Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 52 min ago
Peer-reviewedCC BY 4.0Frontiers in Pharmacology

Integrating multi-omics with machine learning: from genomic variant functional annotation to pharmacogenomics and biomarker discovery

  • Jing Lv1
  • Jinjin Guo2
  • Yangyang Wang3
  • Jihan Wang4
  • Lei Guo5
  • Hongxing Zhang2
5 affiliations
  1. 1Department of Clinical Laboratory, Honghui Hospital, Xi’an Jiaotong University
  2. 2Department of Hand Surgery, Honghui Hospital, Xi’an Jiaotong University
  3. 3School of Physics and Electronic Information, Yan’an University
  4. 4Yan’an Medical College, Yan’an University
  5. 5Department of Spine Surgery, Honghui Hospital, Xi’an Jiaotong University
Read full textPDFDOICite

Abstract

Integrating heterogeneous multi-omics data with machine learning (ML) provides a powerful framework for interpreting genomic variants and advancing pharmacogenomic research in precision medicine. High-throughput technologies have generated vast datasets spanning genomics, transcriptomics, epigenomics, and proteomics, yet integrating these high-dimensional data into clinically meaningful insights remains a major computational challenge. Machine learning and deep learning models, including Graph Neural Networks (GNNs), Transformers, and Variational Autoencoders (VAEs), offer promising solutions. This narrative review provides a state-of-the-art overview of ML-driven multi-omics integration across early, intermediate, and late fusion paradigms. We highlight how these approaches may support functional variant interpretation, including the reclassification of Variants of Uncertain Significance (VUS), and emerging pharmacogenomic applications. Key areas include predictive biomarkers for drug efficacy, therapeutic resistance in precision oncology, and personalized dosing in rare and complex diseases. Finally, we discuss challenges related to data heterogeneity, clinical interpretability, and regulatory approval, as well as the requirements for translating emerging computational approaches into clinically validated pharmacogenomic practice and precision pharmacotherapy.

Related

  1. Integrating CSF and EV Proteomes Enhances Biomarker Discovery by Capturing Shared Variation Across Compartments
    B. R. P. Brown, X. Li, M. R. Grasty +2
    bioRxivPreprintCC BY-NDFull textSystems & synthetic biologybioRxiv
  2. From Closed-Set Annotation to In-Context Discovery: Biologically Grounded LLMs for Cellular Profiling
    M. Gelard, H. Benkirane, T. Pierrot +2
    bioRxivPreprintCC BY-NC-NDFull textBioinformatics & computational biologybioRxiv
  3. PalmLab: A Comprehensive Computational Platform for Systematic Annotation and Functional Interrogation of Protein Palmitoylation
    S. Fu, W. Wang, J. Huang +5
    bioRxivPreprintAll rights reservedFull textBioinformatics & computational biologybioRxiv
  4. A Frozen Plant DNA Language Model for Computational Prioritization and Functional Annotation of Melon (Cucumis melo) Variants
    Guosheng Sun, Yanping Wei, Entong Li +6
    GenesPeer-reviewedCC BYFull textGenetics & genomicsEurope PMC
  5. A low-annotation-budget PubMedBERT classifier for chondrogenesis regulator discovery via active learning
    A.-M. Anhel, M. J. Peffers, D. Young +1
    bioRxivPreprintCC BYFull textBioinformatics & computational biologybioRxiv

Cite

BibTeXRIS
BibTeX
@article{lv2026integrating,
  title = {{Integrating multi-omics with machine learning: from genomic variant functional annotation to pharmacogenomics and biomarker discovery}},
  author = {Jing Lv and Jinjin Guo and Yangyang Wang and Jihan Wang and Lei Guo and Hongxing Zhang},
  journal = {Frontiers in Pharmacology},
  year = {2026},
  month = oct,
  doi = {10.3389/fphar.2026.1980359},
  url = {https://www.frontiersin.org/articles/10.3389/fphar.2026.1980359/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Integrating multi-omics with machine learning: from genomic variant functional annotation to pharmacogenomics and biomarker discovery
AU  - Jing Lv
AU  - Jinjin Guo
AU  - Yangyang Wang
AU  - Jihan Wang
AU  - Lei Guo
AU  - Hongxing Zhang
PY  - 2026
DA  - 2026/10/14
JO  - Frontiers in Pharmacology
DO  - 10.3389/fphar.2026.1980359
UR  - https://www.frontiersin.org/articles/10.3389/fphar.2026.1980359/full
AB  - Integrating heterogeneous multi-omics data with machine learning (ML) provides a powerful framework for interpreting genomic variants and advancing pharmacogenomic research in precision medicine. High-throughput technologies have generated vast datasets spanning genomics, transcriptomics, epigenomics, and proteomics, yet integrating these high-dimensional data into clinically meaningful insights remains a major computational challenge. Machine learning and deep learning models, including Graph Neural Networks (GNNs), Transformers, and Variational Autoencoders (VAEs), offer promising solutions. This narrative review provides a state-of-the-art overview of ML-driven multi-omics integration across early, intermediate, and late fusion paradigms. We highlight how these approaches may support functional variant interpretation, including the reclassification of Variants of Uncertain Significance (VUS), and emerging pharmacogenomic applications. Key areas include predictive biomarkers for drug efficacy, therapeutic resistance in precision oncology, and personalized dosing in rare and complex diseases. Finally, we discuss challenges related to data heterogeneity, clinical interpretability, and regulatory approval, as well as the requirements for translating emerging computational approaches into clinically validated pharmacogenomic practice and precision pharmacotherapy.
SN  - 1663-9812
ER  -