Lightnews — Scholar-powered news

Peter Koo @pkoo562.bsky.social · 1d

This was led by @EESeitz
, a former postdoc who was jointly advised by me and Justin Kinney at CSHL, and also in collaboration with David McCandlish @TheDMMcC

It's a beautiful followup to SQUID, our surrogate modeling approach to interpret genomic DNNs!

www.nature.com/articles/s42...

Interpreting cis-regulatory mechanisms from genomic deep neural networks using surrogate models - Nature Machine Intelligence

The intersection of genomics and deep learning shows promise for real impact on healthcare and biological research, but the lack of interpretability in terms of biological mechanisms is limiting utility and further development. As a potential solution, Koo et al. present SQUID, an interpretability framework built using domain-specific genomic surrogate models.

www.nature.com

Peter Koo @pkoo562.bsky.social · 1d

Check out the paper to find out more!

Code: github.com/evanseitz/se...
Paper: www.biorxiv.org/content/10.1...

Uncovering the Mechanistic Landscape of Regulatory DNA with Deep Learning

The regulatory genome encodes the logic that governs gene expression, enabling cells to respond to developmental, environmental, and evolutionary cues. This logic arises from complex cis-regulatory me...

www.biorxiv.org

1

Peter Koo @pkoo562.bsky.social · 1d

We find regulatory DNA is readily reprogrammable with a few key mutations! We observed similar phenomenon across all genomic DNNs we tested! 12/N

1

Peter Koo @pkoo562.bsky.social · 1d

SEAM is a powerful tool that helps to: 1) explore the high evolvability landscape of regulatory sequences; 2) identifies mutations that drive mechanistic changes; and 3) dissect motif syntax and context dependencies. 11/N

1

Peter Koo @pkoo562.bsky.social · 1d

And we tested the backgrounds across different ChromBPNet models independently trained on DNase-seq and ATAC-seq and we observe similar backgrounds! This suggests these mutagenesis-robust patterns are important context that reflects properties of the local sequence space. 10/N

1

Peter Koo @pkoo562.bsky.social · 1d

While previous analyses focused on differences in attr maps across clusters, a surprising observation was that there were also shared patterns. We disentangled the attribution signals that are sensitive versus robust to mutagenesis – we call them foreground and background. 9/N

1

Peter Koo @pkoo562.bsky.social · 1d

This analysis flagged 2 key mutations at positions 170 & 174 that created a new CAAT box. To test necessity & sufficiency, we mutated each individually and together, then examined attr maps+ predictions
- single mutations -> no change
- double mutation -> CAAT box + new Inr

8/N

1

Peter Koo @pkoo562.bsky.social · 1d

Applying SEAM to CLIPNET, which predicts transcriptional activity measured via PRO-cap, we find that many SNVs lead to new clusters in the PIK3R3 promoter. A few specific mutations can quantitatively tune gene expression and SEAM can find them! 7/N

1 1

Peter Koo @pkoo562.bsky.social · 1d

Now, if we plot the percent mismatch of the nucleotides with respect to WT for each cluster, you can see yellow bars that reflect all sequences in the cluster share the same single nucleotide mutation. This analysis pinpoints the exact mutation that led to the new mechanism! 6/N

1

Peter Koo @pkoo562.bsky.social · 1d

Low entropy reflects all the sequences share the same nucleotides, while high entropy reflects different mutations destroyed the motif. Sometimes, we see motif preserving signature outside the vertical bands. This represents a de novo motif that appeared within that cluster. 5/N

1 1

Peter Koo @pkoo562.bsky.social · 1d

If we calculate the positional entropy of the sequences within each cluster, we get a cluster summary matrix. The vertical bands highlight the locations of the motifs in WT seq and entropy levels indicate whether the motif is present or not in the attr maps in each cluster. 4/N

1

Peter Koo @pkoo562.bsky.social · 1d

Attr maps can sometimes be easy to interpret, and sometimes they're complex. SEAM's clustered attr maps are cleaner (think SmoothGrad) and they decompose complex mechanisms via partial random mutagenesis, which occasionally disrupts key binding sites. 3/N

1 1

Peter Koo @pkoo562.bsky.social · 1d

SEAM is conceptually simple. Starting from a reference sequence:
1) sample in a local region of sequence space via partial random mutagenesis
2) calculate attr maps to unveil the mechanisms
3) cluster attr maps based on shared mechanisms
4) cluster-based sequence analysis

2/N

1 1

Peter Koo @pkoo562.bsky.social · 1d

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 🧵👇

1 8 21

Peter Koo @pkoo562.bsky.social · 2d

Congratulations to John Clarke, Michel Devoret and John Martinis on receiving the 2025 Nobel Prize in Physics!
www.nobelprize.org/prizes/physi...

I have fond memories of my time in the Clarke lab, where I did my Honors Thesis on ultra low-field MRI w/ SQUIDs as an undergrad at UC Berkeley!

8

Peter Koo @pkoo562.bsky.social · 20d

Check out a Research Highlights on our work at @naturemethods by Lin Tang!

www.nature.com/articles/s41...

7

Peter Koo @pkoo562.bsky.social · 28d

Richard Bonneau giving the last keynote on navigating the complexity of drug discovery and their lab-in-the-loop for molecule design! #MLCB

2

Peter Koo @pkoo562.bsky.social · 29d

First talk a (surprise) keynote by Jacob Schreiber from UMass Medical talking about fruit-themed AI tools for understanding and designing regulatory DNA

3

Peter Koo @pkoo562.bsky.social · 29d

2025 MLCB day 2 is starting now!

Streaming live now!
m.youtube.com/watch?v=PxlXNb…

https://m.youtube.com/watch?v=PxlXNb…

1 3

Peter Koo @pkoo562.bsky.social · 29d

Now Barbara Engelhardt giving a keynote on characterizing behaviors of modified T cells in live cell imaging data using machine learning!

4

Peter Koo @pkoo562.bsky.social · 29d

Next talk by Courtney Shearer who is talking about genomic language models for zero shot promoter indel effects!

1 1

Peter Koo @pkoo562.bsky.social · 29d

Next talk by Alan Murphy and Masayuki (Moon) Nagai (from my lab!) who are talking about how naive fine-tuning genomic DNNs leads to catastrophic forgetting and propose *iterative causal refinement* to improve learned associations to causal understanding of cis-regulatory biology!

1

Peter Koo @pkoo562.bsky.social · 29d

Next talk by Johannes Linder at Calico. Talking about expanding genomic seq2fun DNNs with RBP binding and RNA processing data to consider post-transcriptional regulation.

1 1

Peter Koo @pkoo562.bsky.social · Sep 10

Some technical delays but we are all set!

First talk by Alexis Battle! @alexisbattle.bsky.social

1 5

Peter Koo @pkoo562.bsky.social · Sep 10

Here is the YouTube live link:

www.youtube.com/live/19I7xTh...

Starts at 9:30a!

Machine Learning in Computational Biology 2025

YouTube video by Machine Learning in Computational Biology

www.youtube.com

4