The use of generative AI in genetic research, so far, has been held back by the complicated nature of turning DNA sequences into their physical forms – simply stated: The machines can dream up new DNA sequences much faster than we are able to assemble (and then test) them. This is about to change:
The technique, called Sidewinder, can assemble dozens of genetic sequences simultaneously in a single test tube, producing just one incorrect junction for every 10 million assembly events – a level of precision that far surpasses conventional methods, which misfire roughly once every 10 to 30 joins. Sidewinder also draws on cheap raw materials that have until now been too difficult to use reliably.
and:
In a demonstration of how squarely Sidewinder targets this bottleneck, the team behind the technique, led by Caltech synthetic biologist Kaihang Wang, harnessed the power of Evo 2 to redesign a 12,500-letter DNA sequence of the E. coli genome in silico and then used Sidewinder to build it from scratch – with no errors. Sequences of that length can encode entire biochemical pathways, laying the groundwork for engineered microbes that manufacture drugs, biofuels, or specialty chemicals, and eventually to the assembly of vast DNA constructs approaching complete artificial genomes.
Now, just as a thought experiment, consider what this could mean for the hotly-debated issue with the capability of frontier models to be use to assist with biological warfare. With great powers comes great responsibility…
