Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 17, 2025

MTAN-ADMET: A Multi-Task Adaptive Neural Network for Efficient and Accurate Prediction of ADMET Properties

View Full Paper
Ask AI
Bookmark
Share

Authors

SSShamsuddin ShahidDMDibyendu MaitySCSuman Chakrabarty

Discussion

Loading...

Member takes

Overview

MTAN-ADMET demonstrates improved prediction of toxicity and other ADMET properties, suggesting its utility in drug discovery.

Key Points

  • MTAN-ADMET effectively predicts multiple ADMET properties, improving accuracy particularly for toxicity endpoints.
  • Benchmarking on 24 ADMET endpoints shows performance comparable to state-of-the-art models, achieving notable results in cardiotoxicity.
  • This approach utilizes pretrained molecular embeddings, minimizing preprocessing and feature engineering for efficiency.
  • The model's robust performance highlights its potential for addressing challenges related to sparse, imbalanced datasets in drug discovery.

Cite This Study

Shahid et al. (2025) studied this question.

synapsesocial.com/papers/68a36a480a429f797332ed32https://doi.org/10.26434/chemrxiv-2025-zhrsk
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. 1In Silico ADMET: From Current Practices to Novel Profilers2026
  2. 2Advancing ADMET prediction through multiscale fragment-aware pretraining with MSformer-ADMET.2025 · 12 citations
  3. 3DCPM-ADMET: fusion of dual-component pre-trained model and molecular fingerprints to enhance drug ADMET properties prediction2026
  4. 4Auto-ADMET: An Effective and Interpretable AutoML Method for Chemical ADMET Property Prediction2025
  5. 5Predicting ADMET Properties from Molecule SMILE: A Bottom-Up Approach Using Attention-Based Graph Neural Networks2024 · 29 citations