20 December 2023
Automation of chemistry research has focused on developing robots to execute jobs. Artificial-intelligence technology has now been used not only to control robots, but also to plan their tasks on the basis of simple human prompts.
Paywalled Paper:
Takeaway from SLAS (Society for Laboratory Automation and Screening) '26: liquid handling is no longer just about throughput — it’s about integration + control.
Automation teams I met in Boston weren’t asking for “another pipetting robot.”
They were asking for a pipetting module that can:Integrate cleanly into robotic systems
Execute complex liquid handling steps with real control at the channel level
Report status in real time so orchestration doesn’t become guesswork
That’s exactly what the Veon Scientific Ltd i.Prep2 was built for.Physical integration (the part that usually slows projects down):
Open-frame design with access from front / rear / side
Liquid handling control (precision in every channel):
Software integration (no black boxes):
If you’re building or upgrading a lab automation cell and want an integration-focused liquid handling module, email info@hrush.net. Hrush
LUMI-lab is out today in
!
We built a self-driving lab that closes the loop between an AI foundation model + robotics to accelerate lipid nanoparticle (LNP) discovery for mRNA delivery. Free access to the manuscript: https://authors.elsevier.com/a/1mg4aL7PXy21V Code available on GitHub: https://github.com/bowenli-lab/LUMI-lab Check the video here: https://youtube.com/watch?v=POOgIiKRSiE LUMI-lab (Large-scale Unsupervised Modeling followed by Iterative experiments) is a self-driving laboratory that tightly closes the loop between an AI foundation model and automated robotics to accelerate LNP discovery for mRNA delivery. To tackle data scarcity in emerging mRNA delivery domains, we pretrained the model on 28M+ molecular structures, then iteratively improved it with closed-loop experimental data. This is the kind of workflow we believe can meaningfully expand the accessible chemical space for next-generation RNA medicines. In this work, across ten active-learning cycles, LUMI-lab synthesized and evaluated 1,700+ new LNPs and unexpectedly identified a new design feature for efficient delivery: brominated lipid tails. These brominated-tail ionizable lipids delivered mRNA into human lung cells more efficiently than approved benchmarks, despite representing only a small fraction of the initial chemical space explored.
In the title you mentioned " (could be impt for making rapamycin / rapalogs cheaper / more accessible) "
I suspect AI may be helpful in this task (identifying new molecules) - but the bigger issue is that what really takes the most time are the clinical trials of new molecules. I asked Gemini how many mTOR inhibiting molecules have already been identified:
“Based on current pharmacological databases and chemical libraries, approximately 2,000 to 4,500 distinct mTOR inhibitor molecules have been synthesized, characterized, and formally cataloged”
So the real issue will be testing and qualifying the molecules, and unfortunately that takes a lot more time, money and effort and its not clear yet if AI can provide much in the way of benefits in these areas.