Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 8 min ago
Peer-reviewedCC BY-NC-NDNature communications

On-demand design of controlled-release systems using an expert-mimic AI framework.

  • Ying Qin1,2
  • Rushuang Zhou3
  • Yali Ming2,4
  • Bohao Li5
  • Yuning Hu6
  • Donglin Sui2
  • Jingxuan Liu2
  • Hang Wang6
  • Guanghui Ma2,4
  • Yuedong Yang7
  • Yining Dong8
  • Yufei Xia9,10
10 affiliations
  1. 1Department of Data Science, City University of Hong Kong, Hong Kong, PR China.
  2. 2State Key Laboratory of Biopharmaceutical Preparation and Delivery, Institute of Process Engineering, Chinese Academy of Sciences, Beijing, PR China.
  3. 3Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, PR China.
  4. 4University of Chinese Academy of Sciences, Beijing, PR China.
  5. 5School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, PR China.
  6. 6Huili Pharmaceutical Co., Ltd., Suzhou, PR China.
  7. 7School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, PR China. [email protected].
  8. 8Department of Data Science, City University of Hong Kong, Hong Kong, PR China. [email protected].
  9. 9State Key Laboratory of Biopharmaceutical Preparation and Delivery, Institute of Process Engineering, Chinese Academy of Sciences, Beijing, PR China. [email protected].
  10. 10University of Chinese Academy of Sciences, Beijing, PR China. [email protected].
Read full textPDFDOICite

Abstract

Navigating a vast formulation-preparation design space that is highly sensitive to perturbations makes trial-and-error approaches inefficient and costly for diverse clinical needs. Here, we introduce an expert-mimic AI framework called E-MAF that integrates a process-aware surrogate with an optimized genetic algorithm to emulate coarse-to-fine reasoning, autonomously generating lab-ready designs tailored to desired release profiles. We show that E-MAF delivers on-demand release and shortens design cycles from 6-12 months to approximately 1 hour. We demonstrate that in vitro release, in vivo pharmacokinetics and therapeutic effects match or surpass commercial benchmarks across 7 active pharmaceutical ingredients. We show that E-MAF also enables release profiles that are hard to achieve by conventional approaches, exemplified by ≤2% risperidone burst within 1 h and near-zero-order release over ~28 days in vivo. These results demonstrate E-MAF's potential to accelerate polymeric controlled-release system development and drug-delivery industrialization.

Related

  1. Deep learning and metaheuristic optimization for predicting drug release from nanocarrier systems: a data-driven framework for formulation development
    Hadil Faris Alotaibi, Saad S. Alqahtani
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  2. Hydrogel-Based Delivery Systems for Targeted Probiotic Release and Colonization: From Design Principles to Health Outcomes.
    Wenjia Yan, Haichuan Shi, Hao Wang +2
    Gels (Basel, Switzerland)Peer-reviewedCC BYFull textGeneral medicineEurope PMC
  3. Light assisted activation of platelet-rich plasma for enhanced and controlled release of growth factors: a technology-driven proof-of-concept framework.
    Sarassunta Ucci, Valeria Iazzetta, Sara Spaziani +8
    Journal of biological engineeringPeer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMCPMC
  4. Dual-theoretical framework integrating the stress process model and family systems theory-based psychological intervention for caregivers of children and adolescents with mood disorders: study protocol for a randomized controlled trial
    Wei Lin, Hongyan Wu, Xuan Liu +3
    Frontiers in Public HealthPeer-reviewedCC BY 4.0Full textPsychiatry & mental healthCrossrefPMC
  5. Two-period demand phenotypes of oliceridine-based patient-controlled intravenous analgesia after gynecologic surgery: perioperative correlates of persistent high demand.
    Dandan Chen, Ting Qiu, Xiaoquan Yu +2
    Frontiers in medicinePeer-reviewedCC BYFull textSurgery & anaesthesiaEurope PMCPMC

Cite

BibTeXRIS
BibTeX
@article{qin2026ondemand,
  title = {{On-demand design of controlled-release systems using an expert-mimic AI framework.}},
  author = {Ying Qin and Rushuang Zhou and Yali Ming and Bohao Li and Yuning Hu and Donglin Sui and Jingxuan Liu and Hang Wang and Guanghui Ma and Yuedong Yang and Yining Dong and Yufei Xia},
  journal = {Nature communications},
  year = {2026},
  month = sep,
  doi = {10.1038/s41467-026-77619-5},
  url = {https://europepmc.org/article/MED/42875418},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - On-demand design of controlled-release systems using an expert-mimic AI framework.
AU  - Ying Qin
AU  - Rushuang Zhou
AU  - Yali Ming
AU  - Bohao Li
AU  - Yuning Hu
AU  - Donglin Sui
AU  - Jingxuan Liu
AU  - Hang Wang
AU  - Guanghui Ma
AU  - Yuedong Yang
AU  - Yining Dong
AU  - Yufei Xia
PY  - 2026
DA  - 2026/09/15
JO  - Nature communications
DO  - 10.1038/s41467-026-77619-5
UR  - https://europepmc.org/article/MED/42875418
AB  - Navigating a vast formulation-preparation design space that is highly sensitive to perturbations makes trial-and-error approaches inefficient and costly for diverse clinical needs. Here, we introduce an expert-mimic AI framework called E-MAF that integrates a process-aware surrogate with an optimized genetic algorithm to emulate coarse-to-fine reasoning, autonomously generating lab-ready designs tailored to desired release profiles. We show that E-MAF delivers on-demand release and shortens design cycles from 6-12 months to approximately 1 hour. We demonstrate that in vitro release, in vivo pharmacokinetics and therapeutic effects match or surpass commercial benchmarks across 7 active pharmaceutical ingredients. We show that E-MAF also enables release profiles that are hard to achieve by conventional approaches, exemplified by ≤2% risperidone burst within 1 h and near-zero-order release over ~28 days in vivo. These results demonstrate E-MAF's potential to accelerate polymeric controlled-release system development and drug-delivery industrialization.
SN  - 2041-1723
ER  -