{"id":21318,"date":"2022-12-06T14:00:17","date_gmt":"2022-12-06T14:00:17","guid":{"rendered":"https:\/\/mailinvest.blog\/index.php\/2022\/12\/06\/ai-helps-biotech-labs-generate-the-building-blocks-for-new-drugs\/"},"modified":"2022-12-06T14:00:17","modified_gmt":"2022-12-06T14:00:17","slug":"ai-helps-biotech-labs-generate-the-building-blocks-for-new-drugs","status":"publish","type":"post","link":"https:\/\/mailinvest.blog\/index.php\/2022\/12\/06\/ai-helps-biotech-labs-generate-the-building-blocks-for-new-drugs\/","title":{"rendered":"AI Helps Biotech Labs Generate the Building Blocks for New Drugs"},"content":{"rendered":"

<\/a>\n<\/p>\n

\n
This site may earn affiliate commissions from the links on this page. Terms of use<\/a>.<\/div>\n

<\/p>\n

\n
\n\"\" <\/div>\n<\/div>\n

Myotis daubentonii. (Credit: Generate Biomedicines)<\/small><\/center>Proteins are an essential part of life. Not only do they function as the \u201cbuilding blocks\u201d for living organisms, but they also perform nearly every cellular task, from waste management to tissue repair. It tracks, then, that pharmaceuticals often contain or \u201ctarget\u201d proteins in an attempt to change or eliminate symptoms or disease within the body. There\u2019s just one little problem: The only proteins we can use to create drugs are the ones we know.<\/p>\n

But what if we could add new proteins to the resource pile? Two biotech labs have begun using artificial intelligence (AI) to generate novel proteins with the goal of incorporating them into medicine. Chroma, a program by Boston-based Generate Biomedicines, and RoseTTAFold Diffusion, a program out of the University of Washington\u2019s Baker Lab, are often compared with trendy AI art generators thanks to their ability to create new concepts seemingly out of thin air. In fact, Chroma has even been referred to as \u201cthe DALL-E 2 of biology.\u201d<\/p>\n

AI protein generators, a type of denoising diffusion probabilistic model (DDPM), are trained to pull samples from complex datasets. They then use those samples\u2014plus added noise\u2014to construct a product that matches a given prompt. Although art generators<\/a> are the best-known DDPMs, AI isn\u2019t only good for producing images on demand; they\u2019ve also been found to be an ideal method of generating diverse protein models. In a preprint<\/a> on bioRxiv, Baker Labs scientists describe how RoseTTAFold can devise protein structures with virtually any desired size, shape, or function, as well as with any required constraints.<\/p>\n

\"\"<\/p>\n

A protein generated by RoseTTAFold (left) with its lab recreation (right). (Credit: Baker Lab)<\/p>\n<\/div>\n

Chroma works similarly. Generate Biomedicine\u2019s program pulls from what it calls the Protein Data Bank, which houses 3D protein and protein complex structures as well as amino acid sequences. Using the patterns from this data, Chroma<\/a> can create new proteins within size, symmetry, and function constraints. Seemingly capable of heavier lifts than its competitor, Chroma uses a single commodity GPU to generate large proteins and protein complexes in just a few minutes.<\/p>\n

Once RoseTTAFold or Chroma generates a protein, scientists can bring that protein to life in the lab. Baker Lab says it has already synthesized hundreds of RoseTTAFold\u2019s creations, many of which have the potential to be \u201cuseful as medications, vaccines, or even new nanomaterials.\u201d Some of Baker Lab\u2019s proteins even attach to essential hormones better than existing protein-based drugs, offering hope that AI-generated proteins might someday enable the creation of more effective pharmaceuticals.<\/p>\n

Now Read:<\/p>\n

<\/span>\n<\/div>\n