Skip to content
DraconiticResearch
Search Sources API
190,869 studies31 sourcesUpdated 6 min ago
Peer-reviewedCC BY 4.0Genes

Integration of Multi-Omics in AI-Based Models for Predictive Oncology

  • Arnaud Nativel1
  • Sarah Dandou1
  • Florian Favier1
  • Candice Lesage1,2,3
  • Alain Mangé1
  • Julien Aligon4
  • Peter J Coopman5
  • Romain M Larive1
5 affiliations
  1. 1IRCM, Université de Montpellier, ICM, INSERM, F-34298 Montpellier, France.
  2. 2Department of Dermatology, Saint Eloi Hospital, Montpellier University Hospital, 34090 Montpellier, France.
  3. 3Institut du Cancer de Montpellier, Département D'Oncologie Médicale, F-34298 Montpellier, France.
  4. 4Université Toulouse Capitole, IRIT, (CNRS/UMR 5505), 31042 Toulouse, France.
  5. 5IRCM, Université de Montpellier, ICM, INSERM, CNRS, F-34298 Montpellier, France.
Read full textPDFDOICite

Abstract

Cancer heterogeneity and the emergence of innovative therapeutic alternatives have made the development of tools to help in clinical decision making even more necessary. The recent advances in the field of artificial-intelligence-based predictive models make them promising allies due to their ability to integrate vast amounts of descriptors and data, notably omic data, for grasping cancer complexity. However, it is difficult to present a complete picture of this field due to the increasing number of models and the many possible applications. The aim of this review was to offer an overview of omic-based predictive models in oncology through the prism of three important concepts: the objective, the data, and the model. We show that the consideration of these three aspects could help to assess the feasibility, validity and usability of a model and to guide its construction. Lastly, we highlight that taking into account the underlying technical, physiological and biological phenomena inherent to omic data at each step of the project may improve the model predictive capability and its explainability.

Related

  1. Multiscale predictive cellular modeling: integrating hypothesis grammars, digital twins, and multi-omics for In silico oncology and precision theranostics
    S.T. Gopukumar, Dyumn Dwivedi, Mohamed Rahamathulla +6
    Functional & Integrative GenomicsPeer-reviewedLicence not statedFull text7 citedPlant biologyOpenAlex
  2. Multi-Omics Integration Drives Precision Breeding in Sorghum: Molecular Dissection and Breeding Practice
    Plants (Basel, Switzerland)Peer-reviewedCC BYFull textPlant biologyEurope PMC
  3. Biologically Informed Multi-Omics Integration Reveals Clinically Meaningful Patient Representations in Acute Myeloid Leukemia
    D. H. V. Gammune, D. Bui, T. Gu
    bioRxivPreprintAll rights reservedFull textBioinformatics & computational biologybioRxiv
  4. Multi-omics integration reveals L-arginine as a key mediator linking dietary protein to weight change in cats: an exploratory study
    Huakai Wang, Xiaohan Chang, Shuyi Han +3
    Journal of Animal SciencePeer-reviewedPublisher termsFull textZoology & animal behaviourPMC
  5. Plant Responses to Heavy Metal Stress: Molecular Mechanisms, Transcriptomic Regulation, and Multi-Omics Integration in Crop Improvement
    Zagipa Sapakhova, Dias Daurov, Ainash Daurova +7
    Plants (Basel, Switzerland)Peer-reviewedCC BYFull textPlant biologyEurope PMC

Cite

BibTeXRIS
BibTeX
@article{nativel2026integration,
  title = {{Integration of Multi-Omics in AI-Based Models for Predictive Oncology}},
  author = {Arnaud Nativel and Sarah Dandou and Florian Favier and Candice Lesage and Alain Mangé and Julien Aligon and Peter J Coopman and Romain M Larive},
  journal = {Genes},
  year = {2026},
  month = oct,
  doi = {10.3390/genes17101231},
  url = {https://hal.umontpellier.fr/hal-05782911v1},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Integration of Multi-Omics in AI-Based Models for Predictive Oncology
AU  - Arnaud Nativel
AU  - Sarah Dandou
AU  - Florian Favier
AU  - Candice Lesage
AU  - Alain Mangé
AU  - Julien Aligon
AU  - Peter J Coopman
AU  - Romain M Larive
PY  - 2026
DA  - 2026/10/04
JO  - Genes
DO  - 10.3390/genes17101231
UR  - https://hal.umontpellier.fr/hal-05782911v1
AB  - Cancer heterogeneity and the emergence of innovative therapeutic alternatives have made the development of tools to help in clinical decision making even more necessary. The recent advances in the field of artificial-intelligence-based predictive models make them promising allies due to their ability to integrate vast amounts of descriptors and data, notably omic data, for grasping cancer complexity. However, it is difficult to present a complete picture of this field due to the increasing number of models and the many possible applications. The aim of this review was to offer an overview of omic-based predictive models in oncology through the prism of three important concepts: the objective, the data, and the model. We show that the consideration of these three aspects could help to assess the feasibility, validity and usability of a model and to guide its construction. Lastly, we highlight that taking into account the underlying technical, physiological and biological phenomena inherent to omic data at each step of the project may improve the model predictive capability and its explainability.
SN  - 2073-4425
ER  -