PulseTrendingJournal ClubResearchersJournalsExplore
Instagram
HomeTrendingJournal ClubExplore
Synapse
⌘+K
Synapse
October 1, 2025

Advancing ADMET prediction through multiscale fragment-aware pretraining with MSformer-ADMET.

View Full Paper
Ask AI
Bookmark
Share

Authors

HLHuihui LiuBZBingjie ZhuSNShuyang Nie

Discussion

Loading...

Member takes

Overview

Deep learning model enhances ADMET property prediction in drug discovery, indicating improved accuracy and interpretability.

Key Points

  • MSformer-ADMET significantly improves ADMET prediction outcomes compared to traditional methods, indicating its effectiveness.
  • With adaptations for ADMET properties, MSformer-ADMET shows superior performance on 22 tasks from the Therapeutics Data Commons.
  • Attention distributions provide insights into key structural fragments, enhancing the interpretability of molecular properties.
  • The framework combines deep learning with flexible, fragmentation-based molecular representation for robust predictions.

Cite This Study

Liu et al. (2025) studied this question.

synapsesocial.com/papers/68dd89e6fe798ba2fc497fcchttps://doi.org/10.1093/bib/bbaf506
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. 1DCPM-ADMET: fusion of dual-component pre-trained model and molecular fingerprints to enhance drug ADMET properties prediction2026
  2. 2MTAN-ADMET: A Multi-Task Adaptive Neural Network for Efficient and Accurate Prediction of ADMET Properties2025
  3. 3Hybrid fragment-SMILES tokenization for ADMET prediction in drug discovery2024 · 6 citations
  4. 4Quantum-Informed Molecular Representation Learning Enhancing ADMET Property Prediction2024 · 5 citations
  5. 5Hybrid Fragment-SMILES Tokenization for ADMET Prediction in Drug Discovery2024