This shows an ai generated protein

Novel Proteins Designed With Generative AI

Summary: Researchers developed an AI system called ProteinSGM, which uses generative diffusion to create entirely new therapeutic proteins.

The model learns from image representations to generate fully new proteins that appear to be biophysically real, meaning they fold into configurations that enable them to carry out specific functions within cells.

The researchers hope the system will help advance the field of generative biology, promising to speed drug development by making the design and testing of entirely new therapeutic proteins more efficient and flexible.

Key Facts:

  1. Researchers at the University of Toronto have developed an artificial intelligence system called ProteinSGM that uses generative diffusion to create proteins not found in nature.
  2. The system draws from a large set of image-like representations of existing proteins to generate entirely new therapeutic proteins at a high rate, helping to speed up drug development.
  3. The researchers used OmegaFold and experimental testing to confirm that almost all of the novel sequences fold into the desired and also novel protein structures. The next step is to further develop ProteinSGM for antibodies and other proteins with the most therapeutic potential.

Source: University of Toronto

Researchers at the University of Toronto have developed an artificial intelligence system that can create proteins not found in nature using generative diffusion, the same technology behind popular image-creation platforms such as DALL-E and Midjourney.

The system will help advance the field of generative biology, which promises to speed drug development by making the design and testing of entirely new therapeutic proteins more efficient and flexible.

“Our model learns from image representations to generate fully new proteins, at a very high rate,” says Philip M. Kim, a professor in the Donnelly Centre for Cellular and Biomolecular Research at U of T’s Temerty Faculty of Medicine.

“All our proteins appear to be biophysically real, meaning they fold into configurations that enable them to carry out specific functions within cells.” 

Today, the journal Nature Computational Science published the findings, the first of their kind in a peer-reviewed journal. Kim’s lab also published a pre-print on the model last summer through the open-access server bioRxiv, ahead of two similar pre-prints from last December, RF Diffusion by the University of Washington and Chroma by Generate Biomedicines.

Proteins are made from chains of amino acids that fold into three-dimensional shapes, which in turn dictate protein function. Those shapes evolved over billions of years and are varied and complex, but also limited in number. With a better understanding of how existing proteins fold, researchers have begun to design folding patterns not produced in nature.

But a major challenge, says Kim, has been to imagine folds that are both possible and functional.

“It’s been very hard to predict which folds will be real and work in a protein structure,” says Kim, who is also a professor in the departments of molecular genetics and computer science at U of T.

“By combining biophysics-based representations of protein structure with diffusion methods from the image generation space, we can begin to address this problem.”

The new system, which the researchers call ProteinSGM, draws from a large set of image-like representations of existing proteins that encode their structure accurately. The researchers feed these images into a generative diffusion model, which gradually adds noise until each image becomes all noise.

The model tracks how the images become noisier and then runs the process in reverse, learning how to transform random pixels into clear images that correspond to fully novel proteins.

Jin Sub (Michael) Lee, a doctoral student in the Kim lab and first author on the paper, says that optimizing the early stage of this image generation process was one of the biggest challenges in creating ProteinSGM.

“A key idea was the proper image-like representation of protein structure, such that the diffusion model can learn how to generate novel proteins accurately,” says Lee, who is from Vancouver but did his undergraduate degree in South Korea and master’s in Switzerland before choosing U of T for his doctorate.

Also difficult was validation of the proteins produced by ProteinSGM. The system generates many structures, often unlike anything found in nature. Almost all of them look real according to standard metrics, says Lee, but the researchers needed further proof.

To test their new proteins, Lee and his colleagues first turned to OmegaFold, an improved version of DeepMind’s software AlphaFold 2. Both platforms use AI to predict the structure of proteins based on amino acid sequences.

With OmegaFold, the team confirmed that almost all their novel sequences fold into the desired and also novel protein structures. They then chose a smaller number to create physically in test tubes, to confirm the structures were proteins and not just stray strings of chemical compounds.

Credit: Neuroscience News

“With matches in OmegaFold and experimental testing in the lab, we could be confident these were properly folded proteins. It was amazing to see validation of these fully new protein folds that don’t exist anywhere in nature,” Lee says.

Next steps based on this work include further development of ProteinSGM for antibodies and other proteins with the most therapeutic potential, Kim says. “This will be a very exciting area for research and entrepreneurship,” he adds. 

Lee says he would like to see generative biology move toward joint design of protein sequences and structures, including protein side-chain conformations. Most research to date has focussed on generation of backbones, the primary chemical structures that hold proteins together. 

“Side-chain configurations ultimately determine protein function, and although designing them means an exponential increase in complexity, it may be possible with proper engineering,” Lee says. “We hope to find out.”

About this AI research news

Author: Jim Oldfield
Source: University of Toronto
Contact: Jim Oldfield – University of Toronto
Image: The image is credited to Neuroscience News

Original Research: Closed access.
Score-based generative modeling for de novo protein design” by Philip M. Kim et al. Nature Computational Science


Abstract

Score-based generative modeling for de novo protein design

The generation of de novo protein structures with predefined functions and properties remains a challenging problem in protein design. Diffusion models, also known as score-based generative models (SGMs), have recently exhibited astounding empirical performance in image synthesis.

Here we use image-based representations of protein structure to develop ProteinSGM, a score-based generative model that produces realistic de novo proteins.

Through unconditional generation, we show that ProteinSGM can generate native-like protein structures, surpassing the performance of previously reported generative models. We experimentally validate some de novo designs and observe secondary structure compositions consistent with generated backbones.

Finally, we apply conditional generation to de novo protein design by formulating it as an image inpainting problem, allowing precise and modular design of protein structure.

Join our Newsletter
I agree to have my personal information transferred to AWeber for Neuroscience Newsletter ( more information )
Sign up to receive our recent neuroscience headlines and summaries sent to your email once a day, totally free.
We hate spam and only use your email to contact you about newsletters. You can cancel your subscription any time.