pytorch-tutorial VS bonito

I was going through this example of a LSTM language model on github (link).What it does in general is pretty clear to me. But I'm still struggling to understand what calling contiguous() does, which occurs several times in the code.

I tried to move straight to practicing implementing papers and trying to understand other people's codes but failed miserably. I feel like there was too much of a gap between the basic tutorial and being able to implement ideas into code....hence the question: Is there any resource/way to practice pytorch in general? I did find this and this, but I just wanted to hear what others have gone through to become better at PyTorch up to the point they can build stuff from their own ideas

There is a technology called Nanopore. I’ve never used it myself but the concept was to be able to sequence samples of nucleic acid out in the field. A quick pubmed search indicated that it can detect miRNA, but maybe with some modifications. https://nanoporetech.com Best of luck with it!

> An unpopular opinion: there are too many other logos that look like the original logo

There are also too many logos that look like the new logo. The first blue circle logos that spring to mind are Blue Circle Cement/Tarmac/Lafarge [1] and Oxford Nanopore [2].

[1]: https://en.wikipedia.org/wiki/Tarmac_(company)

[2]: https://nanoporetech.com/

Oxford Nanopore Technologies (https://nanoporetech.com/) | Front end developer | Full-time | Oxford | Remote (UK)

Oxford Nanopore Technologies is headquartered at the Oxford Science Park outside Oxford, UK, with satellite offices and commercial presence in many global locations across the US, APAC and Europe. Our DNA/RNA sequencing platform is the only technology that offers real-time analysis (for rapid insights), in fully scalable formats from pocket to population scale. Our goal is to enable the analysis of any living thing, by anyone, anywhere.

Tech stack: Electron, Stencil, React, Typescript, RxJS, GRPC

For more details, please email: [email protected]

Ok this isn't really my area but I know that there are labs/companies performing these types of electrical current disturbance measurements of membrane-type proteins for both DNA sequencing (https://nanoporetech.com/) and protein sequencing (https://www.nature.com/articles/s41587-019-0401-y).

Now nanopore sequencing is solid state and gets much longer reads. https://nanoporetech.com/ and https://en.wikipedia.org/wiki/Nanopore_sequencing

Also best of luck with the basecaller, I will say that the latest guppy versions are very good, both in terms of accuracy and speed, as they are GPU accelerated and the best I've seen in accuracy. You may also be interested in Bonito, a tool to generate your own GPU basecalling model or tweak existing models to your data. https://github.com/nanoporetech/bonito.