Microbiome preterm birth DREAM challenge: Crowdsourcing machine learning approaches to advance preterm birth research
Jonathan L. Golob, Tomiko Oskotsky, Alice Tang, Alennie Roldan, Verena Chung, Connie Ha, Ronald J. Wong, Kaitlin J. Flynn, Rong Chai, Claire Dubin, Antonio Párraga-Leo, Camilla Wibrand, Samuel S. Minot, Boris Oskotsky, Gaia Andreoletti, Idit Kosti, Julie Bletz, Amber Nelson, Jifan Gao, Zhoujingpeng Wei, Guanhua Chen, Zheng-Zheng Tang, Pierfrancesco Novielli, Donato Romano, Ester Pantaleo, Nicola Amoroso, A. Monaco, Mirco Vacca, Maria De Angelis, R. Bellotti, Sabina Tangaro, Zehua Wang, Jiaming Yao, Akhil Goel, Jiangyue Mao, Huiqian Wang, Yuci Zhang, Ambuj Tewari, Abigail Kuntzleman, Isaac Bigcraft, Stephen M. Techtmann, Daehun Bae, Eun Young Kim, Jongbum Jeon, Soobok Joe, Kevin R. Theis, Sherrianne Ng, Yun Sok Lee, Patricia Díaz-Gimeno, Phillip R. Bennett, David A. MacIntyre, Gustavo Stolovitzky, Susan V. Lynch, Jake Albrecht, Nardhy Gomez‐Lopez, Roberto Romero, David K. Stevenson, Nima Aghaeepour, Adi L. Tarca, James C. Costello, Marina Sirota
Abstract
Every year, 11% of infants are born preterm with significant health consequences, with the vaginal microbiome a risk factor for preterm birth. We crowdsource models to predict (1) preterm birth (PTB; <37 weeks) or (2) early preterm birth (ePTB; <32 weeks) from 9 vaginal microbiome studies representing 3,578 samples from 1,268 pregnant individuals, aggregated from public raw data via phylogenetic harmonization. The predictive models are validated on two independent unpublished datasets representing 331 samples from 148 pregnant individuals. The top-performing models (among 148 and 121 submissions from 318 teams) achieve area under the receiver operator characteristic (AUROC) curve scores of 0.69 and 0.87 predicting PTB and ePTB, respectively. Alpha diversity, VALENCIA community state types, and composition are important features in the top-performing models, most of which are tree-based methods. This work is a model for translation of microbiome data into clinically relevant predictive models and to better understand preterm birth.