<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Deep Learning on Maragkakis Lab</title><link>http://maragkakislab.com/tags/deep-learning/</link><description>Recent content in Deep Learning on Maragkakis Lab</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 29 Sep 2024 00:00:00 +0000</lastBuildDate><atom:link href="http://maragkakislab.com/tags/deep-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>Deep learning and direct sequencing of labeled RNA captures transcriptome dynamics</title><link>http://maragkakislab.com/publications/2024-rnakinet/</link><pubDate>Sun, 29 Sep 2024 00:00:00 +0000</pubDate><guid>http://maragkakislab.com/publications/2024-rnakinet/</guid><description>&lt;h2 id="summary"&gt;Summary&lt;/h2&gt;
&lt;p&gt;We developed RNAkinet, a neural network that identifies newly synthesized RNA molecules labeled with 5-ethynyl uridine (5EU) using nanopore direct RNA sequencing, processing raw electrical signals without requiring basecalling or sequence alignment. RNAkinet enables simultaneous analysis of RNA metabolism alongside poly(A) tail length and RNA modifications at single-molecule resolution.&lt;/p&gt;</description></item></channel></rss>