Generative Machine Learning of Conformational Ensembles of Intrinsically Disordered Proteins: Progress and Opportunities #machinelearning#compchem https://t.co/NXmdWlvr9G
Integrating Theory and Experiment with Graph Neural Networks to Classify Molecular Self-Assembly on Metal Surfaces #machinelearning#compchem https://t.co/QpZ7lO0yyE
MAPLE: A Machine-Learning Force-Field-Native Platform for Automated Reaction Modeling and Enzyme Design #machinelearning#compchem https://t.co/c4dvBoE7yr
Introducing Claude Opus 4.7, our most capable Opus model yet.
It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back.
You can hand off your hardest work with less supervision.
To mitigate the risks associated with AI in materials research, SciGuard was developed. SciGuard consists of (1) content-aware risk assessment, (2) structured limitations of scientific models, and (3) consideration of variability in ethical norms.
A comprehensive review of studies utilizing LLMs in materials research. This review covers topics ranging from fundamental approaches, such as NLP, to recent advances, including RAG, multimodal AI, and AI agents.
It provides an overview of the current landscape of this field.
This paper provides an instructive overview of graph neural networks (GNNs) at an early stage of their development. It includes detailed discussions of the fundamental concepts, computational cost, and practical applications.
This is the first report of graph neural network (#GNN). GNN extends recurrent neural network (#RNN), which can treat only directed and acyclic graphs. On the other hand, GNN can be applied on directed, undirected, labelled and cyclic graphs, and thus can be much useful.
Isomorphic Lab, of which CEO is Sir Demis Hassabis, announced reports of Isomorphic Labs Drug Design Engine (#IsoDDE). IsoDDE realizes structure prediction, pocket identification, and binding affinity, all of which are crucial for scalable foundation for AI drug design.