Them: "A PhD provides you with a set of general-purpose and highly transferable skills" Me: "\vspace{-0.254em}"

Today in nature: #AlphaTensor, an AI system for discovering novel, efficient, and exact algorithms for matrix multiplication - a building block of modern computations. AlphaTensor finds faster algorithms for many matrix sizes: dpmd.ai/dm-alpha-tensor & dpmd.ai/nature-alpha-t… 1/

(1/3) Until now, AI translation has focused mainly on written languages. Universal Speech Translator (UST) is the 1st AI-powered speech-to-speech translation system for a primarily oral language, translating Hokkien, one of many primarily spoken languages. bit.ly/3CJP3ew

A lot of Machine Learning (ML) I learned during my Ph.D. was from youtube. I didn't have a guide to do this effectively and thus here it is: A complete guide to studying ML from youtube: 13 best and most recent ML courses available on YouTube. 👩‍🏫🧵⤵️

m6Anet, a neural network-based method that detects m6A modifications from direct RNA sequencing data. @jonathangoeke, @alek_thiery, Christopher Hendra, Computational Transcriptomics, A*STAR Genome Institute of Singapore (A*STAR GIS) OA paper: nature.com/articles/s4159…

Identification of m6A has been possible for some time using Oxford Nanopore direct RNA-Seq. Today we published m6Anet, achieving high accuracy single base, single molecule resolution nature.com/articles/s4159… What is m6Anet, and why this makes a big difference🧵#biodata22 Nature Methods

Our m6Anet paper is featured in this issue of Nature Methods nature.com/articles/s4159…. This work has been a long time coming for us and we are beyond excited to announce its publication #biodata22 🧵

We are happy to announce the preprint for Bambu - “Context-Aware Transcript Quantification from Long Read RNA-Seq data with Bambu” biorxiv.org/content/10.110…. Available now from BioConductor bioconductor.org/packages/bambu/ and Github github.com/GoekeLab/bambu 1/7

After 2 years of open source code development, >200 pull request and >2000 commits from 9 contributors, we are very happy to share the preprint describing Bambu, our method for analysing long read RNA-Seq biorxiv.org/content/10.110… My personal highlights:

We have a new release for m6Anet repository (v-1.1.1) where we fixed a typo with the read-level modification command and PyTorch versioning issue. Additionally, we removed warning messages from pandas to reduce clutter in your stdout! github.com/GoekeLab/m6ane…

1/9 If you are looking to map genome coordinates from one assembly version to another, we have the right tool for you on #Ensembl! Today's #tweetorial will walk you through how to do this 🥳 #bioinf #EnsemblTraining #genomics

A researcher’s guide to preclinical mouse NASH models | Nature Metabolism A good review on animal models to mimic NASH which can be closely linked to phenotypes observed in clinic.Western diet induced models fit well and it’s true from my PhD experience nature.com/articles/s4225…

this is what happens when you don’t recycle your pizza boxes

Scientists develop AI-based method to predict #RNA modifications @AstarHQ Nature Methods doi.org/grrf3f phys.org/news/2023-02-s…

Researchers from the A*STAR and NUS have developed #m6Anet, a software that trains #deepneuralnetworks with abundant direct #Nanopore #RNAsequencing data and Multiple-Instance Learning (MIL) approach, to accurately detect the presence of #m6A. rna-seqblog.com/scientists-dev…

You can report any error or suggestion related to pbs.twimg.com/card_img/16271… as an issue on github.com/GoekeLab/m6ane……If you have questions related to the manuscript, data, or any general comment or suggestion please use github.com/GoekeLab/m6ane… - Christopher Hendra

Segment Anything in High Quality Proposes HQ-SAM, equipping SAM with the ability to accurately segment any object, while maintaining SAM’s original promptable design, efficiency, and zero-shot generalizability repo: github.com/SysCV/SAM-HQ abs: arxiv.org/abs/2306.01567

Today 6 years ago, "Attention is All You Need" went on Arxiv! Happy birthday Transformer! 🎂 Fun facts: - Transformer did not invent attention, but pushed it to the extreme. The first attention paper was published 3 years prior (2014) and had an unassuming title: "Neural Machine

So excited to announce that m6anet now supports the new RNA004 chemistry from Oxford Nanopore!! github.com/GoekeLab/m6anet 1/4

With this release m6A detection is now possible with the RNA004 (development) kit from Oxford Nanopore using m6Anet. Performance looks very good + much higher throughput