New algorithm will accelerate the creation of artificial cells from several years to months

The new development will allow scientists not to spend years on a detailed understanding of each part of the cell and its specific

functions to manage it. Instead, with a limited set of training data, new algorithms will predict how changes in DNA will affect cell behavior and biochemistry, and then provide recommendations for the next engineering cycle, along with likely predictions to achieve the desired goal for engineers.

"Opportunities are revolutionary," said HectorGarcia Martin, a researcher with the Biological Systems and Engineering (BSE) Department of Berkeley Laboratories, who led the study. “Bioengineering is currently a very slow process. It took 150 man-years to develop the antimalarial drug, artemisinin. If you can create new cells to specifications in a couple of weeks or months instead of a few years, it will revolutionize the possibilities of bioengineering. ”

Working with a BSE Data ScientistTijana Radivojevic and an international team of researchers, the team developed and demonstrated a patent-pending algorithm - the Automatic Recommendation Tool (ART). Machine learning allows computers to make predictions after being "trained" based on a significant amount of available data.

The algorithm is adapted to the characteristics of the areasynthetic biology with its small training datasets, the need to quantify uncertainty, and recursive loops. The capabilities of this tool have been demonstrated with simulations and historical data from previous metabolic engineering projects, such as improving the production of renewable biofuels.

Read also

The Doomsday glacier turned out to be more dangerous than scientists thought. We tell the main thing

GitHub has replaced the term "master" with a neutral equivalent

Two pieces of evidence of extraterrestrial life emerged at once. One is on Venus, the other is unknown