Advances in Predictive Modeling for Biomedical and Materials Research

The field of predictive modeling is rapidly advancing in biomedical and materials research, with a focus on developing innovative methods for analyzing complex data and predicting outcomes. Recent developments have centered around the use of machine learning and deep learning techniques to improve the accuracy and efficiency of predictive models. Notably, researchers are exploring the use of multi-scale approaches, graph neural networks, and attention mechanisms to capture complex relationships and patterns in data. These advances have significant implications for applications such as drug development, materials design, and disease diagnosis.

Some noteworthy papers in this area include: A Weak Supervision Approach for Monitoring Recreational Drug Use Effects in Social Media, which leverages social media data to detect substance-specific phenotypic effects. A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction, which proposes a novel framework for predicting drug-drug interactions using multi-scale graph representations and cross-drug co-attention mechanisms. Advancing Universal Deep Learning for Electronic-Structure Hamiltonian Prediction of Materials, which contributes to the development of universal deep learning methods for predicting electronic-structure Hamiltonians of materials. PGCLODA: Prompt-Guided Graph Contrastive Learning for Oligopeptide-Infectious Disease Association Prediction, which introduces a prompt-guided graph-based contrastive learning framework for predicting associations between oligopeptides and infectious diseases.

Sources

A Weak Supervision Approach for Monitoring Recreational Drug Use Effects in Social Media

A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction

Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems

Interplay Between Belief Propagation and Transformer: Differential-Attention Message Passing Transformer

WLFM: A Well-Logs Foundation Model for Multi-Task and Cross-Well Geological Interpretation

Interaction Topological Transformer for Multiscale Learning in Porous Materials

Advancing Universal Deep Learning for Electronic-Structure Hamiltonian Prediction of Materials

A HyperGraphMamba-Based Multichannel Adaptive Model for ncRNA Classification

PGCLODA: Prompt-Guided Graph Contrastive Learning for Oligopeptide-Infectious Disease Association Prediction

Built with on top of