{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T12:13:40Z","timestamp":1789992820691,"version":"4.0.1"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"vor","delay-in-days":20,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2025JBZX064"],"award-info":[{"award-number":["2025JBZX064"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82374302"],"award-info":[{"award-number":["82374302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82274352"],"award-info":[{"award-number":["82274352"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2062"],"award-info":[{"award-number":["U23B2062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing","doi-asserted-by":"publisher","award":["L232033"],"award-info":[{"award-number":["L232033"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Predicting mRNA translation efficiency across diverse tissues is a critical yet challenging task due to the phenomenon of concept shift, where identical genomic sequences exhibit distinct functional profiles across varying cellular environments. Existing static models are often limited by fixed parameterization, struggling to capture these continuous regulatory variations without requiring computationally expensive fine-tuning. To address these limitations, we propose ContiTE, a continuous manifold mixture-of-experts (MoE) framework explicitly designed for efficient few-shot cross-tissue adaptation. Unlike traditional MoE architectures that rely on discrete output-space mixing, ContiTE operates on a continuous parameter manifold by dynamically synthesizing domain-specific weights through a context-aware hyper-router that linearly combines shared atomic basis kernels. This paradigm enables smooth interpolation of translational rules and provides a flexible mechanism to model complex, context-dependent biological regulation. Furthermore, we introduce a gradient-based test-time adaptation strategy that allows the model to rapidly align to new, unseen tissues by solely optimizing low-dimensional context embeddings while keeping the backbone parameters frozen. Experimental results on a comprehensive human and mouse atlas demonstrate that ContiTE significantly outperforms state-of-the-art methods in few-shot scenarios, improving average Pearson correlation coefficient by 12.09% and $R^{2}$ by 18.22%. By mitigating negative transfer and requiring only limited target-domain data for calibration, ContiTE provides a computational framework for tissue-specific mRNA translation-efficiency prediction and demonstrates a parameter-reconstruction strategy that may be extensible to other cross-domain sequence-learning tasks, subject to task-specific validation.<\/jats:p>","DOI":"10.1093\/bib\/bbag518","type":"journal-article","created":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T11:37:28Z","timestamp":1788521848000},"source":"Crossref","is-referenced-by-count":0,"title":["ContiTE: continuous manifold MoE for few-shot cross-tissue mRNA translation efficiency prediction"],"prefix":"10.1093","volume":"27","author":[{"given":"Yuxiao","family":"Wei","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University , Beijing 100044 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology , 200 Xiaolingwei, Nanjing 210094 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sainan","family":"Huo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University , Beijing 100044 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuezhong","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University , Beijing 100044 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"key":"2026092105555319400_ref1","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1038\/nature10098","article-title":"Global quantification of mammalian gene expression control","volume":"473","author":"Schwanh\u00e4usser","year":"2011","journal-title":"Nature."},{"key":"2026092105555319400_ref2","doi-asserted-by":"crossref","first-page":"a011528","DOI":"10.1101\/cshperspect.a011528","article-title":"Principles of translational control: an overview","volume":"4","author":"Hershey","year":"2012","journal-title":"Cold Spring Harb Perspect Biol"},{"key":"2026092105555319400_ref3","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/nrd.2017.243","article-title":"mRNA vaccines\u2014a new era in vaccinology","volume":"17","author":"Pardi","year":"2018","journal-title":"Nat Rev Drug Discov"},{"key":"2026092105555319400_ref4","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1038\/nrd4278","article-title":"mRNA-based therapeutics\u2014developing a new class of drugs","volume":"13","author":"Sahin","year":"2014","journal-title":"Nat Rev Drug Discov"},{"key":"2026092105555319400_ref5","doi-asserted-by":"crossref","first-page":"706","DOI":"10.3390\/ijms26020706","article-title":"Decoding codon bias: the role of tRNA modifications in tissue-specific translation","volume":"26","author":"Ando","year":"2025","journal-title":"Int J Mol Sci"},{"key":"2026092105555319400_ref6","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1146\/annurev.biochem.68.1.913","article-title":"eIF4 initiation factors: effectors of mRNA recruitment to ribosomes and regulators of translation","volume":"68","author":"Gingras","year":"1999","journal-title":"Annu Rev Biochem"},{"key":"2026092105555319400_ref7","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1016\/j.patcog.2011.06.019","article-title":"A unifying view on dataset shift in classification","volume":"45","author":"Moreno-Torres","year":"2012","journal-title":"Pattern Recogn"},{"key":"2026092105555319400_ref8","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1016\/j.cell.2010.03.031","article-title":"An evolutionarily conserved mechanism for controlling the efficiency of protein translation","volume":"141","author":"Tuller","year":"2010","journal-title":"Cell."},{"key":"2026092105555319400_ref9","doi-asserted-by":"crossref","first-page":"8125","DOI":"10.1093\/nar\/15.20.8125","article-title":"An analysis of 5$\\prime $-noncoding sequences from 699 vertebrate messenger RNAs","volume":"15","author":"Kozak","year":"1987","journal-title":"Nucleic Acids Res"},{"key":"2026092105555319400_ref10","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1126\/science.1170160","article-title":"Coding-sequence determinants of gene expression in Escherichia coli","volume":"324","author":"Kudla","year":"2009","journal-title":"Science."},{"key":"2026092105555319400_ref11","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1038\/s41587-019-0164-5","article-title":"Human 5$\\prime $ UTR design and variant effect prediction from a massively parallel translation assay","volume":"37","author":"Sample","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2026092105555319400_ref12","doi-asserted-by":"crossref","first-page":"e1008982","DOI":"10.1371\/journal.pcbi.1008982","article-title":"Predicting mean ribosome load for 5$\\prime $ UTR of any length using deep learning","volume":"17","author":"Karollus","year":"2021","journal-title":"PLoS Comput Biol"},{"key":"2026092105555319400_ref13","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1186\/s13059-022-02811-x","article-title":"The genetic and biochemical determinants of mRNA degradation rates in mammals","volume":"23","author":"Agarwal","year":"2022","journal-title":"Genome Biol"},{"key":"2026092105555319400_ref14","article-title":"Predicting the translation efficiency of messenger RNA in mammalian cells","volume":"44","author":"Zheng","journal-title":"Nat Biotechnol"},{"key":"2026092105555319400_ref15","doi-asserted-by":"crossref","first-page":"bbad001","DOI":"10.1093\/bib\/bbad001","article-title":"Integrated mRNA sequence optimization using deep learning","volume":"24","author":"Gong","year":"2023","journal-title":"Brief Bioinform"},{"key":"2026092105555319400_ref16","doi-asserted-by":"crossref","first-page":"bbae627","DOI":"10.1093\/bib\/bbae627","article-title":"The improved de Bruijn graph for multitask learning: predicting functions, subcellular localization, and interactions of noncoding RNAs","volume":"26","author":"Wei","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026092105555319400_ref17","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac581","article-title":"RNAdegformer: accurate prediction of mRNA degradation at nucleotide resolution with deep learning","volume":"24","author":"He","journal-title":"Brief Bioinform"},{"key":"2026092105555319400_ref18","doi-asserted-by":"crossref","first-page":"10371","DOI":"10.1038\/s41467-025-65340-8","article-title":"mRNABERT: advancing mRNA sequence design with a universal language model and comprehensive dataset","volume":"16","author":"Xiong","year":"2025","journal-title":"Nat Commun"},{"key":"2026092105555319400_ref19","doi-asserted-by":"crossref","first-page":"1616","DOI":"10.1038\/s42256-024-00946-z","article-title":"An interpretable RNA foundation model for exploring functional RNA motifs in plants","volume":"6","author":"Yu","year":"2024","journal-title":"Nat Mach Intell"},{"key":"2026092105555319400_ref20","article-title":"Comprehensive mapping of RNA modification dynamics and crosstalk via deep learning and nanopore direct RNA-sequencing","volume":"17","author":"Dong","year":"2026","journal-title":"Nat Commun"},{"key":"2026092105555319400_ref21","doi-asserted-by":"crossref","first-page":"e1008050","DOI":"10.1371\/journal.pcbi.1008050","article-title":"Cross-species regulatory sequence activity prediction","volume":"16","author":"Kelley","year":"2020","journal-title":"PLoS Comput Biol"},{"key":"2026092105555319400_ref22","article-title":"Improving predictive inference under covariate shift by weighting the log-likelihood function","volume":"90","author":"Shimodaira","journal-title":"J Stat Plan Inference"},{"key":"2026092105555319400_ref23","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1186\/s13059-019-1764-6","article-title":"BERMUDA: a novel deep transfer learning method for single-cell RNA sequencing batch correction reveals hidden high-resolution cellular subtypes","volume":"20","author":"Wang","year":"2019","journal-title":"Genome Biol"},{"key":"2026092105555319400_ref24","doi-asserted-by":"crossref","first-page":"bbae004","DOI":"10.1093\/bib\/bbae004","article-title":"Species-agnostic transfer learning for cross-species transcriptomics data integration without gene orthology","volume":"25","author":"Park","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026092105555319400_ref25","doi-asserted-by":"crossref","first-page":"bbae257","DOI":"10.1093\/bib\/bbae257","article-title":"Multi-modal domain adaptation for revealing spatial functional landscape from spatially resolved transcriptomics","volume":"25","author":"Wang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026092105555319400_ref26","volume-title":"Proceedings of the 36th International Conference on Machine Learning, Long Beach, California, USA, 9\u201315 June 2019","author":""},{"key":"2026092105555319400_ref27","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1038\/nbt.2859","article-title":"The dynamics and regulators of cell fate decisions are revealed by pseudotemporal ordering of single cells","volume":"32","author":"Trapnell","year":"2014","journal-title":"Nat Biotechnol"},{"key":"2026092105555319400_ref28","doi-asserted-by":"crossref","first-page":"1482","DOI":"10.1038\/s41587-019-0336-3","article-title":"Visualizing structure and transitions in high-dimensional biological data","volume":"37","author":"Moon","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2026092105555319400_ref29","article-title":"Quantifying individual health status from multi-omics data by health state manifold","volume":"5","author":"Zhang","journal-title":"Phenomics."},{"key":"2026092105555319400_ref30","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","author":""},{"key":"2026092105555319400_ref31","author":"","journal-title":"International Conference on Learning Representations (ICLR 2017), Toulon, France"},{"key":"2026092105555319400_ref32","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026092105555319400_ref33","article-title":"CondConv: conditionally parameterized convolutions for efficient inference","volume":"32","author":"Yang","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026092105555319400_ref34","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":""},{"key":"2026092105555319400_ref35","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Lvd","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2026092105555319400_ref36","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":""}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag518\/71270011\/bbag518.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag518\/71270011\/bbag518.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T11:44:26Z","timestamp":1789991066000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag518\/8822816"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":36,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag518","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,9,1]]},"article-number":"bbag518"}}