Skip to content
DraconiticResearch
Search Sources API
201,683 studies31 sourcesUpdated 20 min ago
PreprintCC BYChemRxiv

A retrieval-augmented agent bridges virtual screening and automated synthesis

  • Shan Zhu1
  • Xin Chen1,2
  • Pinqi Wang1,2
  • Quan Jiang1,2
  • Mengzhu Li3
  • Qimeng Wang1
  • Guoyun Zhao1
  • Yuan Qi1,3
  • Fenglei Cao1,2
  • Li-Cheng Xu1,2
  1. 1Shanghai Academy of Artificial Intelligence for Science
  2. 2Golab Inc.
  3. 3Artificial Intelligence Innovation and Incubation Institute, Fudan University
Open at sourcePDFDOICite

Abstract

Translating virtually designed drug molecules into executable synthesis protocols is essential for connecting computational discovery with automated synthesis. However, most retrosynthesis methods focus on precursor generation, offer limited route diversity, and lack the detailed reaction conditions required for executable protocols. Here, we present Syn-RRAG, a retrieval-augmented LLM-driven synthesis agent connecting virtual screening with automated synthesis and validation. Syn-RRAG integrates initial retrosynthetic prediction, reaction-precedent retrieval and hierarchical refinement to generate structured protocols with complete experimental parameters. Its local generative model searches over complete reaction hypotheses rather than relying solely on token-level beam search, enabling exploration of feasible routes with distinct reaction classes and bond disconnections. It achieved strong retrosynthesis performance on two patent-derived reaction datasets. Syn-RRAG further generated executable plans for three virtually screened drug candidates, all of which were synthesized and validated on an automated platform. These results establish a workflow connecting virtual molecular design, synthesis planning and experimental validation.

Related

  1. Drug Molecular and Route Similarity-Aware Retrieval-Augmented LLM Generation with Knowledge Graph for Semantic Reasoning
    Jiaxin Lao, Liansuo Zu
    ChemRxivPreprintCC BY-NC-NDFull textGeneral chemistryChemRxiv
  2. An Expert-Augmented Deep Learning Approach for Synthesis Route Evaluation
    Yujia Guo, Marco V. Mijangos, Tat Hong Duong Le +6
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv
  3. Automated transition state generation for mechanistic exploration in organic synthesis
    Li‐Cheng Xu, Junyi An, Weiqi Liu +4
    Nature CommunicationsPeer-reviewedCC BYFull text7 citedMedicinal chemistry & drug discoveryOpenAlex
  4. Systematic DFT Screening of Anti-Perovskite Nitrides for Chemical-Looping Ammonia Synthesis: Ca-Based Compounds as Promising Candidates
    Norifumi Asakuma, Tomoyuki Tamura, Sawao Honda +3
    ACS Applied Energy MaterialsPeer-reviewedPublisher termsFull textGeneral chemistryHAL
  5. Virtual screening, synthesis, solid state characterization, evaluation for solubility, dissolution, and stability of gallic acid-based cocrystals of glimepiride
    Sanket M. Gandhi, Shrinivas K. Mohite, Amol S. Shete +4
    DARU Journal of Pharmaceutical SciencesPeer-reviewedLicence not statedFull textMaterials & polymersPMC

Cite

BibTeXRIS
BibTeX
@misc{zhu2026retrievalaugmented,
  title = {{A retrieval-augmented agent bridges virtual screening and automated synthesis}},
  author = {Shan Zhu and Xin Chen and Pinqi Wang and Quan Jiang and Mengzhu Li and Qimeng Wang and Guoyun Zhao and Yuan Qi and Fenglei Cao and Li-Cheng Xu},
  howpublished = {ChemRxiv},
  year = {2026},
  month = sep,
  doi = {10.26434/chemrxiv.15008409/v1},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008409/v1},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - A retrieval-augmented agent bridges virtual screening and automated synthesis
AU  - Shan Zhu
AU  - Xin Chen
AU  - Pinqi Wang
AU  - Quan Jiang
AU  - Mengzhu Li
AU  - Qimeng Wang
AU  - Guoyun Zhao
AU  - Yuan Qi
AU  - Fenglei Cao
AU  - Li-Cheng Xu
PY  - 2026
DA  - 2026/09/07
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15008409/v1
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008409/v1
AB  - Translating virtually designed drug molecules into executable synthesis protocols is essential for connecting computational discovery with automated synthesis. However, most retrosynthesis methods focus on precursor generation, offer limited route diversity, and lack the detailed reaction conditions required for executable protocols. Here, we present Syn-RRAG, a retrieval-augmented LLM-driven synthesis agent connecting virtual screening with automated synthesis and validation. Syn-RRAG integrates initial retrosynthetic prediction, reaction-precedent retrieval and hierarchical refinement to generate structured protocols with complete experimental parameters. Its local generative model searches over complete reaction hypotheses rather than relying solely on token-level beam search, enabling exploration of feasible routes with distinct reaction classes and bond disconnections. It achieved strong retrosynthesis performance on two patent-derived reaction datasets. Syn-RRAG further generated executable plans for three virtually screened drug candidates, all of which were synthesized and validated on an automated platform. These results establish a workflow connecting virtual molecular design, synthesis planning and experimental validation.
ER  -