Prediction of virus-host associations using protein language models and multiple instance learning
PLOS Computational Biology · 19.11.2024 · 20 (11) · e1012597
DOI: 10.1371/journal.pcbi.1012597 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 19.11.2024. Verfasst von Dan Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: MRC-University of Glasgow Centre for Virus Research, Glasgow, United Kingdom. Hauptthemen laut MEDLINE: Computational Biology, Viruses, Viral Proteins, Host-Pathogen Interactions. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union’s Horizon 2020 research and innovation program, Medical Research Council, Doctoral Training Programme in Precision Medicine studentship.
Abstract (Originalsprache)
Predicting virus-host associations is essential to determine the specific host species that viruses interact with, and discover if new viruses infect humans and animals. Currently, the host of the majority of viruses is unknown, particularly in microbiomes. To address this challenge, we introduce EvoMIL, a deep learning method that predicts the host species for viruses from viral sequences only. It also identifies important viral proteins that significantly contribute to host prediction. The method combines a pre-trained large protein language model (ESM) and attention-based multiple instance learning to allow protein-orientated predictions. Our results show that protein embeddings capture stronger predictive signals than sequence composition features, including amino acids, physiochemical properties, and DNA k-mers. In multi-host prediction tasks, EvoMIL achieves median F1 score improvements of 10.8%, 16.2%, and 4.9% in prokaryotic hosts, and 1.7%, 6.6% and 11.5% in eukaryotic hosts. EvoMIL binary classifiers achieve impressive AUC over 0.95 for all prokaryotic hosts and range from roughly 0.8 to 0.9 for eukaryotic hosts. Furthermore, EvoMIL identifies important proteins in the prediction task, capturing key functions involved in virus-host specificity.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- MRC-University of Glasgow Centre for Virus Research, Glasgow, United Kingdom.
- School of Computing Science, University of Glasgow, Glasgow, United Kingdom.
- School of Cancer Sciences, University of Glasgow, Glasgow, United Kingdom.
- Cancer Research UK Scotland Institute, Glasgow, United Kingdom.
ORCID-Profile: Kieran D Lamb, Ke Yuan
Förderung
- European Union’s Horizon 2020 research and innovation program
- Medical Research Council
- Doctoral Training Programme in Precision Medicine studentship
- Biotechnology and Biological Sciences Research Council
- Engineering and Physical Sciences Research Council
- H2020 Marie Skłodowska-Curie Actions
Zitieren
APA
Liu, D., Young, F., Lamb, K. D., Robertson, D. L., & Yuan, K. (2024). Prediction of virus-host associations using protein language models and multiple instance learning. PLOS Computational Biology, 20(11), e1012597. https://doi.org/10.1371/journal.pcbi.1012597
Vancouver
Liu D, Young F, Lamb KD, Robertson DL, Yuan K. Prediction of virus-host associations using protein language models and multiple instance learning. PLOS Computational Biology. 2024;20(11):e1012597. doi:10.1371/journal.pcbi.1012597
BibTeX
@article{Liu2024,
author = {Liu, Dan and Young, Francesca and Lamb, Kieran D and Robertson, David L and Yuan, Ke},
title = {Prediction of virus-host associations using protein language models and multiple instance learning},
journal = {PLOS Computational Biology},
year = {2024},
volume = {20},
number = {11},
pages = {e1012597},
doi = {10.1371/journal.pcbi.1012597}
}
EUVIMED