📣 Looking for 3 experienced computational scientists to work on multi-agent modelling and gene networks in cancer genomics European Research Council (ERC) project Università Bocconi collab with University of Oxford #MachineLearning #omics #AI #maths #Computational #Biology 👇to apply 👇 jobmarket.unibocconi.eu/application.ph…

And that's a wrap for our SnapperGPS deployments on incubating Manx Shearwaters. Here's a sneak-peek of the data. Now onto monitoring the chick-rearing period. Thanks to everyone in the Oxford Navigation Group who made this possible!

A lot has been happening in AI over the last few weeks Here are a few highlights 1/15 🧵

What's the best cloud GPU service for hobbyists these days? I've been using lambda for personal projects (mostly messing around with LM chess engines) but would appreciate any recommendations!

I don't know how practically useful KANs will be, but I love how this paper is written. Feels more like reading a really good tutorial than an ML paper presenting new ideas.

Get a higher % of graduates to sack off McKinsey & HSBC and instead found startups and 🇬🇧 would be cooking

We love the excitement & results from the community on AlphaFold 3 and are doubling the AF Server daily job limit to 20. Happy to also share that we're working on releasing the AF3 model (incl weights) for academic use, which doesn’t depend on our research infra, within 6 months.

A primer on molecular dynamics (MD) abhishaike.com/p/a-primer-on-… this covers a lot of the absolute basics of MD in a way that is (hopefully) easy to read. at around 7.6k words, this is the longest post ive made click to see the table of contents in the replies 🧵🧵🧵

Genomic sequencing is important for understanding biological systems and human genetics. At Oxford Nanopore, we have integrated the transformer architecture into our basecalling system, significantly improving sequencing accuracy. Read more below.

Transformers now powering nanopore sequencing! New blog post contains an overview of our architecture (SwiGLU, SWA...) including an interesting up/downsampling step to improve inference compute efficiency nanoporetech.com/blog/transform…

The data for lunch session at #nanoporeconf will share the latest developments in #nanopore sequencing data analysis. Discover how you can get more from your data — from more accurate base calling to bacterial isolate & plasmid analysis. Learn more: nanoporetech.com/about/events/c…

We are now open to receive applications for entry in October 2025 Autonomous Intelligent Machines & Systems @Oxford

Major new dorado release v0.9.0!🎅🏼 This release introduces dorado polish for refining draft assemblies, faster DNA modification calling (upto 3x 🚀), improved 6mA FPR, significant barcode demux accuracy improvements, bettter Poly(A) estimations, … github.com/nanoporetech/d…

For more information on dorado polish see the docs & checkout out Rhydian Windsor ‘s talk from NCM earlier this year youtu.be/IB6DmU40NIU?si… dorado-docs.readthedocs.io/en/latest/asse…

New preprint on hifiasm (ONT)! We can now achieve near T2T human genome assembly using only ONT Simplex reads—in just half a day, with or without ultra-long sequencing. biorxiv.org/content/10.110…

Dorado is 1.0! 🎉 This London Calling release updates our DNA and RNA models to v5.2 with a new suite of mod models that are higher accuracy, lower FP rates, and significantly faster. - Introducing dorado variant 👀 - HAC error rate is down over 25%. - New 2’Ome mod models