News Picture Generic

Toward fully autonomous closed-loop molecular discovery – A case study on JAK targets

February 3, 2026
Featured Article

ChemRxiv

Bridging AI and self-driving laboratories, we introduce the first fully-automated, closed-loop molecular discovery cycle, exemplified by the identification of novel JAK inhibitors. With minimal human intervention, we combined AI-driven molecular design and retrosynthesis with IBM’s synthesis automation system RoboRXN and Arctoris’ Ulysses platform for automated in-vitro screening. We performed two Design-Make-Test-Analyze (DMTA) cycles with a total of 36 synthesized compounds. In the first round, the generative model identified structural analogs of established JAK inhibitors despite being blinded from known JAK inhibitors. The second iteration yielded molecules with significantly improved pIC50 and ligand efficiency (p < 0.001) compared to the first round, underscoring the effectiveness of the closed-loop workflow.

For details: 

Toward fully autonomous closed-loop molecular discovery – A case study on JAK targets

Jannis Born 1, Carlo Baldassari 1, Doriela Grabocka 1, Antonio Cardinale 1, Oliver Schilter 1, Alessandro Castrogiovanni 1, Artem Leonov 1, Filip Skogh 1, Jeeven Singh 2, Yaoyao Xiong 2, John Evans 2, Thomas Fleming 2, Teodoro Laino 1, Matteo Manica 1

1) IBM Research - Zurich, Switzerland
2) Arctoris

ChemRxiv
https://chemrxiv.org/doi/10.26434/chemrxiv-2026-q7xdt

Contact us to learn more about this exciting article:https://www.chemspeed.com/contact/

Other Recent News

Discover more news articles you might be interested in

Read more about Identifying critical powder properties for high-throughput dispensing of alumina and organic templates
News Picture 1 1 V2
Jun
16

Identifying critical powder properties for high-throughput dispensing of alumina and organic templates

Screening powder properties such as flowability, compressibility, and particle geometry is crucial for controlling ceramic processing, particularly in automated workflows that demand high reproducibility. Sacrificial templating for porous ceramics is well suited to automation because it is prone to variability arising from manual handling.

Read more about Integration of Machine Learning and Automated Synthesis for Accelerated Drug and Material Research
News Picture 1 1 V2
Jun
2

Integration of Machine Learning and Automated Synthesis for Accelerated Drug and Material Research

The challenges posed by global climate change and disease risks have intensified the demand for efficient and practical materials and molecules. Traditional trial-and-error approaches are becoming increasingly inefficient and resource-intensive. The rapid advancement of artificial intelligence (AI) has opened new avenues to accelerate research and shorten development cycles.

© Chemspeed Technologies 2026