AI is used to compose music, suggests recipes and make investment decisions, but a company has designed a system that can edit human genes.
California-based Profluent Bio developed a system capable of creating a range of bespoke cures for disease by developing molecules that have never existed in nature.
DailyMail.com spoke to Ali Madani, CEO of Profluent Bio, who said the AI-made gene editors have been tested in human cells, which demonstrated high levels of functionality while not 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 down the results to four million sequences, allowing it to identify the gene editor the team named OpenCRISPR-1.
Experiments showed OpenCRISPR-1 performed as well as Cas proteins, but it also reduced the impact on off-target sites by 95 percent.
California-based Profluent Bio developed a system capable of creating a range of bespoke cures for disease by developing molecules that have never existed in nature.
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
‘Attempting 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 technologies in gene editing 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 it has previously relied on ‘gene editors’ found in bacteria.
The technique has altered genes that cause hereditary conditions, such as sickle cell anemia and blindness.
Hilary Eaton, Chief Business Officer at Profluent, said: ‘It’s 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 of other currently incurable diseases.’
‘Our intention with OpenCRISPR is to partner with cutting-edge research institutions and drug developers with a powerful and practical way to safely expedite the development of new CRISPR genetic therapies.’
To achieve the breakthrough, Madani’s team ‘trained’ Large Language Models on huge amounts of genetic data – in the same way that 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 massive scale evolutionary sequences and biological context,’ Madani said.
‘Our vision is to move biology from being constrained by what can be achieved in nature to being able to use AI to design new medicines precisely according to our needs.’
The company believes that 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 that the new AI-designed molecules will boost the capability of gene-editing technology even further.
‘By successfully doing so, we believe we’ve helped to take an important step forward towards a future where AI can be used to design bespoke treatments and cures for patients in need,’ said Madani.
‘Our focus is on partnering with cutting-edge research institutions and drug developers across the globe to utilize our OpenCRISPR gene editor as a tool for advancing 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 open source its system for research and commercial use.
Madani believes that by ‘open-sourcing’ (where tools or code are made freely available for other researchers to use) the AI-designed molecules, he can unleash further creativity in the field.
California-based Profluent Bio developed a system capable of creating a range of bespoke cures for disease by developing molecules that have never existed in nature
Open sourcing is commonly used in software development, less so in genetic research.
He said, ‘Our goal in open-sourcing OpenCRISPR-1 is to encourage the use of AI for ethical research and commercial use, particularly in the development of medicines leveraging CRISPR, the groundbreaking scientific discovery that is being used in the development of new treatments for countless diseases.
‘We believe by doing so, we can help accelerate the pace of discovery and innovation in the field.
As part of this effort, we’ll be gathering feedback from the gene editing community and using that input to further optimize AI-designed gene editors.’
