1. Microbiome preterm birth DREAM challenge: Crowdsourcing machine learning approaches to advance preterm birth research.
- Author
-
Golob JL, Oskotsky TT, Tang AS, Roldan A, Chung V, Ha CWY, Wong RJ, Flynn KJ, Parraga-Leo A, Wibrand C, Minot SS, Oskotsky B, Andreoletti G, Kosti I, Bletz J, Nelson A, Gao J, Wei Z, Chen G, Tang ZZ, Novielli P, Romano D, Pantaleo E, Amoroso N, Monaco A, Vacca M, De Angelis M, Bellotti R, Tangaro S, Kuntzleman A, Bigcraft I, Techtmann S, Bae D, Kim E, Jeon J, Joe S, Theis KR, Ng S, Lee YS, Diaz-Gimeno P, Bennett PR, MacIntyre DA, Stolovitzky G, Lynch SV, Albrecht J, Gomez-Lopez N, Romero R, Stevenson DK, Aghaeepour N, Tarca AL, Costello JC, and Sirota M
- Subjects
- Pregnancy, Female, Infant, Newborn, Humans, Phylogeny, Vagina, Premature Birth, Crowdsourcing, Microbiota genetics
- 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 The predictive models are validated on two independent unpublished datasets representing 331 samples from 148 pregnant individuals.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., Competing Interests: Declaration of interests S.V.L. is a board member at, holds stock in, and consults for Siolta Therapeutics. She also consults for the Atria Academy of Science and Medicine and for Sanofi. J.C.C. is co-founder of PrecisionProfile and OncoRx Insights. N.Aghaeepour. is a member of the scientific advisory boards of January AI, Parallel Bio, Celine Therapeutics, and WellSim Biomedical Technologies and is a paid consultant for Mara BioSystems. J.G. and M.S. have filed a patent related to the phylotype generation process., (Copyright © 2023 The Authors. Published by Elsevier Inc. All rights reserved.)
- Published
- 2024
- Full Text
- View/download PDF