{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T11:27:00Z","timestamp":1792322820834,"version":"4.4.0"},"reference-count":142,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"vor","delay-in-days":57,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Colorectal cancer (CRC) is characterized by profound, multi-layered heterogeneity that limits the precision of conventional single-modality clinical tools. The emergence of multimodal foundation models (MFMs) represents a conceptual paradigm shift, moving beyond static biomarkers to capture the dynamic and evolving nature of CRC. MFMs integrate histopathology, radiology, multi-omics data (including the critical regulatory layer of epigenomics), and clinical variables into shared high-dimensional representational spaces. This integration enables improved prognostication, refined molecular subtyping, and in silico simulation of therapeutic perturbations within the tumor\u2019s functional landscape, thereby supporting rational and model-driven drug development. In this review, we synthesize the rapidly expanding body of CRC-specific MFM research and critically examine the unresolved challenges that currently limit clinical translation. We place particular emphasis on the transition from correlation to causal inference, the establishment of cross-population generalizability, and the resolution of key issues related to trustworthiness and clinical interpretability. Finally, we propose an actionable roadmap outlining regulatory, data governance, and translational requirements, including the lab-in-the-loop paradigm, necessary to position MFMs as a robust and equitable framework in clinical oncology.<\/jats:p>","DOI":"10.1093\/bib\/bbag179","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T11:29:22Z","timestamp":1774870162000},"source":"Crossref","is-referenced-by-count":2,"title":["Multimodal foundation models in colorectal cancer: from prediction to trustworthy clinical insight"],"prefix":"10.1093","volume":"27","author":[{"given":"Danial","family":"Gharaie Amirabadi","sequence":"first","affiliation":[{"name":"Student Research Committee, Birjand University of Medical Sciences , PO Box 9717853577, Birjand , Ghaffari Street, South Khorasan Province,","place":["Iran"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adib","family":"Miraki Feriz","sequence":"additional","affiliation":[{"name":"Cellular and Molecular Research Center, Birjand University of Medical Sciences ,","place":["PO Box 9717853577, Birjand, Ghaffari Street, South Khorasan Province, Iran"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9883-9186","authenticated-orcid":false,"given":"Hossein","family":"Safarpour","sequence":"additional","affiliation":[{"name":"Cellular and Molecular Research Center, Birjand University of Medical Sciences ,","place":["PO Box 9717853577, Birjand, Ghaffari Street, South Khorasan Province, Iran"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,4,27]]},"reference":[{"key":"2026042712204738500_ref1","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J Clin"},{"key":"2026042712204738500_ref2","doi-asserted-by":"publisher","first-page":"2002","DOI":"10.1038\/s41379-022-01166-9","article-title":"CINSARC signature outperforms gold-standard TNM staging and consensus molecular subtypes for clinical outcome in stage II\u2013III colorectal carcinoma","volume":"35","author":"Brunac","year":"2022","journal-title":"Mod Pathol"},{"key":"2026042712204738500_ref3","doi-asserted-by":"publisher","first-page":"5322","DOI":"10.1158\/1078-0432.CCR-14-0332","article-title":"Mismatch repair status and BRAF mutation status in metastatic colorectal cancer patients: a pooled analysis of the CAIRO, CAIRO2, COIN, and FOCUS studies","volume":"20","author":"Venderbosch","year":"2014","journal-title":"Clin Cancer Res"},{"key":"2026042712204738500_ref4","doi-asserted-by":"publisher","first-page":"2509","DOI":"10.1056\/NEJMoa1500596","article-title":"PD-1 blockade in Tumors with mismatch-repair deficiency","volume":"372","author":"Le","year":"2015","journal-title":"N Engl J Med"},{"key":"2026042712204738500_ref5","doi-asserted-by":"publisher","DOI":"10.3390\/jpm9010012","article-title":"The developing story of predictive biomarkers in colorectal cancer","volume":"9","author":"Boussios","year":"2019","journal-title":"J Pers Med"},{"key":"2026042712204738500_ref6","doi-asserted-by":"publisher","first-page":"e1001453","DOI":"10.1371\/journal.pmed.1001453","article-title":"Gene expression classification of colon cancer into molecular subtypes: characterization, validation, and prognostic value","volume":"10","author":"Marisa","year":"2013","journal-title":"PLoS Med"},{"key":"2026042712204738500_ref7","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1053\/j.gastro.2014.09.038","article-title":"Association between molecular subtypes of colorectal cancer and patient survival","volume":"148","author":"Phipps","year":"2015","journal-title":"Gastroenterology"},{"key":"2026042712204738500_ref8","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nat Med"},{"key":"2026042712204738500_ref9","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1146\/annurev-bioeng-071910-124729","article-title":"Multiscale cancer modeling","volume":"13","author":"Deisboeck","year":"2011","journal-title":"Annu Rev Biomed Eng"},{"key":"2026042712204738500_ref10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/117693510700500001","article-title":"Advancing cancer systems biology: introducing the center for the development of a virtual tumor","volume":"5","author":"Deisboeck","year":"2007","journal-title":"CViT Cancer Inform"},{"key":"2026042712204738500_ref11","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"2026042712204738500_ref12","doi-asserted-by":"publisher","first-page":"102900","DOI":"10.1016\/j.artmed.2024.102900","article-title":"Transformers and large language models in healthcare: a review","volume":"154","author":"Nerella","year":"2024","journal-title":"Artif Intell Med"},{"key":"2026042712204738500_ref13","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1109\/RBME.2025.3531360","article-title":"A comprehensive survey of foundation models in medicine","volume":"19","author":"Khan","year":"2025","journal-title":"IEEE Rev Biomed Eng"},{"key":"2026042712204738500_ref14","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1038\/s41586-024-07441-w","article-title":"A whole-slide foundation model for digital pathology from real-world data","volume":"630","author":"Xu","year":"2024","journal-title":"Nature."},{"key":"2026042712204738500_ref15","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1038\/s43018-022-00416-8","article-title":"Multimodal integration of radiology, pathology and genomics for prediction of response to PD-(L)1 blockade in patients with non-small cell lung cancer","volume":"3","author":"Vanguri","year":"2022","journal-title":"Nat Cancer"},{"key":"2026042712204738500_ref16","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf121","article-title":"Deep learning-driven survival prediction in pan-cancer studies by integrating multimodal histology-genomic data","volume":"26","author":"Hu","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026042712204738500_ref17","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"2026042712204738500_ref18","doi-asserted-by":"publisher","first-page":"2112","DOI":"10.1093\/bioinformatics\/btab083","article-title":"DNABERT: pre-trained bidirectional encoder representations from transformers model for DNA-language in genome","volume":"37","author":"Ji","year":"2021","journal-title":"Bioinformatics"},{"key":"2026042712204738500_ref19","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":"2026042712204738500_ref20","doi-asserted-by":"publisher","first-page":"4348","DOI":"10.1038\/s41467-022-32007-7","article-title":"ProtGPT2 is a deep unsupervised language model for protein design","volume":"13","author":"Ferruz","year":"2022","journal-title":"Nat Commun"},{"key":"2026042712204738500_ref21","doi-asserted-by":"crossref","DOI":"10.1101\/2020.03.07.982272","article-title":"Progen: Language modeling for protein generation","author":"Madani","year":"2020"},{"key":"2026042712204738500_ref22","first-page":"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":"2026042712204738500_ref23","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2026042712204738500_ref24","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026042712204738500_ref25","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1109\/RBME.2023.3297604","article-title":"Vision transformers for computational histopathology","volume":"17","author":"Xu","year":"2024","journal-title":"IEEE Rev Biomed Eng"},{"key":"2026042712204738500_ref26","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1016\/j.ccell.2023.08.002","article-title":"Transformer-based biomarker prediction from colorectal cancer histology: a large-scale multicentric study","volume":"41","author":"Wagner","year":"2023","journal-title":"Cancer Cell"},{"key":"2026042712204738500_ref27","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1002\/cjp2.312","article-title":"Predicting microsatellite instability and key biomarkers in colorectal cancer from H&E-stained images: achieving state-of-the-art predictive performance with fewer data using Swin transformer","volume":"9","author":"Guo","year":"2023","journal-title":"J Pathol Clin Res"},{"key":"2026042712204738500_ref28","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Liu","year":"2021"},{"key":"2026042712204738500_ref29","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1186\/s12864-024-09985-7","article-title":"A semi-supervised approach for the integration of multi-omics data based on transformer multi-head self-attention mechanism and graph convolutional networks","volume":"25","author":"Wang","year":"2024","journal-title":"BMC Genomics"},{"key":"2026042712204738500_ref30","doi-asserted-by":"publisher","DOI":"10.1101\/2024.04.15.589472","article-title":"Nicheformer: a foundation model for single-cell and spatial omics","volume":"22","author":"Schaar","journal-title":"Nature Methods"},{"key":"2026042712204738500_ref31","first-page":"205","article-title":"Limits of depth: over-smoothing and over-squashing in gnns","volume":"7","author":"Qureshi","year":"2023","journal-title":"Big Data Mining and Analytics"},{"key":"2026042712204738500_ref32","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1007\/s10462-024-10918-9","article-title":"Graph pooling in graph neural networks: methods and their applications in omics studies","volume":"57","author":"Wang","year":"2024","journal-title":"Artificial Intelligence Review"},{"key":"2026042712204738500_ref33","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"2026042712204738500_ref34","article-title":"dnaGrinder: a lightweight and high-capacity genomic foundation model","author":"Zhao","year":"2024"},{"key":"2026042712204738500_ref35","article-title":"Understanding and mitigating bottlenecks of state space models through the lens of recency and over-smoothing","author":"Wang","year":"2024"},{"key":"2026042712204738500_ref36","article-title":"Leveraging state space models in long range genomics","author":"Popov","year":"2025"},{"key":"2026042712204738500_ref37","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1038\/s41592-021-01252-x","article-title":"Effective gene expression prediction from sequence by integrating long-range interactions","volume":"18","author":"Avsec","year":"2021","journal-title":"Nat Methods"},{"key":"2026042712204738500_ref38","doi-asserted-by":"publisher","first-page":"e59505","DOI":"10.2196\/59505","article-title":"Multimodal large language models in health care: applications, challenges, and future outlook","volume":"26","author":"AlSaad","year":"2024","journal-title":"J Med Internet Res"},{"key":"2026042712204738500_ref39","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s12859-023-05622-4","article-title":"A multimodal graph neural network framework for cancer molecular subtype classification","volume":"25","author":"Li","year":"2024","journal-title":"BMC Bioinformatics"},{"key":"2026042712204738500_ref40","doi-asserted-by":"publisher","first-page":"133617","DOI":"10.1109\/ACCESS.2024.3462543","article-title":"MoVAE: multi-omics variational auto-encoder for cancer subtype detection","volume":"12","author":"Rahmanian","year":"2024","journal-title":"IEEE. Access"},{"key":"2026042712204738500_ref41","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.fmre.2025.01.001","article-title":"Enhancing cell subpopulation discovery in cancer by integrating single-cell transcriptome and expressed variants","volume":"6","author":"Wang","year":"2025","journal-title":"Fundam Res"},{"key":"2026042712204738500_ref42","article-title":"Current pathology foundation models are unrobust to medical center differences","author":"Jong","year":"2025"},{"key":"2026042712204738500_ref43","article-title":"Why foundation models in pathology are failing","author":"Tizhoosh","year":"2025"},{"key":"2026042712204738500_ref44","doi-asserted-by":"publisher","DOI":"10.1093\/bjrai\/ubae014","article-title":"Digital pathology and multimodal learning on oncology data. BJR|artificial","volume":"1","author":"Waqas","year":"2024","journal-title":"Intelligence"},{"key":"2026042712204738500_ref45","doi-asserted-by":"publisher","first-page":"103289","DOI":"10.1016\/j.media.2024.103289","article-title":"PathoDuet: foundation models for pathological slide analysis of H&E and IHC stains","volume":"97","author":"Hua","year":"2024","journal-title":"Med Image Anal"},{"key":"2026042712204738500_ref46","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1038\/s41746-024-01131-7","article-title":"Deep learning to assess microsatellite instability directly from histopathological whole slide images in endometrial cancer","volume":"7","author":"Wang","year":"2024","journal-title":"NPJ Digit Med"},{"key":"2026042712204738500_ref47","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14151605","article-title":"Artificial intelligence models for the detection of microsatellite instability from whole-slide imaging of colorectal cancer","volume":"14","author":"Faa","year":"2024","journal-title":"Diagnostics (Basel)"},{"key":"2026042712204738500_ref48","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1038\/s41746-025-01848-z","article-title":"Systematic review and meta-analysis of deep learning for MSI-H in colorectal cancer whole slide images","volume":"8","author":"Li","year":"2025","journal-title":"NPJ Digit Med"},{"key":"2026042712204738500_ref49","doi-asserted-by":"publisher","first-page":"104730","DOI":"10.1016\/j.compbiomed.2021.104730","article-title":"Deep learning for colon cancer histopathological images analysis","volume":"136","author":"Ben Hamida","year":"2021","journal-title":"Comput Biol Med"},{"key":"2026042712204738500_ref50","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1186\/s12880-025-01826-7","article-title":"Colorectal cancer unmasked: a synergistic AI framework for hyper-granular image dissection, precision segmentation, and automated diagnosis","volume":"25","author":"Raju","year":"2025","journal-title":"BMC Med Imaging"},{"key":"2026042712204738500_ref51","doi-asserted-by":"publisher","first-page":"106928","DOI":"10.1016\/j.bspc.2024.106928","article-title":"Artificial intelligence based real time colorectal cancer screening study: polyp segmentation and classification using multi-house database","volume":"99","author":"Selvaraj","year":"2025","journal-title":"Biomed Signal Process Control"},{"key":"2026042712204738500_ref52","doi-asserted-by":"publisher","first-page":"110633","DOI":"10.1016\/j.engappai.2025.110633","article-title":"Synthetic data-augmented explainable vision transformer for colorectal cancer diagnosis via surface tactile imaging","volume":"151","author":"Kapuria","year":"2025","journal-title":"Eng Appl Artif Intel"},{"key":"2026042712204738500_ref53","doi-asserted-by":"publisher","first-page":"17524","DOI":"10.1109\/ACCESS.2025.3532807","article-title":"Expedited colorectal cancer detection through a dexterous hybrid CADx system with enhanced image processing and augmented polyp visualization","volume":"13","author":"Raju","year":"2025","journal-title":"IEEE Access"},{"key":"2026042712204738500_ref54","doi-asserted-by":"publisher","first-page":"7633","DOI":"10.1038\/s41467-025-62346-0","article-title":"ROSIE: AI generation of multiplex immunofluorescence staining from histopathology images","volume":"16","author":"Wu","year":"2025","journal-title":"Nat Commun"},{"key":"2026042712204738500_ref55","doi-asserted-by":"publisher","first-page":"2079","DOI":"10.1007\/s11548-024-03217-9","article-title":"Transformers for colorectal cancer segmentation in CT imaging","volume":"19","author":"Hille","year":"2024","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"2026042712204738500_ref56","doi-asserted-by":"publisher","first-page":"110542","DOI":"10.1016\/j.clinimag.2025.110542","article-title":"Deep learning based colorectal cancer detection in medical images: a comprehensive analysis of datasets, methods, and future directions","volume":"125","author":"Gulmez","year":"2025","journal-title":"Clin Imaging"},{"key":"2026042712204738500_ref57","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on whole-slide images","volume":"5","author":"Lu","year":"2021","journal-title":"Nat Biomed Eng"},{"key":"2026042712204738500_ref58","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1038\/s41586-024-07747-9","article-title":"The genomic landscape of 2,023 colorectal cancers","volume":"633","author":"Cornish","year":"2024","journal-title":"Nature"},{"key":"2026042712204738500_ref59","doi-asserted-by":"publisher","first-page":"103661","DOI":"10.1016\/j.clon.2024.10.033","article-title":"The evolving role of genomics in colorectal cancer","volume":"37","author":"Berner","year":"2025","journal-title":"Clin Oncol (R Coll Radiol)"},{"key":"2026042712204738500_ref60","doi-asserted-by":"publisher","first-page":"1350","DOI":"10.1038\/nm.3967","article-title":"The consensus molecular subtypes of colorectal cancer","volume":"21","author":"Guinney","year":"2015","journal-title":"Nat Med"},{"key":"2026042712204738500_ref61","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf275","article-title":"Gene Swin transformer: new deep learning method for colorectal cancer prognosis using transcriptomic data","volume":"26","author":"Wang","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026042712204738500_ref62","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1038\/s41586-023-06139-9","article-title":"Transfer learning enables predictions in network biology","volume":"618","author":"Theodoris","year":"2023","journal-title":"Nature"},{"key":"2026042712204738500_ref63","doi-asserted-by":"publisher","first-page":"1470","DOI":"10.1038\/s41592-024-02201-0","article-title":"scGPT: toward building a foundation model for single-cell multi-omics using generative AI","volume":"21","author":"Cui","year":"2024","journal-title":"Nat Methods"},{"key":"2026042712204738500_ref64","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1038\/s42256-022-00534-z","article-title":"scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data","volume":"4","author":"Yang","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2026042712204738500_ref65","doi-asserted-by":"publisher","DOI":"10.1101\/2023.09.11.557287","article-title":"Cell2Sentence: teaching large language models the language of biology","author":"Levine","year":"2024","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref66","doi-asserted-by":"publisher","first-page":"3607","DOI":"10.1038\/s41467-025-58699-1","article-title":"scPRINT: pre-training on 50 million cells allows robust gene network predictions","volume":"16","author":"Kalfon","year":"2025","journal-title":"Nat Commun"},{"key":"2026042712204738500_ref67","doi-asserted-by":"publisher","DOI":"10.1101\/2025.04.25.650731","article-title":"A cross-species generative cell atlas across 1.5 billion years of evolution: the TranscriptFormer single-cell model","author":"Pearce","year":"2025","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref68","first-page":"6323","article-title":"Cell ontology guided transcriptome foundation model","volume":"37","author":"Yuan","year":"2024","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026042712204738500_ref69","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1136\/jcp-2025-210053","article-title":"Deep learning predicts microsatellite instability status in colorectal carcinoma in an ethnically heterogeneous population in South Africa","volume":"79","author":"Aldera","year":"2025","journal-title":"J Clin Pathol"},{"key":"2026042712204738500_ref70","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1038\/s41592-024-02305-7","article-title":"Large-scale foundation model on single-cell transcriptomics","volume":"21","author":"Hao","year":"2024","journal-title":"Nat Methods"},{"key":"2026042712204738500_ref71","doi-asserted-by":"publisher","DOI":"10.1101\/2025.02.05.636714","article-title":"scGPT-spatial: continual pretraining of single-cell foundation model for spatial transcriptomics","author":"Wang","year":"2025","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref72","doi-asserted-by":"publisher","first-page":"1513654","DOI":"10.3389\/fonc.2024.1513654","article-title":"Mechanisms and technologies in cancer epigenetics","volume":"14","author":"Sherif","year":"2024","journal-title":"Front Oncol"},{"key":"2026042712204738500_ref73","first-page":"120","article-title":"The CpG island methylator phenotype (CIMP) in colorectal cancer","volume":"6","author":"Mojarad","year":"2013","journal-title":"Gastroenterol Hepatology Bed Bench"},{"key":"2026042712204738500_ref74","doi-asserted-by":"publisher","DOI":"10.1101\/2024.10.30.621013","article-title":"MethylGPT: a foundation model for the DNA methylome","author":"Ying","year":"2024","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref75","article-title":"CpGPT: a foundation model for DNA methylation","author":"Lima Camillo","year":"2024","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref76","doi-asserted-by":"publisher","first-page":"113810","DOI":"10.1016\/j.celrep.2024.113810","article-title":"Proteogenomic characterization of primary colorectal cancer and metastatic progression identifies proteome-based subtypes and signatures","volume":"43","author":"Tanaka","year":"2024","journal-title":"Cell Rep"},{"key":"2026042712204738500_ref77","doi-asserted-by":"publisher","first-page":"2888","DOI":"10.1158\/0008-5472.CAN-23-1878","article-title":"Comprehensive proteogenomic profiling reveals the molecular characteristics of colorectal cancer at distinct stages of progression","volume":"84","author":"Li","year":"2024","journal-title":"Cancer Res"},{"key":"2026042712204738500_ref78","article-title":"A foundation model for spatial proteomics","author":"Shaban","year":"2025"},{"key":"2026042712204738500_ref79","doi-asserted-by":"publisher","first-page":"2136","DOI":"10.1158\/1078-0432.CCR-13-1939","article-title":"A distinct metabolic signature of human colorectal cancer with prognostic potential","volume":"20","author":"Qiu","year":"2014","journal-title":"Clin Cancer Res"},{"key":"2026042712204738500_ref80","doi-asserted-by":"publisher","first-page":"7","DOI":"10.53941\/hm.2025.100014","article-title":"Application of LLMs\/transformer-based models for metabolite annotation in metabolomics","author":"Liu","year":"2025","journal-title":"Health Metab"},{"key":"2026042712204738500_ref81","doi-asserted-by":"publisher","first-page":"1657","DOI":"10.1038\/s41467-024-46043-y","article-title":"Metabolomic machine learning predictor for diagnosis and prognosis of gastric cancer","volume":"15","author":"Chen","year":"2024","journal-title":"Nat Commun"},{"key":"2026042712204738500_ref82","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1038\/s41587-025-02663-3","article-title":"Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS","volume":"44","author":"Bushuiev","year":"2025","journal-title":"Nat Biotechnol"},{"key":"2026042712204738500_ref83","article-title":"PRISM: a foundation model for life\u2019s chemistry","author":"Healey","year":"2025"},{"key":"2026042712204738500_ref84","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2024-k06gb","article-title":"LSM1-MS2: a self-supervised foundation model for tandem mass spectrometry applications, encompassing extensive chemical property predictions and spectral matching","author":"Asher","year":"2024","journal-title":"ChemRxiv"},{"key":"2026042712204738500_ref85","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae084","article-title":"RT-transformer: retention time prediction for metabolite annotation to assist in metabolite identification","volume":"40","author":"Xue","year":"2024","journal-title":"Bioinformatics"},{"key":"2026042712204738500_ref86","article-title":"Massformer: tandem mass spectrum prediction for small molecules using graph transformers","author":"Young","year":"2021"},{"key":"2026042712204738500_ref87","article-title":"MS2Prop: a machine learning model that directly predicts chemical properties from mass spectrometry data for novel compounds","volume":"10","author":"Voronov","year":"2022","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref88","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s13321-024-00804-5","article-title":"IDSL_MINT: a deep learning framework to predict molecular fingerprints from mass spectra","volume":"16","author":"Baygi","year":"2024","journal-title":"J Chem"},{"key":"2026042712204738500_ref89","volume-title":"Machine Learning Methods for Discovering Metabolite Structures from Mass Spectra","author":"Goldman","year":"2024"},{"key":"2026042712204738500_ref90","article-title":"LipiDetective a deep learning model for the identification of molecular lipid species in tandem mass spectra","author":"W\u00fcrf","year":"2024","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref91","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2023-vsmpx-v3","article-title":"MS2Mol: a transformer model for illuminating dark chemical space from mass spectra","author":"Butler","year":"2023","journal-title":"ChemRxiv"},{"key":"2026042712204738500_ref92","doi-asserted-by":"publisher","first-page":"e2403393","DOI":"10.1002\/advs.202403393","article-title":"An explainable graph neural framework to identify cancer-associated intratumoral microbial communities","volume":"11","author":"Liu","year":"2024","journal-title":"Adv Sci (Weinh)"},{"key":"2026042712204738500_ref93","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1016\/j.chom.2025.05.011","article-title":"Precision nutrition and the gut microbiome: harnessing AI to revolutionize cancer prevention and therapy","volume":"33","author":"Greathouse","year":"2025","journal-title":"Cell Host Microbe"},{"key":"2026042712204738500_ref94","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae702","article-title":"IMPACT: interpretable microbial phenotype analysis via microbial characteristic traits","volume":"41","author":"Mechtersheimer","year":"2024","journal-title":"Bioinformatics"},{"key":"2026042712204738500_ref95","doi-asserted-by":"publisher","first-page":"25268","DOI":"10.1038\/s41598-025-08915-1","article-title":"Integrative analysis of multi-omics data and gut microbiota composition reveals prognostic subtypes and predicts immunotherapy response in colorectal cancer using machine learning","volume":"15","author":"Wang","year":"2025","journal-title":"Sci Rep"},{"key":"2026042712204738500_ref96","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf015","article-title":"Techniques for learning and transferring knowledge for microbiome-based classification and prediction: review and assessment","volume":"26","author":"Han","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026042712204738500_ref97","article-title":"MGM as a large-scale pretrained foundation model for microbiome analyses in diverse contexts","author":"Zhang","year":"2025","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref98","doi-asserted-by":"publisher","DOI":"10.1101\/2025.01.15.633278","article-title":"Towards a generative paradigm for large-scale microbiome analysis by generative language model","author":"Zhang","year":"2025","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref99","doi-asserted-by":"publisher","first-page":"3411","DOI":"10.1109\/TCBB.2022.3199244","article-title":"TransSurv: transformer-based survival analysis model integrating histopathological images and genomic data for colorectal cancer","volume":"20","author":"Lv","year":"2023","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2026042712204738500_ref100","doi-asserted-by":"publisher","first-page":"e2407060","DOI":"10.1002\/advs.202407060","article-title":"Interpretable multimodal fusion model for bridged histology and genomics survival prediction in pan-cancer","volume":"12","author":"Gao","year":"2025","journal-title":"Adv Sci (Weinh)"},{"key":"2026042712204738500_ref101","article-title":"Pluto: pathology-universal transformer","author":"Juyal","year":"2024"},{"key":"2026042712204738500_ref102","article-title":"Multimodal whole slide foundation model for pathology","author":"Ding","year":"2024"},{"key":"2026042712204738500_ref103","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-5271327\/v1","article-title":"Developing generalist foundation models from a multimodal dataset for 3d computed tomography","author":"Hamamci","year":"2024"},{"key":"2026042712204738500_ref104","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1038\/s41586-024-08378-w","article-title":"A vision-language foundation model for precision oncology","volume":"638","author":"Xiang","year":"2025","journal-title":"Nature"},{"key":"2026042712204738500_ref105","doi-asserted-by":"publisher","first-page":"2924","DOI":"10.1038\/s41591-024-03141-0","article-title":"A foundation model for clinical-grade computational pathology and rare cancers detection","volume":"30","author":"Vorontsov","year":"2024","journal-title":"Nat Med"},{"key":"2026042712204738500_ref106","doi-asserted-by":"crossref","DOI":"10.1101\/2022.08.06.503062","article-title":"Interpretable RNA foundation model from unannotated data for highly accurate RNA structure and function predictions","author":"Chen","year":"2022"},{"key":"2026042712204738500_ref107","doi-asserted-by":"publisher","first-page":"106536","DOI":"10.1016\/j.isci.2023.106536","article-title":"Generative pretraining from large-scale transcriptomes for single-cell deciphering","volume":"26","author":"Shen","year":"2023","journal-title":"iScience"},{"key":"2026042712204738500_ref108","article-title":"Molfm: a multimodal molecular foundation model","author":"Luo","year":"2023"},{"key":"2026042712204738500_ref109","doi-asserted-by":"publisher","DOI":"10.1101\/2023.10.16.562533","article-title":"GenePT: a simple but effective foundation model for genes and cells built from ChatGPT","author":"Chen","year":"2024","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref110","article-title":"Dnabert-2: efficient foundation model and benchmark for multi-species genome","author":"Zhou","year":"2023"},{"key":"2026042712204738500_ref111","article-title":"Biomedgpt: open multimodal generative pre-trained transformer for biomedicine","author":"Luo","year":"2023"},{"key":"2026042712204738500_ref112","article-title":"Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023"},{"key":"2026042712204738500_ref113","article-title":"Subtype-former: a deep learning approach for cancer subtype discovery with multi-omics data","author":"Yang","year":"2022"},{"key":"2026042712204738500_ref114","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1038\/s43018-024-00772-7","article-title":"LORIS robustly predicts patient outcomes with immune checkpoint blockade therapy using common clinical, pathologic and genomic features","volume":"5","author":"Chang","year":"2024","journal-title":"Nat Cancer"},{"key":"2026042712204738500_ref115","article-title":"CancerFoundation: a single-cell RNA sequencing foundation model to decipher drug resistance in cancer","author":"Theus","year":"2024","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref116","article-title":"Tahoe-100m: a giga-scale single-cell perturbation atlas for context-dependent gene function and cellular modeling","author":"Zhang","year":"2025","journal-title":"BioRxiv"},{"key":"2026042712204738500_ref117","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.2174\/0929867330666230321103731","article-title":"Exploring scoring function space: developing computational models for drug discovery","volume":"31","author":"Bitencourt-Ferreira","year":"2024","journal-title":"Curr Med Chem"},{"key":"2026042712204738500_ref118","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1038\/s41586-022-05688-9","article-title":"Dissecting cell identity via network inference and in silico gene perturbation","volume":"614","author":"Kamimoto","year":"2023","journal-title":"Nature"},{"key":"2026042712204738500_ref119","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-026-11522-9","article-title":"From classical machine learning to emerging foundation models: review on multimodal data integration for cancer research","volume":"59","author":"Muneer","year":"2026","journal-title":"Artif Intell Rev"},{"key":"2026042712204738500_ref120","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2026042712204738500_ref121","article-title":"Protein complex prediction with AlphaFold-multimer","author":"Evans","year":"2021","journal-title":"biorxiv"},{"key":"2026042712204738500_ref122","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1038\/s42256-021-00325-y","article-title":"Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms","volume":"3","author":"Schulte-Sasse","year":"2021","journal-title":"Nat Mach Intell"},{"key":"2026042712204738500_ref123","first-page":"69391","article-title":"xTrimoGene: an efficient and scalable representation learner for single-cell RNA-seq data","volume":"36","author":"Gong","year":"2023","journal-title":"Adv Neural Inf Proces Syst"},{"key":"2026042712204738500_ref124","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1186\/s12859-023-05524-5","article-title":"Predicting anticancer synergistic drug combinations based on multi-task learning","volume":"24","author":"Chen","year":"2023","journal-title":"BMC Bioinformatics"},{"key":"2026042712204738500_ref125","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1186\/s40364-025-00758-2","article-title":"Integrating artificial intelligence in drug discovery and early drug development: a transformative approach","volume":"13","author":"Ocana","year":"2025","journal-title":"Biomark Res"},{"key":"2026042712204738500_ref126","article-title":"Genentech\u2019s lab in the loop aims to tap the power of quantity for quality drug discovery","author":"Buntz","year":"2025","journal-title":"Drug Discovery and Development"},{"key":"2026042712204738500_ref127","volume-title":"Lab in a Loop: AI to Transform Drug Discovery and Development","author":"Regev","year":"2024"},{"key":"2026042712204738500_ref128","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1038\/s41586-025-08710-y","article-title":"Towards multimodal foundation models in molecular cell biology","volume":"640","author":"Cui","year":"2025","journal-title":"Nature"},{"key":"2026042712204738500_ref129","doi-asserted-by":"publisher","first-page":"100980","DOI":"10.1016\/j.xcrm.2023.100980","article-title":"Generalizable biomarker prediction from cancer pathology slides with self-supervised deep learning: a retrospective multi-centric study","volume":"4","author":"Niehues","year":"2023","journal-title":"Cell Rep Med"},{"key":"2026042712204738500_ref130","doi-asserted-by":"publisher","first-page":"1580195","DOI":"10.3389\/fonc.2025.1580195","article-title":"Hybrid model for predicting microsatellite instability in colorectal cancer using hematoxylin & eosin-stained images and clinical features","volume":"15","author":"Wei","year":"2025","journal-title":"Front Oncol"},{"key":"2026042712204738500_ref131","doi-asserted-by":"publisher","first-page":"99","DOI":"10.3390\/diagnostics14010099","article-title":"Artificial intelligence in predicting microsatellite instability and KRAS, BRAF mutations from whole-slide images in colorectal cancer: a systematic review","volume":"14","author":"Guitton","year":"2024","journal-title":"Diagnostics"},{"key":"2026042712204738500_ref132","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1007\/s12672-025-03119-5","article-title":"Pathological omics prediction of early and advanced colon cancer based on artificial intelligence model","volume":"16","author":"Wang","year":"2025","journal-title":"Discov Oncol"},{"key":"2026042712204738500_ref133","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","article-title":"The future of digital health with federated learning","volume":"3","author":"Rieke","year":"2020","journal-title":"NPJ Digit Med"},{"key":"2026042712204738500_ref134","volume-title":"Machine Learning for Healthcare Conference","author":"Tonekaboni","year":"2019"},{"key":"2026042712204738500_ref135","doi-asserted-by":"publisher","first-page":"e1312","DOI":"10.1002\/widm.1312","article-title":"Causability and explainability of artificial intelligence in medicine","volume":"9","author":"Holzinger","year":"2019","journal-title":"Wiley Interdiscip Rev Data Min Knowl Discov"},{"key":"2026042712204738500_ref136","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1002\/bjs.9736","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"102","author":"Collins","year":"2015","journal-title":"J Br Surg"},{"key":"2026042712204738500_ref137","doi-asserted-by":"publisher","first-page":"866","DOI":"10.7326\/M18-1990","article-title":"Ensuring fairness in machine learning to advance health equity","volume":"169","author":"Rajkomar","year":"2018","journal-title":"Ann Intern Med"},{"key":"2026042712204738500_ref138","first-page":"43177","article-title":"HyenaDNA: long-range genomic sequence modeling at single nucleotide resolution","volume":"36","author":"Nguyen","year":"2023","journal-title":"ArXiv."},{"key":"2026042712204738500_ref139","doi-asserted-by":"publisher","DOI":"10.1101\/2024.12.18.628606","article-title":"Genomic foundationless models: pretraining does not promise performance","author":"Vishniakov","year":"2024","journal-title":"bioRxiv"},{"key":"2026042712204738500_ref140","first-page":"3366","article-title":"A continual learning survey: defying forgetting in classification tasks","volume":"44","author":"De Lange","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026042712204738500_ref141","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1109\/JPROC.2021.3058954","article-title":"Toward causal representation learning","volume":"109","author":"Sch\u00f6lkopf","year":"2021","journal-title":"Proc IEEE"},{"key":"2026042712204738500_ref142","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1038\/s41746-022-00610-z","article-title":"Building digital twins of the human immune system: toward a roadmap","volume":"5","author":"Laubenbacher","year":"2022","journal-title":"NPJ Digit Med"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/2\/bbag179\/68166863\/bbag179.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/2\/bbag179\/68166863\/bbag179.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T16:20:55Z","timestamp":1777306855000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag179\/8663071"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,1]]},"references-count":142,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag179","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,3]]},"published":{"date-parts":[[2026,3,1]]},"article-number":"bbag179"}}