Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jul 13:11:e73671.
doi: 10.7554/eLife.73671.

Using adopted individuals to partition indirect maternal genetic effects into prenatal and postnatal effects on offspring phenotypes

Liang-Dar Hwang  1 , Gunn-Helen Moen  1   2   3   4   5 , David M Evans  1   2   6
Affiliations

Using adopted individuals to partition indirect maternal genetic effects into prenatal and postnatal effects on offspring phenotypes

Liang-Dar Hwang et al. Elife. .

Abstract

Maternal genetic effects can be defined as the effect of a mother's genotype on the phenotype of her offspring, independent of the offspring's genotype. Maternal genetic effects can act via the intrauterine environment during pregnancy and/or via the postnatal environment. In this manuscript, we present a simple extension to the basic adoption design that uses structural equation modelling (SEM) to partition maternal genetic effects into prenatal and postnatal effects. We examine the power, utility and type I error rate of our model using simulations and asymptotic power calculations. We apply our model to polygenic scores of educational attainment and birth weight associated variants, in up to 5,178 adopted singletons, 943 trios, 2687 mother-offspring pairs, 712 father-offspring pairs and 347,980 singletons from the UK Biobank. Our results show the expected pattern of maternal genetic effects on offspring birth weight, but unexpectedly large prenatal maternal genetic effects on offspring educational attainment. Sensitivity and simulation analyses suggest this result may be at least partially due to adopted individuals in the UK Biobank being raised by their biological relatives. We show that accurate modelling of these sorts of cryptic relationships is sufficient to bring type I error rate under control and produce asymptotically unbiased estimates of prenatal and postnatal maternal genetic effects. We conclude that there would be considerable value in following up adopted individuals in the UK Biobank to determine whether they were raised by their biological relatives, and if so, to precisely ascertain the nature of these relationships. These adopted individuals could then be incorporated into informative statistical genetics models like the one described in our manuscript to further elucidate the genetic architecture of complex traits and diseases.

Keywords: adoption study; genetics; genomics; human; indirect maternal genetic effects; maternal genetic effects; postnatal maternal effects; prenatal maternal effects; structural equation modelling.

PubMed Disclaimer

Conflict of interest statement

LH, GM, DE No competing interests declared

Figures

Figure 1.
Figure 1.. Path diagrams illustrating the structural equation models (SEM) underlying the seven family structures modelled in this manuscript (G1 – G7).
Causal relationships are represented by one headed arrows. Two headed arrows represents correlational relationships. Observed variables and latent variables are shown in squares and circles, respectively. Zm represents biological mother’s genotype which influences offspring phenotype (Y) via prenatal (γm) and postnatal (βm) pathways. Zp represents the biological father’s genotype which only influences offspring phenotype postnatally (βp). Zo represents offspring genotype which influences offspring phenotype (βo) and is correlated ½ with the genotypes of its biological parents. Zm_b represents the genotype of a biological mother whose child was adopted and therefore only influences her child’s phenotype through prenatal pathways (γm). Zm_a represents the adoptive mother’s genotype which only influences her adopted offspring’s phenotype via postnatal pathways (βm). Zp_b represents the genotype of a biological father whose child was adopted and therefore has no influence on the adopted offspring phenotype. Zp_a represents the adoptive father’s genotype which influences his adopted offspring postnatally (βp). ρ represents the covariance between parental genotypes, as a result of e.g. assortative mating (it is assumed that this covariance is the same in biological parents and adoptive parents). The total variance of genotypes in the parental generation is set to Φ. Ɛ1 and Ɛ2 represent residual error terms for the biological and adopted offspring phenotypes respectively that we assume have different variances.
Figure 2.
Figure 2.. Power to detect prenatal maternal genetic effects (γm) (top) or postnatal maternal genetic effects (βm) (bottom) whilst also varying the size of prenatal and postnatal maternal genetic effects, paternal genetic effects (βp) or offspring genetic effects (βo).
Effect sizes are parameterized using the path coefficients β and γ. Power was calculated assuming sample sizes approximating the number of white European individuals in the UK Biobank with educational attainment data (i.e. 1000 biological trios, 4000 biological mother-offspring pairs, 1800 biological father-offspring pairs, 300,000 singletons, 6000 adopted individuals, and 50 biological mother-adopted offspring pairs and a covariance of 0 (ρ) between maternal and paternal genotypes).
Figure 3.
Figure 3.. Power to detect prenatal maternal (γm) or postnatal maternal genetic (βm) effects whilst varying the numbers of each family structure, with the sample sizes of other family structures approximating numbers of white European individuals in the UK Biobank reporting educational attainment (1000 biological trios, 4000 biological mother-offspring pairs, 1800 biological father-offspring pairs, 300,000 singletons, 6000 singletons, and 50 biological mother-adopted offspring pairs).
Path coefficients representing postnatal or prenatal maternal genetic effects, paternal genetic effects (βp) and offspring genetic effects (βo) were fixed to 0.1. The covariance between maternal and paternal genotypes was fixed to 0.
Figure 4.
Figure 4.. Diagram illustrating a Mendelian randomization study designed to estimate the causal effect of a maternal prenatal environmental exposure on an offspring later life outcome.
Maternal genotype proxies a perinatal exposure of interest and is used as an instrumental variable to estimate the causal effect of the perinatal exposure on the offspring outcome. The pathway of interest is represented by the blue arrows where the SNP influences the outcome prenatally through the perinatal exposure of interest. In this sort of design, it is important to control for spurious pathways through the offspring genome since offspring genotype will be correlated ½ with maternal genotype. Maternal genotype could also influence the offspring phenotype via other pleiotropic paths through the intrauterine environment (red arrow) or through the postnatal environment (dashed arrows). The inclusion of adopted individuals into the research design may be useful in controlling for the effect of horizontal pleiotropic influences through the postnatal environment. Intuitively this is because adoptive mother’s genotype provides an estimate of the relationship between maternal genotype and offspring outcome through postnatal pathways only. This estimate could be included in statistical models of the relationship between maternal genotype and offspring outcome to help correct for the effect of horizontal pleiotropy.
Appendix 1—figure 1.
Appendix 1—figure 1.. Path diagrams illustrating the structural equation models (SEM) underlying four additional family structures (G8 – G11) where biological and adoptive parents are related.
Observed variables and latent variables are shown in squares and circles respectively. Causal relationships are represented by one headed arrows. Two headed arrows represents correlational relationships. Zo represents offspring genotype which influences offspring phenotype (βo) and is correlated ½ with the genotypes of its biological parents. Zm_b represents the genotype of a biological mother whose child was adopted and therefore only influences her child’s phenotype through prenatal pathways (γm). Zm_a represents the adoptive mother’s genotype which only influences her adopted offspring’s phenotype via postnatal pathways (βm). Zp_b represents the genotype of a biological father whose child was adopted and therefore has no influence on the adopted offspring phenotype. Zp_a represents the adoptive father’s genotype which influences his adopted offspring postnatally (βp). ρ represents the covariance between parental genotypes, as a result of e.g. assortative mating (it is assumed that this covariance is the same in biological parents and adoptive parents). The total variance of genotypes in the parental generation is set to Φ. Ɛ3 through Ɛ6 represent residual error terms for the adopted offspring that we assume have different variances. The (fixed) parameter r represents the covariance between biological and adoptive parents’ genotypes.
Appendix 1—figure 2.
Appendix 1—figure 2.. Power to detect prenatal maternal (γm) or postnatal maternal (βm) genetic effects whilst varying the correlation (rg) between maternal and paternal genotypes.
Power was calculated using sample sizes approximating the number of white European individuals in the UK Biobank reporting their own educational attainment (1000 biological trios, 4000 biological mother-offspring pairs, 1,800 biological father-offspring pairs, 300,000 singletons, 6000 adopted individuals, and 50 biological mother-adopted offspring pairs). Path coefficients representing prenatal maternal (γm), postnatal maternal (βm), paternal (βp) and offspring genetic effects (βo) were fixed to 0.1.
Appendix 1—figure 3.
Appendix 1—figure 3.. Estimated prenatal (γm) and postnatal (βm) maternal effects and type 1 error rates whilst varying the percentage of adoptive mothers being siblings (top) or cousins (bottom) of biological mothers.
An SEM which did not correctly model this relationship was fit to the data. Power was calculated using simulated data with 1000 biological trios, 4000 biological mother-offspring pairs, 1800 biological father-offspring pairs, 300,000 singletons, and 6000 adopted individuals. Prenatal maternal genetic effects were fixed to zero whilst the size of postnatal maternal genetic effects were varied (left panels); postnatal maternal genetic effects were fixed to zero whilst the size of prenatal maternal genetic effects were varied (right panels). Paternal effects (βp) and offspring effects (βo) were fixed to 0.1. The covariance between maternal and paternal genotypes was fixed to zero.
Appendix 1—figure 4.
Appendix 1—figure 4.. Estimated prenatal (γm) and postnatal (βm) maternal effects and type 1 error rates whilst varying the percentage of adoptive mothers being siblings (top) or cousins (bottom) of biological fathers.
An SEM which did not correctly model this relationship was fit to the data. Power was calculated using simulated data with 1000 biological trios, 4000 biological mother-offspring pairs, 1800 biological father-offspring pairs, 300,000 singletons, and 6000 adopted individuals. Prenatal maternal genetic effects were fixed to zero whilst the size of postnatal maternal genetic effects were varied (left panels); postnatal maternal genetic effects were fixed to zero whilst the size of prenatal maternal genetic effects were varied (right panels). Paternal effects (βp) and offspring effects (βo) were fixed to 0.1. The covariance between maternal and paternal genotypes was fixed to zero.
Appendix 1—figure 5.
Appendix 1—figure 5.. Estimated prenatal (γm) and postnatal (βm) maternal effects and type 1 error rates whilst varying the percentage of adoptive fathers being siblings (top) or cousins (bottom) of biological fathers.
An SEM which did not correctly model this relationship was fit to the data. Power was calculated using simulated data with 1000 biological trios, 4000 biological mother-offspring pairs, 1800 biological father-offspring pairs, 300,000 singletons, and 6000 adopted individuals. Prenatal maternal genetic effects were fixed to zero whilst the size of postnatal maternal genetic effects were varied (left panels); postnatal maternal genetic effects were fixed to zero whilst the size of prenatal maternal genetic effects were varied (right panels). Paternal effects (βp) and offspring effects (βo) were fixed to 0.1. The covariance between maternal and paternal genotypes was fixed to zero.
Appendix 1—figure 6.
Appendix 1—figure 6.. Estimated prenatal (γm) and postnatal (βm) maternal effects and type 1 error rates whilst varying the percentage of adoptive fathers being siblings (top) or cousins (bottom) of biological mothers.
An SEM which did not correctly model this relationship was fit to the data. Power was calculated using simulated data with 1000 biological trios, 4000 biological mother-offspring pairs, 1800 biological father-offspring pairs, 300,000 singletons, and 6000 adopted individuals. Prenatal maternal genetic effects were fixed to zero whilst the size of postnatal maternal genetic effects were varied (left panels); postnatal maternal genetic effects were fixed to zero whilst the size of prenatal maternal genetic effects were varied (right panels). Paternal effects (βp) and offspring effects (βo) were fixed to 0.1. The covariance between maternal and paternal genotypes was fixed to zero.
Appendix 1—figure 7.
Appendix 1—figure 7.. Estimated prenatal (γm) and postnatal (βm) maternal effects and type 1 error rates whilst varying the percentage of adoptive mothers being siblings (top) or cousins (bottom) of biological mothers.
An SEM which modelled this relationship correctly was fit to the data. Power was calculated using simulated data with 1000 biological trios, 4000 biological mother-offspring pairs, 1800 biological father-offspring pairs, 300,000 singletons, and 6000 adopted individuals. Prenatal maternal genetic effects were fixed to zero whilst the size of postnatal maternal genetic effects were varied (left panels); postnatal maternal genetic effects were fixed to zero whilst the size of prenatal maternal genetic effects were varied (right panels). Paternal effects (βp) and offspring effects (βo) were fixed to 0.1. The covariance between maternal and paternal genotypes was fixed to zero.
Appendix 1—figure 8.
Appendix 1—figure 8.. Estimated prenatal (γm) and postnatal (βm) maternal effects and type 1 error rates whilst varying the percentage of adoptive mothers being siblings (top) or cousins (bottom) of biological fathers.
An SEM which modelled this relationship correctly was fit to the data. Power was calculated using simulated data with 1000 biological trios, 4000 biological mother-offspring pairs, 1800 biological father-offspring pairs, 300,000 singletons, and 6000 adopted individuals. Prenatal maternal genetic effects were fixed to zero whilst the size of postnatal maternal genetic effects were varied (left panels); postnatal maternal genetic effects were fixed to zero whilst the size of prenatal maternal genetic effects were varied (right panels). Paternal effects (βp) and offspring effects (βo) were fixed to 0.1. The covariance between maternal and paternal genotypes was fixed to zero.
Appendix 1—figure 9.
Appendix 1—figure 9.. Estimated prenatal (γm) and postnatal (βm) maternal effects and type 1 error rates whilst varying the percentage of adoptive fathers being siblings (top) or cousins (bottom) of biological fathers.
An SEM which modelled this relationship correctly was fit to the data. Power was calculated using simulated data with 1000 biological trios, 4000 biological mother-offspring pairs, 1800 biological father-offspring pairs, 300,000 singletons, and 6000 adopted individuals. Prenatal maternal genetic effects were fixed to zero whilst the size of postnatal maternal genetic effects were varied (left panels); postnatal maternal genetic effects were fixed to zero whilst the size of prenatal maternal genetic effects were varied (right panels). Paternal effects (βp) and offspring effects (βo) were fixed to 0.1. The covariance between maternal and paternal genotypes was fixed to zero.
Appendix 1—figure 10.
Appendix 1—figure 10.. Estimated prenatal (γm) and postnatal (βm) maternal effects and type 1 error rates whilst varying the percentage of adoptive fathers being siblings (top) or cousins (bottom) of biological mothers.
An SEM which modelled this relationship correctly was fit to the data. Power was calculated using simulated data with 1000 biological trios, 4000 biological mother-offspring pairs, 1800 biological father-offspring pairs, 300,000 singletons, and 6000 adopted individuals. Prenatal maternal genetic effects were fixed to zero whilst the size of postnatal maternal genetic effects were varied (left panels); postnatal maternal genetic effects were fixed to zero whilst the size of prenatal maternal genetic effects were varied (right panels). Paternal effects (βp) and offspring effects (βo) were fixed to 0.1. The covariance between maternal and paternal genotypes was fixed to zero.
Appendix 1—figure 11.
Appendix 1—figure 11.. Power to detect prenatal (γm) and postnatal maternal (βm) genetic effects when the relationship between adoptive and biological parents are correctly specified in the model.
Power was calculated using simulated data assuming 1000 biological parent-offspring trios, 4000 biological mother-offspring pairs, 1800 biological father-offspring pairs, 300,000 singletons from non-adopted families, and 6000 adopted individuals. Prenatal maternal genetic effects, postnatal maternal genetic effects, paternal genetic effects (βp) and offspring genetic effects (βo) were fixed to 0.1. The covariance between maternal and paternal genotypes was fixed to 0. The percentage of adopted individuals whose adoptive parents were genetically related to their biological parents was varied (x-axis). Note that 0% corresponds to the situation where biological and adoptive parents are unrelated.
See this image and copyright information in PMC

References

    1. Armstrong-Carter E, Trejo S, Hill LJB, Crossley KL, Mason D, Domingue BW. The earliest origins of genetic nurture the prenatal environment mediates the association between maternal genetics and child development. Psychological Science. 2020;31:781–791. doi: 10.1177/0956797620917209. - DOI - PMC - PubMed
    1. Balbona JV, Kim Y, Keller MC. Estimation of parental effects using polygenic scores. Behavior Genetics. 2021;51:264–278. doi: 10.1007/s10519-020-10032-w. - DOI - PMC - PubMed
    1. Bates TC, Maher BS, Medland SE, McAloney K, Wright MJ, Hansell NK, Kendler KS, Martin NG, Gillespie NA. The nature of nurture: using a virtual-parent design to test parenting effects on children’s educational attainment in genotyped families. Twin Research and Human Genetics. 2018;21:73–83. doi: 10.1017/thg.2018.11. - DOI - PubMed
    1. Beaumont RN, Warrington NM, Cavadino A, Tyrrell J, Nodzenski M, Horikoshi M, Geller F, Myhre R, Richmond RC, Paternoster L, Bradfield JP, Kreiner-Møller E, Huikari V, Metrustry S, Lunetta KL, Painter JN, Hottenga JJ, Allard C, Barton SJ, Espinosa A, Marsh JA, Potter C, Zhang G, Ang W, Berry DJ, Bouchard L, Das S, Hakonarson H, Heikkinen J, Helgeland Ø, Hocher B, Hofman A, Inskip HM, Jones SE, Kogevinas M, Lind PA, Marullo L, Medland SE, Murray A, Murray JC, Njølstad PR, Nohr EA, Reichetzeder C, Ring SM, Ruth KS, Santa-Marina L, Scholtens DM, Sebert S, Sengpiel V, Tuke MA, Vaudel M, Weedon MN, Willemsen G, Wood AR, Yaghootkar H, Muglia LJ, Bartels M, Relton CL, Pennell CE, Chatzi L, Estivill X, Holloway JW, Boomsma DI, Montgomery GW, Murabito JM, Spector TD, Power C, Järvelin MR, Bisgaard H, Grant SFA, Sørensen TIA, Jaddoe VW, Jacobsson B, Melbye M, McCarthy MI, Hattersley AT, Hayes MG, Frayling TM, Hivert MF, Felix JF, Hyppönen E, Lowe WL, Evans DM, Lawlor DA, Feenstra B, Freathy RM. Genome-wide association study of offspring birth weight in 86 577 women identifies five novel loci and highlights maternal genetic effects that are independent of fetal genetics. Human Molecular Genetics. 2018;27:742–756. doi: 10.1093/hmg/ddx429. - DOI - PMC - PubMed
    1. Boker S, Neale M, Maes H, Wilde M, Spiegel M, Brick T, Spies J, Estabrook R, Kenny S, Bates T, Mehta P, Fox J. OpenMx: an open source extended structural equation modeling framework. Psychometrika. 2011;76:306–317. doi: 10.1007/s11336-010-9200-6. - DOI - PMC - PubMed

Publication types