EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

InstructPLM-mu: protein fitness prediction from structure instructions

Junde Xu, Yapin Shi, Lijun Lang, Taoyong Cui, Zhiming Zhang, Guangyong Chen, Jiezhong Qiu, Pheng-Ann Heng

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag400 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Junde Xu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, New Territory, Hong Kong SAR, 999077, China. Hauptthemen laut MEDLINE: Proteins, Computational Biology, Software. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal protein language models (PLMs) deliver strong performance on mutation-effect prediction, but training such models from scratch demands substantial computational resources. In this paper, we propose a fine-tuning framework called InstructPLM-mu and investigate the question: Can a pretrained sequence-only PLM, augmented with structural information during fine-tuning, match the performance of end-to-end trained multimodal models? Surprisingly, our experiments show that fine-tuning ESM2 with structural inputs can reach performance comparable to ESM3. To understand how this is achieved, we systematically compare three different feature-fusion designs and fine-tuning recipes. Our results reveal that both the fusion method and the tuning strategy strongly affect final accuracy, indicating that the fine-tuning process is not trivial. We hope this work offers practical guidance for injecting structure into pretrained PLMs and motivates further research on better fusion mechanisms and fine-tuning protocols.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsComputational BiologySoftwareMutationAlgorithmsPrediction AlgorithmsProtein Conformation

Stichwörter der Autor:innen

fine-tuningmultimodal fusionmutation predictionprotein language models

Substanzen

Proteins

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, New Territory, Hong Kong SAR, 999077, China.
  • Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, No. 1, Xiangshan Zhinong, Xihu District, Hangzhou, Zhejiang, 310024, China.
  • Hangzhou Institute of Medicine, Chinese Academy of Sciences, 150 Dongfang Street Xiasha, Qiantang District, Hangzhou, Zhejiang, 310000, China.
  • College of Intelligence and Computing, Tianjin University, No. 135 Yaguan Road, Haihe Education Park, Tianjin, 300350, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Xu, J., Shi, Y., Lang, L., Cui, T., Zhang, Z., Chen, G., Qiu, J., & Heng, P. A. (2026). InstructPLM-mu: protein fitness prediction from structure instructions. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag400

Vancouver

Xu J, Shi Y, Lang L, Cui T, Zhang Z, Chen G, et al. InstructPLM-mu: protein fitness prediction from structure instructions. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag400

BibTeX
@article{Xu2026,
  author = {Xu, Junde and Shi, Yapin and Lang, Lijun and Cui, Taoyong and Zhang, Zhiming and Chen, Guangyong and Qiu, Jiezhong and Heng, Pheng-Ann},
  title = {InstructPLM-mu: protein fitness prediction from structure instructions},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag400}
}
Kostenlos starten →