New AI creates molecules not found in nature that can ALTER human genes to cure even the rarest diseases

AI is used to compose music, suggest recipes and make investment decisions, but one company has designed a system that can edit human genes.

California-based Profluent Bio has developed a system capable of creating a range of customized treatments for diseases molecules that have never existed in nature.

DailyMail.com spoke to Ali Madani, CEO of Profluent Bio, who said the AI-created gene editors have been tested in human cells, which have demonstrated a high level of functionality without editing unintended sites in the DNA.

The AI ​​was trained on a database of 5.1 million CRISPR-associated (Cas) proteins, allowing it to create potential molecules that could be used in gene editing.

The system then narrowed the results down to four million sequences, allowing it to identify the gene editor that the team called OpenCRISPR-1.

Experiments showed that OpenCRISPR-1 performed as well as Cas proteins, but also reduced the impact on off-target sites by 95 percent.

The AI ​​was trained on a database of 5.1 million CRISPR-associated (Cas) proteins, allowing it to create potential molecules for use in gene editing

“Trying to edit human DNA with an AI-designed biological system was a scientific moonshot,” Madani said.

‘The molecules do not exist in nature like previous gene editing technologies such as CRISPR.’

CRISPR is a Nobel Prize-winning technique that can be used to edit the genomes of living organisms, cutting a cell’s genes or adding new ones – but previously this technique relied on ‘gene editors’ found in bacteria.

The technique has changed genes that cause hereditary conditions such as sickle cell anemia and blindness.

Hilary Eaton, Chief Business Officer at Profluent, said: ‘It is phenomenal that the first CRISPR-based treatments for genetic diseases such as sickle cell disease are already changing the lives of patients, but there remains an urgent need to accelerate the development of this technology for thousands other currently incurable diseases.’

“Our intent with OpenCRISPR is to collaborate with cutting-edge research institutions and drug developers with a powerful and practical way to safely accelerate the development of new CRISPR genetic therapies.”

To achieve the breakthrough, Madani’s team ‘trained’ large language models on large amounts of genetic data – just as ChatGPT is ‘trained’ on text and images from the Internet.

“AI was at the heart of this achievement. We trained large language models (LLMs) on large-scale evolutionary sequences and biological context,” Madani said.

‘Our vision is to no longer let biology be limited by what can be achieved in nature, but to be able to use AI to design new medicines exactly according to our needs.’

The company believes AI can work as an “interpreter to decode the language of life.”

Clinical trials have already tested CRISPR technology to treat human genetic diseases – and Madani hopes the new AI-designed molecules will further expand the capabilities of gene editing technology.

“By doing this successfully, we believe we have helped take an important step forward toward a future where AI can be used to design customized treatments and treatments for patients in need,” Madani said.

“Our focus is on collaborating with cutting-edge research institutions and drug developers around the world to use our OpenCRISPR gene editor as a tool to advance new and promising medicines.”

Further research “in other cell lines, animals or patients” is needed to fully assess the performance of the AI-designed gene editors.

Profluent Bio aims to make its system open source for research and commercial use.

Madani believes that by ‘open-sourcing’ (where tools or code are made freely available for use by other researchers) of the AI-designed molecules, he can unleash further creativity in the field.

California-based Profluent Bio has developed a system capable of creating a range of tailor-made treatments for diseases by developing molecules that never existed in nature

Open sourcing is widely used in software development, to a lesser extent in genetic research.

He said: ‘Our goal at open source OpenCRISPR-1 is to encourage the use of AI for ethical research and commercial use, particularly in the development of medicines that use CRISPR, the breakthrough scientific discovery used in the development of new treatments. for numerous diseases.

“We believe that by doing this we can help accelerate the pace of discovery and innovation in the field.

As part of this effort, we will gather feedback from the gene editing community and use that input to further optimize AI-designed gene editors.”