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.

We have trained ESM3 and we're excited to introduce EvolutionaryScale. ESM3 is a generative language model for programming biology. In experiments, we found ESM3 can simulate 500M years of evolution to generate new fluorescent proteins. Read more:

Alex Rives

14,577 subscribers

1,536,623 views • 2 years ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Alex Rives2 years ago

We prompted ESM3 to generate fluorescent proteins with a chain of thought. In the first plate, shown below, we were intrigued to find B8. While very dim, 50x dimmer than natural GFPs, it was far from any known GFPs -- 43% of its sequence differs from the closest natural protein. Continuing the chain of thought from B8 on the second plate below, ESM3 found C10 which is similarly bright to natural fluorescent proteins.

Garry P. Nolan2 years ago

Extraordinary! Can it generate interaction partners of a given protein? Could you design with this a new "general" interaction partner framework (like a new class of small programmable binding proteins that would replace (too expensive) antibodies and which would be easy to produce in bacteria?

Brian Armstrong2 years ago

Congrats!

clem 🤗2 years ago

Very cool and welcome to the @Lux_Capital fam. Let us know if we can help in any way on the @huggingface side (we're crazy excited about open/collaborative biology)!

Derya Unutmaz, MD2 years ago

Amazing! I will read the paper now. If what you claim is true, this would be the holy grail of programming biological systems! 😲 👏

Andrew White 🐦‍⬛2 years ago

Interesting choice on the geometric attention - no equivariant layers. Just using frames and alignment based on heavy backbone atoms (?) Seems like scaling would be difficult but large structures are shown in the preprint. Congrats - love the compression results!!

Atheno2 years ago

Literally the nicest footer I’ve ever seen

Laurens van der Maaten2 years ago

Really cool, congratulations team!!

Christian von Uffel2 years ago

The best use cases I can imagine for ESM3 are finding proteins that can help people metabolize heavy metals and microplastics.

Jadechip2 years ago

Hmm so proteins, sequence, structure are tokenized and ingested by geometric attention blocks? Interesting…

Related Videos

In two new papers we have found that the ESM2 language model generalizes beyond natural proteins, and enables programmable generation of complex and modular protein structures.

In two new papers we have found that the ESM2 language model generalizes beyond natural proteins, and enables programmable generation of complex and modular protein structures.

Alex Rives

202,817 views • 3 years ago

We NOETIK built a new foundation model for spatial biology: OCTO-VirtualCell. This model is prompted to simulate single cell gene expression in "virtual cells," which are placed within real, intact patient tissue. Read about & explore these simulations below:

We NOETIK built a new foundation model for spatial biology: OCTO-VirtualCell. This model is prompted to simulate single cell gene expression in "virtual cells," which are placed within real, intact patient tissue. Read about & explore these simulations below:

Daniel Bear

39,732 views • 1 year ago

Proteins are the machinery of life. Scientists have cataloged billions of protein sequences—but their biology is still mostly unknown. Today we're releasing a world model of protein biology: a scientific engine for prediction, design, and discovery that consists of ESMFold2, ESMC, and ESM Atlas. Together, they're helping to open up a new way for researchers to design proteins and speed up scientific discovery. Our mission is to cure or prevent disease. To do that, we need to accelerate science. That's why we're releasing all three openly.

Proteins are the machinery of life. Scientists have cataloged billions of protein sequences—but their biology is still mostly unknown. Today we're releasing a world model of protein biology: a scientific engine for prediction, design, and discovery that consists of ESMFold2, ESMC, and ESM Atlas. Together, they're helping to open up a new way for researchers to design proteins and speed up scientific discovery. Our mission is to cure or prevent disease. To do that, we need to accelerate science. That's why we're releasing all three openly.

biohub

78,610 views • 1 month ago

Automating the lab bench is the best thing we can do for AI in biology. Most experiments are still run by hand. Every biologist's handiwork is unique and every lab is a little different. So, biology faces widespread reproducibility issues. But, AI will demand more reproducible data than we can produce, and generate more ideas than we can test. Experiments must be communicated and executed in a standardized way to generate reproducible data. So, Tetsuwan is building a lab where users specify experiments in an exact syntax. These experiments are executed by an automated platform to generate transparent, reproducible output. The user never needs physical access to a lab. This is a biology lab you can use like a computer. Our platform, built and tested with pilot labs over the past two years, lets users configure automated workflows rapidly & precisely. Later this year, we will bring our first services online, focusing on functional screens for protein design. Alex and I met at Caltech, where she was one year my senior. We're building this company because we were little kids who wanted to be biologists that grew up into adults who resented the lab bench. We want biology to be about asking questions, not the painful and frustrating manual process of asking them. For those looking to receive updates on our pilot services, looking for a meaningful job, or just to learn more about our work, see the links in the comments!

Automating the lab bench is the best thing we can do for AI in biology. Most experiments are still run by hand. Every biologist's handiwork is unique and every lab is a little different. So, biology faces widespread reproducibility issues. But, AI will demand more reproducible data than we can produce, and generate more ideas than we can test. Experiments must be communicated and executed in a standardized way to generate reproducible data. So, Tetsuwan is building a lab where users specify experiments in an exact syntax. These experiments are executed by an automated platform to generate transparent, reproducible output. The user never needs physical access to a lab. This is a biology lab you can use like a computer. Our platform, built and tested with pilot labs over the past two years, lets users configure automated workflows rapidly & precisely. Later this year, we will bring our first services online, focusing on functional screens for protein design. Alex and I met at Caltech, where she was one year my senior. We're building this company because we were little kids who wanted to be biologists that grew up into adults who resented the lab bench. We want biology to be about asking questions, not the painful and frustrating manual process of asking them. For those looking to receive updates on our pilot services, looking for a meaningful job, or just to learn more about our work, see the links in the comments!

Cristian Ponce

836,946 views • 15 days ago

Today, we couldn't be more excited to premiere Jen [ALPHA]. 🎵 Our ethically-trained generative AI music platform introduces a new standard for copyright compliance in text-to-music generation. Now, you can make music with your mind on

Today, we couldn't be more excited to premiere Jen [ALPHA]. 🎵 Our ethically-trained generative AI music platform introduces a new standard for copyright compliance in text-to-music generation. Now, you can make music with your mind on

Jen

120,831 views • 2 years ago

Let's enter a new era for scheduling wetting agent applications! After years of research, we have created a new way to predict wetting agent performance. The model for Simplot Turf & Horticulture's CounterAct Firm is now in GreenKeeper's Program Builder. Read More:

Let's enter a new era for scheduling wetting agent applications! After years of research, we have created a new way to predict wetting agent performance. The model for Simplot Turf & Horticulture's CounterAct Firm is now in GreenKeeper's Program Builder. Read More:

Bill Kreuser, PhD

12,574 views • 2 years ago

🖼️🎞️🔊📄Excited to introduce Composable Diffusion (CoDi), a new generative-AI foundation model that can take any combo of input modalities & generate any combo of output modalities (text, audio, image, video)! Ziyi Yang Chenguang Zhu Mohit Bansal 🧵👇 #CoDi

🖼️🎞️🔊📄Excited to introduce Composable Diffusion (CoDi), a new generative-AI foundation model that can take any combo of input modalities & generate any combo of output modalities (text, audio, image, video)! Ziyi Yang Chenguang Zhu Mohit Bansal 🧵👇 #CoDi

Zineng Tang

105,269 views • 3 years ago

We are proud of what we have achieved together with our members in our first one hundred years, and we're excited for what's to come – #FocusedForwardTogether. #ACR2023

We are proud of what we have achieved together with our members in our first one hundred years, and we're excited for what's to come – #FocusedForwardTogether. #ACR2023

American College of Radiology

26,043 views • 3 years ago

What seemed like an intractable problem is now possible: To design proteins with a specified nonlinear mechanical response, capturing complex folding and unfolding mechanisms in singe and few-shot computations. We present ForceGen, an end-to-end algorithm for de novo protein generation based on nonlinear mechanical unfolding responses. Rooted in the physics of protein mechanics, this generative strategy provides a powerful way to design new proteins rapidly, including exquisite and rapid predictions about their dynamical behavior. Proteins, like any other mechanical object, respond to forces in peculiar ways. Think of the different response you'd get from pulling on a steel cable versus pulling on a rubber band, or the difference between honey and glass. Now, we can design proteins with a set of desirable mechanical characteristics, with applications from health to sustainable plastics. The key to solving this problem was to integrate a protein language model with denoising diffusion methods, and using accurate atomistic-level physical simulation data to endow the model a first-principles understanding. ForceGen can solve both forward and inverse tasks: In the forward task, we can predict how stable a protein is, how it will unfold and what the forces involved are, all given just the sequence of amino acids. In the inverse task, we can design new proteins that meet complex nonlinear mechanical signature targets. Read the paper, led by LAMM@MIT postdoc Bo Ni, published in Science Advances: Why do we care about the mechanics of proteins? The mechanics of proteins are critical elements of many living systems - as evidenced in many studies of mechanobiology. Through evolution, nature has presented a set of remarkable protein materials with unique mechanical functions like elastins, silks, keratins or collagens that play crucial roles in biology. However, going beyond natural designs to discover proteins that meet specified mechanical properties remains challenging. So far, the only way to do this was to use existing evolutionary concepts or to manually alter proteins. With our new generative model we can directly design proteins to meet complex nonlinear mechanical property-design objectives. ForceGen leverages deep knowledge on protein sequences from a pretrained protein language model and maps mechanical unfolding responses to create proteins. Via full-atom molecular simulations for direct validation from physical and chemical principles, we demonstrate that the designed proteins are de novo, and fulfill the targeted mechanical properties, including unfolding energy and mechanical strength, and a detailed unfolding force-separation curves. ForceGen offers rapid pathways to explore the enormous mechanobiological protein sequence space unconstrained by biological synthesis, to enable the discovery of new protein materials with superior mechanical properties. B. Ni, D.L. Kaplan, M.J. Buehler, ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a language diffusion model. Sci. Adv. 10, eadl4000 (2024). DOI: 10.1126/sciadv.adl4000 Codes and model weights available Hugging Face: David Kaplan

What seemed like an intractable problem is now possible: To design proteins with a specified nonlinear mechanical response, capturing complex folding and unfolding mechanisms in singe and few-shot computations. We present ForceGen, an end-to-end algorithm for de novo protein generation based on nonlinear mechanical unfolding responses. Rooted in the physics of protein mechanics, this generative strategy provides a powerful way to design new proteins rapidly, including exquisite and rapid predictions about their dynamical behavior. Proteins, like any other mechanical object, respond to forces in peculiar ways. Think of the different response you'd get from pulling on a steel cable versus pulling on a rubber band, or the difference between honey and glass. Now, we can design proteins with a set of desirable mechanical characteristics, with applications from health to sustainable plastics. The key to solving this problem was to integrate a protein language model with denoising diffusion methods, and using accurate atomistic-level physical simulation data to endow the model a first-principles understanding. ForceGen can solve both forward and inverse tasks: In the forward task, we can predict how stable a protein is, how it will unfold and what the forces involved are, all given just the sequence of amino acids. In the inverse task, we can design new proteins that meet complex nonlinear mechanical signature targets. Read the paper, led by LAMM@MIT postdoc Bo Ni, published in Science Advances: Why do we care about the mechanics of proteins? The mechanics of proteins are critical elements of many living systems - as evidenced in many studies of mechanobiology. Through evolution, nature has presented a set of remarkable protein materials with unique mechanical functions like elastins, silks, keratins or collagens that play crucial roles in biology. However, going beyond natural designs to discover proteins that meet specified mechanical properties remains challenging. So far, the only way to do this was to use existing evolutionary concepts or to manually alter proteins. With our new generative model we can directly design proteins to meet complex nonlinear mechanical property-design objectives. ForceGen leverages deep knowledge on protein sequences from a pretrained protein language model and maps mechanical unfolding responses to create proteins. Via full-atom molecular simulations for direct validation from physical and chemical principles, we demonstrate that the designed proteins are de novo, and fulfill the targeted mechanical properties, including unfolding energy and mechanical strength, and a detailed unfolding force-separation curves. ForceGen offers rapid pathways to explore the enormous mechanobiological protein sequence space unconstrained by biological synthesis, to enable the discovery of new protein materials with superior mechanical properties. B. Ni, D.L. Kaplan, M.J. Buehler, ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a language diffusion model. Sci. Adv. 10, eadl4000 (2024). DOI: 10.1126/sciadv.adl4000 Codes and model weights available Hugging Face: David Kaplan

Markus J. Buehler

47,242 views • 2 years ago

Today, Generative AI takes its next big step forward. Introducing Gen-1: a new AI model that uses language and images to generate new videos out of existing ones. Sign up for early research access:

Today, Generative AI takes its next big step forward. Introducing Gen-1: a new AI model that uses language and images to generate new videos out of existing ones. Sign up for early research access:

Runway

2,480,438 views • 3 years ago

We found $HBAR at 3 cents. Now it’s 30 cents. Clean 10X. Movement is one of the tokens building using Libra’s programming language called MOVE. Meghan and I are excited to announce we have invested & became paid partners with Movement - $MOVE Watch the video to see why 👇🏼

We found $HBAR at 3 cents. Now it’s 30 cents. Clean 10X. Movement is one of the tokens building using Libra’s programming language called MOVE. Meghan and I are excited to announce we have invested & became paid partners with Movement - $MOVE Watch the video to see why 👇🏼

MASON VERSLUIS

25,826 views • 1 year ago

Today, we are excited to introduce the new Overwatch Esports program and the Overwatch Champions Series! 🔗 Read our Blog

Today, we are excited to introduce the new Overwatch Esports program and the Overwatch Champions Series! 🔗 Read our Blog

Overwatch Esports

4,084,194 views • 2 years ago

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

Agrim Gupta

431,155 views • 2 years ago

Should we design a new programming language for LLMs, that LLMs can use more efficiently? Chris Lattner, the creator of Swift and Mojo doesn't think so, and here's why: (cont'd)

Should we design a new programming language for LLMs, that LLMs can use more efficiently? Chris Lattner, the creator of Swift and Mojo doesn't think so, and here's why: (cont'd)

Gergely Orosz

15,416 views • 8 months ago

Unstoppable.CLAY We're excited to announce that we have partnered with Unstoppable Domains to introduce .CLAY domains! 🧵👇

Unstoppable.CLAY We're excited to announce that we have partnered with Unstoppable Domains to introduce .CLAY domains! 🧵👇

Clay Nation

30,318 views • 2 years ago

Meet the new Template Library in ComfyUI. We now have workflows designed for creative ideas and real tasks, not just model experiments. There is so much you can do in ComfyUI, and we want to showcase what's possible gradually. Build faster and stay in control.

Meet the new Template Library in ComfyUI. We now have workflows designed for creative ideas and real tasks, not just model experiments. There is so much you can do in ComfyUI, and we want to showcase what's possible gradually. Build faster and stay in control.

ComfyUI

14,881 views • 6 months ago

Crazy we can learn to track the entire AMASS dataset in 24h. For MaskedMimic, 1.5 years ago, it took us 2 weeks to train the tracker and another MONTH(!!!) to train the generative model. Now it takes 24h for the tracker and another 24h for the generative model 🤯

Crazy we can learn to track the entire AMASS dataset in 24h. For MaskedMimic, 1.5 years ago, it took us 2 weeks to train the tracker and another MONTH(!!!) to train the generative model. Now it takes 24h for the tracker and another 24h for the generative model 🤯

Chen Tessler

29,220 views • 6 months ago

'This is a symptom of the fact that we have more people in our schools whose English is not their first language.' Fred Kelly discusses new figures revealing that the cost of teaching English as a second language has hit £500m.

'This is a symptom of the fact that we have more people in our schools whose English is not their first language.' Fred Kelly discusses new figures revealing that the cost of teaching English as a second language has hit £500m.

GB News

10,988 views • 6 months ago

1/n: We are excited to share that our paper on Chroma, a general purpose diffusion model for proteins, is out today in nature! A couple of my favorite highlights in the 🧵below 👇

1/n: We are excited to share that our paper on Chroma, a general purpose diffusion model for proteins, is out today in nature! A couple of my favorite highlights in the 🧵below 👇

Andrew Beam

362,073 views • 2 years ago