My reading of this is that they asked the system to redesign the PCB that was used in the i.MX 8M reference system-on-module. It looks like they take a parts list, a PCB shape, and a rough floorplan and pass that to their tool, which spits out a PCB design.
I could actually see myself using this tool, as someone who trained as an EE and still likes to tinker with electronics. It would be fun to just assemble a parts list and a rough layout and then receive a working electronic device a few weeks later with minimal work.
Thanks for the kind words! I have not written it up but would like to. A word of warning: by trying to get into sequencing, I eventually burned through ~20k USD of student loans (still unpaid) with little to show. Nanopore sequencing also requires some specialized equipment (at least a micro centrifuge and micropipette and possibly more) which is not cheap.
Hi, believe it or not, I have actually done what the authors were attempting. I used saliva rather than blood as a source of DNA and extracted it using a Qiagen kit.
My Nanopore flow cell had nearly every pore working from the start. So I would say that is not normal. Maybe it was stored incorrectly.
Adding on: Claude also gave me the following line which was necessary to get the model weights to download from HF. This might be obvious for anyone familiar with HF but it helped me so sharing here!
I think the real story here might be the line below:
"Durham University improved by 30 places year-on-year"
Seems a bit suspicious, no? What methodology change led to this result? How can a university that was previously not as well-regarded become the #3 in the country overnight?