Advancing mutagenicity predictions in drug discovery with an explainable few-shot deep learning framework

Luis H.M. Torres; Sofia M. da Silva; Joel P. Arrais; Catarina Pimentel; Bernardete Ribeiro; Luis H.M. Torres; Sofia M. da Silva; Joel P. Arrais; Catarina Pimentel; Bernardete Ribeiro

doi:10.1039/d5dd00276a

January 1, 2025Digital DiscoveryOpen Access

Advancing mutagenicity predictions in drug discovery with an explainable few-shot deep learning framework

View Full Paper

Ask AI

Bookmark

Share

Key Points

Predictions of mutagenicity advance drug discovery, emphasizing the role of deep learning methodologies.
The model integrates several techniques and approaches, enhancing prediction accuracy in specialized tasks.
Assessment using a few-shot learning strategy broadens the framework's application in predicting mutagenicity.
These tools may enable better predictions in drug safety evaluations, although further validation is needed.

Implication

The framework predicts mutagenicity in drug discovery, suggesting advancements in meta-learning strategies for limited data.

Abstract

Meta-GTMP is a few-shot GNN-Transformer framework that predicts Ames mutagenicity by learning from strain-specific tasks. It integrates graph embeddings and self-attention using a meta-learning strategy to generalize from limited data.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Torres et al. (2025) studied this question.

synapsesocial.com/papers/6925572cc0ce034ddc35a6b3 https://doi.org/10.1039/d5dd00276a

View Full Paper

Ask AI

Bookmark

Share

Advancing mutagenicity predictions in drug discovery with an explainable few-shot deep learning framework

Key Points

Implication

Abstract

Discussion

Cite This Study

Advancing mutagenicity predictions in drug discovery with an explainable few-shot deep learning framework

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading