John Ingraham (original) (raw)

Update: I am currently at the startup FVL56, Inc.

At the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) I was a postdoc working with Tommi Jaakkola and Regina Barzilay as part of the MLPDS consortium. We worked to accelerate the process of molecular and macromolecular design and discovery with structured machine learning models.

Previously, I was a PhD student in Debora Marks' lab at Harvard Medical School. We focused on building probabilistic models of deep evolutionary variation in proteins and RNAs to better decode how the structure, function, and physiological relevance of biomolecules is encoded in their genetic sequence.

[Google Scholar] [Github]

Selected Preprints and Publications

• Generative Models for Graph-Based Protein Design
  John Ingraham, Vikas K. Garg, Regina Barzilay, Tommi Jaakkola
  Neural Information Processing Systems (NeurIPS), 2019
• Learning protein structure with a differentiable simulator
  John B Ingraham, Adam Riesselman, Chris Sander, Debora S Marks
  International Conference on Learning Representations (ICLR), 2019
• Deep generative models of genetic variation capture the effects of mutations
  Adam Riesselman*, John B Ingraham*, Debora S Marks
  Nature Methods, 2018
• Mutation effects predicted from sequence co-variation
  Thomas A Hopf*, John B Ingraham*, Frank J Poelwijk, Charlotta PI Schärfe, Michael Springer, Chris Sander, Debora S Marks
  Nature Biotechnology, 2017
• Variational Inference for Sparse and Undirected Models
  John Ingraham, Debora Marks
  International Conference on Machine Learning (ICML), 2017