Hi,

I am a Research Scientist at Google DeepMind. I use machine learning for translating between protein sequences and natural language (see ProtNLM).

I have a Ph.D. from MIT CSAIL, where I worked on machine learning (generative models, perturbation models), supervised by Prof. Tommi Jaakkola.

My Research

Preprints

• ProtEx: A Retrieval-Augmented Approach for Protein Function Prediction
  Peter Shaw, Bhaskar Gurram, David Belanger, Andreea Gane, Maxwell Bileschi, Lucy Colwell, Kristina Toutanova, Ankur Parikh
  Preprint, 2024
  


• ProtNLM: Model-based Natural Language Protein Annotation
  Andreea Gane*, Maxwell L. Bileschi*, David Dohan, Elena Speretta, Amélie Héliou, Laetitia Meng-Papaxanthos, Hermann Zellner, Eugene Brevdo, Ankur P. Parikh, Maria J. Martin, Sandra Orchard, UniProt Collaborators, Lucy Colwell
  Preprint, 2022
  (See also our UniProt page, blog post, YouTube video, invited talk)
  

Published Work

• Improving Protein Function Annotation via Unsupervised Pre-training: Robustness, Efficiency, and Insights
  David Dohan, Andreea Gane, Max Bileschi, David Belanger, Lucy Colwell
  Knowledge Discovery in Databases, Applied Data Science Track (KDD), 2021
  


• Rethinking Attention with Performers
  Krzysztof Choromanski*, Valerii Likhosherstov*, David Dohan*, Xingyou Song*, Andreea Gane*, Tamas Sarlos*, Peter Hawkins*, Jared Davis*, Afroz Mohiuddin, Lukasz Kaiser, David Belanger, Lucy Colwell, Adrian Weller
  International Conference on Learning Representations (ICLR), 2021
  (See also our Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers)
  


• Population-Based Optimization for Biological Sequence Design
  Christof Angermueller, David Belanger, Andreea Gane, Zelda Mariet, David Dohan, Kevin Murphy, D. Sculley, Lucy Colwell
  International Conference on Machine Learning (ICML), 2020
  


• Direct Optimization through argmax for Discrete Variational Auto-Encoder
  Guy Lorberbom, Andreea Gane, Tommi Jaakkola, Tamir Hazan
  Neural Information Processing Systems (NeurIPS), 2019
  


• A Comparison of Generative Models for Sequence Design
  Andreea Gane, David Belanger, David Dohan, Christof Angermueller, Ramya Deshpande, Suhani Vora, Olivier Chapelle, Babak Alipanahi, Lucy Colwell
  Machine Learning in Computational Biology (MLCB), 2019
  


• Few-shot Learning With Variational Homoencoders
  Luke Hewitt, Maxwell Nye, Andreea Gane, Tommi Jaakkola, Joshua B. Tenenbaum
  The Conference on Uncertainty in Artificial Intelligence (UAI), 2018
  


• Evaluating prerequisite qualities for learning end-to-end dialog systems
  Jesse Dodge*, Andreea Gane*, Xiang Zhang*, Antoine Bordes, Sumit Chopra, Alexander Miller, Arthur Szlam, Jason Weston
  International Conference on Learning Representations (ICLR), 2016
  


• Learning with Maximum A-Posteriori Perturbation Models
  Andreea Gane, Tamir Hazan, Tommi S Jaakkola
  Artificial Intelligence and Statistics (AISTATS), 2014
  

Contributed Chapters

• Learning with Maximum A-Posteriori Perturbation Models
  Andreea Gane, Tamir Hazan, Tommi S Jaakkola
  Perturbations, Optimization, and Statistics, 2016