TY - JOUR
T1 - Crowdsourcing assessment of maternal blood multi-omics for predicting gestational age and preterm birth
AU - The DREAM Preterm Birth Prediction Challenge Consortium
AU - Tarca, Adi L.
AU - Pataki, Bálint Ármin
AU - Romero, Roberto
AU - Sirota, Marina
AU - Guan, Yuanfang
AU - Kutum, Rintu
AU - Gomez-Lopez, Nardhy
AU - Done, Bogdan
AU - Bhatti, Gaurav
AU - Yu, Thomas
AU - Andreoletti, Gaia
AU - Chaiworapongsa, Tinnakorn
AU - Hassan, Sonia S.
AU - Hsu, Chaur Dong
AU - Aghaeepour, Nima
AU - Stolovitzky, Gustavo
AU - Csabai, Istvan
AU - Costello, James C.
N1 - Funding Information:
This research was supported, in part, by the Perinatology Research Branch, Division of Obstetrics and Maternal-Fetal Medicine, Division of Intramural Research, Eunice Kennedy Shriver National Institute of Child Health and Human Development, National Institutes of Health, US Department of Health and Human Services (NICHD/NIH/DHHS) and, in part, with federal funds from NICHD/NIH/DHHS under contract no. HHSN275201300006C. A.L.T. and N.G.-L. were also supported by the Wayne State University Perinatal Initiative in Maternal, Perinatal, and Child Health. R.R. has contributed to this work as part of his official duties as an employee of the US federal government. The authors acknowledge Alison Paquette for insightful discussions about available maternal omics datasets in preterm birth and Maureen McGerty (Wayne State University) and Corina Ghita for proofreading and copyediting this manuscript. N.A. was supported by the Bill and Melinda Gates Foundation (OPP1112382 and OPP1113682), the March of Dimes Prematurity Research Center at Stanford University, the Burroughs Wellcome Fund, the National Center for Advancing Translational Sciences, and the Robertson Family Foundation (KL2TR003143). I.C. and B.A.P. were supported by the National Research, Development, and Innovation Fund of Hungary (project no. FIEK_16-1-2016-0005). Y.G. was supported by grants from the National Institutes of Health (NIH/NIGMS R35GM133346-01) and the National Science Foundation (NSF/DBI #1452656). R.K. was supported by a Senior Research Fellowship Award from the Council of Scientific and Industrial Research of India (HCP00013). G.A. and M.S. were supported by the March of Dimes. A.L.T. R.R. M.S. N.A. G.S. and J.C.C. designed the challenge. A.L.T. T.Y. and J.C.C. developed tools to receive and evaluate participant submissions. The top-performing approach was designed by I.C. and B.A.P. Data analysis for the top-performing approach was conducted by B.A.P. The DREAM Preterm Birth Prediction Challenge Consortium provided predictions for sub-challenge 1 and method implementations and descriptions for sub-challenges 1 and 2. A.L.T. and B.D. applied methods to datasets for sub-challenge 2 and designed and applied hybrid methods between approaches of the top two teams. A.L.T. B.D. B.A.P. G.B. G.A. and J.C.C. performed the post-challenge analyses. A.L.T. R.R. M.S. N.A. J.C.C. and G.S. interpreted the results of the challenge. A.L.T. R.R. N.G.-L. T.C. S.S.H. and C.-D.H. designed the protocol in which patients were enrolled and coordinated the collection and generation of the clinical and omics data. A.L.T. N.G.-L. M.S. and J.C.C. wrote the manuscript. A.L.T. R.R. J.C.C. and G.S. supervised the project. A.L.T. R.R. S.S.H. and T.C. are listed as co-inventors on the US 10,802,030 B2 patent, which involves the prediction of preterm birth using proteomics data. All of the other authors declare no competing interests.
Funding Information:
This research was supported, in part, by the Perinatology Research Branch, Division of Obstetrics and Maternal-Fetal Medicine, Division of Intramural Research, Eunice Kennedy Shriver National Institute of Child Health and Human Development, National Institutes of Health, US Department of Health and Human Services (NICHD/NIH/DHHS) and, in part, with federal funds from NICHD/NIH/DHHS under contract no. HHSN275201300006C . A.L.T. and N.G.-L. were also supported by the Wayne State University Perinatal Initiative in Maternal, Perinatal, and Child Health . R.R. has contributed to this work as part of his official duties as an employee of the US federal government. The authors acknowledge Alison Paquette for insightful discussions about available maternal omics datasets in preterm birth and Maureen McGerty (Wayne State University) and Corina Ghita for proofreading and copyediting this manuscript. N.A. was supported by the Bill and Melinda Gates Foundation ( OPP1112382 and OPP1113682 ), the March of Dimes Prematurity Research Center at Stanford University , the Burroughs Wellcome Fund , the National Center for Advancing Translational Sciences , and the Robertson Family Foundation ( KL2TR003143 ). I.C. and B.A.P. were supported by the National Research, Development, and Innovation Fund of Hungary (project no. FIEK_16-1-2016-0005 ). Y.G. was supported by grants from the National Institutes of Health (NIH/NIGMS R35GM133346-01 ) and the National Science Foundation ( NSF/DBI #1452656 ). R.K. was supported by a Senior Research Fellowship Award from the Council of Scientific and Industrial Research of India ( HCP00013 ). G.A. and M.S. were supported by the March of Dimes .
Publisher Copyright:
© 2021 The Author(s)
PY - 2021/6/15
Y1 - 2021/6/15
N2 - Identification of pregnancies at risk of preterm birth (PTB), the leading cause of newborn deaths, remains challenging given the syndromic nature of the disease. We report a longitudinal multi-omics study coupled with a DREAM challenge to develop predictive models of PTB. The findings indicate that whole-blood gene expression predicts ultrasound-based gestational ages in normal and complicated pregnancies (r = 0.83) and, using data collected before 37 weeks of gestation, also predicts the delivery date in both normal pregnancies (r = 0.86) and those with spontaneous preterm birth (r = 0.75). Based on samples collected before 33 weeks in asymptomatic women, our analysis suggests that expression changes preceding preterm prelabor rupture of the membranes are consistent across time points and cohorts and involve leukocyte-mediated immunity. Models built from plasma proteomic data predict spontaneous preterm delivery with intact membranes with higher accuracy and earlier in pregnancy than transcriptomic models (AUROC = 0.76 versus AUROC = 0.6 at 27–33 weeks of gestation).
AB - Identification of pregnancies at risk of preterm birth (PTB), the leading cause of newborn deaths, remains challenging given the syndromic nature of the disease. We report a longitudinal multi-omics study coupled with a DREAM challenge to develop predictive models of PTB. The findings indicate that whole-blood gene expression predicts ultrasound-based gestational ages in normal and complicated pregnancies (r = 0.83) and, using data collected before 37 weeks of gestation, also predicts the delivery date in both normal pregnancies (r = 0.86) and those with spontaneous preterm birth (r = 0.75). Based on samples collected before 33 weeks in asymptomatic women, our analysis suggests that expression changes preceding preterm prelabor rupture of the membranes are consistent across time points and cohorts and involve leukocyte-mediated immunity. Models built from plasma proteomic data predict spontaneous preterm delivery with intact membranes with higher accuracy and earlier in pregnancy than transcriptomic models (AUROC = 0.76 versus AUROC = 0.6 at 27–33 weeks of gestation).
KW - aptamers
KW - collaborative competition
KW - human transcriptome arrays
KW - machine learning
KW - plasma proteomics
KW - predictive modeling
KW - preterm labor and delivery
KW - spontaneous preterm birth
KW - whole blood transcriptomics
UR - http://www.scopus.com/inward/record.url?scp=85108017952&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85108017952&partnerID=8YFLogxK
U2 - 10.1016/j.xcrm.2021.100323
DO - 10.1016/j.xcrm.2021.100323
M3 - Article
C2 - 34195686
AN - SCOPUS:85108017952
VL - 2
JO - Cell Reports Medicine
JF - Cell Reports Medicine
SN - 2666-3791
IS - 6
M1 - 100323
ER -