Toggle light / dark theme

Biomedical engineers at Duke University have devised a machine learning approach to modeling the interactions between complex variables in engineered bacteria that would otherwise be too cumbersome to predict. Their algorithms are generalizable to many kinds of biological systems.

In the new study, the researchers trained a neural network to predict the circular patterns that would be created by a biological circuit embedded into a bacterial culture. The system worked 30,000 times faster than the existing computational .

To further improve accuracy, the team devised a method for retraining the machine learning model multiple times to compare their answers. Then they used it to solve a second biological system that is computationally demanding in a different way, showing the algorithm can work for disparate challenges.

Despite this economic pressure, rural America remains one of our nation’s most fertile regions, and recent advances in biotechnology are making it easier than ever to sustainably grow new kinds of valuable goods, from biopharmaceuticals to biomaterials. With the right strategic investments, rural America could see a biotech “bloom.”

I propose a Bio-Belt stretching through middle America to bring new skills and high-paying jobs to communities that desperately need them. This initiative would bolster investment in biotechnology training, education, infrastructure and entrepreneurship in rural areas in order to develop new, sustainable sources of income.

The Bio-Belt is about much more than biofuel. Fermentation is an increasingly powerful force for converting sugar and other forms of biomass into value-added goods—all through the rational design of cells that can be sustainably grown wherever land is abundant.

Thinking of #Upskilling? Check this out: If you want to learn machine learning and artificial intelligence, start here:

Two years ago, I started learning machine learning online on my own. I shared my journey through YouTube and my blog. I had no idea what I was doing. I’d never coded before but decided I wanted to learn machine learning.


“I want to learn machine learning and artificial intelligence, where do I start?” Here.

The fruit flies in Noah Whiteman’s lab may be hazardous to your health.

Whiteman and his University of California, Berkeley, colleagues have turned perfectly palatable —palatable, at least, to frogs and birds—into potentially poisonous prey that may cause anything that eats them to puke. In large enough quantities, the flies likely would make a human puke, too, much like the emetic effect of ipecac syrup.

That’s because the team genetically engineered the flies, using CRISPR-Cas9 gene editing, to be able to eat milkweed without dying and to sequester its toxins, just as America’s most beloved butterfly, the , does to deter predators.