Protein large language model–assisted one-to-one gene homology mapping in cross-species single-cell transcriptome integration
Genome Research · 2026-11 · 36 (11) · 2351-2364
DOI: 10.1101/gr.281566.125 ↗Kurz gefasst
Fachartikel in der Zeitschrift Genome Research, online erschienen am 09.10.2026. Verfasst von Ze-Yu Kuang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, School of Basic Medical Sciences, Peking University Health Science Center, Beijing 100191, China. Hauptthemen laut MEDLINE: Transcriptome, Single-Cell Analysis, Chromosome Mapping. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, the Beijing Natural Science Foundation, the Noncommunicable Chronic Diseases-National Science and Technology Major Project.
Abstract (Originalsprache)
Cross-species integration of single-cell transcriptomes requires establishing gene correspondences to enable comparative analysis of expression profiles across organisms. Current approaches predominantly rely on Ensembl homology tables; although gene-family expansion and contraction can reflect biologically meaningful evolutionary divergence, default many-to-many mappings can overweight expanded gene-family signals during integration and generate mapping-associated microclusters that lack clear cell-type identity, thereby complicating direct cell-type alignment. Although restricting mappings to a one-to-one scheme suppresses such artifacts, it reduces the number of homology gene pairs by ∼8% (about 900 pairs). To address this limitation, we develop a protein large language model (pLLM)–based gene homology mapping strategy that boosts the number of homology gene pairs. By enforcing a one-to-one mapping constraint and integrating pLLM-derived representations with sequence similarity, we construct a fused mapping approach, which achieves top performance in a comprehensive benchmark based on a curated cross-species atlas spanning nine data sets, 11 species, and more than 3.2 million cells. Our method further identifies previously unannotated cell-type marker pairs, facilitating novel cross-species marker discovery. These results establish a robust framework for gene homology mapping in cross-species transcriptome integration, improving both accuracy and biological interpretability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biomedical Informatics, School of Basic Medical Sciences, Peking University Health Science Center, Beijing 100191, China.
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Peking University Cancer Hospital and Institute, Beijing 100142, China.
- Center for Single-Cell Omics, School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China.
- Department of Biomedical Informatics, School of Basic Medical Sciences, Peking University Health Science Center, Beijing 100191, China; hjwu@pku.edu.cn.
- Beijing Advanced Center of Cellular Homeostasis and Aging-Related Diseases, Center for Precision Medicine Multi-Omics Research, Institute of Advanced Clinical Medicine, Peking University, Beijing 100191, China.
Förderung
- National Natural Science Foundation of China
- the Beijing Natural Science Foundation
- the Noncommunicable Chronic Diseases-National Science and Technology Major Project
- the Fundamental Research Funds for the Central Universities
Zitieren
APA
Kuang, Z. Y., Sun, Y. C., Wei, N. N., Wang, Y. J., & Wu, H. J. (2026). Protein large language model–assisted one-to-one gene homology mapping in cross-species single-cell transcriptome integration. Genome Research, 36(11), 2351-2364. https://doi.org/10.1101/gr.281566.125
Vancouver
Kuang ZY, Sun YC, Wei NN, Wang YJ, Wu HJ. Protein large language model–assisted one-to-one gene homology mapping in cross-species single-cell transcriptome integration. Genome Research. 2026;36(11):2351-2364. doi:10.1101/gr.281566.125
BibTeX
@article{Kuang2026,
author = {Kuang, Ze-Yu and Sun, Yuan-Chen and Wei, Na-Na and Wang, Yu-Juan and Wu, Hua-Jun},
title = {Protein large language model–assisted one-to-one gene homology mapping in cross-species single-cell transcriptome integration},
journal = {Genome Research},
year = {2026},
volume = {36},
number = {11},
pages = {2351--2364},
doi = {10.1101/gr.281566.125}
}
EUVIMED