#molecular-prediction News & Analysis

5 articles tagged with #molecular-prediction. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

5 articles

AIBullisharXiv – CS AI · Jun 236/10

🧠

Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization

Researchers developed an explainable graph neural network framework that uses group lasso regularization to predict compound-protein affinity and identify critical molecular substructures in drug discovery. The approach leverages activity-cliff molecule pairs to improve predictions for tyrosine-protein kinases and other targets, demonstrating enhanced interpretability and accuracy in molecular property prediction.

AIBullisharXiv – CS AI · May 126/10

🧠

SLASH the Sink: Sharpening Structural Attention Inside LLMs

Researchers present SLASH, a training-free method that improves how Large Language Models understand graph structures by fixing an internal attention bottleneck. The approach leverages LLMs' spontaneous ability to reconstruct graph topologies internally, addressing a fundamental limitation where language-focused attention patterns suppress graph reasoning capabilities.

AIBullisharXiv – CS AI · Mar 37/106

🧠

MultiPUFFIN: A Multimodal Domain-Constrained Foundation Model for Molecular Property Prediction of Small Molecules

Researchers introduce MultiPUFFIN, a multimodal AI foundation model that predicts molecular properties for drug discovery and materials science. The model combines multiple data types and thermodynamic principles to achieve superior performance while using 2000x fewer training molecules than existing models like ChemBERTa-2.

AIBullisharXiv – CS AI · Mar 36/106

🧠

GlassMol: Interpretable Molecular Property Prediction with Concept Bottleneck Models

Researchers introduce GlassMol, a new interpretable AI model for molecular property prediction that addresses the black-box problem in drug discovery. The model uses Concept Bottleneck Models with automated concept curation and LLM-guided selection, achieving performance that matches or exceeds traditional black-box models across thirteen benchmarks.

AINeutralarXiv – CS AI · Feb 274/106

🧠

FlexMS is a flexible framework for benchmarking deep learning-based mass spectrum prediction tools in metabolomics

Researchers have developed FlexMS, a flexible benchmark framework for evaluating deep learning models that predict mass spectra for molecular identification in drug discovery and material science. The framework addresses current challenges in assessing different prediction approaches by providing standardized evaluation methods and insights into performance factors across various model architectures.