Subjects

- Computational science

- Computer science

Abstract

The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experiments1. To address this, we present Empirical Research Assistance (ERA), an AI system that creates expert-level scientific software whose goal is to maximize a quality metric. The system uses a Large Language Model (LLM) and Tree Search (TS)2 to systematically improve the quality metric and intelligently navigate the large space of possible solutions. ERA achieves expert-level results when it explores and integrates complex research ideas from external sources. The effectiveness of tree search is demonstrated across a diverse range of tasks. In bioinformatics, ERA discovered 40 novel methods for single-cell data analysis that outperformed the top human-developed methods on a public leaderboard. In epidemiology, ERA generated 14 models that outperformed the CDC ensemble and all other individual models for forecasting COVID-19 hospitalizations. ERA also produced expert-level software for geospatial analysis, neural activity prediction in zebrafish, and numerical solution of integrals, and a novel rule-based construction for time series forecasting. By devising and implementing novel solutions to diverse tasks, ERA represents a significant step towards accelerating scientific progress.

You have full access to this article via your institution.

Download PDF

Author information

Author notes- These authors contributed equally: Eser Aygün, Anastasiya Belyaeva, Gheorghe Comanici, Marc Coram, Hao Cui, Jake Garrison, Renee Johnston, Anton Kast, Cory Y. McLean, Peter Norgaard, Zahra Shamsi, David Smalling, James Thompson, Subhashini Venugopalan, Brian P. Williams

Authors and Affiliations

- Google DeepMind, Montréal, Quebec, Canada

Eser Aygün, Gheorghe Comanici, David Smalling, Anna Bulanova & Shibl Mourad

- Google Research, Cambridge, MA, USA

Anastasiya Belyaeva, Marc Coram, Hao Cui, Renee Johnston, Anton Kast, Cory Y. McLean, Peter Norgaard, Zahra Shamsi, James Thompson, Subhashini Venugopalan, Brian P. Williams, Chujun He, Sarah Martinson, Martyna Plomecka, Lai Wei, Yuchen Zhou, Qian-Ze Zhu, Matthew Abraham, Erica Brand, Jeffrey A. Cardille, Chris Co, Scott Ellsworth, Grace Joseph, Malcolm Kane, Ryan Krueger, Johan Kartiwa, Dan Liebling, Jan-Matthis Lueckmann, Paul Raccuglia, Xuefei Julie Wang, Katherine Chou, James Manyika, Yossi Matias, John C. Platt, Lizzie Dorfman & Michael P. Brenner

- Google Platforms and Devices, Mountain View, CA, USA

Jake Garrison

- Massachusetts Institute of Technology, Cambridge, MA, USA

Chujun He

- School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA

Sarah Martinson, Qian-Ze Zhu, Ryan Krueger & Michael P. Brenner

- Google DeepMind, New York, New York, USA

Martyna Plomecka

- Faculty of Agricultural and Environmental Sciences, McGill University, Montréal, Quebec, Canada

Jeffrey A. Cardille

- California Institute of Technology, Pasadena, CA, USA

Xuefei Julie Wang

Authors- Eser AygünView author publications