Download full-text PDF |
Source |
---|
Proc Natl Acad Sci U S A
February 2025
Max Planck Institute for Biological Cybernetics, Tübingen, Baden-Württemberg 72076, Germany.
Large language models (LLMs) are being increasingly incorporated into scientific workflows. However, we have yet to fully grasp the implications of this integration. How should the advancement of large language models affect the practice of science? For this opinion piece, we have invited four diverse groups of scientists to reflect on this query, sharing their perspectives and engaging in debate.
View Article and Find Full Text PDFJ Med Internet Res
January 2025
Department of Medical Strategy, Process and Quality Management, University Hospital Tübingen, Tübingen, Germany.
Background: For hospitalized patients, the discharge letter serves as a crucial source of medical information, outlining important discharge instructions and health management tasks. However, these letters are often written in professional jargon, making them difficult for patients with limited medical knowledge to understand. Large language models, such as GPT, have the potential to transform these discharge summaries into patient-friendly letters, improving accessibility and understanding.
View Article and Find Full Text PDFCommun Psychol
January 2025
Helmholtz Institute for Human-Centered AI, Münich, Germany.
Whether it is listening to a piece of music, learning a new language, or solving a mathematical equation, people often acquire abstract notions in the sense of motifs and variables-manifested in musical themes, grammatical categories, or mathematical symbols. How do we create abstract representations of sequences? Are these abstract representations useful for memory recall? In addition to learning transition probabilities, chunking, and tracking ordinal positions, we propose that humans also use abstractions to arrive at efficient representations of sequences. We propose and study two abstraction categories: projectional motifs and variable motifs.
View Article and Find Full Text PDFBioinform Adv
December 2024
Department of Protein Evolution, Max Planck Institute for Biology, Tübingen 72076, Germany.
Motivation: Coiled coils are a widespread structural motif consisting of multiple α-helices that wind around a central axis to bury their hydrophobic core. While AlphaFold has emerged as an effective coiled-coil modeling tool, capable of accurately predicting changes in periodicity and core geometry along coiled-coil stalks, it is not without limitations, such as the generation of spuriously bent models and the inability to effectively model globally non-canonical-coiled coils. To overcome these limitations, we investigated whether dividing full-length sequences into fragments would result in better models.
View Article and Find Full Text PDFElife
December 2024
Plant Evolutionary Ecology, Institute of Evolution and Ecology, University of Tübingen, Tübingen, Germany.
Understanding the genomic basis of natural variation in plant pest resistance is an important goal in plant science, but it usually requires large and labor-intensive phenotyping experiments. Here, we explored the possibility that non-target reads from plant DNA sequencing can serve as phenotyping proxies for addressing such questions. We used data from a whole-genome and -epigenome sequencing study of 207 natural lines of field pennycress () that were grown in a common environment and spontaneously colonized by aphids, mildew, and other microbes.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!