Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing Latent-X — our all-atom frontier AI model for protein binder design. State-of-the-art lab performance, widely accessible via the Latent Labs Platform. Free tier: Blog: Technical report:

Simon Kohl

3,097 subscribers

57,495 views • 1 year ago •via X (Twitter)

Health & Wellness Science & Technology Education

Anya Rossi• Live Now

Private livecam show

32 Comments

Simon Kohl1 year ago

Latent-X achieved breakthrough lab results: Picomolar binding affinities, directly outperforming prior methods in head-to-head validation. Leading experimental hit rates: * 91-100% for macrocycles * 10-64% for mini-binders Testing 30-100 designs per target vs millions traditionally.

Simon Kohl1 year ago

Latent-X generates novel binders from scratch, solving the geometric puzzle of binding at the all-atom level while obeying biochemical rules nature follows. I'm still mesmerized watching the model generate successful binders directly at the atom level — hydrogen bonds included!

Simon Kohl1 year ago

What excites me most: getting this into the hands of scientists through our no-code platform. Replicates our validated workflows, no AI background required. And it’s fast — up to 10x faster than prior methods!

Simon Kohl1 year ago

We’re making Latent-X available with a free tier for commercial and academic users alike. We want to get cutting-edge AI into the hands of scientists at big pharma and small labs without needing AI teams or infrastructure.

Simon Kohl1 year ago

Starting with macrocycles and mini-binders. Can't wait for your feedback! More to come! For requests beyond current platform capabilities: [email protected].

microRoc1 year ago

@razoralign Want to say a word or two about your user agreement?

Chaitanya K. Joshi1 year ago

Congrats team!!

Simon Kohl1 year ago

Thank you, Chaitanya!

Charlie Harris1 year ago

Congrats Simon!

Simon Kohl1 year ago

Thank you, Charlie!

Aidan Gomez1 year ago

Congrats!!

Simon Kohl1 year ago

Thank you, Aidan!!

Kentsis Research Group1 year ago

Great to see joint operation on sequence and structure @CalebLareau

Simon Kohl1 year ago

@CalebLareau Thank you, looking forward to having you try the model!

Rishabh1 year ago

Awesome stuff, Simon!! 🥳🔥

Simon Kohl1 year ago

Thank you Rishabh! It would be great to get your feedback on the platform!

Rishabh1 year ago

Would love to! DM’d :D

Mati Staniszewski1 year ago

Congratulations - that’s amazing!

Simon Kohl1 year ago

Thank you Mati - it’s fantastic to have you on board!

Mattias Ordboken1 year ago

@saakohl Awesome work and business model - congratulations. When will we see models further downstream, e.g. ADME?

Tomas Geffner1 year ago

Congrats @saakohl and team!

Simon Kohl1 year ago

Thank you Tomas and congrats for La Proteina

Ethan Fast1 year ago

congrats on the launch, very exciting! just filled out your interest form, we'd love to give the model a try

Russ Wilcox1 year ago

What a massive change is coming for drug discovery

Simon Kohl1 year ago

Thank you @Russ_Wilcox, and thanks for being onboard from the start! We can't wait to see what our partners and users are achieving with it!

Karsten Kreis1 year ago

Congrats to this strong release, Simon!

Simon Kohl1 year ago

Thank you Karsten, really appreciate it! Congrats on La Proteina as well!

Gina El Nesr1 year ago

Awesome to see!! Congrats Simon!

Simon Kohl1 year ago

Thank you, Gina!

Evgenii1 year ago

Looks neat! Why you didn't validate the structures? These binders look small enough to be tested by NMR or X-rays.

Javin Oza1 year ago

Does it only generate new binders or Is it possible to do 'affinity maturation' if a know binding pair is provided?

Simon Kohl1 year ago

Thanks for the interest! This model generates new binders.

Related Videos

Today we're launching Latent-Y: the world's first autonomous agent for drug design, lab-validated end to end. Give it a research goal. Latent-Y reasons, designs, iterates, and delivers lab-ready antibodies, autonomously or collaboratively, with the biological reasoning of a PhD protein design expert. Technical report: Blog post: Apply for access:

Today we're launching Latent-Y: the world's first autonomous agent for drug design, lab-validated end to end. Give it a research goal. Latent-Y reasons, designs, iterates, and delivers lab-ready antibodies, autonomously or collaboratively, with the biological reasoning of a PhD protein design expert. Technical report: Blog post: Apply for access:

Simon Kohl

121,575 views • 6 months ago

Introducing EmbeddingGemma: our new open, state-of-the-art embedding model designed for on-device AI 📱

Introducing EmbeddingGemma: our new open, state-of-the-art embedding model designed for on-device AI 📱

Google AI Developers

154,169 views • 1 year ago

We connected our autonomous lab to OpenAI's GPT-5 and let it run 36,000 experiments. The result was a new state-of-the-art for Cell-Free Protein Synthesis that cut costs by 40% per gram of protein. You can now order the beta version for your own lab: You can read the full preprint and read OpenAI’s blog post about our work here: See the full press release here:

We connected our autonomous lab to OpenAI's GPT-5 and let it run 36,000 experiments. The result was a new state-of-the-art for Cell-Free Protein Synthesis that cut costs by 40% per gram of protein. You can now order the beta version for your own lab: You can read the full preprint and read OpenAI’s blog post about our work here: See the full press release here:

Ginkgo Bioworks

80,608 views • 8 months ago

AI has solved software. Biology is the next frontier. We're hiring across every team at Adaptyv. We’ve built the best automated lab for protein designers to experimentally test their AI-designed proteins. Today, the most advanced protein design companies run their wet-lab work on Adaptyv, from the biggest biopharmas to frontier AI labs to dozens of virtual biotech startups. Demand has grown faster than we have, so we’re hiring across the board: • Bio: Research associates, scientists and lab technicians to develop and run new assays at scale. • Lab automation: Engineers and interns to onboard new lab instruments and scale our automation infrastructure. • Software: Product and backend engineers to scale LabOS, our internal lab orchestration platform, our API for agents and the data pipelines that turn messy physical-world data into clean results. • Partnerships, customer success and operations: Building partnerships with AI & pharma labs, making sure customers understand their data and can run more campaigns, making sure the company operations run smoothly

AI has solved software. Biology is the next frontier. We're hiring across every team at Adaptyv. We’ve built the best automated lab for protein designers to experimentally test their AI-designed proteins. Today, the most advanced protein design companies run their wet-lab work on Adaptyv, from the biggest biopharmas to frontier AI labs to dozens of virtual biotech startups. Demand has grown faster than we have, so we’re hiring across the board: • Bio: Research associates, scientists and lab technicians to develop and run new assays at scale. • Lab automation: Engineers and interns to onboard new lab instruments and scale our automation infrastructure. • Software: Product and backend engineers to scale LabOS, our internal lab orchestration platform, our API for agents and the data pipelines that turn messy physical-world data into clean results. • Partnerships, customer success and operations: Building partnerships with AI & pharma labs, making sure customers understand their data and can run more campaigns, making sure the company operations run smoothly

Adaptyv Bio

15,109 views • 4 months ago

Really fun No Priors with Walter Goodwin founder of Fractile topics: - how to win the ai chip market, structurally - ai for chip design, what’s compressible - the need to be a frontier lab to serve frontier labs - solving memory bandwidth - new hardware scaling laws

Really fun No Priors with Walter Goodwin founder of Fractile topics: - how to win the ai chip market, structurally - ai for chip design, what’s compressible - the need to be a frontier lab to serve frontier labs - solving memory bandwidth - new hardware scaling laws

sarah guo

30,285 views • 4 days ago

We recently released a technical report highlighting how Isomorphic Labs’ drug design engine is achieving a step change in how we model complex biological mechanisms, consistently outperforming industry benchmarks. Read our blog to discover how we’re bridging the gap between structure prediction and rational drug design. You can find the link in the comments.

We recently released a technical report highlighting how Isomorphic Labs’ drug design engine is achieving a step change in how we model complex biological mechanisms, consistently outperforming industry benchmarks. Read our blog to discover how we’re bridging the gap between structure prediction and rational drug design. You can find the link in the comments.

Isomorphic Labs

125,474 views • 7 months ago

Wave 9 is here: a frontier model built for software engineering. Introducing our new family of models: SWE-1, SWE-1-lite, and SWE-1-mini. Based on internal evals, it has performance nearing that of frontier models from the foundation labs. Available now, only in Windsurf!

Wave 9 is here: a frontier model built for software engineering. Introducing our new family of models: SWE-1, SWE-1-lite, and SWE-1-mini. Based on internal evals, it has performance nearing that of frontier models from the foundation labs. Available now, only in Windsurf!

Devin Desktop

743,273 views • 1 year ago

Introducing Magnific Precision, now on the Freepik AI Suite Upscale your images while keeping the original intact. The lastest state of the art model by Magnific.ai Available for all plans

Introducing Magnific Precision, now on the Freepik AI Suite Upscale your images while keeping the original intact. The lastest state of the art model by Magnific.ai Available for all plans

Magnific

51,831 views • 1 year ago

lab·o·ra·to·ry A place equipped for experimental study in a science or for testing and analysis. Introducing our state-of-the-art, in-stadium Maven Baseball Lab player development lab! #GoHoos

lab·o·ra·to·ry A place equipped for experimental study in a science or for testing and analysis. Introducing our state-of-the-art, in-stadium Maven Baseball Lab player development lab! #GoHoos

Virginia Baseball

35,289 views • 10 months ago

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

AK

718,760 views • 3 years ago

Thesis (Thesis (YC F25)) is an applied research lab accelerating AI R&D. What if every researcher, anywhere, could discover the next Transformer or invent the next AlphaFold? Thesis' mission is to make state-of-the-art AI discovery 10x faster and 10x cheaper, putting frontier research within reach of every lab. With 1 month and $10k, they've achieved state-of-the-art performance on OpenAI’s MLE-bench.

Thesis (Thesis (YC F25)) is an applied research lab accelerating AI R&D. What if every researcher, anywhere, could discover the next Transformer or invent the next AlphaFold? Thesis' mission is to make state-of-the-art AI discovery 10x faster and 10x cheaper, putting frontier research within reach of every lab. With 1 month and $10k, they've achieved state-of-the-art performance on OpenAI’s MLE-bench.

Y Combinator

16,337 views • 10 months ago

Introducing the 𝗚𝗲𝗺𝗶𝗻𝗶 𝗮𝗱𝘃𝗮𝗻𝘁𝗮𝗴𝗲 in Google Marketing Platform. Our best AI for your best ROI Experience unified inventory, accelerated performance, and ease of use. All in one place.

Introducing the 𝗚𝗲𝗺𝗶𝗻𝗶 𝗮𝗱𝘃𝗮𝗻𝘁𝗮𝗴𝗲 in Google Marketing Platform. Our best AI for your best ROI Experience unified inventory, accelerated performance, and ease of use. All in one place.

Google Marketing Platform

111,542 views • 6 months ago

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:

NVIDIA AI

12,152 views • 6 months ago

The possibilities for AI-powered protein design are endless! In this case study we show how we used BindCraft to engineer a programmable maltose biosensor from scratch, including wet lab validation at Adaptyv of course. We envision a future where every biologist can make their own bespoke protein tools to investigate environmental samples, cell behaviour or create therapeutics. AI-based protein design can enable that future if powered by rapid wet lab validation. Once the cycle from design → test → application shrinks to weeks, the frontier explodes.

The possibilities for AI-powered protein design are endless! In this case study we show how we used BindCraft to engineer a programmable maltose biosensor from scratch, including wet lab validation at Adaptyv of course. We envision a future where every biologist can make their own bespoke protein tools to investigate environmental samples, cell behaviour or create therapeutics. AI-based protein design can enable that future if powered by rapid wet lab validation. Once the cycle from design → test → application shrinks to weeks, the frontier explodes.

Adaptyv Bio

52,197 views • 1 year ago

Announcing FastVideo V1, a unified framework for accelerating video generation. FastVideo V1 offers: - A simple, consistent Python API - State of the art model performance optimizations - Optimized implementations of popular models Blog:

Announcing FastVideo V1, a unified framework for accelerating video generation. FastVideo V1 offers: - A simple, consistent Python API - State of the art model performance optimizations - Optimized implementations of popular models Blog:

Hao AI Lab

15,071 views • 1 year ago

Introducing Handshake AI—the most ambitious chapter in our story. We leverage the scale of the largest early career network to source, train, and manage domain experts who test and challenge frontier models to failure for the top AI labs.

Introducing Handshake AI—the most ambitious chapter in our story. We leverage the scale of the largest early career network to source, train, and manage domain experts who test and challenge frontier models to failure for the top AI labs.

Handshake

357,761 views • 1 year ago

Introducing our new frontier video model, Runway Gen-4.5. Previously known as Whisper Thunder (aka) David. Gen-4.5 is state-of-the-art and sets a new standard for video generation motion quality, prompt adherence and visual fidelity. Learn more below.

Introducing our new frontier video model, Runway Gen-4.5. Previously known as Whisper Thunder (aka) David. Gen-4.5 is state-of-the-art and sets a new standard for video generation motion quality, prompt adherence and visual fidelity. Learn more below.

Runway

854,925 views • 10 months ago

Introducing Saaras V4 Multi-speaker Our best-in-class speech recognition model that accurately captures overlapping conversations and multi-speaker interactions, while delivering state-of-the-art performance in English across accents.

Introducing Saaras V4 Multi-speaker Our best-in-class speech recognition model that accurately captures overlapping conversations and multi-speaker interactions, while delivering state-of-the-art performance in English across accents.

Sarvam

31,433 views • 2 months ago

High-quality experimental data fuels biological discovery. Could an AI-enabled "autonomous lab" fundamentally increase the rate at which we generate it, and accelerate our progress toward cures for disease? That's the question I sat down to explore with Jason Kelly, CEO of Ginkgo Bioworks, for a deep-dive and tour of their 52-RAC lab in Boston's Seaport District. In our conversation we covered: → Ginkgo's recent collaboration with OpenAI on cell-free protein synthesis → U.S. Department of Energy's POTUS-backed Genesis Mission to accelerate AI for science → The evolution from cloud labs to truly autonomous labs → An on-the-floor look at Ginkgo's lab, including early challenges and creative workarounds If you're curious about frontier AI models meet the lab bench, check out the latest episode of the Discovery Engines Podcast. Watch or listen: 👀 YouTube: 🎧 Spotify: 🎧 Apple:

High-quality experimental data fuels biological discovery. Could an AI-enabled "autonomous lab" fundamentally increase the rate at which we generate it, and accelerate our progress toward cures for disease? That's the question I sat down to explore with Jason Kelly, CEO of Ginkgo Bioworks, for a deep-dive and tour of their 52-RAC lab in Boston's Seaport District. In our conversation we covered: → Ginkgo's recent collaboration with OpenAI on cell-free protein synthesis → U.S. Department of Energy's POTUS-backed Genesis Mission to accelerate AI for science → The evolution from cloud labs to truly autonomous labs → An on-the-floor look at Ginkgo's lab, including early challenges and creative workarounds If you're curious about frontier AI models meet the lab bench, check out the latest episode of the Discovery Engines Podcast. Watch or listen: 👀 YouTube: 🎧 Spotify: 🎧 Apple:

Nabil Laoudji

11,508 views • 6 months ago

Our bodies’ molecules aren’t static so why do many AI models treat them that way? Without considering the physical movement of molecules, many AI tools fail to robustly capture what makes drug candidates promising. AquaGen is a generative AI framework built to close that gap: an all-atom, explicit-solvent model that runs an order of magnitude faster than traditional MD methods. We’re excited about the implications of this work on early-stage drug discovery. Technical report and blog below.

Our bodies’ molecules aren’t static so why do many AI models treat them that way? Without considering the physical movement of molecules, many AI tools fail to robustly capture what makes drug candidates promising. AquaGen is a generative AI framework built to close that gap: an all-atom, explicit-solvent model that runs an order of magnitude faster than traditional MD methods. We’re excited about the implications of this work on early-stage drug discovery. Technical report and blog below.

Valence Labs

10,379 views • 3 months ago