Skip to content

Bio

profile

I am the Director of Frontier Research at Prescient Design, a Genentech Accelerator, where I co-lead a team working on machine learning for scientific discovery.

Previously, I was Head of Machine Learning at Pfizer R&D, where I built and led a research group focused on developing methods for problems in drug discovery including better adaptation for generative models and active learning. My background is in statistical machine learning and neuroscience, having worked on my Ph.D. in Computer Science and Statistics. I finished my graduate studies at Columbia University and undergraduate studies at Cornell University.



Publications


OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization
Gustaf Ahdritz, Nazim Bouatta, Sachin Kadyan, Qinghgui Xia, William Gerecke, Timothy J O'Donnell, Daniel Berenberg, Ian Fisk, Niccolò Zanichelli, Bo Zhang, Arkadiusz Nowaczynski, Bei Wang, Marta M Stepniewska-Dziubinska, Shang Zhang, Adegoke Ojewole, Murat Efe Guney, Stella Biderman, Andrew M Watkins, Stephen Ra, Pablo Ribalta Lorenzo, Lucas Nivon, Brian Weitzner, Yih-En Andrew Ban, Peter K Sorger, Emad Mostaque, Zhao Zhang, Richard Bonneau, Mohammed AlQuraishi
bioRxiv, 2022
Paper | Code


Learning causal representations of single cells via sparse mechanism shift modeling
Romain Lopez, Nataša Tagasovska, Stephen Ra, Kyunghyn Cho, Jonathan K. Pritchard, Aviv Regev
NeurIPS Causal Machine Learning for Real-World Impact Workshop, 2022
Paper


A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences
Nataša Tagasovska, Nathan C. Frey, Andreas Loukas, Isidro Hötzel, Julien Lafrance-Vanasse, Ryan Lewis Kelly, Yan Wu, Arvind Rajpal, Richard Bonneau, Kyunghyun Cho, Stephen Ra, Vladimir Gligorijević
NeurIPS AI for Science Workshop, 2022
Paper | Poster


PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design
Ji Won Park, Samuel Stanton, Saeed Saremi, Andrew Watkins, Henri Dwyer, Vladimir Gligorijević, Richard Bonneau, Stephen Ra, Kyunghyun Cho
NeurIPS AI for Science Workshop, 2022
Paper | Poster


EquiFold: Protein structure prediction with a novel coarse-grained representation
Jae Hyeon Lee, Payman Yadollahpour, Andrew Watkins, Nathan C. Frey, Andrew Leaver-Fay, Stephen Ra, Kyunghyun Cho, Vladimir Gligorijević, Richard Bonneau, Aviv Regev, Richard Bonneau
NeurIPS Machine Learning for Structural Biology Workshop, 2022 (Selected Talk)
Paper | Code


Multi-segment preserving sampling for deep manifold sampler
Daniel Berenberg, Jae Hyeon Lee, Simon Kelow, Ji Won Park, Andrew Watkins, Vladimir Gligorijević, Richard Bonneau, Stephen Ra, Kyunghyun Cho
ICLR Machine Learning for Drug Discovery Workshop, 2022 (Selected Talk)
Paper | Poster


Function-guided protein design by deep manifold sampling
Vladimir Gligorijević, Daniel Berenberg, Stephen Ra, Andrew Watkins, Simon Kelow, Kyunghyun Cho, and Richard Bonneau
NeurIPS Machine Learning for Structural Biology Workshop, 2021 (Selected Talk)
Paper | Poster


Black box recursive translations for molecular optimization
Farhan Damani, Vishnu Sresht, Stephen Ra
NeurIPS Machine Learning for Molecules Workshop, 2020
Paper | Poster


Deep learning of representations for transcriptomics-based phenotype prediction
Aaron M. Smith, Jonathan R. Walsh, John Long, Craig B. Davis, Peter Henstock, Martin R. Hodge, Mateusz Maciejewski, Xinmeng Jasminue Mu, Stephen Ra, Shanrong Zhao, Daniel Ziemek, Charles K. Fisher
BMC Bioinformatics, 2020 & NeurIPS Learning Meaningful Representations of Life Workshop, 2019 (Oral Presentation)
Paper | Code | Data | Poster | Video


FAAH genetic variation enhances frontoamygdala function in mouse and human
Iva Dincheva, Andrew T. Drysdale, Catherine A. Hartley, David C. Johnson, Deqiang Jing, Elizabeth C. King, Stephen Ra, J. Megan Gray, Ruirong Yang, Ann Marie DeGruccio, Chienchun Huang, Charles E. Glatt, Matthew N. Hill, B.J. Casey, Francis Lee
Nature Communications, 2015; 6, 6395. doi:10.1038/ncomms7395
Paper | NYTimes Op-Ed


Forebrain elimination of cacna1c mediates anxiety-like behavior in mice
Anni S. Lee1, Stephen Ra1, Aditi M. Rajadhyaksha, Jeremiah K. Britt, Héctor De Jesús-Cortés, KL Gonzales, Amy Lee, Sven Moosmang, Franz Hofmann, Andrew A. Pieper, Anjali M. Rajadhyaksha
Nature Molecular Psychiatry, 2012; 17, 1054-55. doi:10.1038/mp.2012.71
Paper


  1. Equal contribution