Chemora: A Multi-Agent AI Framework for Automated Chemical Synthesis Planning

Authors

  • D. Padmaja Usha Rani Department of CSE (AI & ML), Keshav Memorial Engineering College (KMEC), Hyderabad, India Author
  • Jonnalagadda Mahathi Department of CSE (AI & ML), Keshav Memorial Engineering College (KMEC), Hyderabad, India Author
  • G. Harinivas Department of CSE (AI & ML), Keshav Memorial Engineering College (KMEC), Hyderabad, India Author
  • Aryan Sripathi Department of CSE (AI & ML), Keshav Memorial Engineering College (KMEC), Hyderabad, India Author

DOI:

https://doi.org/10.63503/acset.88

Keywords:

Retrosynthesis, Cheminformatics, Multi-Agent Systems

Abstract

Chemora is a multi-agent artificial intelligence system designed for use in safety evaluation and assessment, chemical rationalisation, retrosynthesis planning, and the development of experiments and protocols. Chemora can generate multiple viable synthesis routes for various molecules and experimental conditions by employing cheminformatics and machine-learning classifiers, coupled with modularised execution controls. This renders AI-assisted chemical synthesis planning significantly simpler, faster, and more cost-effective in terms of labour.

References

[1] S. Segler, M. Preuss, and M. Waller, “Planning chemical syntheses with deep neural networks and symbolic AI,” Nature, vol. 555, pp. 604–610, 2018.

[2] P. Schwaller et al., “Molecular transformer: A model for uncertainty-calibrated chemical reaction prediction,” ACS Central Science, vol. 5, no. 9, pp. 1572–1583, 2019.

[3] IBM Research, “RoboRXN: AI for chemical synthesis,” [Online]. Avail-able: https://rxn.res.ibm.com

[4] NextMove Software, “SYNTHIA Retrosynthesis Software,” [Online].

Available: https://www.nextmovesoftware.com/synthia.html

[5] RDKit: Open-source cheminformatics software, [Online]. Available: https://www.rdkit.org

[6] PubChem Database, National Center for Biotechnology Information (NCBI), [Online]. Available: https://pubchem.ncbi.nlm.nih.gov

[7] T. Sterling and J. Irwin, “ZINC 15 – Ligand discovery for everyone,” Journal of Chemical Information and Modeling, vol. 55, no. 11, pp. 2324–2337, 2015.

[8] H. Dai et al., “Retrosynthesis prediction with conditional graph logic network,” Advances in Neural Information Processing Systems, 2019.

[9] LangGraph Documentation, [Online]. Available: https://langchain-ai.github.io/langgraph/

Downloads

Published

2026-09-13

Conference Proceedings Volume

Vol. 2 No. 2 (2026): Proceedings of ICNCDA

Section

Articles

License

Copyright (c) 2026 Adroid Conference Series: Engineering and Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

D. Padmaja Usha Rani, Jonnalagadda Mahathi, G. Harinivas, & Aryan Sripathi. (2026). Chemora: A Multi-Agent AI Framework for Automated Chemical Synthesis Planning. Adroid Conference Series: Engineering and Technology, 2(2), 39-49. https://doi.org/10.63503/acset.88