Wengong Jin

PhD Student, MIT CSAIL

wengong [AT] csail.mit.edu

Bio

I am a Ph.D. student in MIT CSAIL advised by Regina Barzilay and Tommi Jaakkola .

My research seeks to develop novel machine learning algorithms for structured data and utilize them to automate molecular science such as drug discovery, material design, and green chemistry. I am particularly interested in deep generative models and graph neural networks.

News

  • [2020/10] I gave a talk at AI Cures Drug Discovery Conference. We discovered two new synergistic drug combinations for COVID: [Paper]
  • [2020/06] I gave a talk at New York Academy of Science: [link]
  • [2020/02] Paper A deep learning approach to antibiotic discovery is accepted to Cell. Our paper is covered by MIT News Nature Science BBC News Guardian GovTech Innovators Financial Times STAT
  • Publications

    Most recent publications on Google Scholar.
    indicates equal contribution.

    A Deep Learning Approach to Antibiotic Discovery

    Jonathan M. Stokes, Kevin Yang, Kyle Swanson, Wengong Jin, Andres Cubillos-Ruiz, Nina M. Donghia, Craig R. MacNair, Shawn French, Lindsey A. Carfrae, Zohar Bloom-Ackerman, Victoria M. Tran, Anush Chiappino-Pepe, Ahmed H. Badran, Ian W. Andrews, Emma J. Chory, George M. Church, Eric D. Brown, Tommi S. Jaakkola, Regina Barzilay, James J. Collins

    Cell 2020

    Discovering Synergistic Drug Combinations for COVID with Biological Bottleneck Models

    Wengong Jin, Regina Barzilay, Tommi Jaakkola

    NeurIPS Machine Learning for Molecules Workshop 2020

    Multi-Objective Molecule Generation using Interpretable Substructures

    Wengong Jin, Regina Barzilay, Tommi Jaakkola

    International Conference on Machine Learning (ICML) 2020

    Hierarchical Generation of Molecular Graphs using Structural Motifs

    Wengong Jin, Regina Barzilay, Tommi Jaakkola

    International Conference on Machine Learning (ICML) 2020

    Learning Multimodal Graph-to-Graph Translation for Molecular Optimization

    Wengong Jin, Kevin Yang, Regina Barzilay, Tommi Jaakkola

    International Conference on Learning Representations (ICLR) 2019

    Junction Tree Variational Autoencoder for Molecular Graph Generation

    Wengong Jin, Regina Barzilay, Tommi Jaakkola

    International Conference on Machine Learning (ICML) 2018

    Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network

    Wengong Jin, Connor W. Coley, Regina Barzilay, Tommi Jaakkola

    Neural Information Processing Systems (NIPS) 2017

    Deriving Neural Architectures from Sequence and Graph Kernels

    Tao Lei, Wengong Jin, Regina Barzilay, Tommi Jaakkola

    International Conference on Machine Learning (ICML) 2017

    A Deep Learning Approach to Antibiotic Discovery

    Jonathan M. Stokes, Kevin Yang, Kyle Swanson, Wengong Jin, Andres Cubillos-Ruiz, Nina M. Donghia, Craig R. MacNair, Shawn French, Lindsey A. Carfrae, Zohar Bloom-Ackerman, Victoria M. Tran, Anush Chiappino-Pepe, Ahmed H. Badran, Ian W. Andrews, Emma J. Chory, George M. Church, Eric D. Brown, Tommi S. Jaakkola, Regina Barzilay, James J. Collins

    Cell 2020

    Discovering Synergistic Drug Combinations for COVID with Biological Bottleneck Models

    Wengong Jin, Regina Barzilay, Tommi Jaakkola

    NeurIPS Machine Learning for Molecules Workshop 2020

    Enforcing Predictive Invariance across Structured Biomedical Domains

    Wengong Jin, Regina Barzilay, Tommi Jaakkola

    preprint

    Multi-Objective Molecule Generation using Interpretable Substructures

    Wengong Jin, Regina Barzilay, Tommi Jaakkola

    International Conference on Machine Learning (ICML) 2020

    Hierarchical Generation of Molecular Graphs using Structural Motifs

    Wengong Jin, Regina Barzilay, Tommi Jaakkola

    International Conference on Machine Learning (ICML) 2020

    Improving Molecular Design by Stochastic Iterative Target Augmentation

    Kevin Yang, Wengong Jin, Kyle Swanson, Regina Barzilay, Tommi Jaakkola

    International Conference on Machine Learning (ICML) 2020

    Functional Transparency for Structured Data: a Game-Theoretic Approach

    Guang-He Lee, Wengong Jin, David Alvarez-Melis, Tommi Jaakkola

    International Conference on Machine Learning (ICML) 2019

    Learning Multimodal Graph-to-Graph Translation for Molecular Optimization

    Wengong Jin, Kevin Yang, Regina Barzilay, Tommi Jaakkola

    International Conference on Learning Representations (ICLR) 2019

    A graph-convolutional neural network model for the prediction of chemical reactivity

    Connor W Coley, Wengong Jin, Luke Rogers, Timothy F Jamison, Tommi S Jaakkola, William H Green, Regina Barzilay, Klavs F Jensen

    Chemical Science

    Analyzing learned molecular representations for property prediction

    Kevin Yang, Kyle Swanson, Wengong Jin, Connor Coley, Philipp Eiden, Hua Gao, Angel Guzman-Perez, Timothy Hopper, Brian Kelley, Miriam Mathea, Andrew Palmer, Volker Settels, Tommi Jaakkola, Klavs Jensen, Regina Barzilay

    Journal of chemical information and modeling

    Junction Tree Variational Autoencoder for Molecular Graph Generation

    Wengong Jin, Regina Barzilay, Tommi Jaakkola

    International Conference on Machine Learning (ICML) 2018

    Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network

    Wengong Jin, Connor W. Coley, Regina Barzilay, Tommi Jaakkola

    Neural Information Processing Systems (NIPS) 2017

    Deriving Neural Architectures from Sequence and Graph Kernels

    Tao Lei, Wengong Jin, Regina Barzilay, Tommi Jaakkola

    International Conference on Machine Learning (ICML) 2017

    Talks

  • Predictive models for searching COVID-19 drug combinations, AI Cures Drug Discovery Conference, Oct 2020
  • Graph Neural Networks for Drug Discovery, Neurosymbolic.org, Oct 2020
  • Domain Extrapolation via Regret Minimization, MIT Machine Learning Tea, Aug 2020
  • Deep Learning for Drug Discovery, New York Academy of Science, May 2020
  • Hierarchical Generation of Molecular Graphs using Structural Motifs,Aggregate Intellect Socratic Circles (AISC), Mar 2020
  • Representation and Generation of Molecular Graphs, MIT Computational Fabrication Group, Feb 2020
  • Representation and Generation of Molecular Graphs, NeurIPS 2019 Graph Representation Learning Workshop
  • Hierarchical Graph-to-Graph Translation for Molecules, MIT Machine Learning Tea 2019
  • Hierarchical Graph-to-Graph Translation for Molecules, IBM AI Research Week 2019
  • A Graph Translation Approach for Molecular Optimization, NeurIPS 2018 Machine Learning for Molecules and Materials Workshop
  • Learning to Generate Graphs, MIT NetMIT Group, Oct 2018
  • Graph Representation Learning for Chemistry, MILA Tea Talk, Montreal, Aug 2018
  • Junction Tree Variational Autoencoder for Molecular Graph Generation, ICML 2018
  • Junction Tree Variational Autoencoder for Molecular Graph Generation, MIT Speech Group, Mar 2018
  • Deriving Neural Architectures from Sequence and Graph Kernels, ICML 2017
  • Vitæ

    Acknowledgement
    This website was built with jekyll based on a template by Martin Saveski