Search for: All records

An open-hardware automated workflow for mesoporous colloidal silica synthesis is developed and applied to study a compositional parameter space. 

An open-source fine-tuned large language model can extract reaction information from organic synthesis procedure text into structured data that follows the Open Reaction Database (ORD) schema. 

Automated experimentation methods are unlocking a new data-rich research paradigm in materials science that promises to accelerate the pace of materials discovery. However, if our data management practices do not keep pace with progress in automation, this revolution threatens to drown us in unusable data. In this perspective, we highlight the need to update data management practices to track, organize, process, and share data collected from laboratories with deeply integrated automation equipment. We argue that a holistic approach to data management that integrates multiple scales (experiment, group and community scales) is needed. We propose a vision for what this integrated data future could look like and compare existing work against this vision to find gaps in currently available data management tools. To realize this vision, we believe that development of standard protocols for communicating with equipment and data sharing, the development of new open-source software tools for managing data in research groups, and leadership and direction from funding agencies and other organizations are needed. 

Large-language models (LLMs) such as GPT-4 caught the interest of many scientists. Recent studies suggested that these models could be useful in chemistry and materials science. To explore these possibilities, we organized a hackathon. This article chronicles the projects built as part of this hackathon. Participants employed LLMs for various applications, including predicting properties of molecules and materials, designing novel interfaces for tools, extracting knowledge from unstructured data, and developing new educational applications. The diverse topics and the fact that working prototypes could be generated in less than two days highlight that LLMs will profoundly impact the future of our fields. The rich collection of ideas and projects also indicates that the applications of LLMs are not limited to materials science and chemistry but offer potential benefits to a wide range of scientific disciplines.