←
Evan Seitz16 posts
Evan Seitz avatar

Evan Seitz

@EESeitz

Quantitative biologist, currently working to advance deep learning for genomics as a Computational Postdoctoral Fellow @CSHL

◷ Joined July 2017
Peter Koo avatar
⟳ Evan Seitz retweeted
Peter Koo@pkoo562·9 Oct 2025

Which mutations rewire function of regulatory DNA? Excited to share SEAM: Systematic Explanation of Attribtuion-based Mechanisms. SEAM is an explainable AI method that dissects cis-regulatory mechanisms learned by seq2fun genomic deep learning models. Led by @EESetiz 1/N 🧵👇

Post attachment
Peter Koo avatar
⟳ Evan Seitz retweeted
Peter Koo@pkoo562·21 Jun 2024

Very proud that SQUID is now published in Nature Machine Intelligence! @NatMachIntell View only link (no subscription needed): rdcu.be/dLuZe Full link (w/ subscription): nature.com/articles/s42256-0… @EESeitz @jbkinney @TheDMMcC (Thanks to reviewers for feedback)

Excited to share new work on "Interpreting cis-regulatory mechanisms from genomic deep neural networks using surrogate models” led by @EESeitz, jointly advised by me and @jbkinney and in collab with @TheDMMcC Paper: biorxiv.org/content/10.1101/… Docs: squid-nn.readthedocs.io

Post attachment
Peter Koo avatar
⟳ Evan Seitz retweeted
Peter Koo@pkoo562·21 Mar 2024

In genomic deep learning, the trends right now are to build bigger models that consider longer sequence contexts. While predictions are more powerful, their scale makes them difficult to interpret. To address this gap, we have developed CREME. Paper: biorxiv.org/content/10.1101/… 1/N