{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T16:04:25Z","timestamp":1783958665582,"version":"3.55.0"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["22H03691"],"award-info":[{"award-number":["22H03691"]}]},{"name":"Japan Agency for Medical Esearch and Development","award":["JP19ak0101122"],"award-info":[{"award-number":["JP19ak0101122"]}]},{"name":"New Energy and Industrial Technology Development Organization","award":["JPNP14004"],"award-info":[{"award-number":["JPNP14004"]}]},{"name":"Japan Association for Chemical Innovation (JACI) Prize for Encouraging Young Researcher"},{"name":"ROIS National Institute of Genetics"},{"name":"SQUID supercomputer at Cybermedia Center"},{"name":"Osaka University through the HPCI System","award":["hp230057"],"award-info":[{"award-number":["hp230057"]}]},{"name":"Osaka University through the HPCI System","award":["hp240075"],"award-info":[{"award-number":["hp240075"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Data scarcity limits the characterization of protein fitness landscapes and the development of accurate variant effect prediction models. To address this challenge, we introduce fitness translocation, a data augmentation strategy that generates synthetic variants for a target protein by leveraging variant fitness data previously measured in homologous proteins. Using embeddings from protein language models, the method computes the difference between each homolog variant and its wild type and applies these offsets to the target wild-type embedding to create synthetic variants in embedding space.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We illustrate the utility of fitness translocation in the context of variant effect prediction on three protein families: IGPS, GFP, and SARS-CoV-2 spike proteins, across different models and training data sizes. Fitness translocation consistently improves predictive performance, particularly under limited training data, and is effective even when augmenting with remote homologs sharing as little as 35% sequence identity. These results illustrate how biologically grounded data augmentation can expand and diversify protein fitness landscapes, supporting more data-efficient protein engineering.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and Implementation<\/jats:title>\n                    <jats:p>The code and datasets are available at https:\/\/github.com\/adrienmialland\/ProtFitTrans<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag415","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T11:18:34Z","timestamp":1781695114000},"source":"Crossref","is-referenced-by-count":0,"title":["Fitness translocation: improving variant effect prediction with biologically-grounded data augmentation"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5359-674X","authenticated-orcid":false,"given":"Adrien","family":"Mialland","sequence":"first","affiliation":[{"name":"Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology (AIST) , Tokyo,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuzo","family":"Fukunaga","sequence":"additional","affiliation":[{"name":"University of Toronto , Tronto,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Riku","family":"Katsuki","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications , Tokyo,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunfei","family":"Dong","sequence":"additional","affiliation":[{"name":"The University of Tokyo , Chiba,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hideki","family":"Yamaguchi","sequence":"additional","affiliation":[{"name":"The University of Tokyo , Chiba,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4853-0153","authenticated-orcid":false,"given":"Yutaka","family":"Saito","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology (AIST) , Tokyo,","place":["Japan"]},{"name":"The University of Tokyo , Chiba,","place":["Japan"]},{"name":"School of Frontier Engineering, Kitasato University , Kanagawa,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"2026071311073376600_btag415-B1","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1038\/s41592-019-0598-1","article-title":"Unified rational protein engineering with sequence-based deep representation learning","volume":"16","author":"Alley","year":"2019","journal-title":"Nat Methods"},{"key":"2026071311073376600_btag415-B2","doi-asserted-by":"publisher","first-page":"2102","DOI":"10.1093\/bioinformatics\/btac020","article-title":"Proteinbert: a universal deep-learning model of protein sequence and function","volume":"38","author":"Brandes","year":"2022","journal-title":"Bioinformatics"},{"key":"2026071311073376600_btag415-B3","doi-asserted-by":"publisher","first-page":"14614","DOI":"10.1038\/ncomms14614","article-title":"Correlation of fitness landscapes from three orthologous tim barrels originates from sequence and structure constraints","volume":"8","author":"Chan","year":"2017","journal-title":"Nat Commun"},{"key":"2026071311073376600_btag415-B4","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1038\/s41586-024-07636-1","article-title":"Spike deep mutational scanning helps predict success of sars-cov-2 clades","volume":"631","author":"Dadonaite","year":"2024","journal-title":"Nature"},{"key":"2026071311073376600_btag415-B5","doi-asserted-by":"publisher","first-page":"2944","DOI":"10.1093\/molbev\/msv167","article-title":"Site-specific amino acid preferences are mostly conserved in two closely related protein homologs","volume":"32","author":"Doud","year":"2015","journal-title":"Mol Biol Evol"},{"key":"2026071311073376600_btag415-B6","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"Prottrans: toward understanding the language of life through self-supervised learning","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026071311073376600_btag415-B7","doi-asserted-by":"publisher","author":"Feng","year":"2021","DOI":"10.48550\/arXiv.2105.03075"},{"key":"2026071311073376600_btag415-B8","doi-asserted-by":"publisher","first-page":"102713","DOI":"10.1016\/j.copbio.2022.102713","article-title":"Machine learning to navigate fitness landscapes for protein engineering","volume":"75","author":"Freschlin","year":"2022","journal-title":"Curr Opin Biotechnol"},{"key":"2026071311073376600_btag415-B9","doi-asserted-by":"publisher","first-page":"5571","DOI":"10.1021\/acs.chemrev.2c0091","article-title":"Ultrahigh-throughput enzyme engineering and discovery in in vitro compartments","volume":"123","author":"Gantz","year":"2023","journal-title":"Chem Rev"},{"key":"2026071311073376600_btag415-B10","doi-asserted-by":"publisher","first-page":"6235","DOI":"10.1021\/acs.iecr.1c04943","article-title":"Recent advances in machine learning variant effect prediction tools for protein engineering","volume":"61","author":"Horne","year":"2022","journal-title":"Ind Eng Chem Res"},{"key":"2026071311073376600_btag415-B11","doi-asserted-by":"publisher","author":"Hsu","year":"2014","DOI":"10.1002\/9781118445112.stat05929"},{"key":"2026071311073376600_btag415-B12","doi-asserted-by":"publisher","first-page":"10123","DOI":"10.1007\/s00521-023-08459-3","article-title":"Data augmentation techniques in time series domain: a survey and taxonomy","volume":"35","author":"Iglesias","year":"2023","journal-title":"Neural Comput Appl"},{"key":"2026071311073376600_btag415-B13","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1186\/s12859-024-05787-6","article-title":"Assessing the reliability of point mutation as data augmentation for deep learning with genomic data","volume":"25","author":"Lee","year":"2024","journal-title":"BMC Bioinform"},{"key":"2026071311073376600_btag415-B14","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.aiopen.2022.03.001","article-title":"Data augmentation approaches in natural language processing: a survey","volume":"3","author":"Li","year":"2022","journal-title":"Ai Open"},{"key":"2026071311073376600_btag415-B15","doi-asserted-by":"publisher","first-page":"500902","DOI":"10.1101\/2022.07.20.500902","article-title":"Language models of protein sequences at the scale of evolution enable accurate structure prediction","volume":"2022","author":"Lin","year":"2022","journal-title":"BioRxiv"},{"key":"2026071311073376600_btag415-B16","doi-asserted-by":"publisher","first-page":"W521","DOI":"10.1093\/nar\/gkae241","article-title":"The EMBL-EBI job dispatcher sequence analysis tools framework in 2024","volume":"52","author":"Madeira","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026071311073376600_btag415-B17","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1039\/C8CS00981C","article-title":"Advances in ultrahigh-throughput screening for directed enzyme evolution","volume":"49","author":"Markel","year":"2020","journal-title":"Chem Soc Rev"},{"key":"2026071311073376600_btag415-B18","doi-asserted-by":"publisher","first-page":"29287","DOI":"10.1101\/2021.07.09.450648","article-title":"Language models enable zero-shot prediction of the effects of mutations on protein function","volume":"34","author":"Meier","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026071311073376600_btag415-B19","doi-asserted-by":"crossref","first-page":"64331","DOI":"10.52202\/075280-2810","article-title":"ProteinGym: large-scale benchmarks for protein fitness prediction and design","volume":"36","author":"Notin","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026071311073376600_btag415-B20","doi-asserted-by":"publisher","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026071311073376600_btag415-B21","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1038\/nrm2805","article-title":"Exploring protein fitness landscapes by directed evolution","volume":"10","author":"Romero","year":"2009","journal-title":"Nat Rev Mol Cell Biol"},{"key":"2026071311073376600_btag415-B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J Big Data"},{"key":"2026071311073376600_btag415-B23","doi-asserted-by":"publisher","first-page":"e75842","DOI":"10.7554\/eLife.75842","article-title":"Heterogeneity of the GFP fitness landscape and data-driven protein design","volume":"11","author":"Somermeyer","year":"2022","journal-title":"Elife"},{"key":"2026071311073376600_btag415-B24","doi-asserted-by":"publisher","author":"Sun","year":"2024","DOI":"10.48550\/arXiv.2403.00875"},{"key":"2026071311073376600_btag415-B25","doi-asserted-by":"publisher","first-page":"2917","DOI":"10.1109\/TCSVT.2019.2935128","article-title":"Data augmentation using random image cropping and patching for deep CNNs","volume":"30","author":"Takahashi","year":"2020","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2026071311073376600_btag415-B26","doi-asserted-by":"publisher","author":"Tang","DOI":"10.1093\/bib\/bbae338"},{"key":"2026071311073376600_btag415-B27","doi-asserted-by":"publisher","first-page":"e0224365","DOI":"10.1371\/journal.pone.0224365","article-title":"Machine learning algorithm validation with a limited sample size","volume":"14","author":"Vabalas","year":"2019","journal-title":"PLoS One"},{"key":"2026071311073376600_btag415-B28","doi-asserted-by":"publisher","first-page":"2455","DOI":"10.1039\/D1CC04635G","article-title":"High-throughput screening, next generation sequencing and machine learning: advanced methods in enzyme engineering","volume":"58","author":"Vanella","year":"2022","journal-title":"Chem Commun (Camb)"},{"key":"2026071311073376600_btag415-B29","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.sbi.2021.01.008","article-title":"Advances in machine learning for directed evolution","volume":"69","author":"Wittmann","year":"2021","journal-title":"Curr Opin Struct Biol"},{"key":"2026071311073376600_btag415-B30","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1038\/s41592-019-0496-6","article-title":"Machine-learning-guided directed evolution for protein engineering","volume":"16","author":"Yang","year":"2019","journal-title":"Nat Methods"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag415\/68568039\/btag415.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/7\/btag415\/68568039\/btag415.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/7\/btag415\/68568039\/btag415.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T15:07:43Z","timestamp":1783955263000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag415\/8712836"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,20]]},"references-count":30,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag415","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,6,20]]},"article-number":"btag415"}}