{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T20:54:57Z","timestamp":1781902497467,"version":"3.54.5"},"posted":{"date-parts":[[2026,1,23]]},"group-title":"Bioinformatics","reference-count":52,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.biorxiv.org\/about\/FAQ#license"}],"funder":[{"name":"National Cancer Institute","award":["U2CCA233280"],"award-info":[{"award-number":["U2CCA233280"]}]},{"name":"Cancer Early Detection Advanced Research Center, Oregon Health and Science University, Knight Cancer Institute","award":["CEDAR 2023-1796"],"award-info":[{"award-number":["CEDAR 2023-1796"]}]},{"name":"National Cancer Institute","award":["R01 CA253860"],"award-info":[{"award-number":["R01 CA253860"]}]},{"name":"National Cancer Institute","award":["R01 CA276224"],"award-info":[{"award-number":["R01 CA276224"]}]},{"name":"National Cancer Institute","award":["U01 294548"],"award-info":[{"award-number":["U01 294548"]}]},{"DOI":"10.13039\/100018138","name":"Kuni Foundation","doi-asserted-by":"crossref","award":["Imagination Grants"],"award-info":[{"award-number":["Imagination Grants"]}],"id":[{"id":"10.13039\/100018138","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000892","name":"Prostate Cancer Foundation","doi-asserted-by":"crossref","award":["GCNCR1865A"],"award-info":[{"award-number":["GCNCR1865A"]}],"id":[{"id":"10.13039\/100000892","id-type":"DOI","asserted-by":"crossref"}]},{"name":"International Alliance for Cancer Early Detection","award":["ACED 2022-1508"],"award-info":[{"award-number":["ACED 2022-1508"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["S10OD034224"],"award-info":[{"award-number":["S10OD034224"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,1,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Virtual multiplexing from routine histology has advanced rapidly, yet morphology alone provides limited access to molecular state, imposing an intrinsic ceiling on H&amp;E-only inference. Here, we introduce miniMTI, a molecularly anchored virtual staining framework that determines the minimal set of experimentally measured markers required, alongside H&amp;E, to accurately reconstruct large multiplex tissue imaging (MTI) panels while preserving biologically and clinically relevant information. miniMTI learns from paired same-section H&amp;E\u2013MTI data using a unified multimodal generative model that can condition on arbitrary combinations of measured marker channels, coupled with an iterative panel selection strategy to rank informative molecular anchors. Across colorectal and prostate cancer cohorts spanning two MTI platforms and over 40 million cells, miniMTI reduces a 40-marker MTI assay to H&amp;E plus as few as three measured molecular markers, while accurately recovering withheld markers, preserving cellular phenotypes and spatial tissue architecture, and disease-associated molecular programs, including Gleason grade-linked signatures. By integrating histology context with sparse molecular grounding, miniMTI overcomes the limitations of morphology-only virtual staining and provides a scalable, cost-effective approach for expanding MTI-level biomarker coverage with retained biological interpretability and clinical relevance.<\/jats:p>","DOI":"10.64898\/2026.01.21.700911","type":"posted-content","created":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T03:30:15Z","timestamp":1769225415000},"source":"Crossref","is-referenced-by-count":1,"title":["miniMTI: minimal multiplex tissue imaging enhances biomarker expression prediction from histology"],"prefix":"10.64898","author":[{"given":"Zachary","family":"Sims","sequence":"first","affiliation":[{"name":"Biomedical Engineering, Oregon Health and Science University, Portland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandhya","family":"Govindarajan","sequence":"additional","affiliation":[{"name":"Biomedical Engineering, Oregon Health and Science University, Portland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaoutar","family":"Ait-Ahmad","sequence":"additional","affiliation":[{"name":"Cancer Early Detection Advanced Research (CEDAR), OHSU, Portland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2563-4539","authenticated-orcid":false,"given":"Cigdem","family":"Ak","sequence":"additional","affiliation":[{"name":"Cancer Early Detection Advanced Research (CEDAR), OHSU, Portland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marigold","family":"Kuykendall","sequence":"additional","affiliation":[{"name":"Cancer Early Detection Advanced Research (CEDAR), OHSU, Portland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0144-9614","authenticated-orcid":false,"given":"Gordon B.","family":"Mills","sequence":"additional","affiliation":[{"name":"Knight Cancer Institute, OHSU, Portland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1012-5571","authenticated-orcid":false,"given":"Ece","family":"Eksi","sequence":"additional","affiliation":[{"name":"Cancer Early Detection Advanced Research (CEDAR), OHSU, Portland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8764-1959","authenticated-orcid":false,"given":"Young Hwan","family":"Chang","sequence":"additional","affiliation":[{"name":"Biomedical Engineering, Oregon Health and Science University, Portland, USA"},{"name":"Knight Cancer Institute, OHSU, Portland, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026020503344433000_2026.01.21.700911v1.1","doi-asserted-by":"crossref","unstructured":"Lin, J.-R. et al. Highly multiplexed immunofluorescence imaging of human tissues and tumors using t-CyCIF and conventional optical microscopes. Elife 7, (2018).","DOI":"10.7554\/eLife.31657"},{"key":"2026020503344433000_2026.01.21.700911v1.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.07.010"},{"key":"2026020503344433000_2026.01.21.700911v1.3","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2017.03.037"},{"key":"2026020503344433000_2026.01.21.700911v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1629-x"},{"key":"2026020503344433000_2026.01.21.700911v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.03.053"},{"key":"2026020503344433000_2026.01.21.700911v1.6","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1007\/s00428-023-03509-6","article-title":"High-multiplex tissue imaging in routine pathology-are we there yet?","volume":"482","year":"2023","journal-title":"Virchows Arch"},{"key":"2026020503344433000_2026.01.21.700911v1.7","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-23-1165"},{"key":"2026020503344433000_2026.01.21.700911v1.8","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-023-00657-4"},{"key":"2026020503344433000_2026.01.21.700911v1.9","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1038\/s42256-024-00889-5","article-title":"Accelerating histopathology workflows with generative AI-based virtually multiplexed tumour profiling. Nat","volume":"6","year":"2024","journal-title":"Mach. Intell"},{"key":"2026020503344433000_2026.01.21.700911v1.10","doi-asserted-by":"crossref","first-page":"e1010505","DOI":"10.1371\/journal.pcbi.1010505","article-title":"Computational multiplex panel reduction to maximize information retention in breast cancer tissue microarrays","volume":"18","year":"2022","journal-title":"PLoS Comput Biol"},{"key":"2026020503344433000_2026.01.21.700911v1.11","doi-asserted-by":"crossref","first-page":"gad171","DOI":"10.1093\/pnasnexus\/pgad171","article-title":"Generating in silico CODEX from a small set of immunofluorescence markers","volume":"2","year":"2023","journal-title":"PNAS Nexus"},{"key":"2026020503344433000_2026.01.21.700911v1.12","doi-asserted-by":"crossref","unstructured":"Sun, H. , Li, J. & Murphy, R. F . Expanding the coverage of spatial proteomics: a machine learning approach. Bioinformatics 40, (2024).","DOI":"10.1093\/bioinformatics\/btae062"},{"key":"2026020503344433000_2026.01.21.700911v1.13","doi-asserted-by":"crossref","unstructured":"Sims, Z. , Mills, G. B. & Chang, Y. H . MIM-CyCIF: masked imaging modeling for enhancing cyclic immunofluorescence (CyCIF) with panel reduction and imputation. Commun Biol 7, 409 (2024).","DOI":"10.1038\/s42003-024-06110-y"},{"key":"2026020503344433000_2026.01.21.700911v1.14","doi-asserted-by":"crossref","first-page":"7633","DOI":"10.1038\/s41467-025-62346-0","article-title":"ROSIE: AI generation of multiplex immunofluorescence staining from histopathology images","volume":"16","year":"2025","journal-title":"Nat Commun"},{"key":"2026020503344433000_2026.01.21.700911v1.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2025.11.016"},{"key":"2026020503344433000_2026.01.21.700911v1.16","doi-asserted-by":"crossref","unstructured":"Burlingame, E. A. et al. SHIFT: speedy histological-to-immunofluorescent translation of a tumor signature enabled by deep learning. Sci Rep 10, 17507 (2020).","DOI":"10.1038\/s41598-020-74500-3"},{"key":"2026020503344433000_2026.01.21.700911v1.17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.14681"},{"key":"2026020503344433000_2026.01.21.700911v1.18","doi-asserted-by":"crossref","unstructured":"Zhou, Z. et al. Virtual multiplexed immunofluorescence staining from non-antibody-stained fluorescence imaging for gastric cancer prognosis. EBioMedicine 107, 105287 (2024).","DOI":"10.1016\/j.ebiom.2024.105287"},{"key":"2026020503344433000_2026.01.21.700911v1.19","unstructured":"AI-Powered Virtual Tissues from Spatial Proteomics for Clinical Diagnostics and Biomedical Discovery. https:\/\/iclr.cc\/virtual\/2025\/37004."},{"key":"2026020503344433000_2026.01.21.700911v1.20","doi-asserted-by":"crossref","unstructured":"Dayao, M. T. , Mayer, A. T. , Trevino, A. E. & Bar-Joseph, Z . Using spatial proteomics to enhance cell type assignments in histology images. Cell Rep . Methods 5, 101204 (2025).","DOI":"10.1016\/j.crmeth.2025.101204"},{"key":"2026020503344433000_2026.01.21.700911v1.21","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.1038\/s42256-025-01074-y","article-title":"Histopathology-based protein multiplex generation using deep learning. Nat","volume":"7","year":"2025","journal-title":"Mach. Intell"},{"key":"2026020503344433000_2026.01.21.700911v1.22","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1038\/s42256-022-00471-x","article-title":"Deep learning-inferred multiplex ImmunoFluorescence for immunohistochemical image quantification. Nat","volume":"4","year":"2022","journal-title":"Mach. Intell"},{"key":"2026020503344433000_2026.01.21.700911v1.23","doi-asserted-by":"crossref","first-page":"1036","DOI":"10.1038\/s43018-023-00576-1","article-title":"High-plex immunofluorescence imaging and traditional histology of the same tissue section for discovering image-based biomarkers","volume":"4","year":"2023","journal-title":"Nat Cancer"},{"key":"2026020503344433000_2026.01.21.700911v1.24","doi-asserted-by":"crossref","first-page":"e1013325","DOI":"10.1371\/journal.pcbi.1013325","article-title":"COEXIST: Coordinated single-cell integration of serial multiplexed tissue images","volume":"21","year":"2025","journal-title":"PLoS Comput Biol"},{"key":"2026020503344433000_2026.01.21.700911v1.25","doi-asserted-by":"crossref","unstructured":"Azam, A. B. et al. Training immunophenotyping deep learning models with the same-section ground truth cell label derivation method improves virtual staining accuracy. Front Immunol 15, 1404640 (2024).","DOI":"10.3389\/fimmu.2024.1404640"},{"key":"2026020503344433000_2026.01.21.700911v1.26","doi-asserted-by":"publisher","DOI":"10.1101\/2024.12.20.629650"},{"key":"2026020503344433000_2026.01.21.700911v1.27","unstructured":"Chameleon: Mixed-Modal Early-Fusion Foundation Models. (2024)."},{"key":"2026020503344433000_2026.01.21.700911v1.28","first-page":"58363","article-title":"4M: Massively Multimodal Masked Modeling","volume":"36","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026020503344433000_2026.01.21.700911v1.29","doi-asserted-by":"crossref","unstructured":"Sims, Z. , Govindarajan, S. , Mills, G. B. , Eksi, E. & Chang, Y. H. Language of stains: tokenization enhances multiplex immunofluorescence and histology image synthesis. in International Conference on Medical Image Computing and Computer-Assisted Intervention 274\u2013284 (Springer, 2025).","DOI":"10.1007\/978-3-032-04965-0_26"},{"key":"2026020503344433000_2026.01.21.700911v1.30","unstructured":"Van Den Oord , A., Vinyals , O. & Others . Neural discrete representation learning. Advances in neural information processing systems 30, (2017)."},{"key":"2026020503344433000_2026.01.21.700911v1.31","doi-asserted-by":"crossref","unstructured":"Esser, P. , Rombach, R. & Ommer, B. Taming transformers for high-resolution image synthesis. in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 12873\u201312883 (2021).","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"2026020503344433000_2026.01.21.700911v1.32","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. in Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","year":"2019","journal-title":"long and short papers"},{"key":"2026020503344433000_2026.01.21.700911v1.33","doi-asserted-by":"crossref","unstructured":"Chang, H. , Zhang, H. , Jiang, L. , Liu, C. & Freeman, W. T. Maskgit: Masked generative image transformer. in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 11315\u201311325 (2022).","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"2026020503344433000_2026.01.21.700911v1.34","unstructured":"Sims, Z. S. & Chang, Y. H. A Masked Image Modeling Approach to CyCIF Panel Reduction and Marker Imputation. in Machine Learning in Computational Biology 1\u20139 (PMLR, 2024)."},{"key":"2026020503344433000_2026.01.21.700911v1.35","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01308-y"},{"key":"2026020503344433000_2026.01.21.700911v1.36","doi-asserted-by":"crossref","unstructured":"Burlingame, E. A. et al. Toward reproducible, scalable, and robust data analysis across multiplex tissue imaging platforms. Cell Rep . Methods 1, 100053 (2021).","DOI":"10.1016\/j.crmeth.2021.100053"},{"key":"2026020503344433000_2026.01.21.700911v1.37","doi-asserted-by":"crossref","unstructured":"Baker, G. J. et al. Morphology-Aware Profiling of Highly Multiplexed Tissue Images using Variational Autoencoders. bioRxiv 2025\u20132006 (2025).","DOI":"10.1101\/2025.06.23.661064"},{"key":"2026020503344433000_2026.01.21.700911v1.38","doi-asserted-by":"crossref","unstructured":"Ternes, L. et al. A multi-encoder variational autoencoder controls multiple transformational features in single-cell image analysis. Commun Biol 5, 255 (2022).","DOI":"10.1038\/s42003-022-03218-x"},{"key":"2026020503344433000_2026.01.21.700911v1.39","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02857-3"},{"key":"2026020503344433000_2026.01.21.700911v1.40","unstructured":"Shaban, M. , et al. A Foundation Model for Spatial Proteomics. arXiv preprint arXiv:2506.03373 (2025)."},{"key":"2026020503344433000_2026.01.21.700911v1.41","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-023-01588-4"},{"key":"2026020503344433000_2026.01.21.700911v1.42","doi-asserted-by":"crossref","unstructured":"Ak, \u00c7. et al. Multiplex imaging of localized prostate tumors reveals altered spatial organization of AR-positive cells in the microenvironment. iScience 27, 110668 (2024).","DOI":"10.1016\/j.isci.2024.110668"},{"key":"2026020503344433000_2026.01.21.700911v1.43","doi-asserted-by":"crossref","unstructured":"Salazar, J. , Liang, D. , Nguyen, T. Q. & Kirchhoff, K. Masked language model scoring. in Proceedings of the 58th annual meeting of the association for computational linguistics 2699\u20132712 (2020).","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"2026020503344433000_2026.01.21.700911v1.44","unstructured":"Nie, S. et al. Large language diffusion models. arXiv preprint arXiv:2502. 09992 (2025)."},{"key":"2026020503344433000_2026.01.21.700911v1.45","doi-asserted-by":"publisher","DOI":"10.1126\/science.ads0018"},{"key":"2026020503344433000_2026.01.21.700911v1.46","unstructured":"Swerdlow, A. , Prabhudesai, M. , Gandhi, S. , Pathak, D. & Fragkiadaki, K . Unified multimodal discrete diffusion. arXiv preprint arXiv:2503. 20853 (2025)."},{"key":"2026020503344433000_2026.01.21.700911v1.47","unstructured":"Yang, L. et al. Mmada: Multimodal large diffusion language models. arXiv preprint arXiv:2505. 15809 (2025)."},{"key":"2026020503344433000_2026.01.21.700911v1.48","unstructured":"Kunz, L. et al. 3D high-multiplex imaging in cancer immunology. NATURE METHODS (2024)."},{"key":"2026020503344433000_2026.01.21.700911v1.49","unstructured":"Jain, E. , Wenckstern, J. , von Querfurth, B. & Bunne, C. Test-time view selection for multi-modal decision making. in ICLR 2025 Workshop on Machine Learning for Genomics Explorations (2025)."},{"key":"2026020503344433000_2026.01.21.700911v1.50","doi-asserted-by":"crossref","unstructured":"Liu, Y. et al. High-parameter spatial multi-omics through histology-anchored integration. Nat. Methods 1\u201314 (2025).","DOI":"10.1038\/s41592-025-02926-6"},{"key":"2026020503344433000_2026.01.21.700911v1.51","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-021-01094-0"},{"key":"2026020503344433000_2026.01.21.700911v1.52","doi-asserted-by":"publisher","DOI":"10.1109\/icccnt.2012.6396024"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.01.21.700911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:35:02Z","timestamp":1770291302000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.01.21.700911"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,23]]},"references-count":52,"URL":"https:\/\/doi.org\/10.64898\/2026.01.21.700911","relation":{},"subject":[],"published":{"date-parts":[[2026,1,23]]},"subtype":"preprint"}}