The First AI-Powered Platinum Drug Candidate That Defeats Cisplatin Resistance – The Babak Lab
The Babak Lab shared a post on LinkedIn about a paper by Daniil A. Rusanov et al. published in ChemRxiv:
“Our Team Designed First AI-Powered Platinum Drug Candidate That Defeats Cisplatin Resistance
We’re proud to share that our latest research, ‘Overcoming Cisplatin Resistance via Deep Learning–Assisted De Novo Design of Platinum Complexes’, is now available as a preprint on ChemRxiv:
Importance
Cisplatin resistance is a persistent challenge in cancer therapy – and for the first time, we’ve harnessed deep learning to tackle it head-on by designing a novel platinum complex from scratch: PlatinAI.
What we did
- Built the largest curated dataset of platinum anticancer complexes: 4,078 structures with ~19,000 IC₅₀ values.
- Solved a major cheminformatics bottleneck by adapting RDKit for transition metal SMILES.
- Developed a metal-specific KANO deep learning model for activity prediction.
- Designed and synthesized PlatinAI, a bis-NHC Pt(II) complex, via a de novo fragment-based assembly approach.
What we found
PlatinAI showed strong cytotoxicity against cisplatin-resistant A2780cis cells
It acts via a non-DNA-binding mechanism, unlike cisplatin.
In vivo validation confirmed its antitumor activity and safety in mouse models.
Why it matters
This is the first demonstration of AI-driven design and validation of a metal-based anticancer drug, opening new doors for drug discovery beyond organic chemistry.
Next steps
We’re expanding this platform to predict geometries, tackle other metal scaffolds, and further develop AI-assisted design tools for metallodrugs.
Authors: Daniil Rusanov, Dmitrii Brezgunov, Egor Matnurov, Bekir Pashaliev, Varvara V. Vetrova, and Maria (Masha) Babak.”
Maria Babak, Head of The Babak Lab, shared this post, adding:
“AI tools are becoming essential in drug development, specifically in metallodrug discovery. I hope our study will help accelerate the discovery of new platinum-based drugs with reduced side effects and improved outcomes for patients.”
Title: Overcoming cisplatin resistance via deep learning-assisted de novo design of platinum complexes
Authors: Daniil A. Rusanov, Dmitrii Yu. Brezgunov, Egor M. Matnurov, Bekir L. Pashaliev, Varvara V. Vetrova, Maria V. Babak.
You can read the Full Article in ChemRxiv.
More posts featuring The Babak Lab and Maria Babak.
-
Challenging the Status Quo in Colorectal Cancer 2024
December 6-8, 2024
-
ESMO 2024 Congress
September 13-17, 2024
-
ASCO Annual Meeting
May 30 - June 4, 2024
-
Yvonne Award 2024
May 31, 2024
-
OncoThon 2024, Online
Feb. 15, 2024
-
Global Summit on War & Cancer 2023, Online
Dec. 14-16, 2023