We're an AI platform for protein engineering (customers include Novo Nordisk, J&J, Grifols). We run our own wet lab in Amsterdam to generate training data for our ML models and to build the automation playbook we share openly with the field.
We're hiring a software engineer to work embedded with our bioengineering team. You'd build things like: computer vision pipelines for colony picking, interfaces for lab automation workcells, integrations between lab instruments and Benchling. Python, APIs, databases, some frontend.
No PhD or biotech background needed. You'll pick up the biology. We care about solid engineering skills and curiosity about working at the intersection of software and hardware.
My point is not about having the cheapest solution. I just don't trust anyone else with my genomic information, even if they say it's anonymous. (I'm a biotech engineer, from Europe; maybe that explains my reservation ;-))
At some point, I would love to setup something like this but then completely local and open-source. This could e.g. include a sequencing kit (Nanopore MinION sequencer (<$ 1,000) plus necessary consumables), protocols, and in silico workflows for basecalling, SNP calling, and interpretation.
I can recommend checking out https://openepaperlink.de/. It's a project to repurpose e-ink electronic shelf labels (in various sizes, ranging from 1.54" to 7.4"). I have been playing around with it the last few weeks and it's a lot of fun! The community around this is very active on Discord.
Yeah, good point - don't know. When I tried I actually did get a (personal?) email saying that it didn't match closely enough. After uploading another sample (based on a different text) it went through.
I like your idea of just training on the consent text! That wasn't the case when I tried it as you needed around 3h (optimally) of training data.
There are indeed a few practical applications. Next to Berkely lights, there is e.g. the LabChip from PerkinElmer that separates DNA and proteins. I had hoped that there would be many more examples by now. Most presentations that I see about microfluids still go in a lot of detail on how difficult it is to make. This hasn't really changed over the last decade, which signals to me we still need quite some innovation to make this mainstream.
If you want to play around with digital microfluids at home, check out the OpenDrop from gaudi.ch (http://www.gaudi.ch/OpenDrop/). I haven't played around with it yet, as I haven't found a practical use of this.
We're an AI platform for protein engineering (customers include Novo Nordisk, J&J, Grifols). We run our own wet lab in Amsterdam to generate training data for our ML models and to build the automation playbook we share openly with the field. We're hiring a software engineer to work embedded with our bioengineering team. You'd build things like: computer vision pipelines for colony picking, interfaces for lab automation workcells, integrations between lab instruments and Benchling. Python, APIs, databases, some frontend.
No PhD or biotech background needed. You'll pick up the biology. We care about solid engineering skills and curiosity about working at the intersection of software and hardware.
Apply: https://jobs.ashbyhq.com/cradlebio/7a4f7d2d-714e-4c01-84bb-9...