Unknown

Dataset Information

0

Microbiome preterm birth DREAM challenge: Crowdsourcing machine learning approaches to advance preterm birth research.


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 The predictive models are validated on two independent unpublished datasets representing 331 samples from 148 pregnant individuals.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.

SUBMITTER: Golob JL 

PROVIDER: S-EPMC10829755 | biostudies-literature | 2024 Jan

REPOSITORIES: biostudies-literature

altmetric image

Publications

Microbiome preterm birth DREAM challenge: Crowdsourcing machine learning approaches to advance preterm birth research.

Golob Jonathan L JL   Oskotsky Tomiko T TT   Tang Alice S AS   Roldan Alennie A   Chung Verena V   Ha Connie W Y CWY   Wong Ronald J RJ   Flynn Kaitlin J KJ   Parraga-Leo Antonio A   Wibrand Camilla C   Minot Samuel S SS   Oskotsky Boris B   Andreoletti Gaia G   Kosti Idit I   Bletz Julie J   Nelson Amber A   Gao Jifan J   Wei Zhoujingpeng Z   Chen Guanhua G   Tang Zheng-Zheng ZZ   Novielli Pierfrancesco P   Romano Donato D   Pantaleo Ester E   Amoroso Nicola N   Monaco Alfonso A   Vacca Mirco M   De Angelis Maria M   Bellotti Roberto R   Tangaro Sabina S   Kuntzleman Abigail A   Bigcraft Isaac I   Techtmann Stephen S   Bae Daehun D   Kim Eunyoung E   Jeon Jongbum J   Joe Soobok S   Theis Kevin R KR   Ng Sherrianne S   Lee Yun S YS   Diaz-Gimeno Patricia P   Bennett Phillip R PR   MacIntyre David A DA   Stolovitzky Gustavo G   Lynch Susan V SV   Albrecht Jake J   Gomez-Lopez Nardhy N   Romero Roberto R   Stevenson David K DK   Aghaeepour Nima N   Tarca Adi L AL   Costello James C JC   Sirota Marina M  

Cell reports. Medicine 20231221 1


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 representi  ...[more]

Similar Datasets

| S-EPMC10029035 | biostudies-literature
| S-EPMC10689490 | biostudies-literature
| S-EPMC7979931 | biostudies-literature
| S-EPMC10556866 | biostudies-literature
| S-EPMC10441245 | biostudies-literature
| S-EPMC11415355 | biostudies-literature
| S-EPMC6750801 | biostudies-literature
| S-EPMC8233692 | biostudies-literature
| S-EPMC10794556 | biostudies-literature
| S-EPMC9238383 | biostudies-literature