What does it mean to be on #TeamScience? Find out what Benchlings have to say about our mission and culture — and above all, why we’re so passionate about helping scientists power new possibilities for humanity. piped.video/KiBmXAGoMgU

How do you run over 600 AI-generated code executions a day, across hundreds of tenants a week, with zero security incidents? Check out our technical deep dive with @AWS on securing multi-tenant code execution with account-level isolation, DNS exfiltration defenses, and per-job credential scoping. aws.amazon.com/blogs/machine…

One of the themes of my career has been deploying ML to to experts in complex domains, including to oncologists in 2017 and to medicinal chemists in 2022. Communicating about ML in a way that creates trust has been deeply important in both cases. It was fun to chat with @benchling about this after the launch of our models into their platform.

Get the stories behind the models. @inductive_bio cofounder @benbirnbaum talks about ADMET modeling, the “whack-a-mole” of compound optimization, and why trust is earned through transparency. benchling.com/blog/how-induc…

Ask Benchling AI to build a weekly update agent that runs every Monday. It can sum up what's done, what's in motion, and what needs your attention. Save the agent once, share access with your team, and everyone benefits from the same automation.

Today, we’re announcing mBER-2, our latest AI protein design system, and sharing a bit of how we use it to explore biology in vivo at scale. For a long time, we’ve been working on what I think of as “frontier problems” in medicine and biology. We know a lot about the targets involved in disease, but there is still an enormous amount of biology we haven’t explored, and potential uses for that biology we haven’t discovered. One of those problems is drug delivery. There are thousands of potential targets, and most receptors remain unexplored as routes for delivering medicines. We want to understand which ones we can use, where they can take a drug, and what kinds of molecules make that possible. Ultimately, we need to test these molecules in vivo to understand what they actually do. We’ve spent the last six years building measurement technologies that let us generate millions of measurements in living systems. mBER-2 is an AI protein design system built for that scale of in vivo measurement. Our goal is to generate binders across the full range of targets we care about, while systematically exploring the possible binding sites on each one. It’s not just what you bind, but where and how you bind that determines whether a molecule performs it's function. mBER-2 lets us probe those differences at massive scale. We’re also sharing a look at some of our in vivo data. We’ve designed more than 50 million molecules across over 4,000 targets, and screened millions of molecules in living systems. By probing hundreds of receptors, we’ve found new pathways for delivering genetic medicines into fat that outperform industry benchmarks by a large margin. This is just the beginning. We call the space of all bindable sites across proteomes the EpiTome. As we explore it, we’re building the data to connect AI design, receptor binding, and what a molecule actually does in a living organism. Much like the idea of a virtual cell, we envision a Virtual Organism that helps us design medicines with specific properties in mind. The foundation is our own in vivo data, connecting molecular design to outcomes measured in living systems. The endgame is to use AI to explore more biology, measure what happens, and use what we learn to design better medicines. Every round should deepen our understanding of biology and improve our ability to build molecules that do what we need them to do.

We’re hearing two kinds of voices on the potential of AI to cure all disease: One says AI will cure everything, but without a concrete path to get there. The other says biology is too complex to ever tame, but underestimates the power of the tools that will unlock the full potential of frontier intelligence. At Manifold Bio, we see a path and we’re already building it: a high-throughput interface into living system biology. Millions of protein designs, measured directly in vivo, to learn how molecules behave in the body and ultimately predict what they’ll do before they reach a patient. Today we share mBER-2, the latest iteration of our AI protein design model that is a core piece of this mission.

Hands-free data capture is here. Now you can talk to Benchling AI instead of typing out every question or instruction.

@benchling Voice mode in Preview! Most scientific work still happens in the lab, so AI needs to be able to work in the lab

Build it once, then run it again and again. Use Benchling AI to build a workflow that automatically turns raw instrument data into analyzed results. Save it as a template, then reuse it on your next dataset.

Another job for Benchling Agents: inventory management. Set up an Agent to automatically track reagent usage, flag trends, and forecast what you’ll need next.

There's still a tremendous gap between what people believe models can do (design bioweapons) and what models can actually do (fail to optimize protocols more than half the time). Even "bio-specific" models like GPT-Rosalind still struggle on real wet lab tasks. I spend a lot of time talking to scientists and this is one of the biggest reasons there's a huge gap between what the AI world thinks models can do and what scientists who use these models every day think they can do.

Switch to “full actions” mode to let Benchling AI take actions for you, whether that’s creating notebook entries or registering samples. See how it takes a shipment manifest and turns it into a set of prefilled receipt entries.

Narrative violation: Astra is better than Sol, but still not SOTA on hard wet lab biology tasks Most biological reasoning is not captured in public data, so hard to train for this. Excited to see the progress though!

From HPLC data to chromatograms, just like that. Set up the workflow once, and Benchling automatically processes and analyzes your instrument data the same way every time. benchling.com/automation?utm…

Vibe coding is changing who gets to build software. What does that mean for science? Now scientists can build custom R&D apps in minutes, while agents take action across scientific workflows, and models keep getting better at reasoning through real lab problems. Our Head of AI @nlarusstone spoke with @RandDWorld about the emerging AI stack for science and what comes next. rdworldonline.com/benchling-…

@benchling now offers @EliLillyandCo’s TuneLab models for antibody developability and small-molecule ADME/Tox predictions. Participating biotechs can use the models through federated learning without directly exposing sensitive proprietary data. benchling.com/blog/lilly-tun… Subscribe to our newsletter and get the biggest biotech news straight to your inbox 🧬 syntheticbiologysummit.com/?…

love @benchling 🪼

What if AI could check every new study against what your org already knows? With Benchling Agents, it can. Build an Agent, choose when it runs, and let it take action automatically. A Study Design Review Agent can compare new studies against past work and flag potential redundancy before work begins. What will you build? benchling.com/blog/introduci… #AIForScientists