Preprints

Alex J. DeGrave, Joseph D. Janizek, and Su-In Lee*. AI for radiographic COVID-19 detection selects shortcuts over signal. [https://www.medrxiv.org/content/10.1101/2020.09.13.20193565v1]

Safiye Celik, Josh C. Russell, Cezar R. Pestana, Ting-I Lee, Shubhabrata Mukherjee, Paul K. Crane, C. Dirk Keene, Jennifer F. Bobb, Matt Kaeberlein*, and Su-In Lee*. DECODER: A probabilistic approach to integrate big data reveals mitochondrial Complex I as a potential therapeutic target for Alzheimer’s disease. [https://www.biorxiv.org/content/10.1101/302737v4]

Ayse B. Dincer, Joseph D. Janizek, Safiye Celik, Naozumi Hiranuma, Kamila Naxerova* and Su-In Lee*. DeepProfile: Interpretable Deep Learning of Latent Variables from a Compendium of Expression Profiles for 18 Human Cancers. Highlighted as a spotlight talk at MLCB; ICML Workshop on Computational Biology. Journal version will be available soon. [bioRxiv]

Nicasia Beebe-Wang, Safiye Celik, Pascal Sturmfels, Sara Mostafavi* and Su-In Lee*. MD-AD: Multi-task deep learning for Alzheimer’s disease neuropathology. Highlighted as a spotlight talk at MLCB; ICML Workshop on Computational Biology. Journal version will be available soon. [bioRxiv]

Joseph Janizek, Safiye Celik, and Su-In Lee. Explainable machine learning prediction of synergistic drug combinations for precision cancer medicine. ICML Workshop on Computational Biology. Journal version will be available soon. [biorxiv]

William Chen, Joseph D. Janizek and Su-In. Lee. EXPERT: Explainable Prediction of Transcription Factor Binding based on Histone Modification Data. Highlighted as a spotlight talk at MLCB.

Gabriel Erion*, Joseph D. Janizek*, Pascal Sturmfels*, Scott Lundberg, Su-In Lee. Learning Explainable Models using Attribution Priors. [arxiv] (*These authors contributed equally to this work and are listed alphabetically.)

Joseph D. Janizek*, Pascal Sturmfels*, and Su-In Lee. Explaining Explanations: Axiomatic Feature Interactions for Deep Networks. [arxiv] (*These authors contributed equally to this work and are listed alphabetically.)

Parmita Mehta, Christine Petersen, Joanne C. Wen, Michael R. Banitt, Philip P. Chen, Karine D. Bojikian, Catherine Egan, Su-In Lee, Magdalena Balazinska, Aaron Y. Lee, Ariel Rokem, The UK Biobank Eye and Vision Consortium. Automated detection of glaucoma with interpretable machine learning using clinical data and multi-modal retinal images [bioRxiv]


Lee lab members

Journal Publications

Scott M. Lundberg, Gabriel Erion, Hugh Chen, Alex DeGrave, Jordan M. Prutkin, Bala Nair, Ronit Katz, Jonathan Himmelfarb, Nisha Bansal, and Su-In Lee. From Local Explanations to Global Understanding with Explainable AI for Trees. Nature Machine Intelligence 2, 56–67 (Jan 2020) https://doi.org/10.1038/s42256-019-0138-9 - Featured on the Cover [Paper]

Pascal Sturmfels, Scott M. Lundberg, and Su-In Lee. Visualizing the Impact of Feature Attribution Baselines. Distill 5 (1), e22 10.23915/distill.00021 [Paper]

Naozumi Hiranuma, Scott M. Lundberg, and Su-In Lee. AIControl: Replacing matched control experiments with machine learning improves ChIP-seq peak identification. Nucleic Acids Research (June 2019) vol. 47, issue 10, page e58 [Paper] [Github]

  • Allen School News - With AIControl, Allen School researchers replace biological experiments with AI to better understand the human genome

Sara Rolfe, Su-In Lee, and Linda Shapiro. Associations Between Genetic Data and Quantitative Assessment of Normal Facial Asymmetry. Frontiers in Genetics, 18 December 2018 [Paper]

Scott M. Lundberg, Bala Nair, Monica S. Vavilala, Mayumi Horibe, Michael J. Eisses, Trevor Adams, David E. Liston, Daniel King-Wai Low, Shu-Fang Newman, Jerry Kim, and Su-In Lee. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. [Paper] Nature Biomedical Engineering 2, 749–760 (Oct 2018) - Featured on the Cover

  • Nature BME Editorial - Towards trustable machine learning

  • UW News - Prescience: Helping doctors predict the future

  • GeekWire - Univ. of Washington researchers unveil Prescience, an AI system that predicts problems during surgery

  • Allen School News - “Prescience” interpretable machine-learning system for predicting complications during surgery featured in Nature Biomedical Engineering

Su-In Lee*,C, Safiye CelikC , Benjamin A. Logsdon, Scott M. Lundberg, Timothy J. Martins, Vivian M. Oehler, Elihu H. Estey, Chris P. Miller, Sylvia Chien, Akanksha Saxena, C. Anthony Blau, and Pamela S. Becker. A machine learning approach to integrate big data for precision medicine in acute myeloid leukemia. Nature Communications 9, Article number: 42 2018 [Paper] [MERGE website]

Safiye Celik, Benjamin A. Logsdon, Stephanie Battle, Charles W. Drescher, Mara H. Rendi, David R. Hawkins, and Su-In Lee. Extracting a low-dimensional description of multiple gene expression datasets reveals a potential driver for tumor-associated stroma in ovarian cancer. Genome Medicine 2016 Jun 10;8(1):66. [Paper] [INSPIRE website]

  • Featured in Casey S. Greene. The future is unsupervised. Science Translational Medicine 06 Jul 2016, Vol. 8 (346), pp. 346ec108 Editors' Choice [Link]

Scott M. Lundberg, William B. Tu, Brian Raught, Linda Z. Penn, Michael M. Hoffman, and Su-In Lee. ChromNet: Learning the human chromatin network from all ENCODE ChIP-seq data. Genome Biology 2016 Apr 30;17(1):82. [Paper] [ChromNet browser]

  • Recommended in F1000Prime as being of special significance in its field:

Maxim Grechkin, Benjamin A. Logsdon, Andrew J. Gentles, and Su-In Lee*. Identifying Network Perturbation in Cancer. PLOS Computational Biology 2016 12(5): e1004888. [Paper] [DISCERN website]

C. Anthony Blau, Arturo B. Ramirez, Sibel Blau, Colin C. Pritchard, Michael O. Dorschner, Stephen C. Schmechel, Timothy J. Martins, Elisabeth M. Mahen, Kimberly A. Burton, Vitalina M. Komashko, Amie J. Radenbaugh, Katy Dougherty, Anju Thomas, Christopher P. Miller, James Annis, Jonathan R. Fromm, Chaozhong Song, Elizabeth Chang, Kellie Howard, Sharon Austin, Rodney A. Schmidt, Michael L. Linenberger, Pamela S. Becker, Francis M. Senecal, Brigham H. Mecham, Su-In Lee, Anup Madan, Roy Ronen, Janusz Dutkowski, Shelly Heimfeld, Brent L. Wood, Jackie L. Stilwell, Eric P. Kaldjian, David Haussler, and Jingchun Zhu. A Distributed Network for Intensive Longitudinal Monitoring in Metastatic Triple Negative Breast Cancer. Journal of the National Comprehensive Cancer Network. 2016 Jan;14(1):8 - 17.[Paper]

Robert T. Lawrence, Elizabeth M. Perez, Daniel Hernández, Chris P. Miller, Kelsey M. Haas, Hanna Y. Irie, Su-In Lee, C. Anthony Blau, and Judit Villén (2015). The Proteomic Landscape of Triple-Negative Breast Cancer. Cell Reports Volume 11, Issue 4, p630–644, 28. [Paper]

Benjamin A. Logsdon, Andrew J. Gentles, Chris P. Miller, C. Anthony Blau, Pamela S. Becker, and Su-In Lee (2015). Sparse expression bases in cancer reveal tumor drivers. Nucleic Acids Research 10.1093/nar/gku1290. [Paper] [SPARROW website (Software & Data)]

Kean Ming Tan, Palma London, Karthik Mohan, Su-In Lee, Maryam Fazel, and Daniela Witten (2014). Learning Graphical Models with Hubs. Journal of Machine Learning Research (JMLR) 15(Oct):3297 - 3331.[Paper]

Karthik Mohan, Palma London, Maryam Fazel, Daniela Witten, and Su-In Lee (2014). Node-Based Learning of Multiple Gaussian Graphical Models. Journal of Machine Learning Research (JMLR) 15(Feb):445 - 488. [Paper] [Software]

Stephen M. Schwartz*, Hillel T. Schwartz, Steve Horvath, Eric Schadt, and Su-In Lee (2012). A Systematic Approach to Multifactorial Cardiovascular Disease: Causal Analysis. Arteriosclerosis, Thrombosis, and Vascular Biology, 32(12):2821-35. [Paper]

Rupali P. Patwardhan, Joseph B. Hiatt, Daniela M. Witten, Mee J. Kim, Robin P. Smith, Dalit May, Choli Lee, Jennifer M. Andrie, Su-In Lee, Gregory M. Cooper, Nadav Ahituv*, Len A. Pennacchio*, and Jay Shendure* (2012). Massively parallel functional dissection of mammalian enhancers in vivo. Nature Biotechnology, 30(3), 265-70. [Paper] [Link]

Iain M. Dykes, Lynne Tempest, Su-In Lee, and Eric E. Turner (2011). Brn3a and Islet1 act epistatically to regulate the gene expression program of sensory differentiation. Journal of Neuroscience, 31(27), 9789-99. [Paper] [Link]

Sivaraman Balakrishnan, Hetunandan Kamisetty, Jaime G. Carbonell, Su-In Lee, and Christopher J. Langmead (2011). Learning Generative Models for Protein Fold Families. PROTEINS: Structure, Function, and Bioinformatics, 79(4), 1061-78. [Paper] [Link]

Andrew J. Gentles, Ash A. Alizadeh, Su-In Lee, June H. Myklebust, Catherine M. Shachaf, Babak Shahbaba, Ronald Levy, Daphne Koller, and Sylvia Plevrities (2009). A pluripotency signature predicts histologic transformation and influences survival in follicular lymphoma patients. Blood, 114(15), 3133-4. [Paper]

Su-In Lee, Aimee M. Dudley, David Drubin, Pamela A. Silver, Nevan J. Krogan, Dana Pe’er, and Daphne Koller (2009). Learning a Prior on Regulatory Potential from eQTL Data. PLOS Genetics, 5(1), e1000358. [Paper] [Software]

Su-In Lee*, Dana Pe’er*, Aimee M. Dudley, George M. Church, and Daphne Koller (2006). Identifying Regulatory Mechanisms using Individual Variation Reveals Key Role for Chromatin Modification. Proceedings of the National Academy of Sciences (PNAS), 103, 14062-14067.[Paper]

James E. Galagan, Sarah E. Calvo, Christina Cuomo, Li-Jun Ma, Jennifer R. Wortman, Sarafim Batzoglou, Su-In Lee, et al. (2005). Sequencing of Aspergillus nidulans and comparative analysis with A. fumigatus and A. oryzae. Nature, 438(7071), 1105-1115. [Paper]

S.-I. Lee, and S. Batzoglou (2003). Application of Independent Component Analysis to Microarrays. Genome Biology, 4(11), R76. [Paper]

S.-I. Lee, and S.-Y. Lee (2000). Biologically Inspired Neural Network Approach using Feature Extraction and Top-Down Selective Attention for Robust Optical Character Recognition. Proceedings of Humantech Paper Competition held by Samsung Electronics, Inc.. Gold prize (the first prize) [Link]

Conference Publications

Ethan Weinberger, Joseph Janizek, and Su-In Lee. Learning Deep Attribution Priors Based On Prior Knowledge. [arxiv] Accepted to Neural Information Processing Systems (NeurIPS) 2020

Ian Covert, Scott Lundberg, and Su-In Lee. Understanding Global Feature Contributions through Additive Importance Measures. [arxiv] Accepted to Neural Information Processing Systems (NeurIPS) 2020

Ayse B. Dincer, Joseph D. Janizek, and Su-In Lee. Adversarial Deconfounding Autoencoder for Learning Robust Gene Expression Embeddings. [bioRxiv] Accepted to ECCB 2020

Joseph D. Janizek, Gabriel Erion, Alex J. DeGrave, and Su-In Lee. An Adversarial Approach for the Robust Classification of Pneumonia from Chest Radiographs. [Paper] [github] ACM Conference on Health, Inference, and Learning (CHIL 2020)

Frances Linzee Mabrey, Sylvia S Chien, Timothy S Martins, James Annis, Taylor S Sekizaki, Jin Dai, Robert A. Beckman, Lawrence A. Loeb, Andrew Carson, Bradley Patay, Carl Anthony Blau, Vivian G. Oehler, Safiye S Celik, Su-In Lee, Raymond J. Monnat, Janis L. Abkowitz, Frederick R. Appelbaum, Elihu H. Estey and Pamela S Becker. High Throughput Drug Screening of Leukemia Stem Cells Reveals Resistance to Standard Therapies and Sensitivity to Other Agents in Acute Myeloid Leukemia. Blood 2018 132:180

Sumit Mukherjee, Alberto Carignano, Georg Seelig*, and Su-In Lee*. Identifying progressive gene network perturbation from single-cell RNA-seq data. IEEE Engineering in Medicine and Biology Society (EMBC) 2018. [Paper in bioRxiv]

Scott M. Lundberg, and Su-In Lee. A unified approach to interpreting model predictions. Neural Information Processing Systems (NeurIPS) 2017 Oral Presentation [Paper] [GitHub]

Javad Hosseini, and Su-In Lee . Learning Sparse Gaussian Graphical Models with Overlapping Blocks. Neural Information Processing Systems (NeurIPS) 2016. [Paper] [GRAB website]

Naozumi Hiranuma, Scott Lundberg, and Su-In Lee. Cloud Control: Leveraging many public ChIP-seq control experiments to better remove background noise. The 7th ACM Conference on Bioinformatics, Computational Biology (ACM-BCB) 2016. [Paper]

Maxim Grechkin, Maryam Fazel, Daniela Witten, and Su-In Lee (2015). Pathway Graphical Lasso. The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15). acceptance rate (oral presentation) 11.7% [Paper] [Software & Data]

Safiye Celik, Benjamin Logsdon, and Su-In Lee (2014). Efficient Dimensionality Reduction for High-Dimensional Network Estimation. International Conference on Machine Learning (ICML). acceptance rate 22% [Paper] [Software]

Ezgi Mercan, Linda Shapiro, Seth Weinberg, and Su-In Lee (2013). The Use of Pseudo-Landmarks for Craniofacial Analysis: A Comparative Study with L1-Regularized Logistic Regression. IEEE Engineering in Medicine and Biology Society (EMBC). acceptance rate (oral) 40% PMID: 24111127 [Paper]

Karthik Mohan, Mike Chung, Seungyeop Han, Daniela Witten, Su-In Lee, and Maryam Fazel (2012). Structured Learning of Gaussian Graphical Models. Neural Information Processing Systems (NeurIPS). acceptance rate 25% [Paper] [Software]

Shulin Yang, Linda Shapiro, Michael Cunningham, Matthew Speltz, Craig Birgfeld, Indriyati Atmosukarto, and Su-In Lee (2012). Skull Retrieval for Craniosynostosis Using Sparse Logistic Regression Models. Medical Image Computing and Computer Assisted Intervention (MICCAI). acceptance rate: 30% best paper award. [Paper]

Bilge Soran, Jeng-Neng Hwang, Su-In Lee, and Linda Shapiro (2012). Tremor Detection Using Motion Filter and SVM. International Conference on Pattern Recognition. [Paper]

Bilge Soran, Zhiyong Xie, Rosalia Tungaraza, Su-In Lee, Linda Shapiro, and Thomas Grabowski (2012). Parcellation of Human Inferior Parietal Lobule Based On Diffusion MRI. IEEE Engineering in Medicine & Biology Society, Engineering Innovation in Global Health. PMID: 23366611 [Paper]

Shulin Yang, Linda Shapiro, Michael L. Cunningham, Matthew Speltz, and Su-In Lee (2011). Classification and Interest Region Localization on Craniosynostosis Skulls. ACM Conference on Bioinformatics, Computational Biology and Biomedicine (ACM BCB). acceptance rate: 28%[Paper]

Sivaraman Balakrishnan, Hetunandan Kamisetty, Jaime G. Carbonell, Su-In Lee, and Christopher J. Langmead (2010). Learning Networks of Statistical Couplings in Protein Fold Families using L1-regularization. Proceedings of 3DSIG Structural Bioinformatics and Computational Biophysics.

Su-In Lee, Vassil Chatalbashev, David Vickrey, and Daphne Koller (2007). Learning a Meta-Level Prior for Feature Relevance from Multiple Related Tasks. Proceedings of International Conference on Machine Learning (ICML). acceptance rate: 20% [Paper]

Su-In Lee, Varun Ganapathi, and Daphne Koller (2007). Efficient Structure Learning of Markov Networks using L1-Regularization. Proceedings of Neural Information Processing Systems (NeurIPS). acceptance rate: 24% [Paper] [Bibtex]

Su-In Lee, Honglak Lee, Pieter Abbeel, and Andrew Y. Ng (2006). Efficient L1 Regularized Logistic Regression. Proceedings of the 21th National Conference on Artificial Intelligence (AAAI). (acceptance rate: 21%) [Paper] [Bibtex] [Software]

Su-In Lee, and Serafim Batzoglou (2004). ICA-based Clustering of Genes from Microarray Expression Data. Proceedings of Neural Information Processing Systems (NeurIPS). (acceptance rate: 27.6%) [Paper] [Bibtex]

S.-I. Lee, and S.-Y. Lee (2000). Top-Down Attention Control at Feature Selection. Proceedings of IEEE International Workshop on Biologically Motivated Computer Vision (BMCV).[Bibtex]

Workshop Papers

Ayse Dincer, Safiye Celik, Nao Hiranuma, and Su-In Lee*. DeepProfile: Deep learning of cancer molecular profiles for precision medicine. [Short Paper in bioRxiv] ICML 2018 Workshop on Computational Biology

Joseph D. Janizek, Safiye Celik, and Su-In Lee*. MERGE-Combo: Explainable machine learning prediction of synergistic drug combinations for precision cancer medicine. [Short Paper in bioRxiv] ICML 2018 Workshop on Computational Biology

Nicasia Bebee-Wang, Safiye Celik, and Su-In Lee*. MD-AD: Multi-task deep learning for Alzheimer’s disease neuropathology. [Short Paper in bioRxiv] ICML 2018 Workshop on Computational Biology

Hugh Chen, Scott M. Lundberg, and Su-In Lee. Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data. Neural Information Processing Systems (NeurIPS) 2017 Workshop ML4H: Machine Learning for Health

Nao Hiranuma, Scott Lundberg, and Su-In Lee. DeepATAC: A deep-learning method to estimate regulatory factor binding activity from ATAC-seq signals. International Conference on Machine Learning (ICML) 2017 Workshop on Computational Biology [Paper]

Scott Lundberg, and Su-In Lee. An unexpected unity among methods for interpreting model predictions. Neural Information Processing Systems (NeurIPS) 2016 Workshop "Interpretable Machine Learning for Complex Systems." [Short Paper] [Software]

  • Received the Best Paper Award.

Safiye Celik, Benjamin Logsdon, and Su-In Lee (2013). Sparse Estimation of Module Gaussian Graphical Models with Applications to Cancer Systems Biology. NeurIPS Workshop on Machine Learning in Computational Biology. acceptance rate (oral) 20.45% [Link]

Ka Yee Yeung, C. Anthony Blau, Vivian Oehler, Su-In Lee, Christopher Miller, Sylvia Chien, Timothy Martins, Elihu Estey and Pamela Becker (2013). Personalized Approach To Treatment of Acute Myeloid Leukemia Using a High-Throughput Chemosensitivity Assay. American Society of Hematology Annual Meeting. Blood 122 (21). acceptance rate (oral) 10% [Link]

Min Fang, Scott McElhone, Xin Zhao, Barry Storer, Su-In Lee, C. Anthony Blau, Vivian Oehler, Elihu Estey, Frederick Appelbaum, and Pamela Becker (2013). Proof-Of-Concept Study For Precision Medicine With Chromosome Genomic Array Testing (CGAT) For Drug Sensitivity Screening In Acute Myeloid Leukemia. American Society of Hematology Annual Meeting. Blood 122 (21). acceptance rate (poster) 20% [Link]

Mohammad Javad Hosseini, Noah A. Smith, and Su-In Lee. Detecting Multiword Expressions and Supersenses using Double-Chained Conditional Random Fields. NAACL Workshop SemEval 2016 Task10: Detecting Minimal Semantic Units and their Meanings. [Short Paper]

Scott M. Lundberg, William B. Tu, Brian Raught, Linda Z. Penn, Michael M. Hoffman, and Su-In Lee (2015). Learning the human chromatin network from all ENCODE ChIP-seq data. NeurIPS Workshop on Machine Learning in Computational Biology. acceptance rate (oral presentation) 20.9%

Mohammad Javad Hosseini, and Su-In Lee (2015). Gaussian graphical models with overlapping blocks. NeurIPS Workshop on Machine Learning in Computational Biology. acceptance rate (spotslight presentation) 30%

Su-In Lee, Benjamin Logsdon, Akanksha Saxena, Vivian Oehler, Chris P. Miller, C. Anthony Blau, and Pamela Becker (2014). Big Data Approach to Identify Molecular Basis for Drug Sensitivity Phenotypes in Acute Myeloid Leukemia. American Society of Hematology Annual Meeting. acceptance rate (oral) 13% Blood 124:265. [Link]

Benjamin Logsdon, Andrew Gentles, Chris Miller, C. Anthony Blau, Pamela Becker, and Su-In Lee (2014). Identifying expression drivers in gene expression data. NeurIPS Workshop on Machine Learning in Computational Biology. acceptance rate (oral) 30% best-scoring paper [Link]

Maxim Grechkin, and Su-In Lee (2013). Identifying Perturbed Genes in the Regulatory Networks from Gene Expression Data. NeurIPS Workshop on Machine Learning in Computational Biology. acceptance rate (oral) 20.45% [Link]