skip to main content


This content will become publicly available on August 8, 2024

Title: 14 examples of how LLMs can transform materials science and chemistry: a reflection on a large language model hackathon
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.  more » « less
Award ID(s):
2226414 2226416 2226418 1931298 1835677
NSF-PAR ID:
10456031
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; more » ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; « less
Date Published:
Journal Name:
Digital Discovery
ISSN:
2635-098X
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Large language models (LLMs) have recently taken the world by storm. They can generate coherent text, hold meaningful conversations, and be taught concepts and basic sets of instructions—such as the steps of an algorithm. In this context, we are interested in exploring the application of LLMs to graph drawing algorithms by performing experiments on ChatGPT. These algorithms are used to improve the readability of graph visualizations. The probabilistic nature of LLMs presents challenges to implementing algorithms correctly, but we believe that LLMs’ ability to learn from vast amounts of data and apply complex operations may lead to interesting graph drawing results. For example, we could enable users with limited coding backgrounds to use simple natural language to create effective graph visualizations. Natural language specification would make data visualization more accessible and user-friendly for a wider range of users. Exploring LLMs’ capabilities for graph drawing can also help us better understand how to formulate complex algorithms for LLMs; a type of knowledge that could transfer to other areas of computer science. Overall, our goal is to shed light on the exciting possibilities of using LLMs for graph drawing while providing a balanced assessment of the challenges and opportunities they present. A free copy of this paper with all supplemental materials to reproduce our results is available at https://osf.io/n5rxd/. 
    more » « less
  2. Kazarinoff, P. ; Cossette, M. (Ed.)
    Life science organizations are increasingly using hackathons to bring communities together to tackle shared problems, teach skills, and develop new resources. In this study, we explored the potential benefits of hackathons for the biotechnology workforce education community by organizing two hackathons centered around developing research projects in antibody engineering—a practice widely employed in the biotechnology industry but uncommon in biotechnology education. To integrate antibody engineering into courses, instructors need protocols for both computational and laboratory methods. Developing and testing these protocols provides rich opportunities for undergraduate research, allowing students to learn industry-relevant skills and contribute to creating materials for the community. During the hackathons, teams of faculty, students, and industry partners collaborated to generate several new research projects. Each hackathon was only a few days, yet student participants reported benefits similar to those attributed to traditional undergraduate research experiences. We share lessons learned from these hackathons and provide insights for the workforce education community for hosting similar events. 
    more » « less
  3. null (Ed.)
    Nanoscience and nanotechnology play a significant role in every field of our society. Nanotechnology is the backbone of high-tech industries and widely used in consumer products and industrial applications. Therefore, it is essential to highlight the importance of nanoscience and nanotechnology to undergraduate students and explain the science behind nanotechnology. For this purpose, an upper-level elective mechanical engineering course, Nanoscale Science and Engineering, is designed and added to the mechanical and mechatronic engineering curriculum. This course introduces students to the interdisciplinary field of nanoscience and engineering including the areas of engineering, materials science, chemistry, and physics. The topics covered include advanced materials, synthesis, and modification of nanomaterials, properties of nanomaterials, materials characterization, nanofabrication methods, and applications. It has three modules, which are formal lectures, guest speakers, and projects. Projects will help students learn to conduct a literature search, critically review scientific articles, and learn advanced materials characterization techniques on a given topic. They will further have a chance to propose their own ideas for potential applications and asked to give a detailed methodology to execute the project. In this work-in-progress study, we present the impact of the Nanoscale Science and Engineering course on undergraduate mechanical and mechatronic engineering students. Students were invited to complete a survey at the beginning of the semester, which will be also given to the students, at the end of the semester. The survey consists of 15 questions, which are aimed to analyze the pre-existing knowledge of students in nanotechnology-related topics and their interest level to increase their knowledge and advance their career in a nanotechnology-related field. In order to assess the impact of the course on students, the results of the survey will be compared. Student demographics will be included in the results. Possible changes in course content to improve student engagement in nanotechnology will be discussed. The purpose of this course is to introduce undergraduate engineering students to nanotechnology. The inclusion of Nanoscale Science and Engineering course to the undergraduate engineering curriculum has a significant role in the advancement of nanotechnology. Students graduating with a solid understanding of broad applications of nanotechnology and advanced material fabrication and characterization techniques will have a focused start in their graduate research and education or faster adaptation to nanotechnology-related industrial job positions. 
    more » « less
  4. Undergraduate research experiences are increasingly important in biology education with efforts underway to provide more projects by embedded them in a course. The shift to online learning at the beginning of the pandemic presented a challenge. How could biology instructors provide research experiences to students who were unable to attend in-person labs? During the 2021 ISMB (Intelligent Systems for Molecular Biology) iCn3D Hackathon–Collaborative Tools for Protein Analysis–we learned about new capabilities in iCn3D for analyzing the interactions between amino acids in the paratopes of antibodies with amino acids in the epitopes of antigens and predicting the effects of mutations on binding. Additionally, new sequence alignment tools in iCn3D support aligning protein sequences with sequences in structure models. We used these methods to create a new undergraduate research project, that students could perform online as part of a course, by combining the use of new features in iCn3D with analysis tools in NextStrain, and a data set of anti-SARS-CoV-2 antibodies. We present results from an example project to illustrate how students would investigate the likelihood of SARS-CoV-2 variants escaping from commercial antibodies and use chemical interaction data to support their hypotheses. We also demonstrate that online tools (iCn3D, NextStrain, and the NCBI databases) can be used to carry out the necessary steps and that this work satisfies the requirements for course-based undergraduate research. This project reinforces major concepts in undergraduate biology–evolution and the relationship between the sequence of a protein, its three-dimensional structure, and its function. 
    more » « less
  5. The FAIR Hackathon Workshop for Mathematics and the Physical Sciences (MPS) February 27-28, 2019 in Alexandria, Virginia brought together forty-four stakeholders in the physical sciences community to share skills, tools and techniques to FAIRify research data. As one of the first efforts of its kind in the US, the workshop offered participants a way to engage with FAIR principles (Findable, Accessible, Interoperable and Reusable) Data and metrics in the context of a hackathon. The workshop was designed to address issues of public access to data and to provide experience with FAIR tools and relevant hands-on experience for researchers. Existing FAIR tools and infrastructure were introduced. Hands-on hackathon breakout time was devoted to testing FAIR metrics and tools against physical sciences data. The hackathon invited MPS research data management stakeholders to react to the FAIR principles and to jointly consider gaps in the MPS data sharing ecosystem in the context of researcher’s actual projects. FAIR Gap analysis was introduced as a way to identify community-specific tools or infrastructure that could dramatically enhance the ability of domain scientists to make their data more FAIR. 
    more » « less