{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T15:27:40Z","timestamp":1789658860198,"version":"4.0.1"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009398","name":"Medizinische Fakult\u00e4t, RWTH Aachen University","doi-asserted-by":"publisher","award":["START"],"award-info":[{"award-number":["START"]}],"id":[{"id":"10.13039\/501100009398","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Universit\u00e4tsklinikum RWTH Aachen","id":[{"id":"https:\/\/ror.org\/04xfq0f34","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Genome Biol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Decoding the genetic code to unveil its genome functionality is a monumental task which would greatly advance the understanding of disease mechanisms and development of targeted treatments. Although large language models (LLMs) have transformed natural language processing across diverse domains, translating the complex language of DNA into human-readable form remains challenging due to genomic data complexity and unexplored regions of the human genome. Current language models either are capable of processing natural language or the genomic code. Models fusing both aspects are largely lacking.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Here we present Genolator, a multimodal large language model that integrates embeddings from DNA sequences, amino acid sequences, and protein structures with natural language queries. Fine-tuned on over 365,000 question\u2013answer pairs generated using abstracted Gene-Ontology (GO) terms, Genolator effectively answers queries regarding protein subcellular localization, molecular function, and biological processes. Evaluation demonstrates high accuracy in confirming or denying protein function associations, outperforming baseline models such as openly available allrounder LLMs like GPT 4.1 as well as smaller domain-specific models integrating knowledge from a protein structure transformer. Explorations of Genolator\u2019s hidden states unveil a biologically and linguistically plausible organization of its learned representations. Analysis of the attention heads of the underlying language model and an ablation study provide evidence for a benefit of the multi-modal approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Genolator enhances accessibility to genomic information by enabling natural language interaction with protein data, facilitating biological discovery, and clinical research. It represents a step towards bridging genomic code and human language through the integration of a multimodal LLM.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13059-026-04274-w","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T02:23:58Z","timestamp":1789525438000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Genolator enables protein function interpretation using a multimodal large language model fusing genomic and structural interpretation with natural language interaction"],"prefix":"10.1186","volume":"27","author":[{"given":"Martin","family":"Danner","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanhim","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Begemann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Kraft","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miriam","family":"Elbracht","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ingo","family":"Kurth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9915-7400","authenticated-orcid":false,"given":"Jeremias","family":"Krause","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"4274_CR1","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1146\/annurev.biochem.72.121801.161809","volume":"72","author":"JB Lowe","year":"2003","unstructured":"Lowe JB, Marth JD. A genetic approach to mammalian glycan function. Annu Rev Biochem. 2003;72:643\u201391.","journal-title":"Annu Rev Biochem"},{"key":"4274_CR2","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.tcb.2021.10.010","volume":"32","author":"BW Wright","year":"2022","unstructured":"Wright BW, Yi Z, Weissman JS, Chen J. The dark proteome: translation from noncanonical open reading frames. Trends Cell Biol. 2022;32:243\u201358.","journal-title":"Trends Cell Biol"},{"key":"4274_CR3","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1038\/d41586-025-00217-w","volume":"637","author":"E Callaway","year":"2025","unstructured":"Callaway E. \u2018Dark proteins\u2019 hiding in our cells could hold clues to cancer and other diseases. Nature. 2025;637:1038\u201340.","journal-title":"Nature"},{"key":"4274_CR4","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1016\/j.ccell.2022.07.003","volume":"40","author":"AR Cahn","year":"2022","unstructured":"Cahn AR, Bhardwaj N, Vabret N. Dark genome, bright ideas: recent approaches to harness transposable elements in immunotherapies. Cancer Cell. 2022;40:792\u20137.","journal-title":"Cancer Cell"},{"key":"4274_CR5","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1186\/s13059-024-03258-y","volume":"25","author":"D Blanco-Melo","year":"2024","unstructured":"Blanco-Melo D, et al. A novel approach to exploring the dark genome and its application to mapping of the vertebrate virus fossil record. Genome Biol. 2024;25:120.","journal-title":"Genome Biol"},{"key":"4274_CR6","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-023-05870-7","volume":"616","author":"J Kreitz","year":"2023","unstructured":"Kreitz J, et al. Programmable protein delivery with a bacterial contractile injection system. Nature. 2023;616:357\u201364.","journal-title":"Nature"},{"key":"4274_CR7","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1038\/s42256-024-00795-w","volume":"6","author":"M Kulmanov","year":"2024","unstructured":"Kulmanov M, et al. Protein function prediction as approximate semantic entailment. Nat Mach Intell. 2024;6:220\u20138.","journal-title":"Nat Mach Intell"},{"key":"4274_CR8","doi-asserted-by":"publisher","first-page":"btaf390","DOI":"10.1093\/bioinformatics\/btaf390","volume":"41","author":"B Wang","year":"2025","unstructured":"Wang B, et al. ProtGO: universal protein function prediction utilizing multi-modal gene ontology knowledge. Bioinformatics. 2025;41:btaf390.","journal-title":"Bioinformatics"},{"issue":"1","key":"4274_CR9","doi-asserted-by":"publisher","first-page":"vbae120","DOI":"10.1093\/bioadv\/vbae120","volume":"4","author":"F Boadu","year":"2024","unstructured":"Boadu F, Cheng J. Improving protein function prediction by learning and integrating representations of protein sequences and function labels. Bioinformatics Adv. 2024;4:vbae120.","journal-title":"Bioinformatics Adv"},{"key":"4274_CR10","doi-asserted-by":"publisher","first-page":"3168","DOI":"10.1038\/s41467-021-23303-9","volume":"12","author":"V Gligorijevi\u0107","year":"2021","unstructured":"Gligorijevi\u0107 V, et al. Structure-based protein function prediction using graph convolutional networks. Nat Commun. 2021;12:3168.","journal-title":"Nat Commun"},{"key":"4274_CR11","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1109\/TCBB.2022.3143480","volume":"20","author":"H Wang","year":"2023","unstructured":"Wang H, Zheng H, Chen DZ. TANGO: a GO-term embedding based method for protein semantic similarity prediction. IEEE ACM Trans Comput Biol Bioinform. 2023;20:694\u2013706.","journal-title":"IEEE ACM Trans Comput Biol Bioinform"},{"key":"4274_CR12","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6272-2","volume":"20","author":"X Zhong","year":"2019","unstructured":"Zhong X, Kaalia R, Rajapakse JC. GO2Vec: transforming GO terms and proteins to vector representations via graph embeddings. BMC Genomics. 2019;20:918.","journal-title":"BMC Genomics"},{"key":"4274_CR13","doi-asserted-by":"publisher","first-page":"4488","DOI":"10.1093\/bioinformatics\/btac536","volume":"38","author":"GA Merino","year":"2022","unstructured":"Merino GA, Saidi R, Milone DH, Stegmayer G, Martin MJ. Hierarchical deep learning for predicting GO annotations by integrating protein knowledge. Bioinformatics. 2022;38:4488\u201396.","journal-title":"Bioinformatics"},{"key":"4274_CR14","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1016\/j.ygeno.2018.02.008","volume":"111","author":"Y Zhao","year":"2019","unstructured":"Zhao Y, Fu G, Wang J, Guo M, Yu G. Gene function prediction based on Gene Ontology Hierarchy Preserving Hashing. Genomics. 2019;111:334\u201342.","journal-title":"Genomics"},{"key":"4274_CR15","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae050","volume":"25","author":"W Wang","year":"2024","unstructured":"Wang W, et al. A comprehensive computational benchmark for evaluating deep learning-based protein function prediction approaches. Brief Bioinform. 2024;25:bbae050.","journal-title":"Brief Bioinform"},{"key":"4274_CR16","doi-asserted-by":"publisher","first-page":"2269","DOI":"10.1093\/bioinformatics\/btac104","volume":"38","author":"I Ieremie","year":"2022","unstructured":"Ieremie I, Ewing RM, Niranjan M. TransformerGO: predicting protein\u2013protein interactions by modelling the attention between sets of gene ontology terms. Bioinformatics. 2022;38:2269\u201377.","journal-title":"Bioinformatics"},{"key":"4274_CR17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-98483-1","volume":"15","author":"M Raza","year":"2025","unstructured":"Raza M, Jahangir Z, Riaz MB, Saeed MJ, Sattar MA. Industrial applications of large language models. Sci Rep. 2025;15:13755.","journal-title":"Sci Rep"},{"key":"4274_CR18","doi-asserted-by":"publisher","first-page":"btae075","DOI":"10.1093\/bioinformatics\/btae075","volume":"40","author":"Q Jin","year":"2024","unstructured":"Jin Q, Yang Y, Chen Q, Lu Z. GeneGPT: augmenting large language models with domain tools for improved access to biomedical information. Bioinformatics. 2024;40:btae075.","journal-title":"Bioinformatics"},{"key":"4274_CR19","doi-asserted-by":"publisher","unstructured":"Wang S, et al. Large Language Models for Education: A Survey and Outlook. 2024. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2403.18105.","DOI":"10.48550\/arXiv.2403.18105"},{"key":"4274_CR20","doi-asserted-by":"publisher","unstructured":"Masri S, Ashqar HI, Elhenawy M. Leveraging Large Language Models (LLMs) for Traffic Management at Urban Intersections: The Case of Mixed Traffic Scenarios. 2024. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2408.00948.","DOI":"10.48550\/arXiv.2408.00948"},{"key":"4274_CR21","doi-asserted-by":"publisher","unstructured":"Li Y, Wang S, Ding H, Chen H. Large Language Models in Finance: A Survey. 2024. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2311.10723.","DOI":"10.48550\/arXiv.2311.10723"},{"key":"4274_CR22","doi-asserted-by":"publisher","unstructured":"Brixi G, et al. Genome modeling and design across all domains of life with Evo 2. 2025.02.18.638918. 2025. Preprint at https:\/\/doi.org\/10.1101\/2025.02.18.638918.","DOI":"10.1101\/2025.02.18.638918"},{"key":"4274_CR23","doi-asserted-by":"publisher","DOI":"10.1126\/science.ado9336","volume":"386","author":"E Nguyen","year":"2024","unstructured":"Nguyen E, et al. Sequence modeling and design from molecular to genome scale with Evo. Science. 2024;386:eado9336.","journal-title":"Science"},{"key":"4274_CR24","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1038\/s41592-024-02523-z","volume":"22","author":"H Dalla-Torre","year":"2025","unstructured":"Dalla-Torre H, et al. Nucleotide transformer: building and evaluating robust foundation models for human genomics. Nat Methods. 2025;22:287\u201397.","journal-title":"Nat Methods"},{"key":"4274_CR25","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1038\/s42256-024-00872-0","volume":"6","author":"M Sanabria","year":"2024","unstructured":"Sanabria M, Hirsch J, Joubert PM, Poetsch AR. DNA language model GROVER learns sequence context in the human genome. Nat Mach Intell. 2024;6:911\u201323.","journal-title":"Nat Mach Intell"},{"key":"4274_CR26","doi-asserted-by":"publisher","unstructured":"Nguyen E, et al. HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution. 2023. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2306.15794.","DOI":"10.48550\/arXiv.2306.15794"},{"key":"4274_CR27","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2421738122","author":"J Zhai","year":"2025","unstructured":"Zhai J, et al. Cross-species modeling of plant genomes at single-nucleotide resolution using a pretrained DNA language model. Proc Natl Acad Sci U S A. 2025. https:\/\/doi.org\/10.1073\/pnas.2421738122.","journal-title":"Proc Natl Acad Sci U S A"},{"key":"4274_CR28","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1038\/s42256-025-01047-1","volume":"7","author":"BP de Almeida","year":"2025","unstructured":"de Almeida BP, et al. A multimodal conversational agent for DNA, RNA and protein tasks. Nat Mach Intell. 2025;7:928\u201341.","journal-title":"Nat Mach Intell"},{"key":"4274_CR29","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1038\/75556","volume":"25","author":"M Ashburner","year":"2000","unstructured":"Ashburner M, et al. Gene ontology: tool for the unification of biology. Nat Genet. 2000;25:25\u20139.","journal-title":"Nat Genet"},{"key":"4274_CR30","doi-asserted-by":"publisher","unstructured":"Danner M, Begemann M, Elbracht M, Kurth I, Krause J. Utilizing protein structure graph embeddings to predict the pathogenicity of missense variants. 2024.11.15.623748. 2024. Preprint at https:\/\/doi.org\/10.1101\/2024.11.15.623748.","DOI":"10.1101\/2024.11.15.623748"},{"key":"4274_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2025.105509","volume":"158","author":"V Guarrasi","year":"2025","unstructured":"Guarrasi V, et al. A systematic review of intermediate fusion in multimodal deep learning for biomedical applications. Image Vis Comput. 2025;158:105509.","journal-title":"Image Vis Comput"},{"key":"4274_CR32","unstructured":"Wang J, et al. A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different Tasks. 2024. arXiv.org https:\/\/arxiv.org\/abs\/2408.01319v1."},{"key":"4274_CR33","doi-asserted-by":"publisher","unstructured":"Grattafiori A, et al. The Llama 3 Herd of Models. 2024. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2407.21783.","DOI":"10.48550\/arXiv.2407.21783"},{"key":"4274_CR34","unstructured":"Touvron H, et al. Llama 2: Open Foundation and Fine-Tuned Chat Models. 2023. arXiv.org https:\/\/arxiv.org\/abs\/2307.09288v2."},{"key":"4274_CR35","unstructured":"Touvron H, et al. LLaMA: Open and Efficient Foundation Language Models. 2023. arXiv.org https:\/\/arxiv.org\/abs\/2302.13971v1."},{"key":"4274_CR36","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","volume":"379","author":"Z Lin","year":"2023","unstructured":"Lin Z, et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science. 2023;379:1123\u201330.","journal-title":"Science"},{"key":"4274_CR37","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaf582","volume":"41","author":"P Hartout","year":"2025","unstructured":"Hartout P, Chen D, Pellizzoni P, Oliver C, Borgwardt K. Endowing protein language models with structural knowledge. Bioinformatics. 2025;41:btaf582.","journal-title":"Bioinformatics"},{"key":"4274_CR38","doi-asserted-by":"publisher","unstructured":"OpenAI et al. GPT-4 Technical Report. 2024. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2303.08774.","DOI":"10.48550\/arXiv.2303.08774"},{"key":"4274_CR39","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.ins.2022.11.139","volume":"622","author":"AM Ikotun","year":"2023","unstructured":"Ikotun AM, Ezugwu AE, Abualigah L, Abuhaija B, Heming J. K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data. Inf Sci. 2023;622:178\u2013210.","journal-title":"Inf Sci"},{"key":"4274_CR40","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-023-00322-4","volume":"16","author":"D Chicco","year":"2023","unstructured":"Chicco D, Jurman G. The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification. BioData Min. 2023;16:4.","journal-title":"BioData Min"},{"key":"4274_CR41","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. 2016. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1603.02754.","DOI":"10.48550\/arXiv.1603.02754"},{"key":"4274_CR42","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee J, et al. BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics. 2020;36:1234\u201340.","journal-title":"Bioinformatics"},{"key":"4274_CR43","doi-asserted-by":"publisher","unstructured":"Altschul SF, Gish W, Miller W, Myers EW, Lipman DJ. Basic local alignment search tool. J Mol Biol. 1990;215(3):403\u201310. https:\/\/doi.org\/10.1016\/S0022-2836(05)80360-2.","DOI":"10.1016\/S0022-2836(05)80360-2"},{"key":"4274_CR44","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008;9:2579\u2013605.","journal-title":"J Mach Learn Res"},{"key":"4274_CR45","doi-asserted-by":"crossref","unstructured":"Wang S, Hu M, Li Q, Safari M, Yang X. Capabilities of GPT-5 on Multimodal Medical Reasoning. 2025. arXiv.org https:\/\/arxiv.org\/abs\/2508.08224v2.","DOI":"10.1117\/12.3086794"},{"key":"4274_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2025.102620","volume":"136","author":"M Leon","year":"2026","unstructured":"Leon M. GPT-5 and open-weight large language models: advances in reasoning, transparency, and control. Inf Syst. 2026;136:102620.","journal-title":"Inf Syst"},{"key":"4274_CR47","doi-asserted-by":"publisher","unstructured":"Team G, et al. Gemini: A Family of Highly Capable Multimodal Models. 2025. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2312.11805.","DOI":"10.48550\/arXiv.2312.11805"},{"key":"4274_CR48","doi-asserted-by":"publisher","unstructured":"Comanici G, et al. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities. 2025. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2507.06261.","DOI":"10.48550\/arXiv.2507.06261"},{"key":"4274_CR49","doi-asserted-by":"publisher","first-page":"1206","DOI":"10.1038\/s41586-025-10014-0","volume":"649","author":"\u017d Avsec","year":"2026","unstructured":"Avsec \u017d, et al. Advancing regulatory variant effect prediction with AlphaGenome. Nature. 2026;649:1206\u201318.","journal-title":"Nature"},{"key":"4274_CR50","doi-asserted-by":"publisher","unstructured":"Hinton G, Vinyals O, Dean J. Distilling the Knowledge in a Neural Network. 2015. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1503.02531.","DOI":"10.48550\/arXiv.1503.02531"},{"key":"4274_CR51","unstructured":"Cooper N, Scholak T. Perplexed: Understanding When Large Language Models are Confused. 2024. arXiv.org https:\/\/arxiv.org\/abs\/2404.06634v1."},{"key":"4274_CR52","doi-asserted-by":"publisher","unstructured":"Muhlgay D, Ram O, Magar I, Levine Y, Ratner N, Belinkov Y, Abend O, Leyton-Brown K, Shashua A, Shoham Y. Generating benchmarks for factuality evaluation of language models. In: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). In: Graham Y, Purver M (eds.) St. Julian\u2019s, Malta: Association for Computational Linguistics; 2024. pp. 49\u201366. https:\/\/doi.org\/10.18653\/v1\/2024.eacl-long.4.","DOI":"10.18653\/v1\/2024.eacl-long.4"},{"key":"4274_CR53","doi-asserted-by":"publisher","unstructured":"Dathathri S, et al. Plug and Play Language Models: A Simple Approach to Controlled Text Generation. 2020. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1912.02164.","DOI":"10.48550\/arXiv.1912.02164"},{"key":"4274_CR54","doi-asserted-by":"publisher","unstructured":"Liu C-W, et al. How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin, Texas: Association for Computational Linguistics;2016. pp. 2122\u20132132. https:\/\/doi.org\/10.18653\/v1\/D16-1230.","DOI":"10.18653\/v1\/D16-1230"},{"key":"4274_CR55","doi-asserted-by":"publisher","unstructured":"Jain S, Wallace BC. Attention is not Explanation. in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). In: Burstein J, Doran C, Solorio T (eds.) Minneapolis, Minnesota: Association for Computational Linguistics; 2019. pp. 3543\u20133556. https:\/\/doi.org\/10.18653\/v1\/N19-1357.","DOI":"10.18653\/v1\/N19-1357"},{"key":"4274_CR56","doi-asserted-by":"publisher","unstructured":"Wiegreffe S, Pinter Y. Attention is not not Explanation. 2019. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1908.04626.","DOI":"10.48550\/arXiv.1908.04626"},{"key":"4274_CR57","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1038\/s41586-022-04558-8","volume":"604","author":"J Morales","year":"2022","unstructured":"Morales J, et al. A joint NCBI and EMBL-EBI transcript set for clinical genomics and research. Nature. 2022;604:310\u20135.","journal-title":"Nature"},{"key":"4274_CR58","doi-asserted-by":"publisher","first-page":"1422","DOI":"10.1093\/bioinformatics\/btp163","volume":"25","author":"PJA Cock","year":"2009","unstructured":"Cock PJA, et al. Biopython: freely available Python tools for computational molecular biology and bioinformatics. Bioinformatics. 2009;25:1422\u20133.","journal-title":"Bioinformatics"},{"key":"4274_CR59","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","volume":"596","author":"J Jumper","year":"2021","unstructured":"Jumper J, et al. Highly accurate protein structure prediction with AlphaFold. Nature. 2021;596:583\u20139.","journal-title":"Nature"},{"key":"4274_CR60","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","volume":"630","author":"J Abramson","year":"2024","unstructured":"Abramson J, et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature. 2024;630:493\u2013500.","journal-title":"Nature"},{"key":"4274_CR61","doi-asserted-by":"publisher","first-page":"D368","DOI":"10.1093\/nar\/gkad1011","volume":"52","author":"M Varadi","year":"2024","unstructured":"Varadi M, et al. AlphaFold protein structure database in 2024: providing structure coverage for over 214 million protein sequences. Nucleic Acids Res. 2024;52:D368-75.","journal-title":"Nucleic Acids Res"},{"key":"4274_CR62","doi-asserted-by":"publisher","unstructured":"Wolf T, et al. Hugging Face\u2019s Transformers: State-of-the-art Natural Language Processing. 2020. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1910.03771.","DOI":"10.48550\/arXiv.1910.03771"},{"key":"4274_CR63","unstructured":"Han D, Han M, Unsloth team. Unsloth. GitHub. 2023. https:\/\/github.com\/unslothai\/unsloth."},{"key":"4274_CR64","unstructured":"Hu EJ, et al. LoRA: Low-Rank Adaptation of Large Language Models. 2021. arXiv.org https:\/\/arxiv.org\/abs\/2106.09685v2."},{"key":"4274_CR65","doi-asserted-by":"publisher","unstructured":"Paszke A, et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. 2019. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1912.01703.","DOI":"10.48550\/arXiv.1912.01703"},{"key":"4274_CR66","doi-asserted-by":"publisher","unstructured":"Chen A, et al. Developments in MLflow: A System to Accelerate the Machine Learning Lifecycle. in Proceedings of the Fourth International Workshop on Data Management for End-to-End Machine Learning. New York, NY, USA: Association for Computing Machinery; 2020. pp. 1\u20134. https:\/\/doi.org\/10.1145\/3399579.3399867.","DOI":"10.1145\/3399579.3399867"},{"key":"4274_CR67","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.22008517","author":"M Danner","year":"2026","unstructured":"Danner M, Islam T, Begemann M, Kraft F, Elbracht M, Kurth I, et al. Genolator enables protein function interpretation using a multimodal large language model fusing genomic and structural interpretation with natural language interaction. 2026. Code Repos Zenodo. https:\/\/doi.org\/10.5281\/zenodo.22008517."},{"key":"4274_CR68","doi-asserted-by":"publisher","unstructured":"Center for Human Genetics and Genomic Medicine, Danner M, Krause J. Llama-3-Genolator-v1-PST (Revision 60d0460). Data repository. Hugging Face. 2026. https:\/\/doi.org\/10.57967\/hf\/10054.","DOI":"10.57967\/hf\/10054"},{"key":"4274_CR69","doi-asserted-by":"publisher","unstructured":"Center for Human Genetics and Genomic Medicine, Danner M, Krause J. Llama-3-Genolator-v1-ESM (Revision 47d0de4). Data repository. Hugging Face. 2026. https:\/\/doi.org\/10.57967\/hf\/10055.","DOI":"10.57967\/hf\/10055"},{"key":"4274_CR70","doi-asserted-by":"publisher","unstructured":"Center for Human Genetics and Genomic Medicine, Danner M, Krause J. genolator-v1-qa (Revision 006ae08). Data repository. Hugging Face. 2026. https:\/\/doi.org\/10.57967\/hf\/10034.","DOI":"10.57967\/hf\/10034"},{"key":"4274_CR71","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.3025","volume":"11","author":"AA Wani","year":"2025","unstructured":"Wani AA. Comprehensive review of dimensionality reduction algorithms: challenges, limitations, and innovative solutions. PeerJ Comput Sci. 2025;11:e3025.","journal-title":"PeerJ Comput Sci"},{"key":"4274_CR72","doi-asserted-by":"publisher","unstructured":"Jeon H, Park J, Shin S, Seo J. Stop Misusing t-SNE and UMAP for Visual Analytics. 2025. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2506.08725.","DOI":"10.48550\/arXiv.2506.08725"}],"container-title":["Genome Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13059-026-04274-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13059-026-04274-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13059-026-04274-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T08:07:53Z","timestamp":1789546073000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13059-026-04274-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":72,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["4274"],"URL":"https:\/\/doi.org\/10.1186\/s13059-026-04274-w","relation":{"references":[{"id-type":"doi","id":"10.5281\/zenodo.22008517","asserted-by":"subject"}]},"ISSN":["1474-760X"],"issn-type":[{"value":"1474-760X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"assertion":[{"value":"19 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Martin Danner is employed by scieneers GmbH. The remaining authors declare no conflicts of interest.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"290"}}