Skip to content
DraconiticResearch
Search Sources API
194,220 studies31 sourcesUpdated 42 min ago
Peer-reviewedCC BYBriefings in bioinformatics

Virtual cells: progress and challenges from mechanistic modeling to data-driven integration.

  • Nuoran Ma1
  • Zihao Wang2
  • Xu Yang2
  • Guoxing Yang2
  • Rui Yang2
  • Zhenxing Wang3
  • Qinghua Jiang4
  • Yanshuo Chu5
5 affiliations
  1. 1Department of Artificial Intelligence, School of Future Technology, Harbin Institute of Technology, 92 Xidazhi Street, Nangang District, Harbin 150001, Heilongjiang, China.
  2. 2Harbin Institute of Technology, Harbin 150001, Heilongjiang, China.
  3. 3School of Computer Science and Artificial Intelligence, Northeast Forestry University, Harbin 150040, Heilongjiang, China.
  4. 4Center for Bioinformatics, School of Life Science and Technology, Harbin Institute of Technology, Harbin 150001, Heilongjiang, China.
  5. 5School of Medicine and Health, Harbin Institute of Technology, Harbin 150000, Heilongjiang, China.
Read full textPDFDOICite

Abstract

Virtual cells aim to represent cellular states computationally and predict responses to genetic, chemical, environmental, temporal, and spatial conditions. For comparative purposes, this review uses state encoding (E), state transition (T), and observation decoding (D) as a conceptual abstraction spanning explicit mechanistic models, data-driven foundation and perturbation models, multimodal systems, and spatial and multiscale simulation. We examine model boundaries, data foundations, resource disclosure, out-of-distribution evaluation, causal evidence, and experimental validation. Independent benchmarks show that parameter count and training-set size do not automatically yield robust out-of-distribution generalization, while transcriptomic representations alone do not capture the full functional state of a cell. Trustworthy virtual cells will require perturbation-responsive transitions, cross-modal alignment, continuous-time dynamics, mechanistic constraints, calibrated uncertainty, independent experimental validation, and, where appropriate, closed-loop experimental feedback.

Related

  1. Challenges and progress in RNA velocity: Comparative analysis across multiple biological contexts
    Sarah Ancheta, Leah C. Dorman, Guillaume Le Treut +5
    PLoS Computational BiologyPeer-reviewedCC BYFull text9 citedMolecular biology & gene regulationOpenAlex
  2. Dynamic three-dimensional chromatin remodeling in lung disease: mechanistic principles, pathogenic regulatory networks, and translational challenges
    Tiantian Liu, Songshan Jiang, Jing Wang +1
    Frontiers in cell and developmental biologyPeer-reviewedCC BYFull textGeneral biochemistryEurope PMC
  3. Transcription factor targeting strategies in cancer: mechanisms, challenges and cutting-edge progress
    Hui Chen, Rong Fu, Zhao-qiu Wu
    Acta Pharmacologica SinicaPeer-reviewedCC BY-NC-ND 4.0Full text2 citedMolecular biology & gene regulationPMC
  4. Enhanced exosome biomanufacturing, precision isolation, and advanced engineering: toward mechanistic regulation and biomaterial integration for osteoarthritis therapy
    Meipei Gao, Qiaotian Yin, Zejian Zhong +7
    Journal of NanobiotechnologyPeer-reviewedCC BY-NC-ND 4.0Full text3 citedMolecular biology & gene regulationPMC
  5. Panax ginseng Across the Cardiovascular Continuum: Molecular Targets, Mechanistic Convergence, and Translational Challenges
    Min Qiao, Chang Sun, Yangyang Qin +5
    BiomoleculesPeer-reviewedCC BY 4.0General biochemistryCrossref

Cite

BibTeXRIS
BibTeX
@article{ma2026virtual,
  title = {{Virtual cells: progress and challenges from mechanistic modeling to data-driven integration.}},
  author = {Nuoran Ma and Zihao Wang and Xu Yang and Guoxing Yang and Rui Yang and Zhenxing Wang and Qinghua Jiang and Yanshuo Chu},
  journal = {Briefings in bioinformatics},
  year = {2026},
  month = sep,
  doi = {10.1093/bib/bbag562},
  url = {https://europepmc.org/article/MED/42893561},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Virtual cells: progress and challenges from mechanistic modeling to data-driven integration.
AU  - Nuoran Ma
AU  - Zihao Wang
AU  - Xu Yang
AU  - Guoxing Yang
AU  - Rui Yang
AU  - Zhenxing Wang
AU  - Qinghua Jiang
AU  - Yanshuo Chu
PY  - 2026
DA  - 2026/09/01
JO  - Briefings in bioinformatics
DO  - 10.1093/bib/bbag562
UR  - https://europepmc.org/article/MED/42893561
AB  - Virtual cells aim to represent cellular states computationally and predict responses to genetic, chemical, environmental, temporal, and spatial conditions. For comparative purposes, this review uses state encoding (E), state transition (T), and observation decoding (D) as a conceptual abstraction spanning explicit mechanistic models, data-driven foundation and perturbation models, multimodal systems, and spatial and multiscale simulation. We examine model boundaries, data foundations, resource disclosure, out-of-distribution evaluation, causal evidence, and experimental validation. Independent benchmarks show that parameter count and training-set size do not automatically yield robust out-of-distribution generalization, while transcriptomic representations alone do not capture the full functional state of a cell. Trustworthy virtual cells will require perturbation-responsive transitions, cross-modal alignment, continuous-time dynamics, mechanistic constraints, calibrated uncertainty, independent experimental validation, and, where appropriate, closed-loop experimental feedback.
SN  - 1467-5463
SN  - 1477-4054
ER  -