A study of the Genomic Regulation Center (CRG), in Barcelona, describes for the first time an artificial intelligence (AI) that designs synthetic molecules capable of controlling gene expression in healthy mammalian cells.
This study, published on Thursday in Cell magazine, reveals a new strategy to activate or disable genes in cell types with great precision and, according to its authors, it is the first case of generative biology to regulate the genome of healthy mammal cells.
A team from the Genomic Regulation Center (CRG) created an AI tool that designs DNA regulatory sequences never seen in nature.
As indicated by the CRG researchers, the model of AI that creates synthetic DNA fragments with personalized criteria such as, for example, with instructions such as: “activates this gene in the stem cells that will become red blood cells, but not in platelets, can be asked.
Next, the model predicts which combination of letters of DNA (A, T, C, G) are necessary for the desired gene expression patterns in specific types of cells.
Thus, researchers can use this information to chemically synthesize DNA fragments of approximately 250 letters and add them to a virus so that it delivers it inside the cells.
As proof of concept, the authors of the study asked the AI to design synthetic fragments that activate a gene that encode a fluorescent protein in some cells, but to leave the patterns of generated gene expression in other types.
Then they created the fragments from scratch and inserted them into mouse blood cells, where the synthetic DNA merged with the genome in random places and the experiment worked exactly as it had predicted.
Dr. Robert Frömel, the first author of the study that carried out the work at the Genomic Regulation Center (CRG), points out that “the potential applications are enormous” since “it is like writing software, but for biology.”
We recommend you: Why are AI and skills to save the world?
The study could help develop new gene therapies that increase or reduce the activity of genes in cell types or tissues where necessary.
It also paves the way to new strategies to adjust a patient’s genes and make treatments more effective and with less side effects.
To date, advances in this field served mostly for protein design, and helped create completely new enzymes and antibodies.
However, many human diseases derive from a defective gene expression that is specific to the cell type, so it is possible that there is never the perfect protein for a potential drug.
Potentiators activate or deactivate genes
The gene expression is controlled by regulatory elements such as potentiating, small DNA fragments that activate or deactivate genes.
To correct the defective gene expression, the researchers seek potentiars who already exist naturally in the genome and that can adjust to their needs, and this is limited to the sequences that evolution has produced.
The AI can help design ultraselective potentiars that nature has not yet invented, explain the authors of the study, and being made made may have exactly the required power/off patterns required in specific types of cells.
Decipher the language of the enhancers
However, the development of AI models requires a large amount of high quality data, which have historically scarce in the case of potentiators.
The authors of the study created huge volumes of biological data to build their AI model by carrying out thousands of experiments with laboratory models, and thus being able to study both potentiars and transcription factors, proteins that also intervene in the control of gene expression.
For five years the team designed more than 64,000 synthetic enhancers, each meticulously built to prove its interaction with the union sites for 38 different transcription factors.
This means having created “the largest library of synthetic potentiators ever built in blood cells to date,” says the study authors.
Once inserted in the cells, the equipment measured the activity of each synthetic enhancer in seven stages of the development of blood cells, and discovered that many potentiars activate genes in a cell type, but repress the activity in another.
With EFE information
Do you like to inform yourself for Google News? Follow our showcase to have the best stories
