipeptidyl Peptidase-4 Inhibitor2026
  5. 5Pharmacophore-based virtual screening of bioactive peptides as dipeptidyl peptidase 4 inhibitor for type 2 diabetes mellitus drug candidates2024