Search for: All records

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. 

Here, we present the outcomes from the second Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry, which engaged participants across global hybrid locations, resulting in 34 team submissions. The submissions spanned seven key application areas and demonstrated the diverse utility of LLMs for applications in (1) molecular and material property prediction; (2) molecular and material design; (3) automation and novel interfaces; (4) scientific communication and education; (5) research data management and automation; (6) hypothesis generation and evaluation; and (7) knowledge extraction and reasoning from scientific literature. Each team submission is presented in a summary table with links to the code and as brief papers in the appendix. Beyond team results, we discuss the hackathon event and its hybrid format, which included physical hubs in Toronto, Montreal, San Francisco, Berlin, Lausanne, and Tokyo, alongside a global online hub to enable local and virtual collaboration. Overall, the event highlighted significant improvements in LLM capabilities since the previous year's hackathon, suggesting continued expansion of LLMs for applications in materials science and chemistry research. These outcomes demonstrate the dual utility of LLMs as both multipurpose models for diverse machine learning tasks and platforms for rapid prototyping custom applications in scientific research. 

The multiexciton quintet state,⁵TT, generated as a singlet fission intermediate in pairs of molecular chromophores, is a promising candidate as a qubit or qudit in future quantum information science schemes. 

The electronic and optical responses of an organic semiconductor (OSC) are dictated by the chemistries of the molecular or polymer building blocks and how these chromophores pack in the solid state. Understanding the physicochemical nature of these responses is not only critical for determining the OSC performance for a particular application, but the UV/visible optical response may also be of potential use to determine aspects of the molecular-scale solid-state packing for crystal polymorphs or thin-film morphologies that are difficult to determine otherwise. To probe these relationships, we report the quantum-chemical investigation of a series of trialkyltetrelethynyl acenes (tetrel = silicon or germanium) that adopt the brickwork, slip-stack, or herringbone (HB) packing configurations; the π-conjugated backbones considered here are pentacene and anthradithiophene. For comparison, HB-packed (unsubstituted) pentacene is also included. Density functional theory and G 0 W 0 (single-shot Green’s function G and/or screened Coulomb function W) electronic band structures, G 0 W 0 -Bethe–Salpeter equation-derived optical spectra, polarized ϵ 2 spectra, and distributions of both singlet and triplet exciton wave functions are reported. Configurational disorder is also considered. Furthermore, we evaluate the probability of singlet fission in these materials through energy conservation relationships. 

Despite its simplicity, the composition of a material can be used as input to machine learning models to predict a range of materials properties. However, many property optimization tasks require the generation of novel but realistic materials compositions. In this study, we describe a way to generate compositions of hybrid organic–inorganic crystals through adapting Augmented CycleGAN, a novel generative model that can learn many-to-many relations between two domains. Specifically, we investigate the problem of composition change upon amine swap: for a specific chemical system (set of elements) crystalized with amine A, how would the product chemical compositions change if it is crystalized with amine B? By training with limited data from Cambridge Structural Database, our model can generate realistic chemical compositions for hybrid crystalline materials. The Augmented CycleGAN model can also utilize abundant unpaired data (compositions of different chemical systems), a feature that traditional supervised methods lack. The generated compositions can be used for many tasks, for example, as input fed to a classifier that predicts structural dimensionality. 

The rapid development and application of machine learning (ML) techniques in materials science have led to new tools for machine-enabled and autonomous/high-throughput materials design and discovery. Alongside, efforts to extract data from traditional experiments in the published literature with natural language processing (NLP) algorithms provide opportunities to develop tremendous data troves for these in silico design and discovery endeavors. While NLP is used in all aspects of society, its application in materials science is still in the very early stages. This perspective provides a case study on the application of NLP to extract information related to the preparation of organic materials. We present the case study at a basic level with the aim to discuss these technologies and processes with researchers from diverse scientific backgrounds. We also discuss the challenges faced in the case study and provide an assessment to improve the accuracy of NLP techniques for materials science with the aid of community contributions. 

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.