←
ZeitlingerLab172 posts
ZeitlingerLab avatar

ZeitlingerLab

@ZeitlingerLab

Our long-term research goal is to understand and predict gene regulation based on DNA sequence information and genome-wide experimental data.

◷ Joined December 2018▧ 45 Photos and videos
Stowers Institute avatar
⟳ ZeitlingerLab retweeted
Stowers Institute@ScienceStowers·Aug 25

NEW #Research published @NatureComms: Scientists in the @ZeitlingerLab developed PISA, a new #AI interpretation method that lets researchers see, at high resolution, what AI models learn from DNA sequences. Using that insight, the team discovered they could better control what the models learn next. By separating the biology they wanted to study from bias introduced by the experiment, the researchers were able to train a more focused model and uncover patterns in DNA they didn’t see before. That clearer view led to a surprising biological insight with implications for understanding gene regulation and, potentially, genetic disease: the way #DNA is wrapped around nucleosomes may help predict how it is organized in 3D inside the nucleus. Hear Investigator @JuliaZeitlinger, Ph.D., explain how PISA could become a broadly useful tool for scientists to help bridge the gap between powerful AI models and the biological mechanisms researchers want to understand. 🔗bit.ly/4gwN0Oy

4:12
Julia Zeitlinger (@jzeitlinger@genomic.social) avatar
⟳ ZeitlingerLab retweeted
Julia Zeitlinger (@jzeitlinger@genomic.social)@JuliaZeitlinger·Sep 8

Happy to have contributed to this work! Amazing to see cis-regulatory motif maps across so many cell types readily available. Get a bird’s eye view of the cis-regulatory code or dive in deep into specific details, I highly recommend it!

Excited to release AlphaGenome Atlas 🧬 We used AlphaGenome to predict the regulatory impact of all 9B possible SNVs in the human genome. We collaborated with amazing scientists to analyze and apply it, and developed a portal to browse the genome using this new lens 🔬 🌐 Portal: alphagenome.google/atlas 📖 Blog: goo.gle/4heuCvn 📄 Preprint: deepmind.google/blog/alphage… 🧵 1/6

3:36
ZeitlingerLab avatar
ZeitlingerLab@ZeitlingerLab·Sep 8

What a wonderful collaboration, excited to see this released to the public!

We’re launching AlphaGenome Atlas: an AI-powered searchable database mapping the predicted impact of all 9 billion possible single-letter DNA changes. Here’s how it could help researchers better understand our biology 🧵

1:04
ZeitlingerLab avatar
ZeitlingerLab@ZeitlingerLab·Sep 8

Excited to be a part of this collaboration! The AlphaGenome Atlas will be a huge accelerant in our field for understanding regulatory encoding.

Excited to release AlphaGenome Atlas 🧬 We used AlphaGenome to predict the regulatory impact of all 9B possible SNVs in the human genome. We collaborated with amazing scientists to analyze and apply it, and developed a portal to browse the genome using this new lens 🔬 🌐 Portal: alphagenome.google/atlas 📖 Blog: goo.gle/4heuCvn 📄 Preprint: deepmind.google/blog/alphage… 🧵 1/6

3:36
Žiga Avsec avatar
⟳ ZeitlingerLab retweeted
Žiga Avsec@Avsecz·Sep 8

Excited to release AlphaGenome Atlas 🧬 We used AlphaGenome to predict the regulatory impact of all 9B possible SNVs in the human genome. We collaborated with amazing scientists to analyze and apply it, and developed a portal to browse the genome using this new lens 🔬 🌐 Portal: alphagenome.google/atlas 📖 Blog: goo.gle/4heuCvn 📄 Preprint: deepmind.google/blog/alphage… 🧵 1/6

3:36
ZeitlingerLab avatar
ZeitlingerLab@ZeitlingerLab·Feb 5

(9/10) Our BPReveal package provides tools to engineer sequences with desired properties. For example, we designed mutations to alter a nucleosome’s presence in vivo, and our design was corroborated experimentally.

Post attachment
ZeitlingerLab avatar
ZeitlingerLab@ZeitlingerLab·Feb 5

(8/10) These models detect barrier elements in nucleosome occupancy and chromatin organization. Around barriers, motif effects are asymmetric, and the most asymmetric regions align with known domain boundaries.

Post attachment
ZeitlingerLab avatar
ZeitlingerLab@ZeitlingerLab·Feb 5

(7/10) Overcoming enzymatic sequence biases using PISA reveals the nucleosome motif grammar. Upon correcting the AT-rich sequences of a BPNet model trained to predict MNase-seq nucleosome occupancy, resulting attribution scores clearly identify motifs.

Post attachment
ZeitlingerLab avatar
ZeitlingerLab@ZeitlingerLab·Feb 5

(6/10) PISA can detect enzymatic biases in various sequencing data. Sequence-to-function models learn both enzymatic bias of the sequencing experiment and the underlying biology. Here, a BPNet MNase-seq model trained in yeast exhibits expected preference for AT-rich sequences.

Post attachment
ZeitlingerLab avatar
ZeitlingerLab@ZeitlingerLab·Feb 5

(5/10) PISA reveals complex motif effects on histone modification ChIP-seq data. In a H3K27ac BPNet model predicting activity in early embryo fly, a pioneering Zelda motif produces a dual response in H3K27ac profile: a central depletion, flanked by an increase in activity.

Post attachment
ZeitlingerLab avatar
ZeitlingerLab@ZeitlingerLab·Feb 5

(4/10) PISA can reveal “hidden” motifs that possess disparate effects on the output window. In a ChromBPNet model predicting accessibility in early embryo fly, a CA-rich “Cackle” motif is revealed to possess a positive and negative contributions depending on the output locus.

Post attachment
ZeitlingerLab avatar
ZeitlingerLab@ZeitlingerLab·Feb 5

(3/10) PISA can visualize the influence range of sequences, including TF motifs. In a mESC BPNet model predicting Nanog binding, PISA can distinguish the nucleosome-range effects of pioneering motif Oct4-Sox2 versus the binding-range effects of the Nanog motif itself.

Post attachment
ZeitlingerLab avatar
ZeitlingerLab@ZeitlingerLab·Feb 5

(2/10) Our new interpretation tool called PISA (pairwise influence by sequence attribution) overcomes this limitation and quantifies how each individual base impacts the predicted readout at each genomic coordinate.

Post attachment
ZeitlingerLab avatar
ZeitlingerLab@ZeitlingerLab·Feb 5

(1/10) When interpreting sequence-to-function models, current attribution methods typically summarize an input base’s effect on the entire output. But what happens if a single nucleotide causes one effect at one output position, but a different effect elsewhere?

Post attachment