Peter Koo

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 🧵👇

Check out the paper to find out more! Code: github.com/evanseitz/se... Paper: www.biorxiv.org/content/10.1...

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 🧵👇

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

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 🧵👇

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

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 🧵👇

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

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 🧵👇

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

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 🧵👇

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

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 🧵👇

2025 MLCB day 2 is starting now! Streaming live now! m.youtube.com/watch?v=PxlXNb…

Some technical delays but we are all set! First talk by Alexis Battle! @alexisbattle.bsky.social

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

Some technical delays but we are all set! First talk by Alexis Battle! @alexisbattle.bsky.social

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.

2025 Machine Learning in Computational Biology (#MLCB) meeting starts TODAY (9/10) at 9:30a (EST) at the NY Genome Center in NYC! We have a great lineup of keynotes, contributed talks, and posters today and tomorrow Schedule: mlcb.org/schedule Join for free via livestream: m.youtube.com/@mlcbconf

*Easter egg alert* NOT in the published paper. We also benchmarked Evo 2 and while it did better than other gLMs (consistent that scale can improve gLMs), it still falls short of a basic CNN trained using one-hot sequences and far short of supervised SOTA

But, when we trained D3 (score-entropy discrete diffusion for regulatory DNA) in an unsupervised manner on the genomic sequences, probing the representations of D3 was comparable to supervised SOTA (even with a basic CNN)! (100M parameters vs 40B parameters)

Our work on "Evaluating the representational power of pre-trained DNA language models for regulatory genomics" led by @AmberZqt with help from @NiraliSomia & @stevenyuyy is finally published in Genome Biology! Check it out! genomebiology.biomedcentral.com/articles/10....

gLMs provide promise in learning structure in the genome, but we need to rethink how we either tokenize the genome (and no byte pair encoding isn't the answer either) or come up with a better masking strategy for non-coding genome that is different from other regions (eg coding).

Our work on "Evaluating the representational power of pre-trained DNA language models for regulatory genomics" led by @AmberZqt with help from @NiraliSomia & @stevenyuyy is finally published in Genome Biology! Check it out! genomebiology.biomedcentral.com/articles/10....

It's unclear whether standard NLP-based objectives (MLM or CLM) will bring us to the promised land. Unlike proteins, which have conservation at sequence and covariation levels, non-coding genome is conserved at functional level -- lots of drift and uninformative positions!

Our work on "Evaluating the representational power of pre-trained DNA language models for regulatory genomics" led by @AmberZqt with help from @NiraliSomia & @stevenyuyy is finally published in Genome Biology! Check it out! genomebiology.biomedcentral.com/articles/10....

Breaking the constant propagation of pointless gLM benchmarks in the ML field (that are disconnected from how biologists will use them) is what is giving gLMs unwarranted hype. The field must rally around useful applications of gLMs.

Our work on "Evaluating the representational power of pre-trained DNA language models for regulatory genomics" led by @AmberZqt with help from @NiraliSomia & @stevenyuyy is finally published in Genome Biology! Check it out! genomebiology.biomedcentral.com/articles/10....

This went 3 rounds of review in another journal, but 1 reviewer was adamant that this type of benchmark might be harmful to the burgeoning gLM field, which currently only benchmarks relative performance on (nearly) useless benchmarks in the non-coding regions. It was rejected!

Our work on "Evaluating the representational power of pre-trained DNA language models for regulatory genomics" led by @AmberZqt with help from @NiraliSomia & @stevenyuyy is finally published in Genome Biology! Check it out! genomebiology.biomedcentral.com/articles/10....

This went 3 rounds of review in another journal, but 1 reviewer was adamant that this type of benchmark might be harmful to the burgeoning gLM field, which currently only benchmarks relative performance on (nearly) useless benchmarks in the non-coding regions. It was rejected!