2020
Beyond user self-reported Likert scale ratings: a comparison model for automatic dialog evaluation. [PDF]
Weixin Liang, James Zou, Zhou Yu.
Annual Conference of the Association of Computational Linguistics (ACL 2020).
PB-Net: automatic peak integration by sequential deep learning for multiple reaction monitoring. [PDF]
Zhenqin Wu, Daniel Serie, Gege Xu, James Zou.
Journal of Proteomics (2020).
RNA-GPS predicts RNA subcellular localization and highlights the role of splicing. [PDF]
Kevin Wu, Kevin Parker, Furqan Fazal, Howard Chang, James Zou.
RNA (2020).
Video-based AI for beat-to-beat assessment of cardiac function. [PDF]
David Ouyang, Bryan He, Amirata Ghorbani, N. Yuan, J. Ebinger, C. Langlotz, P. Heidenrich, R. Harrington, D. Liang, E. Ashley, James Zou.
Nature (2020).
A benchmark of algorithms for the analysis of pooled CRISPR screens. [PDF]
Sunil Bodapati, Tim Daley, Xueqiu Lin, James Zou*, Lei Qi*.
Genome Biology (2020).
An online platform for interactive feedback in biomedical machine learning. [PDF]
Abubakar Abid, Ali Abdalla, Ali Abid, Dawood Khan, Abdulrahman Alfozan, James Zou.
Nature Machine Intelligence (2020).
Learning transport cost from subset correspondence. [PDF]
Ruishan Liu, Akshay Balsubramani, James Zou.
International Conference on Learning Representations (ICLR 2020).
Deep learning interpretation of echocardiograms. [PDF]
Amirata Ghorbani, David Ouyang, Abubakar Abid, Bryan He, Jonathan Chen, Robert Harrington, David Liang, Euan Ashley, James Zou.
Nature Digital Medicine (2020).
LitGen: genetic literature recommendation guided by human explanations.
Allen Nie, et al., James Zou.
Pacific Symposium on Biocomputing (PSB 2020).
2019
Sex and gender analysis improves science and engineering. [PDF]
Cara Tannenbaum*, Robert Ellis*, Friederike Eyssel*, James Zou*, Londa Schiebinger.
Nature (2019). *co-first authors
Making AI forget you: data deletion in machine learning. [arXiv]
Tony Ginart, Melody Guan, Greg Valiant, James Zou.
NeurIPS (2019). Selected for spotlight talk (top 3% of submissions).
Toward automatic concept based explanations. [PDF]
Amirata Ghorbani, James Wexler, James Zou, Been Kim.
NeurIPS (2019).
How much does your data exploration overfit? Controlling bias via information usage. [arXiv]
Daniel Russo, James Zou.
IEEE Transactions on Information Theory (2019).
Large dataset enables prediction of repair after CRISPR-Cas9 editing in primary T cells. [arXiv]
Ryan Leenay, Amirali Aghazadeh, Joseph Hiatt, David Tse, Theo Roth, Ryan Apathy, Eric Shifrut, Judd Hulquist, Nevan Krogan, Zhenqin Wu, Giana Cirolia, Hera Canaj, Manu Leonetti, Alex Marson, Andrew May, James Zou.
Nature Biotechnology (2019).
AdaFDR: a Fast, Powerful and Covariate-Adaptive Approach for Multiple Hypothesis Testing. [arXiv]
Martin Zhang, Fei Xia, James Zou.
Nature Communications (2019). Preliminary version won the RECOMB Best Paper Award.
VetTag: improving automated veterinary diagnosis coding via large-scale language modeling. [arXiv]
Yuhui Zhang, Allen Nie, Ashley Zehnder, Rodney Page, James Zou.
Nature Digital Medicine (2019).
Data Shapley: Equitable Data Valuation for Machine Learning. [arXiv]
Amirata Ghorbani, James Zou.
ICML (2019).
Concrete Autoencoders for Differentiable Feature Selection and Reconstruction. [arXiv]
Abubakar Abid, Muhammad Balin, James Zou.
ICML (2019).
Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits. [arXiv]
Martin Zhang, James Zou, David Tse.
ICML (2019).
Discovering Conditionally Salient Features with Statistical Guarantees.
Jaime Roquero, James Zou.
ICML (2019).
Contrastive multivariate singular spectrum analysis. [arXiv]
Abdi-Hakin Dirie, Abubakar Abid, James Zou.
IEEE Allerton (2019). Preliminary version selected for spotlight at NIPS'18 Spatio-temporal Workshop.
A Knowledge Graph-based Approach for Exploring the U.S. Opioid Epidemic.
Maulik Kamdar, Tymor Hamansy, Shea Zhao, Ayin Vala, Tome Eftimov, James Zou, Suzanne Tamang.
ICLR AI for Social Good (2019). Best Poster Award.
Modeling spatial correlation of transcripts with application to pancreas development. [PDF]
Ruishan Liu, Marco Mignardi, Robert Jones, Martin Enge, Seung Kim, Steve Quake, James Zou.
Scientific Reports (2019).
Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings.
Dora Demszky, Nikhil Garg, Rob Voigt, James Zou, Jesse Shapiro, Matthew Gentzkow, Dan Jurafsky
NAACL (2019). Washington Post coverage.
Interpretation of neural network is fragile. [arXiv]
Amirata Ghorbani, Abubakar Abid, James Zou.
AAAI (2019). Selected for oral presentation.
Improving knockoff stability: simultaneous multiple knockoffs and entropy maximization. [arXiv]
Jaime Gimenez, James Zou.
AISTATS (2019).
Knockoffs for the mass: new feature importance statistics with false discovery guarantees. [arXiv]
Jaime Gimenez, Amirata Ghorbani, James Zou.
AISTATS (2019).
Feedback GAN for DNA optimizes protein functions. [PDF]
Anvita Gupta, James Zou.
Nature Machine Intelligence (2019).
Multiaccuracy: black-box post-processing for fairness in classification. [PDF]
Michael Kim, Amirata Ghorbani, James Zou.
ACM/AAAI Conference of AI Ethics and Society (2019).
Contingent Payment Mechanisms for Resource Utilization.
Hongyao Ma, Reshef Meir, David Parkes, James Zou.
18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS) (2019). Finalist for Best Paper Award.
A large CRISPR-induced bystander mutation causes immune dysregulation. [PDF]
Dimitre Simeonov et al.
Communications Biology (2019).
2018
DeepTag: inferring diagnoses from veterinary clinical notes. [PDF] [press]
Allen Nie, Ashley Zehnder, Rodney Page, Y. Zhang, A. Pineda, M. Rivas, C. Bustamante, James Zou.
Nature Digital Medicine (2018).
A primer on deep learning in genomics. [PDF]
James Zou, Mikael Huss, Abubakar Abid, Pejman Mohammadi, Ali Torkamani, Amalio Telenti.
Nature Genetics (2018).
Design AI so that it's fair. [PDF]
James Zou and Londa Schiebinger.
Nature (2018).
Autowarp: learning a warping distance from unlabeled time series using sequence autoencoders. [PDF]
Abubakar Abid, James Zou.
NIPS (2018).
Stochastic EM for shuffled linear regression. [arXiv]
Abubakar Abid, James Zou.
IEEE Allerton (2018).
Minimizing close-k aggregate loss improves classification. [arXiv]
Bryan He, James Zou.
Under submission (2018).
Exploring patterns enriched in a dataset with contrastive principal component analysis. [PDF]
Abubakar Abid, Vivek Bagaria, Martin Zhang, James Zou.
Nature Communications (2018). ICML CompBio Workshop Top Paper Award Winner.
Word embeddings quantify 100 years of gender and ethnic stereotypes. [PDF]
Nikhil Garg, Londa Schiebinger, Dan Jurafsky, James Zou.
Proceedings of the National Academy of Sciences (2018).
CoVeR: learning covariate-specific vector representations with tensor decompositions. [arXiv]
Kevin Tian, Teng Zhang, James Zou.
International Conference of Machine Learning (ICML 2018).
Predicting target genes of non-coding regulatory variants with ICE.
Michael Wu, Nilah Ioannidis and James Zou.
Under submission (2018).
The clinical imperative for inclusivity: race, ethnicity and ancestry in genomics.
Alice Popejoy et al.
Human Mutation (2018).
Why adaptively collected data has negative bias and how to correct for it. [arXiv]
Xinkun Nie, Xiaoying Tian-Harris, Jonathan Taylor, James Zou.
AISTATS 2018. ICML Workshop on Picky Learners Best Paper Award.
Embedding for missingness: deep learning with incomplete data.
Amirata Ghorbani, James Zou.
IEEE Allerton (2018).
The effects of memory replay in reinforcement learning. [arXiv]
Ruishan Liu and James Zou. Best Poster Award at BayLearn.
IEEE Allerton (2018).
The proteome of malaria plastid organelle, a key anti-parasitic target. [arXiv]
Michael J Boucher, Sreejoyee Ghosh, Lichao Zhang, Avantika Lal, Se Won Jang, An Ju, Shuying Zhang, Xinzi Wang, Stuart A Ralph, James Zou, Joshua E Elias, Ellen Yeh.
PLoS Biology (2018).
2017
Mutation-convolution-max layers enhance deep learning of DNA motifs.
Abubakar Abid, Amirata Ghorbani, James Zou.
NIPS Machine Learning for CompBio Workshop (NIPS MLCB 2017). Spotlight paper
NeuralFDR: learning decision threshold from hypothesis features.
Martin Zhang, Fei Xia, James Zou, David Tse.
Neural Information Processing Systems (NIPS 2017).
Linear regression with shuffled labels. [arXiv]
Abubakar Abid, Ada Poon, James Zou.
Submitted 2017.
Estimating the unseen from multiple populations. [arXiv]
Aditi Rangunathan, Greg Valiant, James Zou.
International Conference on Machine Learning (ICML 2017).
Learning latent space models with angular constraints. [arXiv]
Pengtao Xie, Yuntian Deng, Yi Zhou, Abhimanu Kumar, Yaoliang Yu, James Zou, Eric Xing.
International Conference on Machine Learning (ICML 2017).
Quantifying the accuracy of approximate diffusions and Markov chains. [arXiv]
Jonathan Huggins, James Zou.
AISTATS (2017).
Beyond bilingual: multi-sense word embedding using multi-lingual context. [arXiv]
Shyam Upadhyay, Kai-Wei Chang, Matt Taddy, Adam Kalai, James Zou. Representation Learning for NLP (Rep4NLP 2017). Best Paper Award.
Correcting for cell-type heterogeneity in DNA methylation: avoiding statistical flaws.
Elior Rahmani, Noah Zaitlen, Yael Baran, Celeste Eng, Donglei Hu, Joshua Galanter, Sam Oh, Esteban Burchard, Eleazar Eskin, James Zou, Eran Halperin.
Nature Methods (2017).
2016 and earlier
Computational biology
Quantifying the unobserved protein-coding variants in human populations provides a roadmap for large-scale sequencing projects. [PDF]
James Zou, Greg Valiant, Paul Valiant, Konrad Karczewski, Siu On Chan, Kaitlin Samocha, Monkol Lek, Exome Aggregation Consortium, Shamil Sunyaev, Mark Daly, Daniel MacArthur
Nature Communications (2016).
Analysis of protein-coding genetic variation in 60,706 humans. [arXiv]
Exome Aggregation Consortium.
Nature (2016).
Sparse PCA corrects for cell type heterogeneity in epigenome-wide association studies.
Elior Rahmani, Noah Zaitlen, Yael Baran, Celeste Eng, Donglei Hu, Joshua Galanter, Sam Oh, Esteban Burchard, Eleazar Eskin, James Zou, Eran Halperin.
Nature Methods (2016).
A genetic and socio-economic study of mate choice in Latinos reveals novel assortment patterns. [PDF] [Press]
James Zou, Danny Park, Esteban Burchard, Dara Torgerson, Maria Pino-Yanes, Yun Song, Sriram Sankararaman, Eran Halperin, Noah Zaitlen
Proceedings of the National Academy of Sciences 112(44):13621-6 (2015).
Inferring parental genomic ancestries using pooled semi-Markov processes. [PDF]
James Zou, Eran Halperin, Esteban Burchard, Sriram Sankararaman.
Bioinformatics 31(12):i190-6 (2015).
Correcting for sample heterogeneity in epigenome-wide association studies. [PDF]
James Zou.
Methods Mol Biol. (2015).
Undesired usage and the robust self-assembly of heterogeneous structures. [PDF]
Arvind Murugan, James Zou, Michael Brenner.
Nature Communications 11;6:6203 (2015).
Extended fertility and longevity: the genetic and epigenetic link. [PDF]
Kerem Wainer-Katsir, James Zou, Michal Linial.
Fertil Steril. 103(5):1117-24 (2015).
Epigenome-wide association studies without the need for cell-type composition. [PDF]
James Zou, Christoph Lippert, David Heckerman, Martin Aryee, Jennifer Listgarten.
Nature Methods 11(3):309-11 (2014).
Highlight talk at ISMB 2015.
Highlight talk at RECOMB 2015.
Platform presentation at the 2013 Wellcome Trust Epigenomics of Common Diseases conference.
Platform presentation at the 2013 Machine Learning in Computational Biology meeting.
Genome-wide chromatin state transitions elicited by developmental and environmental cues. [PDF]
Jiang Zhu, Mazhar Adli, James Zou, et al.
Cell 152(3):642-54 (2013).
Locus-specific chromatin inactivation at endogenous enhancers with programmable TALE-LSD1 fusions. [PDF]
Eric Mendenhall, Kaylyn Williamson, Deepak Reyon, James Zou, et al.
Nature Biotechnology 31(12):1133-6 (2013).
Getting the biggest birch for the bang: restoring and expanding upland birchwoods in the Scottish Highlands by managing red deer. [PDF]
Andrew Tanentzap, James Zou, David Coomes.
Ecology and Evolution 3(7):1890-901 (2013).
Genome-wide analysis reveals conserved and divergent features of Notch1/RBPJ binding in human and murine T-lymphoblastic leukemia cells. [PDF]
Hongfang Wang, James Zou [co-first author, corresponding author], et al.
Proceedings of the National Academy of Sciences 108(36):14908-13 (2011).
Epstein-Barr virus exploits intrinsic B-lymphocyte transcription programs to achieve immortal cell growth. [PDF]
Bo Zhao, James Zou [co-first author], et al.
Proceedings of the National Academy of Sciences 108(36):14902-7 (2011).
Canonical NF-kappaB activation is essential for Epstein-Barr virus latent membrane protein 1 TES2/CTAR2 gene regulation. [PDF]
Ben Gewurz, Jessica Mar, Megha Padi, Bo Zhao, Nicholas Shinners, Kaoru Takasaki, Edward Bedoya, James Zou, et al.
Journal of Virology 85(13):6764-73 (2011).
Epstein-Barr virus nuclear antigens 3C and 3A maintain lymphoblastoid cell growth by repressing p16INK4A and p14ARF expression. [PDF]
Seiji Maruo, Bo Zhao, Eric Johannsen, Elliott Kieff, James Zou, Kenzo Takada.
Proceedings of the National Academy of Sciences 108(5):1919-24 (2011).
Religion and HIV in Tanzania: influence of religious beliefs on HIV stigma, disclosure, and treatment attitudes.[PDF]
James Zou, Yvonne Yamanaka, et al.
BMC Public Health 9:75 (2009).
Machine learning and AI
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. [arXiv] [TechReview] [Vice] [NPR]
Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, Adam Kalai.
Neural Information Processing Systems (NIPS 2016).
Rich component analysis. [arXiv]
Rong Ge, James Zou.
International Conference on Machine Learning (ICML 2016).
Controlling bias in adaptive data analysis using information theory. [arXiv]
Daniel Russo, James Zou.
AISTATS (2016) (full oral; top 7% of submissions).
Information Theory and Applications (ITA) invited talk.
Clustering with a reject option: interactive clustering as Bayesian prior elicitation.
Akash Srivastava, James Zou, Ryan Adams, Charles Sutton.
ArXiv (2016).
Intersecting faces: non-negative matrix factorization with new guarantees. [PDF]
Rong Ge, James Zou.
International Conference on Machine Learning (ICML 2015).
Crowdsourcing feature discovery via adaptively chosen comparisons. [PDF]
James Zou, Kamalika Chaudhuri, Adam Kalai.
HCOMP (2015); CrowdML workshop (ICML 2015); Feature extraction workshop (NIPS 2015)
Invited to Journal of Machine Learning Research (JMLR) special issue (2015).
Incentive compatible experimental design. [PDF]
Panos Toulis, David Parkes, Elery Pfeffer, James Zou.
ACM Conference on Economics and Computation (EC 2015).
Approval voting behavior in Doodle. [PDF]
James Zou, Reshef Meir, David Parkes.
ACM Conference CSCW (2015). Honorable mention for best paper (top 5% of submissions).
Coordination through contingent payment mechanisms.
Hongyao Ma, Reshef Meir, David C. Parkes, James Zou.
Conference on Auctions, Market Mechanisms and Their Applications (2015). INFORMS (2015)
Contrastive learning using spectral methods. [PDF]
James Zou, Daniel Hsu, David Parkes, Ryan Adams.
Neural Information Processing Systems (NIPS 2013).
Priors for diversity in generative latent variable models. [PDF]
James Zou, Ryan Adams.
Neural Information Processing Systems (NIPS 2012).
A slime mold solver for linear programming problems. [PDF]
Anders Johannson, James Zou.
Lecture Notes in Computer Science 7318 (2012).
Get another worker? Active crowdlearning with sequential arrivals.
James Zou, David Parkes.
Proceedings of Workshop on Machine Learning in Human Computation and Crowdsourcing (ICML 2012).
Threats and trade-Offs in resource critical crowdsourcing tasks over networks. [arXiv]
Swaprava Nath, Pankaj Dayama, Dinesh Garg, Y. Narahari, James Zou.
Proceedings 8th Workshop on Internet and Network Economics (WINE 2012).
Tolerable manipulability in dynamic assignment without money. [PDF]
James Zou, Sujit Gujar, David Parkes.
Proceedings 24th AAAI Conference on Artificial Intelligence (AAAI 2010).
Dynamic House Allocation.
Sujit Gujar, James Zou, David Parkes.
Proceedings 5th Multidisciplinary Workshop on Advances in Preference Handling (MPREF 2010).