Sarah K. Yorke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sarah K. Yorke has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
Akashaditya Das
Department of Pathology, University of Cambridge, Cambridge, UK
2 shared publications- Kaikai Chen
University of Chinese Academy of Sciences
2 shared publications - Markus J. Buehler
Massachusetts Institute of Technology
2 shared publications - Nicole E. Weckman
Cavendish Laboratory, University of Cambridge, Cambridge, UK
2 shared publications Richard Gutierrez
Oxford Nanopore Technologies, Oxford Science Park, Oxford, UK
2 shared publications- Sarah E. Sandler
Cavendish Laboratory, University of Cambridge, Cambridge, UK
2 shared publications
Latest Publications
- 14 April 2025
- Published by Springer Nature in Nature Reviews Materials
- Vol. 10 (10) , 750-768
Design and sustainability of polypeptide material systems
- 14 April 2025
- Published by Springer Nature in Nature Reviews Materials
- Vol. 10 (10) , 750-768
Design and sustainability of polypeptide material systems
- Open Access
- 28 March 2025
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 11 (13) , eadv1971
Learning the rules of peptide self-assembly through data mining with large language models
Peptides are ubiquitous and important biomolecules that self-assemble into diverse structures. Although extensive research has explored the effects of chemical composition and exterior conditions on self-assembly, a systematic study consolidating these data to uncover global rules is lacking. In this work, we curate a peptide assembly database through a combination of manual processing by human experts and large language model–assisted literature mining. As a result, we collect over 1000 experimental data entries with information about peptide sequence, experimental conditions, and corresponding self-assembly phases. Using the data, machine learning models are developed, demonstrating excellent accuracy (>80%) in assembly phase classification. Moreover, we fine-tune a GPT model for peptide literature mining with the developed dataset, which markedly outperforms the pretrained model in extracting information from academic publications. This workflow can improve efficiency when exploring potential self-assembling peptide candidates, through guiding experimental work, while also deepening our understanding of the governing mechanisms.
- 28 March 2025
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 11 (13) , eadv1971
Open AccessLearning the rules of peptide self-assembly through data mining with large language models
Peptides are ubiquitous and important biomolecules that self-assemble into diverse structures. Although extensive research has explored the effects of chemical composition and exterior conditions on self-assembly, a systematic study consolidating these data to uncover global rules is lacking. In this work, we curate a peptide assembly database through a combination of manual processing by human experts and large language model–assisted literature mining. As a result, we collect over 1000 experimental data entries with information about peptide sequence, experimental conditions, and corresponding self-assembly phases. Using the data, machine learning models are developed, demonstrating excellent accuracy (>80%) in assembly phase classification. Moreover, we fine-tune a GPT model for peptide literature mining with the developed dataset, which markedly outperforms the pretrained model in extracting information from academic publications. This workflow can improve efficiency when exploring potential self-assembling peptide candidates, through guiding experimental work, while also deepening our understanding of the governing mechanisms.
- Open Access
- 4 September 2023
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 8 (3) , 335
Author Correction: Sensing the DNA-mismatch tolerance of catalytically inactive Cas9 via barcoded DNA nanostructures in solid-state nanopores
- 4 September 2023
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 8 (3) , 335
Open AccessAuthor Correction: Sensing the DNA-mismatch tolerance of catalytically inactive Cas9 via barcoded DNA nanostructures in solid-state nanopores
- Open Access
- 7 August 2023
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 8 (3) , 325-334
Sensing the DNA-mismatch tolerance of catalytically inactive Cas9 via barcoded DNA nanostructures in solid-state nanopores
Single-molecule quantification of the strength and sequence specificity of interactions between proteins and nucleic acids would facilitate the probing of protein–DNA binding. Here we show that binding events between the catalytically inactive Cas9 ribonucleoprotein and any pre-defined short sequence of double-stranded DNA can be identified by sensing changes in ionic current as suitably designed barcoded linear DNA nanostructures with Cas9-binding double-stranded DNA overhangs translocate through solid-state nanopores. We designed barcoded DNA nanostructures to study the relationships between DNA sequence and the DNA-binding specificity, DNA-binding efficiency and DNA-mismatch tolerance of Cas9 at the single-nucleotide level. Nanopore-based sensing of DNA-barcoded nanostructures may help to improve the design of efficient and specific ribonucleoproteins for biomedical applications, and could be developed into sensitive protein-sensing assays.
- 7 August 2023
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 8 (3) , 325-334
Open AccessSensing the DNA-mismatch tolerance of catalytically inactive Cas9 via barcoded DNA nanostructures in solid-state nanopores
Single-molecule quantification of the strength and sequence specificity of interactions between proteins and nucleic acids would facilitate the probing of protein–DNA binding. Here we show that binding events between the catalytically inactive Cas9 ribonucleoprotein and any pre-defined short sequence of double-stranded DNA can be identified by sensing changes in ionic current as suitably designed barcoded linear DNA nanostructures with Cas9-binding double-stranded DNA overhangs translocate through solid-state nanopores. We designed barcoded DNA nanostructures to study the relationships between DNA sequence and the DNA-binding specificity, DNA-binding efficiency and DNA-mismatch tolerance of Cas9 at the single-nucleotide level. Nanopore-based sensing of DNA-barcoded nanostructures may help to improve the design of efficient and specific ribonucleoproteins for biomedical applications, and could be developed into sensitive protein-sensing assays.