Chris Seymour
@iiseymour.bsky.social
Software, Hardware, Machine Learning Inference.
Dorado is 1.0! 🎉 LC25 release adds v5.2 DNA/RNA models 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 - Hopper & Blackwell SUP speed ups #Nanoporeconf
Dorado v0.9.5 adds support for Nvidia Blackwell GPUs. Alongside the latest generation, we’ve given Volta & Orin a boost, v5 transformer sup >2X, LSTM hac on Hopper is boosted 20%, dorado correct and polish both receive performance updates, plus a whole bunch more; see.. github.com/nanoporetech...
Release v0.9.5 · nanoporetech/dorado
[0.9.5] (31 March 2025) This release of Dorado delivers significant performance improvements and broader hardware support: Major speed increase of the v5 SUP basecalling models on Volta (7.0) and ...
github.com
Huge performance update in today’s dorado v0.9.1 release on Ampere 8.6/8.7 & Ada Lovelace 8.9 nvidia GPUs with up to 2x increase in throughput with hac calling and 3x sup! 🚀 Plus a whole bunch of updates for dorado polish and the odd misc bug fix. github.com/nanoporetech...
🎄 New Dorado release (v0.9.0) – and it's big! 🚀 Dorado polish command (experimental) for improving draft assemblies – faster & more accurate than Medaka ⚡ Faster modified base calling models 🔧 Usability & accuracy improvements: PolyA, Barcoding, 6mA calling github.com/nanoporetech...
Release v0.9.0 · nanoporetech/dorado
[0.9.0] (16 Dec 2024) This major release of Dorado introduces several new features and enhancements. The polish command, currently experimental, is optimised for refining draft assemblies of human ...
github.com
Exciting news! The latest hifiasm release from Haoyu Cheng and Heng Li adds beta support for @nanoporetech.com simplex R10 reads. Initial results look very promising. 🚀 Check it out: github.com/chhylp123/hi...
Release Hifiasm-0.21.0-r686 · chhylp123/hifiasm
Since Hifiasm-0.20.0 (r639): New Feature: Introduced a beta module for ONT assembly using ONT simplex R10 reads. To enable this feature, add the --ont option as shown below: hifiasm -t64 --ont -o...
github.com
