A community-powered search of machine learning strategy space to find NMR property prediction models.

• Main Authors: Lars A Bratholm, Will Gerrard, Brandon Anderson, Shaojie Bai, Sunghwan Choi, Lam Dang, Pavel Hanchar, Addison Howard, Sanghoon Kim, Zico Kolter, Risi Kondor, Mordechai Kornbluth, Youhan Lee, Youngsoo Lee, Jonathan P Mailoa, Thanh Tu Nguyen, Milos Popovic, Goran Rakocevic, Walter Reade, Wonho Song, Luka Stojanovic, Erik H Thiede, Nebojsa Tijanic, Andres Torrubia, Devin Willmott, Craig P Butts, David R Glowacki
• Format: Article
• Language: English
• Published: Public Library of Science (PLoS) 2021-01-01
• Series: PLoS ONE
• Online Access: https://doi.org/10.1371/journal.pone.0253612

The rise of machine learning (ML) has created an explosion in the potential strategies for using data to make scientific predictions. For physical scientists wishing to apply ML strategies to a particular domain, it can be difficult to assess in advance what strategy to adopt within a vast space of possibilities. Here we outline the results of an online community-powered effort to swarm search the space of ML strategies and develop algorithms for predicting atomic-pairwise nuclear magnetic resonance (NMR) properties in molecules. Using an open-source dataset, we worked with Kaggle to design and host a 3-month competition which received 47,800 ML model predictions from 2,700 teams in 84 countries. Within 3 weeks, the Kaggle community produced models with comparable accuracy to our best previously published 'in-house' efforts. A meta-ensemble model constructed as a linear combination of the top predictions has a prediction accuracy which exceeds that of any individual model, 7-19x better than our previous state-of-the-art. The results highlight the potential of transformer architectures for predicting quantum mechanical (QM) molecular properties.