Mike Vella

Mike Vella

@vellamike.bsky.social

Head of Machine Learning at Oxford Nanopore, driving fast algorithms and research to analyze DNA/RNA/Proteins.

300 Followers 47 Following 42 Posts Joined Nov 2023
6 months ago
Post image

Yesterday in Malta the season for Dorado (Lampuki in Maltese) fishing opened, which is fantastic luck for me as I can enjoy a delicious dinner! My favourite basecaller and favourite fish share the same name.

3 0 0 0
8 months ago
Preview
Chromatin accessibility data and tool release Functional epigenomics uses high-throughput sequencing data to study how epigenetic modifications…

In this blog post, we show how chromatin accessibility can be profiled with minimal processing using nanopore sequencing – preserving native structure and capturing rich signal.
Read it here: epi2me.nanoporetech.com/chromatin-ac...

6 1 0 1
9 months ago
Post image

PolyA tail lengths can be accurately estimated using Nanopore dRNA

4 1 1 0
9 months ago
Post image

We have developed workflows for Plasmid precursor quality control

2 0 0 0
9 months ago
Post image

Oxford Nanopore simplifies RNA QC in GMP

2 1 0 0
9 months ago
Post image

GMP QC is laborious and complex

1 0 0 0
9 months ago
Post image

mRNA shows huge promise in personalised cancer vaccines

2 0 0 0
9 months ago
Post image

Next up - Chris Alder discusses QC workflows in biopharma

0 0 0 0
9 months ago
Post image

New for 2025 in EPI2ME - Teloseq, trio and pharmacogenomics workflows

2 0 0 0
9 months ago
Post image

Single cell workflows now adds the ability to detect gene fusions

1 0 0 0
9 months ago
Post image

Taxonomic classification

0 0 0 0
9 months ago
Post image

EPI2ME workflows are next flow based you can upload your own

0 0 0 0
9 months ago
Post image

2ME format allows users to share workflows offline - code available on GitHub

0 0 0 0
9 months ago
Post image

EPI2ME free to download and runs on Windows, Mac and Linux

0 0 0 0
9 months ago
Post image

Sarah Grifftihs next up with updates on EIPI2ME

0 0 0 0
9 months ago
Post image

We observe SOTA results in INDEL F1 scores for GIAB benchmarks, particularly big improvements in long INDELs

1 0 0 0
9 months ago
Post image

Dorado variant is a completely new architecture - not a port of an existing variant caller

2 0 0 0
9 months ago
Post image

Dorado v1.0.0 includes a preview release of our very own variant caller

1 0 0 0
9 months ago
Post image

Dorado polish goes hand in hand with hifiasm- >2Q improvement to assemblies

2 0 0 0
9 months ago
Post image

Dorado polish uses much more information than before, leading to higher quality assembly polishing.

2 1 0 0
9 months ago
Post image

LSK-only Nanopore reads able to produce 23 gapless chromosomes , 10 scaffolded, and N50>130Mb

3 2 0 0
9 months ago
Post image

Huge strides have been made in assembly. Nanopore-only T2T assembly is now feasible and will soon be routine.

3 1 0 0
9 months ago
Post image

Many ways of answering the question “what is the genotype of my sample?”

1 0 0 0
9 months ago
Post image

Up next - @rwinds.bsky.social discusses the latest in variant calling and assembly

0 0 0 0
9 months ago
Post image

Base calling obeys scaling laws in deep learning - a Q28 base caller using standard chemistry is now available on demand.

2 1 1 0
9 months ago
Post image

Base calling accuracy is compute-limited. As GPUs get faster so does accuracy!

3 1 0 0
9 months ago
Post image

Dorado v1.0.0 introduces dramatic improvement to modified base calling speed

1 2 0 0
9 months ago
Post image

Big improvements in modification calling accuracy - 6mA increases from Q16 to Q24

2 2 0 0
9 months ago
Post image

New HAC models are 1.4Q more accurate - a 25% error reduction

2 2 0 1
9 months ago
Post image

Dorado is no longer “just” a base caller - now includes alignment, mod base calling, alignment, and now even variant calling

1 0 0 0