Profluent, a California-based artificial intelligence (AI)-first protein design company, announced its AI model that can generate CRISPR-like proteins that do not occur in nature on Tuesday. CRISPR or Clustered Regularly Interspaced Short Palindromic Repeats is a complex containing important proteins that scientists can use for precise gene editing in organisms. The company claims the usage of AI can create a vast number of such proteins that can help in creating bespoke cures for diseases which, at present, remain incurable.
Ali Madani, the founder and CEO of Profluent announced the AI model in a series of posts on X (formerly known as Twitter). The company has also made a blog post detailing the initiative and a pre-print version of its research paper has been published on bioRxiv. Besides announcing the DNA editor-generating AI model, the company also launched OpenCRISPR-1, one of the AI-created gene editors, as an initial open-source release licencing it for both ethical research and commercial uses.
Why OpenCRISPR AI Model matters
While CRISPR is a major focus of scientists, the research is limited due to the protein Cas9, which acts as a gene editor, and its equivalent being only available in nature. As a result, scientists spend a significant amount of time discovering different types of gene editors and their impact. Profluent claims its AI model, which is powered by an in-house large language model (LLM) trained on “massive scale sequence and biological context”, can now generate millions of diverse CRISPR-like proteins that do not occur in nature. In theory, these synthetic gene editors can play a pivotal role in finding cures for diseases previously thought to be incurable.
In its blog post, the company said, “OpenCRISPR-1 gene editor maintains the prototypical architecture of a Type II Cas9 nuclease but is more than 400 mutations away from SpCas9 and nearly 200 mutations away from any other known natural CRISPR-associated protein.”
What is CRISPR
CRISPR, put simply, is a complex or system found in bacteria and some other unicellular organisms. This complex contains the Cas9 (or similar proteins like Cas12 and Cas13) proteins that have a specific ability to make precise cuts in gene strands of DNA to enable editing. It was first discovered in 1987, and ever since scientists have been researching it extensively. The technology has vast applications and has already been used to artificially create crop variants that have a higher yield, are resistant to diseases, and are drought tolerant.
It is also used to change the DNA of mosquitoes so that they cannot spread diseases like malaria. Experiments are being conducted to cure patients suffering from diseases such as sickle-cell anaemia. It is also theorised that the technology can be used to edit the DNA of the embryo to create babies who are naturally resistant to diseases and possess genes that promote higher physical and mental abilities.