pith. sign in

arxiv: 2507.09028 · v2 · submitted 2025-07-11 · 🧬 q-bio.QM · cs.AI

From Classical Machine Learning to Emerging Foundation Models: Review on Multimodal Data Integration for Cancer Research

Amgad Muneer , Muhammad Waqas , Maliazurina B Saad , Eman Showkatian , Rukhmini Bandyopadhyay , Hui Xu , Wentao Li , Joe Y Chang
show 11 more authors
Zhongxing Liao Cara Haymaker Luisa Solis Soto Carol C Wu Natalie I Vokes Xiuning Le Lauren A Byers Don L Gibbons John V Heymach Jianjun Zhang Jia Wu
This is my paper

Pith reviewed 2026-05-19 05:06 UTC · model grok-4.3

classification 🧬 q-bio.QM cs.AI
keywords multimodal data integrationcancer researchfoundation modelsmachine learningoncologydeep learningmulti-omicsbiomarker discovery
0
0 comments X

The pith

Current multimodal integration methods in cancer research lay groundwork for next-generation foundation models.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper reviews strategies for combining diverse data types such as genomics, proteomics, imaging, and clinical factors in cancer studies. It traces the progression from traditional machine learning techniques to foundation models, which are large pretrained deep learning systems that support various downstream tasks. The authors identify key frameworks, validation methods, open resources, and challenges in this area. A sympathetic reader cares because successful integration could enable better biomarker discovery, more accurate diagnoses, personalized treatments, and improved outcome predictions. The central argument is that existing integrative approaches are essential building blocks for powerful future AI models in oncology.

Core claim

The paper establishes that state-of-the-art integrative methods for multimodal data provide the essential groundwork for developing the next generation of large-scale, pre-trained models poised to further revolutionize oncology. It comprehensively covers the shift from traditional ML to FMs for multimodal integration and presents a holistic view of recent advancements and challenges in integrating multi-omics with advanced imaging data.

What carries the argument

The systematic mapping of the transition from conventional machine learning to foundation models for multimodal data integration, which serves to identify state-of-the-art approaches and frame them as foundational for large-scale AI in cancer research.

If this is right

  • Improved extraction of actionable insights from heterogeneous cancer datasets.
  • Enhanced capabilities for cancer subtype classification, biomarker discovery, treatment guidance, and outcome prediction.
  • Identification of public multi-modal repositories and tools accelerates research progress.
  • Current methods enable the development of more advanced foundation models in oncology.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Future work could focus on creating hybrid systems that combine proven classical integration techniques with emerging foundation model architectures.
  • This transition might influence similar multimodal integration efforts in other medical domains like neurology or cardiology.
  • Researchers could test the review's trends by surveying the most cited papers in the field post-publication to verify the described shift.
  • Open-source resources highlighted may lower barriers for smaller labs to contribute to foundation model development in cancer research.

Load-bearing premise

The selected body of literature is comprehensive and representative of the field without major selection bias.

What would settle it

Publication of a subsequent review that documents a significantly different trajectory or major unaddressed gaps in the transition from classical ML to foundation models for multimodal cancer data integration.

Figures

Figures reproduced from arXiv: 2507.09028 by Amgad Muneer, Cara Haymaker, Carol C Wu, Don L Gibbons, Eman Showkatian, Hui Xu, Jianjun Zhang, Jia Wu, Joe Y Chang, John V Heymach, Lauren A Byers, Luisa Solis Soto, Maliazurina B Saad, Muhammad Waqas, Natalie I Vokes, Rukhmini Bandyopadhyay, Wentao Li, Xiuning Le, Zhongxing Liao.

Figure 1
Figure 1. Figure 1: Multi-modal data integration towards personalized medicine. Artificial Intelligence (AI), mainly ML and DL, has revolutionized the integration and analysis of high-dimensional, multimodal cancer datasets [27]. ML algorithms, such as random forests, support vector machines, and ensemble methods, are highly effective in identifying patterns and making pre￾dictions from multi-omics data [28-30]. DL has furthe… view at source ↗
Figure 2
Figure 2. Figure 2: Timeline of (a) DL Advancements in Cancer Research through Multimodal Approaches; (b) Imaging/ molecular technology and cancer treatment. While previous reviews have explored various facets of multimodal integration techniques, many have focused narrowly on specific methodologies, individual cancer types, or singular data modalities. Consequently, a clear gap remains: a comprehensive synthesis evaluating s… view at source ↗
read the original abstract

Cancer research is increasingly driven by the integration of diverse data modalities, spanning from genomics and proteomics to imaging and clinical factors. However, extracting actionable insights from these vast and heterogeneous datasets remains a key challenge. The rise of foundation models (FMs) -- large deep-learning models pretrained on extensive amounts of data serving as a backbone for a wide range of downstream tasks -- offers new avenues for discovering biomarkers, improving diagnosis, and personalizing treatment. This paper presents a comprehensive review of widely adopted integration strategies of multimodal data to assist advance the computational approaches for data-driven discoveries in oncology. We examine emerging trends in machine learning (ML) and deep learning (DL), including methodological frameworks, validation protocols, and open-source resources targeting cancer subtype classification, biomarker discovery, treatment guidance, and outcome prediction. This study also comprehensively covers the shift from traditional ML to FMs for multimodal integration. We present a holistic view of recent FMs advancements and challenges faced during the integration of multi-omics with advanced imaging data. We identify the state-of-the-art FMs, publicly available multi-modal repositories, and advanced tools and methods for data integration. We argue that current state-of-the-art integrative methods provide the essential groundwork for developing the next generation of large-scale, pre-trained models poised to further revolutionize oncology. To the best of our knowledge, this is the first review to systematically map the transition from conventional ML to advanced FM for multimodal data integration in oncology, while also framing these developments as foundational for the forthcoming era of large-scale AI models in cancer research.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript is a review surveying multimodal data integration in cancer research. It covers classical machine learning and deep learning strategies for tasks including cancer subtype classification, biomarker discovery, treatment guidance, and outcome prediction; examines the shift to foundation models (FMs); identifies state-of-the-art FMs, publicly available multimodal repositories, and integration tools; and argues that current integrative methods supply the essential groundwork for next-generation large-scale pre-trained models in oncology. The authors position the work as the first systematic mapping of this transition from conventional ML to FMs.

Significance. If the literature synthesis proves comprehensive and free of major selection bias, the review could usefully consolidate trends, frameworks, validation approaches, and resources for computational oncology researchers, thereby supporting the development of foundation models. The forward-looking claim that existing methods provide essential groundwork is plausible but rests entirely on the representativeness of the cited body of work.

major comments (2)
  1. [Abstract and Introduction] The abstract and introduction claim a 'comprehensive review' and 'systematically map the transition' from classical ML to FMs, yet the manuscript provides no explicit literature-search protocol (databases, keywords, date ranges, inclusion/exclusion criteria, or PRISMA-style flow diagram). This omission is load-bearing for the central argument, as the skeptic correctly notes that the forward-looking claim about groundwork for next-gen FMs is only as reliable as the underlying synthesis; without the protocol, potential selection bias cannot be assessed.
  2. [Sections on challenges and FM advancements] In the sections reviewing challenges of multi-omics plus imaging integration and FM limitations, the discussion remains largely qualitative. Specific quantitative evidence (e.g., reported failure rates, scalability benchmarks, or negative results from cited studies) is not systematically presented, weakening the balanced assessment needed to support the claim that current methods are 'essential groundwork.'
minor comments (2)
  1. [Abstract] The abstract contains a minor grammatical issue: 'to assist advance the computational approaches' should read 'to advance the computational approaches.'
  2. [Resources section] A consolidated table listing the publicly available multimodal repositories and tools mentioned throughout the text would improve readability and utility for readers.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback. We have addressed each major comment below with targeted revisions to enhance transparency and balance in the review.

read point-by-point responses

  1. Referee: [Abstract and Introduction] The abstract and introduction claim a 'comprehensive review' and 'systematically map the transition' from classical ML to FMs, yet the manuscript provides no explicit literature-search protocol (databases, keywords, date ranges, inclusion/exclusion criteria, or PRISMA-style flow diagram). This omission is load-bearing for the central argument, as the skeptic correctly notes that the forward-looking claim about groundwork for next-gen FMs is only as reliable as the underlying synthesis; without the protocol, potential selection bias cannot be assessed.

    Authors: We agree that an explicit literature-search protocol is important for assessing potential selection bias and supporting the reliability of our synthesis. In the revised manuscript, we have added a dedicated 'Literature Review Methodology' subsection that specifies the databases searched (PubMed, arXiv, Google Scholar), search keywords and strings, date range (primarily 2015–2024 with key earlier works), inclusion/exclusion criteria, and a PRISMA-style flow diagram now included as Supplementary Figure S1. These additions directly address the concern and allow readers to evaluate the representativeness of the cited body of work. revision: yes

  2. Referee: [Sections on challenges and FM advancements] In the sections reviewing challenges of multi-omics plus imaging integration and FM limitations, the discussion remains largely qualitative. Specific quantitative evidence (e.g., reported failure rates, scalability benchmarks, or negative results from cited studies) is not systematically presented, weakening the balanced assessment needed to support the claim that current methods are 'essential groundwork.'

    Authors: We acknowledge that the original treatment of challenges and limitations was primarily qualitative. In the revised sections, we have incorporated specific quantitative evidence from the referenced studies, including examples of reported performance degradation or failure rates in multi-omics fusion methods (e.g., 12–30% drops in certain cross-modal alignment tasks), scalability benchmarks (such as GPU-hour requirements scaling with dataset size), and selected negative or null findings on foundation model generalization in oncology. These additions are now systematically presented with citations to provide a more balanced assessment supporting the groundwork claim. revision: yes

Circularity Check

0 steps flagged

Review paper surveys external literature with no internal derivation chain

full rationale

This paper is a literature review that summarizes trends in multimodal data integration for oncology, covering classical ML to foundation models. The central claim is an interpretive argument based on the body of reviewed external works rather than any new derivation, equation, or fitted parameter internal to the paper. No self-definitional reductions, fitted inputs renamed as predictions, or load-bearing self-citations appear in the abstract or described structure. The synthesis relies on external benchmarks and cited studies, making the derivation self-contained against outside sources. The absence of an explicit search protocol is a potential limitation for representativeness but does not constitute circularity under the defined patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a literature review the paper introduces no new free parameters, axioms, or invented entities; its conclusions rest on the standard assumption that the surveyed papers adequately represent the field.

pith-pipeline@v0.9.0 · 5893 in / 1120 out tokens · 57599 ms · 2026-05-19T05:06:40.497397+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Towards Responsible Multimodal Medical Reasoning via Context-Aligned Vision-Language Models

    cs.CV 2026-04 unverdicted novelty 4.0

    Context alignment in medical VLMs raises AUC from 0.918 to 0.925, cuts hallucinated keywords from 1.14 to 0.25, shortens explanations to 15.3 words, and maintains calibrated uncertainty without raising model confidence.

Reference graph

Works this paper leans on

202 extracted references · 202 canonical work pages · cited by 1 Pith paper · 2 internal anchors

  1. [1]

    Global cancer statistics for adolescents and young adults: population based study,

    W. Li et al., "Global cancer statistics for adolescents and young adults: population based study," Journal of Hematology & Oncology, vol. 17, no. 1, p. 99, 2024

    work page 2024

  2. [2]

    Cancer cachexia: multilevel metabolic dysfunction,

    M. Berriel Diaz, M. Rohm, and S. Herzig, "Cancer cachexia: multilevel metabolic dysfunction," Nature Metabolism, pp. 1-24, 2024

    work page 2024

  3. [3]

    Beyond genetics: driving cancer with the tumour microenvironment behind the wheel,

    S. Yuan, J. Almagro, and E. Fuchs, "Beyond genetics: driving cancer with the tumour microenvironment behind the wheel," Nature Reviews Cancer, vol. 24, no. 4, pp. 274-286, 2024

    work page 2024

  4. [4]

    Multimodal data integration for precision oncology: Challenges and future directions,

    H. Zhou, F. Zhou, C. Zhao, Y. Xu, L. Luo, and H. Chen, "Multimodal data integration for precision oncology: Challenges and future directions," arXiv preprint arXiv:2406.19611, 2024

    work page arXiv 2024

  5. [5]

    Pan-cancer classification of multi-omics data based on machine learning models,

    C. Cava, S. Sabetian, C. Salvatore, and I. Castiglioni, "Pan-cancer classification of multi-omics data based on machine learning models," Network Modeling Analysis in Health Informatics and Bioinformatics, vol. 13, no. 1, p. 6, 2024

    work page 2024

  6. [6]

    Spatial multi-omics: deciphering technological landscape of integration of multi -omics and its applications,

    X. Liu et al., "Spatial multi-omics: deciphering technological landscape of integration of multi -omics and its applications," Journal of Hematology & Oncology, vol. 17, no. 1, p. 72, 2024

    work page 2024

  7. [7]

    CRISPR ‐Cas9 technology: As an efficient genome modification tool in the cancer diagnosis and treatment,

    G. Behrouzian Fard et al., "CRISPR ‐Cas9 technology: As an efficient genome modification tool in the cancer diagnosis and treatment," Biotechnology and Bioengineering, vol. 121, no. 2, pp. 472-488, 2024

    work page 2024

  8. [8]

    A deep-learning framework to predict cancer treatment response from histopathology images through imputed transcriptomics,

    D.-T. Hoang et al., "A deep-learning framework to predict cancer treatment response from histopathology images through imputed transcriptomics," Nature Cancer, pp. 1-13, 2024

    work page 2024

  9. [9]

    Serum Proteomic Signatures in Cervical Cancer: Current Status and Future Directions,

    C. Weaver et al., "Serum Proteomic Signatures in Cervical Cancer: Current Status and Future Directions," Cancers, vol. 16, no. 9, p. 1629, 2024

    work page 2024

  10. [10]

    Construction of a diagnostic model for small cell lung cancer combining metabolomics and integrated machine learning,

    X. Shang, C. Zhang, R. Kong, C. Zhao, and H. Wang, "Construction of a diagnostic model for small cell lung cancer combining metabolomics and integrated machine learning," The Oncologist, vol. 29, no. 3, pp. e392-e401, 2024

    work page 2024

  11. [11]

    Machine learning in epigenomics: Insights into cancer biology and medicine,

    E. Arslan, J. Schulz, and K. Rai, "Machine learning in epigenomics: Insights into cancer biology and medicine," Biochimica et Biophysica Acta (BBA)-Reviews on Cancer, vol. 1876, no. 2, p. 188588, 2021

    work page 2021

  12. [12]

    Multi -omics approaches for biomarker discovery in early ovarian cancer diagnosis,

    Y. Xiao, M. Bi, H. Guo, and M. Li, "Multi -omics approaches for biomarker discovery in early ovarian cancer diagnosis," EBioMedicine, vol. 79, 2022

    work page 2022

  13. [13]

    Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms,

    R. Schulte -Sasse, S. Budach, D. Hnisz, and A. Marsico, "Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms," Nature Machine Intelligence, vol. 3, no. 6, pp. 513-526, 2021

    work page 2021

  14. [14]

    Multi-omic machine learning predictor of breast cancer therapy response,

    S.-J. Sammut et al., "Multi-omic machine learning predictor of breast cancer therapy response," Nature, vol. 601, no. 7894, pp. 623-629, 2022

    work page 2022

  15. [15]

    Deep learning in ovarian cancer diagnosis: a comprehensive review of various imaging modalities,

    M. H. Sadeghi, S. Sina, H. Omidi, A. H. Farshchitabrizi, and M. Alavi, "Deep learning in ovarian cancer diagnosis: a comprehensive review of various imaging modalities," Polish Journal of Radiology, vol. 89, p. e30, 2024

    work page 2024

  16. [16]

    A review of various modalities in breast imaging: technical aspects and clinical outcomes,

    S. Iranmakani et al. , "A review of various modalities in breast imaging: technical aspects and clinical outcomes," Egyptian Journal of Radiology and Nuclear Medicine, vol. 51, pp. 1-22, 2020

    work page 2020

  17. [17]

    Artificial Intelligence -based methods in head and neck cancer diagnosis: an overview,

    H. Mahmood, M. Shaban, N. Rajpoot, and S. A. Khurram, "Artificial Intelligence -based methods in head and neck cancer diagnosis: an overview," British journal of cancer, vol. 124, no. 12, pp. 1934-1940, 2021

    work page 1934

  18. [18]

    Recent trend in medical imaging modalities and their applications in disease diagnosis: a review,

    B. Abhisheka, S. K. Biswas, B. Purkayastha, D. Das, and A. Escargueil, "Recent trend in medical imaging modalities and their applications in disease diagnosis: a review," Multimedia Tools and Applications, vol. 83, no. 14, pp. 43035-43070, 2024

    work page 2024

  19. [19]

    Metabolic Imaging for Radiation Therapy Treatment Planning: The Role of Hybrid PET/MR Imaging,

    L. Deantonio, F. Castronovo, G. Paone, G. Treglia, and T. Zilli, "Metabolic Imaging for Radiation Therapy Treatment Planning: The Role of Hybrid PET/MR Imaging," Magnetic Resonance Imaging Clinics, vol. 31, no. 4, pp. 637-654, 2023

    work page 2023

  20. [20]

    Imaging Modalities in Radiation Therapy Planning: MRI and X-ray,

    L. Khalida and W. Orof, "Imaging Modalities in Radiation Therapy Planning: MRI and X-ray," 2023

    work page 2023

  21. [21]

    Imaging methods to evaluate tumor microenvironment factors affecting nanoparticle drug delivery and antitumor response,

    A. S. Moody, P. A. Dayton, and W. C. Zamboni, "Imaging methods to evaluate tumor microenvironment factors affecting nanoparticle drug delivery and antitumor response," Cancer Drug Resistance, vol. 4, no. 2, pp. 382-413, 2021. [Online]. Available: https://www.oaepublish.com/articles/cdr.2020.94

    work page 2021

  22. [22]

    Navigating challenges and opportunities in multi -omics integration for personalized healthcare,

    A. E. Mohr, C. P. Ortega-Santos, C. M. Whisner, J. Klein-Seetharaman, and P. Jasbi, "Navigating challenges and opportunities in multi -omics integration for personalized healthcare," Biomedicines, vol. 12, no. 7, p. 1496, 2024

    work page 2024

  23. [23]

    Uncovering the key dimensions of high -throughput biomolecular data using deep learning,

    S. Zhang, X. Li, Q. Lin, J. Lin, and K. -C. Wong, "Uncovering the key dimensions of high -throughput biomolecular data using deep learning," Nucleic acids research, vol. 48, no. 10, pp. e56-e56, 2020

    work page 2020

  24. [24]

    AI in medical imaging informatics: current challenges and future directions,

    A. S. Panayides et al., "AI in medical imaging informatics: current challenges and future directions," IEEE journal of biomedical and health informatics, vol. 24, no. 7, pp. 1837-1857, 2020

    work page 2020

  25. [25]

    Methods for the integration of multi -omics data: mathematical aspects,

    M. Bersanelli et al. , "Methods for the integration of multi -omics data: mathematical aspects," BMC bioinformatics, vol. 17, pp. 167-177, 2016

    work page 2016

  26. [26]

    Multi -omics data integration, interpretation, and its application,

    I. Subramanian, S. Verma, S. Kumar, A. Jere, and K. Anamika, "Multi -omics data integration, interpretation, and its application," Bioinformatics and biology insights, vol. 14, p. 1177932219899051, 2020

    work page 2020

  27. [27]

    A comprehensive investigation of multimodal deep learning fusion strategies for breast cancer classification,

    F.-Z. Nakach, A. Idri, and E. Goceri, "A comprehensive investigation of multimodal deep learning fusion strategies for breast cancer classification," Artificial Intelligence Review, vol. 57, no. 12, pp. 1-53, 2024

    work page 2024

  28. [28]

    Machine learning applications in genetics and genomics,

    M. W. Libbrecht and W. S. Noble, "Machine learning applications in genetics and genomics," Nature Reviews Genetics, vol. 16, no. 6, pp. 321-332, 2015

    work page 2015

  29. [29]

    Integrative network fusion: a multi-omics approach in molecular profiling,

    M. Chierici et al., "Integrative network fusion: a multi-omics approach in molecular profiling," Frontiers in oncology, vol. 10, p. 1065, 2020

    work page 2020

  30. [30]

    A cascade deep forest model for breast cancer subtype classification using multi-omics data,

    A. a. El-Nabawy, N. A. Belal, and N. El-Bendary, "A cascade deep forest model for breast cancer subtype classification using multi-omics data," Mathematics, vol. 9, no. 13, p. 1574, 2021

    work page 2021

  31. [31]

    Interpretable deep learning methods for multiview learning,

    H. Wang, H. Lu, J. Sun, and S. E. Safo, "Interpretable deep learning methods for multiview learning," BMC bioinformatics, vol. 25, no. 1, p. 69, 2024

    work page 2024

  32. [32]

    Deep learning based feature -level integration of multi- omics data for breast cancer patients survival analysis,

    L. Tong, J. Mitchel, K. Chatlin, and M. D. Wang, "Deep learning based feature -level integration of multi- omics data for breast cancer patients survival analysis," BMC medical informatics and decision making, vol. 20, pp. 1-12, 2020

    work page 2020

  33. [33]

    Convolutional neural networks: an overview and application in radiology,

    R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, "Convolutional neural networks: an overview and application in radiology," Insights into imaging, vol. 9, pp. 611-629, 2018

    work page 2018

  34. [34]

    Identifying time-delayed gene regulatory networks via an evolvable hierarchical recurrent neural network,

    M. M. Kordmahalleh, M. G. Sefidmazgi, S. H. Harrison, and A. Homaifar, "Identifying time-delayed gene regulatory networks via an evolvable hierarchical recurrent neural network," BioData mining, vol. 10, pp. 1-25, 2017

    work page 2017

  35. [35]

    Deep model predictive control of gene expression in thousands of single cells,

    J.-B. Lugagne, C. M. Blassick, and M. J. Dunlop, "Deep model predictive control of gene expression in thousands of single cells," Nature Communications, vol. 15, no. 1, p. 2148, 2024

    work page 2024

  36. [36]

    Pathformer: a biological pathway informed transformer for disease diagnosis and prognosis using multi-omics data,

    X. Liu et al., "Pathformer: a biological pathway informed transformer for disease diagnosis and prognosis using multi-omics data," Bioinformatics, vol. 40, no. 5, p. btae316, 2024

    work page 2024

  37. [37]

    Improving diagnosis and prognosis of lung cancer using vision transformers: a scoping review,

    H. Ali, F. Mohsen, and Z. Shah, "Improving diagnosis and prognosis of lung cancer using vision transformers: a scoping review," BMC Medical Imaging, vol. 23, no. 1, p. 129, 2023

    work page 2023

  38. [38]

    Foundation models for generalist medical artificial intelligence,

    M. Moor et al., "Foundation models for generalist medical artificial intelligence," Nature, vol. 616, no. 7956, pp. 259-265, 2023

    work page 2023

  39. [39]

    Leveraging foundation and large language models in medical artificial intelligence,

    I. N. Wong et al., "Leveraging foundation and large language models in medical artificial intelligence," Chinese Medical Journal, vol. 137, no. 21, pp. 2529-2539, 2024

    work page 2024

  40. [40]

    Molfm: A multimodal molecular foundation model.arXiv preprint arXiv:2307.09484, 2023

    Y. Luo, K. Yang, M. Hong, X. Y. Liu, and Z. Nie, "Molfm: A multimodal molecular foundation model," arXiv preprint arXiv:2307.09484, 2023

    work page arXiv 2023

  41. [41]

    scGPT: toward building a foundation model for single -cell multi-omics using generative AI,

    H. Cui et al., "scGPT: toward building a foundation model for single -cell multi-omics using generative AI," Nature Methods, pp. 1-11, 2024

    work page 2024

  42. [42]

    Foundation model for cancer imaging biomarkers,

    S. Pai et al., "Foundation model for cancer imaging biomarkers," Nature machine intelligence, vol. 6, no. 3, pp. 354-367, 2024

    work page 2024

  43. [43]

    A foundation model for clinical -grade computational pathology and rare cancers detection,

    E. Vorontsov et al., "A foundation model for clinical -grade computational pathology and rare cancers detection," Nature medicine, pp. 1-12, 2024

    work page 2024

  44. [44]

    A benchmark study of deep learning-based multi-omics data fusion methods for cancer,

    D. Leng et al., "A benchmark study of deep learning-based multi-omics data fusion methods for cancer," Genome biology, vol. 23, no. 1, p. 171, 2022

    work page 2022

  45. [45]

    Estimating the Average Treatment Effect Using Weighting Methods in Lung Cancer Immunotherapy,

    M. B. Saad et al., "Estimating the Average Treatment Effect Using Weighting Methods in Lung Cancer Immunotherapy," in International Workshop on Computational Mathematics Modeling in Cancer Analysis, 2024: Springer, pp. 90-98

    work page 2024

  46. [46]

    Hierarchical multi -omics data integration and modeling predict cell -specific chemical proteomics and drug responses,

    Y. Wu, Q. Liu, and L. Xie, "Hierarchical multi -omics data integration and modeling predict cell -specific chemical proteomics and drug responses," Cell Reports Methods, vol. 3, no. 4, 2023

    work page 2023

  47. [47]

    iBAG: integrative Bayesian analysis of high -dimensional multiplatform genomics data,

    W. Wang, V. Baladandayuthapani, J. S. Morris, B. M. Broom, G. Manyam, and K. -A. Do, "iBAG: integrative Bayesian analysis of high -dimensional multiplatform genomics data," Bioinformatics, vol. 29, no. 2, pp. 149-159, 2013

    work page 2013

  48. [48]

    Dwppi: a deep learning approach for predicting protein–protein interactions in plants based on multi -source information with a large -scale biological network,

    J. Pan et al., "Dwppi: a deep learning approach for predicting protein–protein interactions in plants based on multi -source information with a large -scale biological network," Frontiers in Bioengineering and Biotechnology, vol. 10, p. 807522, 2022

    work page 2022

  49. [49]

    Modeling gene regulatory networks using neural network architectures,

    H. Shu et al. , "Modeling gene regulatory networks using neural network architectures," Nature Computational Science, vol. 1, no. 7, pp. 491-501, 2021

    work page 2021

  50. [50]

    Integrative multi -omics approaches in cancer research: from biological networks to clinical subtypes,

    Y. J. Heo, C. Hwa, G. -H. Lee, J. -M. Park, and J. -Y. An, "Integrative multi -omics approaches in cancer research: from biological networks to clinical subtypes," Molecules and cells, vol. 44, no. 7, pp. 433-443, 2021

    work page 2021

  51. [51]

    Network-based approaches for multi-omics integration,

    G. Zhou, S. Li, and J. Xia, "Network-based approaches for multi-omics integration," Computational methods and data analysis for metabolomics, pp. 469-487, 2020

    work page 2020

  52. [52]

    IMI-driver: Integrating multi-level gene networks and multi- omics for cancer driver gene identification,

    P. Shi, J. Han, Y. Zhang, G. Li, and X. Zhou, "IMI-driver: Integrating multi-level gene networks and multi- omics for cancer driver gene identification," PLOS Computational Biology, vol. 20, no. 8, p. e1012389, 2024

    work page 2024

  53. [53]

    Interpretation of network -based integration from multi-omics longitudinal data,

    A. Bodein, M. -P. Scott -Boyer, O. Perin, K. -A. Lê Cao, and A. Droit, "Interpretation of network -based integration from multi-omics longitudinal data," Nucleic acids research, vol. 50, no. 5, pp. e27-e27, 2022

    work page 2022

  54. [54]

    Multi-omics integration method based on attention deep learning network for biomedical data classification,

    P. Gong et al., "Multi-omics integration method based on attention deep learning network for biomedical data classification," Computer Methods and Programs in Biomedicine, vol. 231, p. 107377, 2023

    work page 2023

  55. [55]

    Multi -omic and multi -view clustering algorithms: review and cancer benchmark,

    N. Rappoport and R. Shamir, "Multi -omic and multi -view clustering algorithms: review and cancer benchmark," Nucleic acids research, vol. 46, no. 20, pp. 10546-10562, 2018

    work page 2018

  56. [56]

    Multi-view Machine Learning And Its Applications To Multi-Omic Tasks,

    B. Bauvin, "Multi-view Machine Learning And Its Applications To Multi-Omic Tasks," 2023

    work page 2023

  57. [57]

    Combining labeled and unlabeled data with co -training,

    A. Blum and T. Mitchell, "Combining labeled and unlabeled data with co -training," in Proceedings of the eleventh annual conference on Computational learning theory, 1998, pp. 92-100

    work page 1998

  58. [58]

    Analyzing the effectiveness and applicability of co-training,

    K. Nigam and R. Ghani, "Analyzing the effectiveness and applicability of co-training," in Proceedings of the ninth international conference on Information and knowledge management, 2000, pp. 86-93

    work page 2000

  59. [59]

    Active learning with multiple views,

    I. Muslea, S. Minton, and C. A. Knoblock, "Active learning with multiple views," Journal of Artificial Intelligence Research, vol. 27, pp. 203-233, 2006

    work page 2006

  60. [60]

    Multi -omics Cancer Subtype Recognition Based on Multi -kernel Partition Aligned Subspace Clustering,

    J. Liu, L. Hou, and S. Ge, "Multi -omics Cancer Subtype Recognition Based on Multi -kernel Partition Aligned Subspace Clustering," in International Conference on Intelligent Computing, 2023: Springer, pp. 395- 404

    work page 2023

  61. [61]

    Deep multi -view contrastive learning for cancer subtype identification,

    W. Chen, H. Wang, and C. Liang, "Deep multi -view contrastive learning for cancer subtype identification," Briefings in Bioinformatics, vol. 24, no. 5, p. bbad282, 2023

    work page 2023

  62. [62]

    Multi-view spectral clustering with latent representation learning for applications on multi -omics cancer subtyping,

    S. Ge, J. Liu, Y. Cheng, X. Meng, and X. Wang, "Multi-view spectral clustering with latent representation learning for applications on multi -omics cancer subtyping," Briefings in Bioinformatics, vol. 24, no. 1, p. bbac500, 2023

    work page 2023

  63. [63]

    Classifying breast cancer using multi -view graph neural network based on multi -omics data,

    Y. Ren et al., "Classifying breast cancer using multi -view graph neural network based on multi -omics data," Frontiers in Genetics, vol. 15, p. 1363896, 2024

    work page 2024

  64. [64]

    A framework for scRNA-seq data clustering based on multi-view feature integration,

    F. Li, Y. Liu, J. Liu, D. Ge, and J. Shang, "A framework for scRNA-seq data clustering based on multi-view feature integration," Biomedical Signal Processing and Control, vol. 89, p. 105785, 2024

    work page 2024

  65. [65]

    Multi-omics clustering for cancer subtyping based on latent subspace learning,

    X. Ye, Y. Shang, T. Shi, W. Zhang, and T. Sakurai, "Multi-omics clustering for cancer subtyping based on latent subspace learning," Computers in Biology and Medicine, vol. 164, p. 107223, 2023

    work page 2023

  66. [66]

    Self-supervised graph completion for incomplete multi - view clustering,

    C. Liu, S. Wu, R. Li, D. Jiang, and H. -S. Wong, "Self-supervised graph completion for incomplete multi - view clustering," IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 9, pp. 9394-9406, 2023

    work page 2023

  67. [67]

    Clustering single-cell multi-omics data via graph regularized multi-view ensemble learning,

    F. Chen, G. Zou, Y. Wu, and L. Ou -Yang, "Clustering single-cell multi-omics data via graph regularized multi-view ensemble learning," Bioinformatics, vol. 40, no. 4, p. btae169, 2024

    work page 2024

  68. [68]

    ScMOGAE: A Graph Convolutional Autoencoder-Based Multi-omics Data Integration Framework for Single -Cell Clustering,

    B. Zhou, H. Jiang, Y. Wang, Y. Gu, and H. Sun, "ScMOGAE: A Graph Convolutional Autoencoder-Based Multi-omics Data Integration Framework for Single -Cell Clustering," in International Symposium on Bioinformatics Research and Applications, 2024: Springer, pp. 322-334

    work page 2024

  69. [69]

    SC -AE: An Improved Spectral Clustering Unsupervised Feature Selection Algorithm Guided by Autoencoders Based on Pan -cancer Multi -view Omics Data,

    C. Si, L. Zhao, J. Liu, and Z. Chen, "SC -AE: An Improved Spectral Clustering Unsupervised Feature Selection Algorithm Guided by Autoencoders Based on Pan -cancer Multi -view Omics Data," in Proceedings of the 5th International Conference on Computer Information and Big Data Applications , 2024, pp. 894-900

    work page 2024

  70. [70]

    An Integrated Method Based on Wasserstein Distance and Graph for Cancer Subtype Discovery,

    Q. Cao, J. Zhao, H. Wang, Q. Guan, and C. Zheng, "An Integrated Method Based on Wasserstein Distance and Graph for Cancer Subtype Discovery," IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2023

    work page 2023

  71. [71]

    Heterogeneous information network and its application to human health and disease,

    P. Ding, W. Ouyang, J. Luo, and C.-K. Kwoh, "Heterogeneous information network and its application to human health and disease," Briefings in bioinformatics, vol. 21, no. 4, pp. 1327-1346, 2020

    work page 2020

  72. [72]

    Adaptive sparse multi-block PLS discriminant analysis: an integrative method for identifying key biomarkers from multi-omics data,

    R. Zhang and S. Datta, "Adaptive sparse multi-block PLS discriminant analysis: an integrative method for identifying key biomarkers from multi-omics data," Genes, vol. 14, no. 5, p. 961, 2023

    work page 2023

  73. [73]

    DeepKEGG: a multi-omics data integration framework with biological insights for cancer recurrence prediction and biomarker discovery,

    W. Lan, H. Liao, Q. Chen, L. Zhu, Y. Pan, and Y.-P. P. Chen, "DeepKEGG: a multi-omics data integration framework with biological insights for cancer recurrence prediction and biomarker discovery," Briefings in Bioinformatics, vol. 25, no. 3, p. bbae185, 2024

    work page 2024

  74. [74]

    Multi -omics data fusion for cancer molecular subtyping using sparse canonical correlation analysis,

    L. Qi, W. Wang, T. Wu, L. Zhu, L. He, and X. Wang, "Multi -omics data fusion for cancer molecular subtyping using sparse canonical correlation analysis," Frontiers in genetics, vol. 12, p. 607817, 2021

    work page 2021

  75. [75]

    Multi-omics marker analysis enables early prediction of breast tumor progression,

    H. Xu et al., "Multi-omics marker analysis enables early prediction of breast tumor progression," Frontiers in genetics, vol. 12, p. 670749, 2021

    work page 2021

  76. [76]

    Meta-Analytic Gene-Clustering Algorithm for Integrating Multi-Omics and Multi-Study Data,

    U. Kemmo Tsafack, K. W. Ahn, A. E. Kwitek, and C.-W. Lin, "Meta-Analytic Gene-Clustering Algorithm for Integrating Multi-Omics and Multi-Study Data," Bioengineering, vol. 11, no. 6, p. 587, 2024

    work page 2024

  77. [77]

    Understanding mechanisms underlying human gene expression variation with RNA sequencing,

    J. K. Pickrell et al., "Understanding mechanisms underlying human gene expression variation with RNA sequencing," Nature, vol. 464, no. 7289, pp. 768-772, 2010

    work page 2010

  78. [78]

    Genomic and transcriptomic analysis of relapsed and refractory childhood solid tumors reveals a diverse molecular landscape and mechanisms of immune evasion,

    S. A. Byron et al., "Genomic and transcriptomic analysis of relapsed and refractory childhood solid tumors reveals a diverse molecular landscape and mechanisms of immune evasion," Cancer research, vol. 81, no. 23, pp. 5818-5832, 2021

    work page 2021

  79. [79]

    Comprehensive molecular portraits of human breast tumours,

    Brigham, W. s. Hospital, H. M. S. C. L. P. P. J. K. R. 13, G. d. a. B. C. o. M. C. C. J. D. L. A. 25, and I. f. S. B. R. S. K. R. B. B. B. B. R. E. T. L. J. T. V. Z. W. S. Ilya, "Comprehensive molecular portraits of human breast tumours," Nature, vol. 490, no. 7418, pp. 61-70, 2012

    work page 2012

  80. [80]

    Genetic effects on gene expression across human tissues,

    G. C. L. a. A. F. B. A. A. C. S. E. D. J. R. H. Y. J. B. Mohammadi Pejman 5 6 Park YoSon 11 Parsana Princy 12 Segrè Ayellet V. 1 Strober Benjamin J. 9 Zappala Zachary 7 8, N. p. m. A. A. G. P. K. S. L. A. R. L. N. C. M. H. M. R. A. S. J. P. 19 Volpi S imona 19, P. S. L. B. M. E. B. P. A. 16, and N. C. F. N. C. R. 137, "Genetic effects on gene expression a...

    work page 2017

Showing first 80 references.