Su-In Lee

Atul Butte died yesterday.
The world lost a giant.
A big bear of a man.
With a huge smile.
With love for everyone.
With energy that could power a room.
I loved everything about Atul.
I loved how he was always happy.
I loved how excited he was about science and helping people.

Atul Butte’s talk introduced me to systems biology—I was presynapse scientist and opened my horizon to "biomedical moments, thawing frozen discoveries in data". Ideas that changed my career. Thank you for the science, the spirit, and the inspiration. You will be remembered.

A Unified Approach to Interpreting Model Predictions Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by c...

Wow, this paper on interpreting ML models by
@suinlee.bsky.social
and Scott Lundberg came out in 2017 and has 34k citations! Congratulations
@suinlee.bsky.social
and your team, what an achievement :-). arxiv.org/abs/1705.07874

📢📢 Junior researchers attending #ICLR2025, be sure to check out the mentoring chat sessions!

More info here:
blog.iclr.cc/2025/04/23/i...

You can find all the sessions on the ICLR.cc schedule!

Thrilled to share that @ethanweinberger.bsky.social is becoming Dr. Weinberger in CSE2, where he is presenting his work, including the popular contrastiveVI for single-cell data (Weinberger et al. Nature Methods)! I feel so fortunate to work with such amazing Ph.D. students at @uwcse.bsky.social! 🎉🎓

Genomic language models: opportunities and challenges Large language models (LLMs) are having transformative impacts across a wide range of scientific fields, particularly in the biomedical sciences. Just as the goal of natural language processing is to ...

Genomic language models: opportunities and challenges: Trends in Genetics www.cell.com/trends/genet...

‘Pushing the field to the next stage’: Allen School professor Su-In Lee recognized as a Fellow of the International Society for Computational Biology - Allen School News Allen School professor Su-In Lee, who directs the University of Washington’s AI for bioMedical Sciences (AIMS) Lab, is shaping the future of biology and medicine through artificial intelligence. Her r...

#UWAllen's @suinlee.bsky.social was recently elected a Fellow of the @iscb.bsky.social for her work on #AI techniques to provide new insights into disease and drive #healthcare breakthroughs. Read more about her contributions: news.cs.washington.edu/2025/04/02/s... #ThisIsUW #CompBio #AIforGood

‘Pushing the field to the next stage’: Allen School professor Su-In Lee recognized as a Fellow of the International Society for Computational Biology - Allen School News Allen School professor Su-In Lee, who directs the University of Washington’s AI for bioMedical Sciences (AIMS) Lab, is shaping the future of biology and medicine through artificial intelligence. Her r...

Thank you @uwcse.bsky.social!

“Su-In’s body of work has completely transformed how people analyze and interpret AI/ML models. Her SHAP approach is used by essentially the entire field, not only in computational biology but all of computer science...”

news.cs.washington.edu/2025/04/02/s...

The cover of Nature Biomedical Engineering features work from #UWAllen’s @suinlee.bsky.social on techniques for auditing #AI dermatology image classifiers—one of two projects from the lab highlighted in this issue, alongside a deep learning model for cancer insights. www.nature.com/natbiomedeng...

Thank you so much for the highlight and for the nice summary of our recent work!

Portrait of Su-In Lee looking off to the side, holding a pen in front of a whiteboard with part of a handwritten algorithm visible behind her

Congratulations to #UWAllen professor @suinlee.bsky.social on her election as a Fellow of the International Society for Computational Biology! @iscb.bsky.social honored Lee for her pioneering work on explainable #AI for biology and medicine. www.iscb.org/iscb-news-it... #PopulationHealth #ThisIsUW

🌟 Congrats to the 2025 ISCB Fellows! 🌟 Honoring leaders in #computationalbiology for outstanding research, innovation and service. See this year's Fellows and their contributions here: https://t.ly/VYfLk

Congratulations, Jian! Absolutely deserved!!

I'm deeply honored to be elected as an ISCB Fellow this year!🏅 Following last year’s ISCB Innovator Award, this recognition strengthens my commitment to advancing computational biology.🧬 Grateful to my students, mentors, and colleagues for their support!
www.iscb.org/iscb-news-it...

Allen School professor Amy X. Zhang receives Sloan Research Fellowship for empowering users to make ‘our online spaces as rich and varied as our offline ones’ - Allen School News As the head of the Allen School’s Social Futures Lab, professor Amy X. Zhang’s research draws on the design of offline public institutions and communities to then develop new social computing systems ...

Allen School professor Amy X. Zhang receives Sloan Research Fellowship for empowering users to make ‘our online spaces as rich and varied as our offline ones’ news.cs.washington.edu/2025/02/24/a...

Check out LUNA by my colleague @mariabrbic—a generative AI model that reassembles tissues from dissociated cells! 🚀🔬 A potential game-changer for single-cell & spatial transcriptomic, IMHO!

Thrilled to share LUNA🌕 – our new generative AI model that reassembles tissue structures from dissociated cells! LUNA learns spatial priors over existing spatially resolved datasets with the aim to predict cell locations de novo.

Check out our paper here: www.biorxiv.org/content/10.1...

A scalable approach to investigating sequence-to-expression prediction from personal genomes A key promise of sequence-to-function (S2F) models is their ability to evaluate arbitrary sequence inputs, providing a robust framework for understanding genotype-phenotype relationships. However, despite strong performance across genomic loci , S2F models struggle with inter-individual variation. Training a model to make genotype-dependent predictions at a single locus-an approach we call personal genome training-offers a potential solution. We introduce SAGE-net, a scalable framework and software package for training and evaluating S2F models using personal genomes. Leveraging its scalability, we conduct extensive experiments on model and training hyperparameters, demonstrating that training on personal genomes improves predictions for held-out individuals. However, the model achieves this by identifying predictive variants rather than learning a cis-regulatory grammar that generalizes across loci. This failure to generalize persists across a range of hyperparameter settings. These findings highlight the need for further exploration to unlock the full potential of S2F models in decoding the regulatory grammar of personal genomes. Scalable software and infrastructure development will be critical to this progress. ### Competing Interest Statement The authors have declared no competing interest.

Our new paper describing a scalable approach for training sequence-to-function models on personal genomes ("personal genome training"), includes our observations on when this works and its limitations. www.biorxiv.org/content/10.1...
Congrats: Anna, @xinmingtu.bsky.social , @lxsasse.bsky.social

Congratulations! 🥳🎉 This is so well-deserved! I'm truly honored to have you as part of my ISCB Award alumni.😊

Fabian Theis Honored with ISCB Innovator Award

Congratulations to Prof. Fabian Theis on winning the ISCB Innovator Award! 🏆

💡Theis is honored for his pioneering research in #ComputationalBiology.

👉More in our news:
t1p.de/u8olc

@fabiantheis.bsky.social @iscb.bsky.social

#AI #MachineLearning #ISCBInnovatorAward #CellResearch

📣Meet our amazing @HiTSeq Keynotes speakers at the #ISMB2024 conference on July 12-16 in Montréal, Canada! Bringing the most novel statistical and computational methods for medicine and cell evolution to you! Call for abstracts is already open! iscb.org/ismb2024/home #ISCB

Overland AI opens new factory in Seattle to manufacture off-road autonomous vehicles Inside Overland AI's new factory in south Seattle. (Overland Photo) Seattle startup Overland AI is bringing manufacturing operations close to

#UWAllen - www.geekwire.com/2025/overlan...

Incredibly grateful and honored to receive the 2025 Overton Prize ♥️

Surreal to follow the steps of my science heroes🙏 Truly, credit goes to my amazing students, collaborators and mentors who make research so inspiring!

Also underscores the value of open academic environment that make this possible

More than deserved—no surprise there at all!

I am deeply honored to be named a Sloan Fellow this year. Thank you to my students, collaborators, and colleagues for making all of our work in @socialfutureslab.bsky.social possible. And thank you to the Sloan Foundation for your support of science and early career scientists in these times.

Three UW scientists named Sloan Fellows Three University of Washington faculty members have been awarded early-career fellowships from the Alfred P. Sloan Foundation. The new Sloan Fellows, announced Feb. 18, are Amy L. Orsborn, the Clare.....

Zhang, whose research aims to empower people to take control of their online social experiences, is one of 3 @uofwa.bsky.social faculty to earn Sloan Fellowships this year, joined by @neuroamyo.bsky.social and @uwchemistry.bsky.social ’s Diane Xiao: www.washington.edu/news/2025/02... #UWdiscovers /2

GeekWire Breaking News in Technology & Business

‘Open source will win’: Allen Institute for AI CEO Ali Farhadi on the new era of artificial intelligence https://www.geekwire.com/2025/open-source-will-win-allen-institute-for-ai-ceo-ali-farhadi-on-the-new-era-of-artificial-intelligence/

Transformers in single-cell omics: a review and new perspectives - Nature Methods This Perspective presents a comprehensive and in-depth overview of computational models based on the deep learning architecture of transformers for single-cell omics analysis.

This week our class had an awesome discussion on this review article discussing #transformers for #SingleCell. One of my favorite parts was discussing Figure 3 on current strategies for how to transform the counts to a format that can be used by transformer. 1/n 🧪🧬💻

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

[SAVE THE DATE] MLCB 2025 is happening Sept 10-11 at the NY Genome Center in NYC!

Attend the premier conference at the intersection of ML & Bio, share your research and make lasting connections!

Submission deadline: June 1
More details: mlcb.github.io

Help spread the word—please RT! #MLCB2025

AI for radiographic COVID-19 detection selects shortcuts over signal - Nature Machine Intelligence The urgency of the developing COVID-19 epidemic has led to a large number of novel diagnostic approaches, many of which use machine learning. DeGrave and colleagues use explainable AI techniques to an...

I think this has been shown in several studies where neural nets have been used to classify X-ray images, in particular. Machine models used in different hospitals/wards introduce confounders. Here's a good one from @suinlee.bsky.social :
www.nature.com/articles/s42...