Abstract
Prenatal exposure to maternal psychological stress is associated with increased risk for adverse birth and child health outcomes. Accumulating evidence suggests that preconceptional maternal stress may also be transmitted intergenerationally to negatively impact offspring. However, understanding of mechanisms linking these exposures to offspring outcomes, particularly those related to placenta, is limited. Using RNA sequencing, we identified placental transcriptomic signatures associated with maternal prenatal stressful life events (SLEs) and childhood traumatic events (CTEs) in 1 029 mother-child pairs in two birth cohorts from Washington state and Memphis, Tennessee. We evaluated individual gene-SLE/CTE associations and performed an ensemble of gene set enrichment analyses combing across 11 popular enrichment methods. Higher number of prenatal SLEs was significantly (FDR < 0.05) associated with increased expression of ADGRG6, a placental tissue-specific gene critical in placental remodeling, and decreased expression of RAB11FIP3, an endocytosis and endocytic recycling gene, and SMYD5, a histone methyltransferase. Prenatal SLEs and maternal CTEs were associated with gene sets related to several biological pathways, including upregulation of protein processing in the endoplasmic reticulum, protein secretion, and ubiquitin mediated proteolysis, and down regulation of ribosome, epithelial mesenchymal transition, DNA repair, MYC targets, and amino acid-related pathways. The directional associations in these pathways corroborate prior non-transcriptomic mechanistic studies of psychological stress and mental health disorders, and have previously been implicated in pregnancy complications and adverse birth outcomes. Accordingly, our findings suggest that maternal exposure to psychosocial stressors during pregnancy as well as the mother’s childhood may disrupt placental function, which may ultimately contribute to adverse pregnancy, birth, and child health outcomes.
Similar content being viewed by others
Introduction
Maternal stress before and during pregnancy has emerged as a major contributor to long term offspring health based on the Developmental Origins of Health and Disease (DOHaD) premise [1, 2]. Recent meta-analyses suggest the importance of maternal prenatal stress for offspring health across a range of outcomes including birth weight [3, 4], obesity [5,6,7], asthma [8, 9], mental health [10, 11], and neurodevelopmental disorders such as autism spectrum disorder and attention-deficit hyperactivity disorder [12]. However, the mechanisms linking prenatal stress to child development are not fully understood. Evidence suggests mediating roles of the neuroendocrine stress system, immune system, gut microbiome, and telomere biology [13, 14], although more mechanistic research is critically needed in tissues that play functional roles in the maternal-fetal interface. Improved mechanistic insight may support the development of interventions and open up new avenues in precision medicine aimed at reducing the burden of maternal stress-associated disease.
As the regulator of nutrient, waste, and gas exchange between the mother and fetus, the placenta is recognized as an essential functional link between the maternal environment and fetal programming [15, 16]. For instance, phenotypes related to the efficiency of placental transfer, including weight, thickness, surface area, and the ratio of placental to fetal weight have been linked to both maternal nutrition [17, 18] and offspring coronary heart disease [19, 20]. In addition to structural adjustments in response to the maternal environment, the placenta may also go through changes at the molecular level by altering gene expression. Because gene expression is cell type and tissue specific, it is essential to quantify the transcriptome in the most relevant, functional tissues in relation to a study question. Given its unique role in the maternal-fetal interface, the placenta is the ideal target tissue for the study of prenatal exposures. Moreover, studies show that the placental transcriptome and epigenome may respond to maternal exposures including particulate matter [21, 22], phthalates [23, 24], and stress [25, 26]. Investigating placental gene expression and epigenetic changes associated with maternal stress during pregnancy may help uncover mechanisms linking prenatal stress with child development [23].
Although DNA methylation differences associated with maternal stress have been examined [26, 27], the literature investigating transcriptomic alterations remains limited. Epigenomic and transcriptomic analyses generate distinct, complementary information, but the transcriptome may provide better functional insights by capturing all RNA molecules transcribed from genes that are actively expressed. The majority of studies investigating differential gene expression associated with maternal stress have utilized targeted approaches, which limit examination to just a handful of candidate genes [28,29,30]. One study profiled the placental transcriptomic signatures in 131 mother-child dyads associated with pregnancy during the environmental stressor of living through Hurricane Sandy [25]. In addition to identifying 221 differentially expressed genes associated with pregnancy during that natural disaster, Nomura et al. uncovered genes that mediated associations between this maternal stress exposure with child aggression and anxiety [25]. To more comprehensively explore gene expression differences associated with prenatal stress, larger, better powered transcriptomic studies, and studies of more commonly experienced stressors not restricted to natural disaster-associated stress, are needed.
DOHaD approaches have expanded to encompass a wider window during which exposures may affect development. In addition to maternal stress during pregnancy, emerging evidence suggests that stressful experiences during the mother’s earlier developmental periods may confer changes to her biology that later affect the development of her child [10, 31]. Compared with prenatal stress, the mechanisms of intergenerational transmission of the effects of preconceptional stress are less understood. Very few studies have investigated whether the effects of preconceptional traumatic experiences may be transmitted to later generations via changes in gene expression or DNA methylation [32, 33]. One of the first studies examining the transmission of preconceptional trauma found lower blood FKBP prolyl isomerase 5 (FKBP5) methylation in the children of Holocaust survivors compared to demographically comparable controls [34]. Placental DNA methylation in key regulatory regions of this gene is associated with both placental FKBP5 gene expression and infant neurodevelopmental outcomes [35]. Taken together, this work illustrates how placental molecular biology may serve as an intermediate between preconceptional stress and child development. Another targeted approach found sex-specific associations of maternal childhood trauma with gene expression and methylation of BDNF in cord blood [36]. Genome-wide approaches are even rarer. One study examined child genome-wide DNA methylation patterns in saliva associated with a maternal trauma measure designed to screen for potentially traumatic events over the respondent’s lifetime (Life Events Checklist) [33]. Another study examined placental genome-wide DNA methylation differences associated with socioeconomic adversity, framed as a chronic source of stress throughout the mother’s life [26]. However, to the best of our knowledge, there are no transcriptome-wide association studies simultaneously examining and distinguishing between prenatal and preconceptional maternal stress and the transcriptome of any tissue, including the placenta.
The primary objectives of this study were to examine associations of maternal exposure to stressors during pregnancy and her own childhood with the transcriptome of her infant’s placenta. Accumulating evidence indicates fetal sex differences in developmental vulnerability to prenatal stress [37]. We have also observed that fetal sex is a modifier of the relationship between other prenatal exposures and the placental transcriptome [23, 38]. Thus, we further hypothesized that associations of intergenerational stress with placental gene expression may be sex-specific. This study addresses several limitations of prior transcriptomic studies of prenatal stress, namely, small sample sizes, targeted gene approaches, lack of transcriptome-wide analyses of preconceptional maternal stress, and focus on natural disaster-related stress, which may not be generalizable to other sources of stress such as socioeconomic risk and family violence.
Methods
Study population
The ECHO prenatal and early childhood pathways to health (ECHO-PATHWAYS) consortium, described previously [39], is a study that harmonizes extant data and develops new data collection protocols for three pregnancy cohorts from diverse populations across the country. The consortium’s core aim is to explore the impact of chemical exposures and psychosocial stressors experienced by the mother during pregnancy on offspring growth and child development, and to assess potential underlying placental mechanisms. This analysis includes data from two of the consortium’s cohort studies in which placental transcriptomics data are available: the Conditions Affecting Neurocognitive Development and Learning in Early Childhood (CANDLE) study [40], and a subset of the Global Alliance to Prevent Prematurity and Stillbirth (GAPPS) study sample that has been enrolled in ECHO-PATHWAYS (GAPPS-PW) after their children were born.
CANDLE enrolled 1 503 women from Shelby County/Memphis, Tennessee, from 2006 to 2011 during the second trimester of pregnancy. Briefly, women were considered eligible if they were Shelby County, TN residents, between 16 and 40 years of age, had singleton pregnancies without complications at enrollment, and planned to deliver at a participating study hospital. Participants aged 18 years or older provided informed consent, while assent and consent from legally authorized representatives were obtained for those under 18 years prior to enrollment.
GAPPS was launched by the Seattle Children’s Hospital in 2007 to study the impact of adverse birth outcomes. In 2017, eligible participants were re-contacted to participate in the ECHO-PATHWAYS study. More than 600 mothers and children have been re-enrolled, and recruitment is still ongoing. Eligibility criteria included delivery in Seattle, WA (Swedish Medical Center) or Yakima, WA (Yakima Valley Memorial Hospital), availability of at least one pregnancy urine sample, initial GAPPS enrollment and completion of questionnaire, and GAPPS child currently 4–7 years of age. Study protocols were approved by the Institutional Review Boards of the University of Tennessee Health Science Center for CANDLE, the Seattle Children’s Research Institute for GAPPS, and the University of Washington for ECHO-PATHWAYS.
An inclusion criteria flowchart is presented in Fig. 1. Briefly, from the CANDLE (n = 1 503) and GAPPS (n = 657) cohorts, the ECHO-PATHWAYS consortium collected and conducted RNA-sequencing on a subset of placentas (n = 794 from CANDLE and n = 289 from GAPPS). After removing participants with missing placental transcriptomics data and placental abruption (n = 18), our study included 1 065 participants, among whom 1 029 had complete CTE data and 874 had complete SLE data (Fig. 1).
Study flowchart for inclusion of participants shows analytic sample sizes remaining from the implementation of each exclusion criterion. Participants come from two US pregnancy cohorts in the ECHO-PATHWAYS Consortium: CANDLE (Conditions Affecting Neurocognitive Development and Learning in Early Childhood) and GAPPS (Global Alliance to Prevent Prematurity and Stillbirth).
Exposures
Objective maternal stress exposures were retrospectively evaluated during postnatal follow up assessments (age 4–6 for GAPPS, age 8 for CANDLE). Exposures to prenatal Stressful Life Events (SLEs) were assessed using a survey adapted from the Centers for Disease Control and Prevention Pregnancy Risk Assessment Monitoring System (PRAMS) [41]. Women were asked to respond yes or no to 14 statements covering multiple types of stressful life events they experienced during pregnancy, such as those relating to relationship problems, housing or financial issues, legal problems, and illness or death of a loved one (Supplementary Table 1). Maternal childhood trauma exposures (CTEs) were assessed via responses to three questions from the Traumatic Life Events Questionnaire [42]. In this questionnaire, women reported whether they were physically abused before age 18 years, witnessed family violence before age 18 years, or experienced sexual abuse before age 13 years. Affirmative responses were summed to produce scores for both prenatal SLEs (range = 0-14) and maternal CTEs (range = 0-3), where higher scores indicate more SLEs experienced during pregnancy and more traumatic exposures experienced during childhood, respectively. Prior studies have shown consistency in the retrospective report of exposure to traumatic events during childhood [43] and stressful life experiences during pregnancy [44].
Placental transcriptomics
The ECHO PATHWAYS consortium sequenced a subset of placentas from each cohort (n = 289 from GAPPS and n = 794 from CANDLE). Placental tissue sampling, RNA isolation, and RNA sequencing have previously been described for CANDLE and GAPPS participants [21, 23]. In the CANDLE study, within 15 min of delivery, a piece of placental villous tissue in the shape of a rectangular prism with approximate dimensions of 2×0.5×0.5 cm was dissected from the placental parenchyma and cut into four ∼0.5-cm cubes. The tissue cubes were placed in a 50-mL tube with 20 mL of RNAlater and refrigerated at 4°C overnight ( ≥ 8 h but≤24 h). Each tissue cube was transferred to an individual 1.8-mL cryovial containing fresh RNAlater. The cryovials were stored at −80°C, and the fetal villous tissue was manually dissected and cleared of maternal decidua. Following dissection, the fetal samples were placed into RNAlater and stored at −80°C.
In the GAPPS study, within 30 min of delivery, 8 mm full-thickness vertical tissue punches from the placental disc were taken and put into 5 ml tubes containing approximately 3 ml of RNAlater and stored at −20 °C before specimens were shipped to the GAPPS facility. Samples were then stored at −20 °C. Punches were thawed and maternal decidua was removed, and the fetal-side of the placental punch was cut-off from the rest of the punch, and divided into 1–3 pieces with mass ranging from 10 mg to 30 mg. Each sample was placed in 1 ml RNAlater and stored at −20 °C until shipment for further processing.
For both cohorts, approximately 30 mg of fetal villous placental tissue was used for RNA isolation. The tissue was homogenized in tubes containing 600 μL of Buffer RLT Plus with β-mercaptoethanol using a TissueLyser LT instrument (Qiagen, Germantown, MD). RNA was isolated using the AllPrep DNA/RNA/miRNA Universal Kit (Qiagen) according to the manufacturer’s recommended protocol. RNA purity was assessed by measuring optical density ratios (OD260/230 and OD280/260) with a NanoDrop 8000 spectrophotometer (Thermo Fischer Scientific, Waltham MA). RNA integrity was determined with a Bioanalyzer 2100 using RNA 6000 Nanochips (Agilent, Santa Clara, CA). Only RNA samples with an RNA integrity number (RIN) of >7 were sequenced.
All RNA sequencing was performed at the University of Washington Northwest Genomics Center. Total RNA was poly-A enriched to remove ribosomal RNA, and cDNA libraries were prepared from 1 μg of total RNA using the TruSeq Stranded mRNA kit (Illumina, San Diego, CA) and the Sciclone NGSx Workstation (Perkin Elmer, Waltham, MA). Each library was uniquely barcoded and subsequently amplified using a total of 13 cycles of PCR. Library concentrations were quantified using Qubit Quant-it dsDNA High Sensitivity assay fluorometric quantitation (Life Technologies, Carlsbad, CA). Average fragment size and overall quality were evaluated with the DNA1000 assay on an Agilent 2100 Bioanalyzer. Each library was sequenced to an approximate depth of 30 million reads on an Illumina HiSeq sequencer. RNA sequencing quality control was performed using both the FASTX-toolkit (v0.0.13) and FastQC (v0.11.2) [45]. Transcript abundances were estimated by aligning to the GRCh38 transcriptome (Gencode v33) using Kallisto [46], then collapsed to the gene level using the Bioconductor tximport package, scaling to the average transcript length [47].
Other covariates
Covariate data on maternal and child characteristics were collected in the CANDLE and GAPPS studies via questionnaires and medical record abstraction and harmonized by the ECHO-PATHWAYS consortium. Supplementary Fig. 1 depicts a Directed Acyclic Graph (DAG) for our conceptual model of associations between maternal stress exposures and the placental transcriptome. Confounders were defined as factors that may influence both the exposure and the placental transcriptome, including self-reported race (White vs. Black vs. Multiple race vs. Asian vs. Other vs. American Indian/Alaska Native), self-reported ethnicity (Hispanic/Latino vs. Not Hispanic/Latino), and socioeconomic position. We did not consider race/ethnicity as proxies for genetic ancestry labels. Race is a political and social construct that often serves as a proxy for the impact of racist practices and structural inequality; it is not a biological construct [48] and thus is examined in the current paper with this premise in mind. Models adjusted for multiple covariates that capture different aspects of socioeconomic position, including household income adjusted for region and inflation (continuous), household size (2–3 vs. 4 vs. 5 vs. ≥6), maternal education ( < High School vs. High School completion/Graduate Equivalency Diploma vs. Graduated college or technical school vs. Some graduate work or graduate/professional degree), and geospatially-linked indicators of neighborhood deprivation (continuous standardized score) [49].
We also included precision variables, defined as variables that could affect the placental transcriptome but have no clear casual effect on the exposure. Precision variables included fetal sex (Male vs. Female), maternal gravidity (continuous number of pregnancies), delivery mode (Vaginal vs. C-section), labor type (Spontaneous vs. Spontaneous, augmented vs. Induced vs. No labor), study site, maternal age (continuous years), and sequencing batch. While socioeconomic position variables were conceptualized as confounders in prenatal SLE models, they were measured temporally after maternal childhood, and thus cannot be upstream causes of maternal CTEs. However, socioeconomic position variables may still influence the placental transcriptome and serve as precision variables in maternal CTE exposure models. Alternatively, these variables may still be conceptualized as confounders of the association between maternal CTEs and the placental transcriptome if they serve as proxies for maternal socioeconomic position during childhood.
Finally, we also considered variables that could be potential confounders but may also serve as mediators (i.e., variables on the causal pathway between maternal stress and placental gene expression). These factors included gestational age at birth (continuous weeks), maternal pre-pregnancy BMI (continuous kg/m2), and maternal tobacco (Yes vs. No) and alcohol (Yes vs. No) use during pregnancy. Given that BMI, tobacco use, and alcohol use may reflect mechanisms of coping with stress, we considered the models adjusting for these potential mediators as our primary analysis, with the objective of isolating placental transcriptomic responses to maternal stress that are independent of mechanisms of coping with stress. Gestational age at birth was not included as a covariate in the main models because: 1) as opposed to stress-coping pathways, gestational age at birth may reflect potential biological pathways through which maternal stress impacts the placental transcriptome, and 2) it is plausible that placental gene expression is an upstream cause of gestational age at birth, making gestational age a collider rather than a mediator. Thus, gestational age was included as an additional covariate in sensitivity analyses but not the main models. Since including potential mediators is a conservative approach – adjusting for effects that are likely on the causal path between the exposure and placental transcriptome is expected to attenuate results toward the null – we also report sensitivity models that do not adjust for any of these potential mediators. Maternal alcohol use was based on self-report. The positive tobacco exposure group included individuals with maternal urine cotinine above 200 ng/mL [50], as well as individuals who were below this cut-off but self-reported tobacco use during pregnancy. Covariates were determined a priori.
Statistical analysis
Descriptive statistics were calculated to understand characteristics of the study sample, and to compare our study sample with the entire CANDLE and GAPPS cohort populations. Because prior work in this sample indicates that prenatal SLEs and maternal CTEs may interact in their effects on child health [10], we initially tested associations of SLEs, CTEs, and SLE by CTE interactions with gene expression controlling for all covariates discussed above. There were no significant SLE by CTE interaction product terms for any genes (not shown). Therefore, we constructed separate models to evaluate associations of prenatal SLEs and maternal CTEs with placental gene expression. For all models, independent variables included one of the stress-related exposures along with all covariates discussed above, with gene expression of individual genes acting as the dependent variable. We retained only protein-coding genes, processed pseudogenes, and lncRNAs, and removed genes with average log counts per million (CPM) < 0. Transcript filtering was applied separately to the analytic samples with SLE (n = 874) and CTE (n = 1 029) data available, resulting in a final sample of 14 047 and 14 030 transcripts for prenatal SLEs and maternal CTEs, respectively. Log-cpm values were normalized to library size using the weighted trimmed mean of M-values [51].
In our primary analysis, missing covariate data were imputed using a multiple imputation method designed specifically for RNA-seq studies, implemented within the RNAseqCovarImpute package [52]. Exposure (stress) and outcome (gene expression) data were not imputed. Unlike single imputation, multiple imputation accounts for uncertainty in the prediction of missing data points. However, because multiple imputation methods must include the outcome as a predictor of missing data to avoid bias [53], they are difficult to apply given the high dimensionality of the outcome data in RNA-sequencing studies (e.g., 14 047 outcome genes). RNAseqCovarImpute accommodates high dimensional expression data by binning genes into smaller groups, creating separate multiply imputed datasets and differential expression models within each bin, and pooling results with Rubin’s rules. This method integrates with the limma-voom differential expression pipeline to fit weighted linear models for each gene that take into account individual-level precision weights based on the mean-variance trend [54]. Results are further moderated using the limma empirical Bayes procedure in which gene-wise variances are squeezed towards a global gene variance prior [55]. We report log2-adjusted fold-changes (Log2FCs) for each one number increase in SLEs or CTEs. Log2FCs were transformed into percent gene expression changes using the formula (2Log2FC-1)*100%.
For sensitivity analyses, we constructed 1) complete-case analyses, and 2) random forest single imputation models using the missForest package [56]. As in the primary analysis, both sensitivity analyses were fit using the limma-voom pipeline. The voomLmFit function from the edgeR package was used to fit weighted linear models for each gene, and the eBayes function from the limma package was used to apply the empirical Bayes procedure. In all differential expression analyses, genes were considered statistically significant at false discovery rate (FDR) < 0.05 using the Benjamini-Hochberg method [57], and we additionally report the number of genes with FDR < 0.10. We evaluated differences between these two sensitivity analyses and the multiple imputation models by assigning P-value rankings to each gene and comparing these ranks across the three methods.
To identify gene sets and pathways associated with prenatal SLEs and maternal CTEs, we performed Ensemble of Gene Set Enrichment Analyses (EGSEA), an approach that integrates the results of several separate gene set enrichment methods to produce combined P-values and gene set rankings [58]. Specifically, we examined MSigDB hallmark gene sets [59, 60] and KEGG pathways (excluding KEGG human diseases) [61] with the over-representation analysis (ora) [62], globaltest [63], plage [64], safe [65], zscore [66], ssgsea [67], roast [68], fry [68], padog [69], camera [70], and gsva [70] methods. Of note, the compatibility of pathway and gene set enrichment methods with multiple imputation depends on their inputs. The RNAseqCovarImpute multiple imputation method produces one final list of genes with their associated t-statistics, log fold changes, and P-values for differential expression. Thus, the method is compatible with gene set enrichment analyses that utilize gene rankings such as ora, or gene level statistics such as camera and gage [71]. However, RNAseqCovarImpute is not compatible with gene set enrichment analyses that require as input a gene expression matrix or data at the individual sample level, as the nature of multiple imputation requires the creation of multiple gene expression matrices across each imputed dataset.
Owing to the limited compatibility of multiple imputation with existing gene set enrichment methods, we utilized EGSEA by passing the “voom” object from the single imputation analysis, which includes the design matrix, precision weights, and normalized log-CPM values, into the egsea function from the EGSEA package. EGSEA was run using all gene set enrichment methods listed above. The single imputation results were considered as a reasonable alternative to the multiple imputation results because, as shown in the results section, the gene P-value rank orders produced by each method were very similar. In an additional sensitivity analysis, we performed gene set enrichment analysis using the gene t-statistics from the multiple imputation differential expression analysis with three compatible methods, namely, ora, gage, and camera, using the EGSEA, gage, and limma packages, respectively.
To explore sex-specific effects, we performed EGSEA separately on male and female strata with the single imputation data as described above.
Results
Covariate and stress data are described in Table 1. Women reported an average of 1.6 stressful life events (SLEs) during pregnancy (range = 0-14), and 0.5 childhood traumatic events (CTEs) in their own childhood (range = 0-3). Among the participants, 26.1% of women reported exposure to both prenatal SLEs and maternal CTEs, 36.0% prenatal SLEs only, 27.7% neither prenatal SLEs or maternal CTEs, and 10.2% maternal CTEs only. Rates of individual maternal CTEs were as follows: 26.3% witnessed family violence, 8% experienced physical abuse, and 19% experienced sexual abuse. Prenatal SLEs and maternal CTEs were weakly, positively correlated (Spearman’s rho = 0.226). On average, women were 27.9 years of age at delivery (range = 16-43), and most individuals self-identified as White (48.2%) or Black (42.1%). The majority of participants reported no tobacco (92.3%) or alcohol (90.6%) use during pregnancy, underwent labor (83.4%), and delivered vaginally (61.7%). Compared with the entire CANDLE and GAPPS cohorts, our sample with placental transcriptomics data and no placental abruption had higher mean maternal age (27.9 vs. 26.3), lower frequency of prenatal tobacco exposure (7.7% vs. 10.4%), and higher frequency of induced labor (32.5% vs. 27.2%). Socioeconomic status differences were mixed, with our sample having lower mean household income ($56 300 vs. $64 000), but higher maternal educational attainment and lower neighborhood deprivation index (Supplementary Table 2).
In placental transcriptome-wide analysis with FDR < 0.05, controlling for potential confounders, mediators, and precision variables, prenatal SLEs were associated with three differentially expressed genes (DEGs) in the multiple imputation models (n = 874, Fig. 2A, Supplementary Table 3). Each one number higher prenatal SLE was associated with 5.0% higher expression of adhesion G protein-coupled receptor G6 (ADGRG6) (Log2FC = 0.07, Fig. 2B), 2.7% lower expression of RAB11 family interacting protein 3 (RAB11FIP3) (Log2FC = -0.04, Fig. 2C), and 2.1% lower expression of SMYD family member 5 (SMYD5) (Log2FC = -0.03, Fig. 2D). Results were the same in a sensitivity analysis that additionally adjusted for gestational age at birth (Supplementary Table 3). Results were similar in a sensitivity analysis that did not include potential mediators as covariates, except the association with decreased SMYD5 expression was no longer significant (FDR P-value = 0.074, Supplementary Table 3). At the FDR < 0.10 threshold, prenatal SLEs were additionally associated with upregulation of 89 genes and downregulation of 91 genes (Fig. 2A, Supplementary Table 3).
Volcano plot depicts log2-adjusted fold-changes in 14 047 genes for each one number increase in prenatal stressful life events (SLEs), from multiple imputation analyses adjusting for maternal age, race, ethnicity, pre-pregnancy BMI, gravidity, tobacco and alcohol use during pregnancy, household income adjusted for region and inflation, household size, maternal education, neighborhood deprivation index, fetal sex, labor type, delivery method, study site, and sequencing batch (A). Horizontal line at P = 0.05. Limma-voom linear model trends (lines) for ADGRG6 (B), RAB11FIP3 (C), and SMYD5 (D). For each gene, one point per participant (gray points) and means (red diamonds) summarize the distributions of log2-counts per million (CPM) normalized to library size at each level of prenatal SLEs.
Controlling for potential confounders, mediators, and precision variables, maternal CTEs were not associated with any DEGs (Supplementary Table 4). Similarly, there were no significant associations of maternal CTEs with gene expression in a sensitivity analysis that additionally adjusted for gestational age at birth and a sensitivity analysis that did not include potential mediators as covariates (Supplementary Table 4). Differential expression analysis results for SLEs and CTEs were similar when using two alternative methods for handling missing data: single imputation and complete case analysis (Supplementary Results, Supplementary Fig. 2, Supplementary Tables 3–6).
In addition to evaluating individual gene associations with maternal stress, we performed gene set enrichment analysis using EGSEA on the single imputation results to combine across 11 popular gene set testing methods. All MsigDB hallmark and KEGG pathway terms that were significantly associated (FDR < 0.05) with either prenatal SLEs or maternal CTEs in EGSEA analyses are presented in Fig. 3. Prenatal SLEs were associated with altered regulation of 13 MsigDB hallmark gene sets and 7 KEGG pathways. Although maternal CTEs were not associated with differential expression of any single gene (Supplementary Table 4), they were associated with 8 MsigDB hallmark gene sets (Fig. 3). Among these 8 CTE-associated gene sets, 6 were also significantly associated with prenatal SLEs and in the same direction as their association with maternal CTEs. No KEGG pathways were significantly associated with maternal CTEs (Fig. 3). The EGSEA results on the single imputation models were similar to our sensitivity analyses applying the camera, gage, and ora methods to the multiple imputation differential expression models. As in EGSEA, prenatal SLEs were associated with genes involved in upregulation of the protein secretion and protein processing in the endoplasmic reticulum pathways, and downregulation of the epithelial mesenchymal transition, MYC targets v2, and ribosome pathways (cf. Figure 3, Supplementary Table 7). As in EGSEA, maternal CTEs were associated with downregulation of genes that were members of the MYC targets v1 and v2 pathways (cf. Fig. 3, Supplementary Table 7).
Associations of mutation signatures database (MSigDB) hallmarks and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways with prenatal SLEs and maternal CTEs. Log2 adjusted fold-changes (LogFC) and P-values come from ensemble of gene set enrichment analyses combining across 11 popular gene set testing methods. All terms with false discovery rate (FDR) adjusted P-value < 0.05 in association with prenatal SLEs and/or maternal CTEs shown.
We also performed sex-stratified EGSEA analyses to explore sex-specific effects of maternal stress. All MsigDB hallmarks and KEGG pathways that were significantly associated with prenatal SLEs in either male or female strata are presented in Fig. 4. The majority of gene sets associated with prenatal SLEs were altered in the same direction in both males and females. Among 9 gene sets with significant associations in both strata, 8 were directionally concordant. However, genes related to the adipogenesis pathway were upregulated by prenatal SLEs in females but downregulated in males (Fig. 4).
Associations of mutation signatures database (MSigDB) hallmarks and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways with prenatal SLEs stratified by sex. Log2 adjusted fold-changes (LogFC) and P-values come from ensemble of gene set enrichment analyses combining across 11 popular gene set testing methods. All terms with false discovery rate (FDR) adjusted P-value < 0.05 in either stratum shown.
All MsigDB hallmarks and KEGG pathways that were significantly associated with maternal CTEs in either male or female strata are presented in Fig. 5. Unlike the similarities across strata for prenatal SLEs, 4 of the 10 gene sets with significant associations in both strata were regulated in opposite directions by maternal CTEs in males and females. Moreover, maternal CTEs were not associated with any KEGG pathways in the main analysis (Fig. 3), but were associated with several KEGG pathways in the sex-stratified analyses, and the directions of association were generally opposite in males versus females (Fig. 5).
Associations of mutation signatures database (MSigDB) hallmarks and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways with prenatal SLEs stratified by sex. Log2 adjusted fold-changes (LogFC) and P-values come from ensemble of gene set enrichment analyses combining across 11 popular gene set testing methods. All terms with false discovery rate (FDR) adjusted P-value < 0.05 in either stratum shown.
Discussion
In this study of over 1 000 mother-child dyads, maternal stressful life events (SLEs) during pregnancy and childhood traumatic events (CTEs) were associated with gene expression patterns in the placenta. Prenatal SLEs were associated with differences in placental expression of three genes. Both prenatal SLEs and maternal CTEs were associated with transcriptomic differences in pathways from the molecular signatures database (MsigDB) and Kyoto Encyclopedia of Genes and Genomes (KEGG) gene sets, suggesting alterations to placental function, with implications for the etiology of pregnancy complications and adverse birth outcomes.
In our transcriptome-wide analysis, prenatal SLEs were positively associated with ADGRG6 expression and negatively associated with expression of RAB11FIP3 and SMYD5. ADGRG6 (also known as GPR126) encodes a G protein-coupled receptor and is involved in cellular adhesion. It is expressed specifically within the liver and placenta based on definitions provided by the human protein atlas [72]. In humans, genetic mutations in ADGRG6 are associated with the most common pediatric skeletal disease, adolescent idiopathic scoliosis [73], and with lethal arthrogryposis multiplex congenita [74]. Recent work using mouse and zebrafish models show that ADGRG6 inactivation is embryonically lethal owing to defective placental remodeling, which may precede the adverse human health conditions above [75]. RAB11FIP3 encodes a protein that interacts with the RAB11 family of proteins, which play roles in secretory pathways and protein transport. RAB11FIP3 is specifically involved in endocytosis and endocytic recycling [76], processes that mediate placental transfer [77]. SMYD5 is a histone methyltransferase, and has been shown to be involved in epigenetic transcriptional repression of inflammatory response genes [78]. These genes are involved in cellular adhesion, secretion, and inflammation, which are central pathways to core placental functions including maternal-fetal communication and immune protection.
In addition to being the largest analysis of the relationship between prenatal stress and the placental transcriptome to date, this study is also the first to examine the association of maternal preconceptional stress with the human transcriptome. Preconceptional stress, operationalized as maternal CTEs, was not associated with differential expression of any single genes. Compared with prenatal stress, there is a longer latency between maternal childhood trauma and the measurement of the placental transcriptome, which may explain the lack of any CTE-gene expression associations. Additionally, the 3-item CTE measure, which evaluates exposure to violence, physical abuse, and sexual abuse, may capture a different and smaller range of stressful exposures compared with the 14-item prenatal SLE measure, which evaluates a broad range of economic and interpersonal adversities. Similar results were found in a prior ECHO-PATHWAYS study, where higher prenatal SLEs predicted higher levels of child anxiety and depression at age 8-9, while no significant associations were observed for maternal CTEs [11]. Despite the lack of single gene associations, functional enrichment analyses considering the placental transcriptome holistically, rather than as isolated genes detached from biological context, uncovered associations of maternal CTEs with gene sets related to several biological pathways (discussed below).
To the best of our knowledge, this is the first large-scale analysis of prenatal stress and the placental transcriptome that is not linked to natural disasters. Although a prior placental transcriptomic study in 131 individuals documented many differentially expressed genes related to being pregnant during Hurricane Sandy [25], those alterations could be specific to that natural disaster or population, and may not be generalizable to all forms of stress exposure. Moreover, certain differentially expressed genes could be attributable to month/season/year of birth [79, 80], as the control group consisted of children whose mothers were pregnant within a three-year window surrounding the storm. One strength of our study was the adjustment for numerous potential confounders, and socioeconomic confounding either by family income or neighborhood deprivation could explain some of the differences between our results and the differentially expressed genes associated with pregnancy during Hurricane Sandy. Strikingly, however, our results corroborate some of the transcriptomic differences uncovered in that study: ADGRG6 was upregulated (P-adj = 0.006), and there was evidence that RAB11FIP3 was downregulated (P-adj = 0.062) in the placentas of participants who were pregnant during Hurricane Sandy versus pregnancies that occurred before Hurricane Sandy [25].
Consistent with prior work implicating perceived stress during pregnancy as a risk factor for preeclampsia [81,82,83] and reduced birth weight [3, 4], we found that prenatal SLEs were associated with gene expression differences that may increase risk for pregnancy complications and adverse birth outcomes. For instance, prenatal SLEs were associated with several pathways related to protein homeostasis, and the directional changes of these associations were consistent with endoplasmic reticulum (ER) stress. ER stress, which occurs following an imbalance in redox homeostasis between the ER and cytosol, triggers the unfolded protein response and activates signaling events consistent with the suppression of mRNA translational initiation, the upregulation of protein processing in the ER, and the degradation of misfolded proteins [84,85,86]. In agreement with the suppression of mRNA translational initiation associated with ER stress, increased prenatal SLEs were associated with downregulation of the KEGG ribosome pathway and downregulation of several amino acid metabolism pathways. In agreement with upregulation of protein processing and recycling associated with ER stress, prenatal SLEs were associated with upregulation of pathways related to protein processing in the ER and protein secretion, and, in the multiple imputation analysis, upregulation of ubiquitin mediated proteolysis. The ER is essential for protein processing and secretion, and through this role coordinates signaling pathways regulating metabolism, cell proliferation, and cell death by modifying proteins involved in these biological pathways. These ER functions are critical to the placenta’s role in maternal-fetal signaling, as the peptide hormones involved in this signaling are processed by the placental ER. Thus, perturbation of ER function can interfere with placental endocrine regulation of maternal metabolism, which may ultimately restrict nutrient transport to the fetus [87]. Consistent with the core role of the ER in placental biology, prior work implicates ER stress in the etiology of pregnancy complications including intrauterine growth restriction and preeclampsia [87,88,89,90]. Thus, findings from our study support ER stress as a candidate mechanism underlying prenatal psychological stress-associated pregnancy complications.
In addition to ER stress, prenatal SLEs and maternal CTEs were associated with placental gene expression within other pathways that have previously been linked with pregnancy complications. For instance, one study has shown that the down regulation of amino acid transport may precede intrauterine growth restriction [91], and we observed associations of maternal stress with down regulation of several amino acid related pathways (cysteine and methionine metabolism, and valine, leucine, and isoleucine degradation). We also observed negative associations between prenatal stress and expression of genes within the epithelial mesenchymal transition pathway. Invasive extravillous trophoblasts, originating from trophoblast cells through epithelial-mesenchymal transition, are critical for normal placental function. Dysregulated epithelial-mesenchymal transition of extravillous trophoblasts may induce defective migration and invasion and disrupt the process of spiral artery remodeling during the first trimester of pregnancy [92]. The importance of the epithelial mesenchymal transition pathway in normal placental development is underscored by prior work showing that it may be downregulated in preeclampsia [93,94,95,96]. Prenatal SLEs and maternal CTEs were also associated with repression of the DNA repair pathway. Down regulation of DNA repair pathways in trophoblasts owing to abnormal RNA degradation and miRNA expression may contribute to recurrent pregnancy loss [97]. Both prenatal SLEs and maternal CTEs were associated with downregulation of MYC signaling, which is involved in multiple growth promoting and signal transduction pathways, most frequently studied in the context of cancer [98]. However, there is evidence that aberrant MYC signaling is related to placental pathology as decreased MYC expression has been observed in preeclamptic versus normal human placentas [99].
Prenatal SLEs were associated with several pathways relating to energy metabolism, including oxidative phosphorylation, the citrate cycle (TCA cycle), carbon metabolism, and nitrogen metabolism. The citric acid cycle produces the precursor metabolites that are utilized via oxidative phosphorylation to produce adenosine triphosphate (ATP), the primary cellular energy source. The placenta has substantial energy requirements compared to other tissues, and it may regulate its energy metabolism in response to environmental conditions [15] or stress [100]. It has been recently hypothesized that, in some cases, the inability of the placenta to modulate its metabolism under such circumstances may underlie adverse outcomes such as preeclampsia [101]. However, whether these associations of stress with energy metabolism pathways represent a negative effect of the exposure or an adaptive response remains unknown.
Many of the pathway signatures detected here corroborate prior mechanistic studies of psychological stress and mental health disorders. Consistent with our findings, prior work shows positive associations of the unfolded protein response and ER stress with depression and emotional stressors [102,103,104]. For instance, elevated expression of ER-related genes has been seen among individuals with major depressive and post-traumatic stress disorders [105, 106], and both ER stress and the unfolded protein response are enhanced in animal models of depression [107, 108]. We also uncovered associations of prenatal SLEs and maternal CTEs with down regulated DNA repair pathways. These results are consistent with prior studies that have linked psychological stress with increased levels of DNA damage owing, in part, to impaired DNA checkpoint and repair mechanisms [109, 110].
Gene set enrichment analyses stratified by sex revealed which pathways were either consistently or differentially expressed depending on fetal sex. For instance, prenatal SLEs and maternal CTEs were associated with upregulation of mTORC1 signaling in females. In males, however, prenatal SLEs had no association with mTORC1 signaling, and maternal CTEs were associated with downregulation of this pathway. Mammalian target of rapamycin (MTOR) is a central regulator of protein translation, cell growth, and proliferation [111, 112]. MTOR regulates amino acid transport in the placenta [113], and studies show associations of MTOR inhibition with IUGR, reduced birth weight, and preeclampsia [114,115,116,117,118]. Prior studies have also shown sex-specific changes in MTOR, for instance in association with aging in mice [119] and maternal diet quality in humans [120]. Associations of fetal sex with differential pregnancy outcomes [121] and differential survival in preeclampsia [122] have been reported. It is possible that the sex-specific placental gene expression responses to environmental stress observed here may play a role in differential pregnancy and birth outcomes by sex. However, fetal sex did not modify the relationship between placental gene expression and spontaneous preterm birth in a prior analysis [123].
Our results should be considered in the context of several limitations. First, prenatal SLEs and maternal CTEs were assessed retrospectively. However, prior studies have shown substantial consistency in the retrospective report of exposure to traumatic events during childhood [43] and life experiences during pregnancy [44]. Second, gene expression was measured via bulk placental tissue RNA sequencing, which does not capture the differential transcriptomic contributions of the many different cell types found in placental villous tissue. Confounding by cell type heterogeneity is implausible, however, as placental cell type proportions are not an upstream cause of maternal stress. Nevertheless, changes in cell type proportions within the placenta could mediate the associations of maternal stress with gene expression, and mediation analyses to explore this possibility could be the subject of future studies. Third, generalizability of observational study results should always be considered, as exposure-outcome associations may vary between populations with different characteristics. Improving confidence in generalizability of the results, our study included socioeconomically and racially/ethnically diverse participants from two regionally distinct cohorts, and maternal stress exposure rates were comparable with rates in other populations: the mean of 1.58 SLEs during pregnancy reported here was similar to national rates (mean of 1.78 SLEs in one study of >100 000 participants from 31 states [124]), and rates of individual maternal CTEs in the domains of physical abuse, sexual abuse, and witnessing violence were within the range of rates from other studies [125,126,127]. Fourth, our prenatal SLE and maternal CTE stress exposures capture different multi-domain stressors, but our modeling approach assumes that each type of stress reflected in the questionnaires has the same effect on placental gene expression. Future research utilizing a larger sample size is needed to adequately assess independent associations of different domains of stress with placental gene expression. Finally, although we addressed potential confounding by including a wide range of maternal and socioeconomic factors in our models, residual confounding is always a possibility in observational studies.
In summary, this study stands apart as the largest investigation of the relationship between maternal stressful experiences during pregnancy and the placental transcriptome, and the first placental transcriptomic study of maternal childhood trauma. Prenatal and preconceptional maternal stress were associated with altered expression of single genes and gene expression pathways that are critical to normal placental functioning. Moreover, our results corroborate prior studies that have implicated many of the specific, directional gene and pathway changes detected here in association with psychological stress, mental health, pregnancy complications and adverse birth outcomes. Accordingly, our findings suggest that maternal prenatal and preconceptional stress may alter placental function, illuminating a potential key mechanism for intergenerational effects of stress on pregnancy, birth, and child health outcomes.
Data availability
The data utilized for this study are not publicly available but de-identified data may be available on request, subject to approval by the internal review board and under a formal data use agreement. Contact the corresponding author for more information.
Code availability
The RNAseqCovarImpute R package is available at https://doi.org/10.18129/B9.bioc.RNAseqCovarImpute. Sample R code used for these analyses is available at https://github.com/brennanhilton/Placental_Transcriptomic_Signatures_of_Prenatal_and_Preconceptional_Maternal_Stress.
References
Wadhwa PD. Psychoneuroendocrine processes in human pregnancy influence fetal development and health. Psychoneuroendocrinology. 2005;30:724–43.
Talge NM, Neal C, Glover V, the Early Stress, Translational Research and Prevention Science Network: Fetal and Neonatal Experience on Child and Adolescent Mental Health. Antenatal maternal stress and long‐term effects on child neurodevelopment: how and why? J Child Psychol Psychiatry. 2007;48:245–61.
Littleton HL, Bye K, Buck K, Amacker A. Psychosocial stress during pregnancy and perinatal outcomes: a meta-analytic review. J Psychosom Obstet Gynecol. 2010;31:219–28.
Bussieres E-L, Tarabulsy GM, Pearson J, Tessier R, Forest J-C, Giguere Y. Maternal prenatal stress and infant birth weight and gestational age: A meta-analysis of prospective studies. Dev Rev. 2015;36:179–99.
Dancause KN, Laplante DP, Fraser S, Brunet A, Ciampi A, Schmitz N, et al. Prenatal exposure to a natural disaster increases risk for obesity in 5½-year-old children. Pediatr Res. 2012;71:126–31.
Li J, Olsen J, Vestergaard M, Obel C, Baker JL, Sørensen TI. Prenatal stress exposure related to maternal bereavement and risk of childhood overweight. PloS one. 2010;5:e11896.
Felder JN, Epel E, Coccia M, Cordeiro A, Laraia B, Adler N, et al. Prenatal maternal objective and subjective stress exposures and rapid infant weight gain. J Pediatr. 2020;222:45–51.
Flanigan C, Sheikh A, DunnGalvin A, Brew BK, Almqvist C, Nwaru BI. Prenatal maternal psychosocial stress and offspring’s asthma and allergic disease: a systematic review and meta‐analysis. Clin Exp Allergy. 2018;48:403–14.
van de Loo KF, van Gelder MM, Roukema J, Roeleveld N, Merkus PJ, Verhaak CM. Prenatal maternal psychological stress and childhood asthma and wheezing: a meta-analysis. Eur Respiratory J. 2016;47:133–46.
Bush NR, Noroña-Zhou A, Coccia M, Rudd KL, Ahmad SI, Loftus CT, et al. Intergenerational transmission of stress: Multi-domain stressors from maternal childhood and pregnancy predict children’s mental health in a racially and socioeconomically diverse, multi-site cohort. Social Psychiatry and Psychiatric Epidemiology. 58 1625–1636 (2023).
Noroña-Zhou A, Coccia M, Sullivan A, O’Connor TG, Collett BR, Derefinko K, et al. A multi-cohort examination of the independent contributions of maternal childhood adversity and pregnancy stressors to the prediction of children’s anxiety and depression. Res Child Adolesc Psychopathol. 2023;51:497–512.
Manzari N, Matvienko-Sikar K, Baldoni F, O’Keeffe GW, Khashan AS. Prenatal maternal stress and risk of neurodevelopmental disorders in the offspring: a systematic review and meta-analysis. Soc psychiatry Psychiatr Epidemiol. 2019;54:1299–309.
Van den Bergh BR, van den Heuvel MI, Lahti M, Braeken M, de Rooij SR, Entringer S, et al. Prenatal developmental origins of behavior and mental health: The influence of maternal stress in pregnancy. Neurosci Biobehav Rev. 2020;117:26–64.
Müller JJ, Antonow-Schlorke I, Kroegel N, Rupprecht S, Rakers F, Witte OW, et al. Cardiovascular effects of prenatal stress—are there implications for cerebrovascular, cognitive and mental health outcome? Neurosci Biobehav Rev. 2020;117:78–97.
Thornburg KL, Marshall N. The placenta is the center of the chronic disease universe. Am J Obstet Gynecol. 2015;213:S14–S20.
Lapehn S, Paquette AG. The placental epigenome as a molecular link between prenatal exposures and fetal health outcomes through the DOHaD hypothesis. Curr Environ Health Rep. 2022;9:490–501.
Roseboom T, Painter R, De Rooij S, Van Abeelen A, Veenendaal M, Osmond C, et al. Effects of famine on placental size and efficiency. Placenta. 2011;32:395–9.
Alwasel S, Abotalib Z, Aljarallah J, Osmond C, Alkharaz S, Alhazza I, et al. Changes in placental size during Ramadan. Placenta. 2010;31:607–10.
Barker DJ, Larsen G, Osmond C, Thornburg KL, Kajantie E, Eriksson JG. The placental origins of sudden cardiac death. Int J Epidemiol. 2012;41:1394–9.
Eriksson JG, Kajantie E, Thornburg KL, Osmond C, Barker DJ. Mother’s body size and placental size predict coronary heart disease in men. Eur Heart J. 2011;32:2297–303.
Enquobahrie DA, MacDonald J, Hussey M, Bammler TK, Loftus CT, Paquette AG, et al. Prenatal exposure to particulate matter and placental gene expression. Environ Int. 2022;165:107310.
Zhao Y, Wang P, Zhou Y, Xia B, Zhu Q, Ge W, et al. Prenatal fine particulate matter exposure, placental DNA methylation changes, and fetal growth. Environ Int. 2021;147:106313.
Paquette AG, MacDonald J, Lapehn S, Bammler T, Kruger L, Day DB, et al. A comprehensive assessment of associations between prenatal phthalate exposure and the placental transcriptomic landscape. Environ Health Perspect. 2021;129:097003.
Jedynak P, Tost J, Calafat AM, Bourova-Flin E, Broséus L, Busato F, et al. Pregnancy exposure to phthalates and DNA methylation in male placenta—An epigenome-wide association study. Environ Int. 2022;160:107054.
Nomura Y, Rompala G, Pritchett L, Aushev V, Chen J, Hurd YL. Natural disaster stress during pregnancy is linked to reprogramming of the placenta transcriptome in relation to anxiety and stress hormones in young offspring. Mol Psych. 2021;26:6520–30.
Santos HP Jr, Bhattacharya A, Martin EM, Addo K, Psioda M, Smeester L, et al. Epigenome-wide DNA methylation in placentas from preterm infants: association with maternal socioeconomic status. Epigenetics. 2019;14:751–65.
Kotsakis Ruehlmann A, Sammallahti S, Cortés Hidalgo AP, Bakulski KM, Binder EB, Campbell ML, et al. Epigenome-wide meta-analysis of prenatal maternal stressful life events and newborn DNA methylation. Mol Psych. 2023; 1–11. https://www.nature.com/articles/s41380-023-02010-5.
Litzky JF, Deyssenroth MA, Everson TM, Lester BM, Lambertini L, Chen J, et al. Prenatal exposure to maternal depression and anxiety on imprinted gene expression in placenta and infant neurodevelopment and growth. Pediatr Res. 2018;83:1075–83.
Capron LE, Ramchandani PG, Glover V. Maternal prenatal stress and placental gene expression of NR3C1 and HSD11B2: the effects of maternal ethnicity. Psychoneuroendocrinology. 2018;87:166–72.
Appleton AA, Armstrong DA, Lesseur C, Lee J, Padbury JF, Lester BM, et al. Patterning in placental 11-B hydroxysteroid dehydrogenase methylation according to prenatal socioeconomic adversity. PloS One. 2013;8:e74691.
Plant DT, Pawlby S, Pariante CM, Jones FW. When one childhood meets another–maternal childhood trauma and offspring child psychopathology: A systematic review. Clin Child Psychol Psych. 2018;23:483–500.
Yehuda R, Lehrner A. Intergenerational transmission of trauma effects: putative role of epigenetic mechanisms. World Psych. 2018;17:243–57.
Barcelona V, Huang Y, Caceres BA, Newhall KP, Hui Q, Cerdeña JP, et al. Experiences of Trauma and DNA Methylation Profiles among African American Mothers and Children. Int J Mol Sci. 2022;23:8951.
Yehuda R, Daskalakis NP, Bierer LM, Bader HN, Klengel T, Holsboer F, et al. Holocaust exposure induced intergenerational effects on FKBP5 methylation. Biol Psych. 2016;80:372–80.
Paquette AG, Lester BM, Koestler DC, Lesseur C, Armstrong DA, Marsit C. Placental FKBP5 genetic and epigenetic variation is associated with infant neurobehavioral outcomes in the RICHS cohort. PloS One. 2014;9:e104913.
Pilkay SR, Combs-Orme T, Tylavsky F, Bush N, Smith AK. Maternal trauma and fear history predict BDNF methylation and gene expression in newborns. PeerJ. 2020;8:e8858.
Sutherland S, Brunwasser SM. Sex differences in vulnerability to prenatal stress: a review of the recent literature. Curr Psychiatry Rep. 2018;20:1–12.
Paquette AG, Lapehn S, Freije S, MacDonald J, Bammler T, Day DB, et al. Placental transcriptomic signatures of prenatal exposure to hydroxy-polycyclic aromatic hydrocarbons. Environ Int. 2023;172:107763.
LeWinn KZ, Karr CJ, Hazlehurst M, Carroll K, Loftus C, Nguyen R, et al. Cohort profile: the ECHO prenatal and early childhood pathways to health consortium (ECHO-PATHWAYS). BMJ Open. 2022;12:e064288.
Sontag-Padilla L, Burns RM, Shih RA, Griffin BA, Martin LT, Chandra A, et al. The urban child institute CANDLE study. Santa Monica, CA: RAND Corporation. (2015).
Whitehead N, Brogan D, Blackmore-Prince C, Hill H. Correlates of experiencing life events just before or during pregnancy. J Psychosom Obstet Gynecol. 2003;24:77–86.
Kubany ES, Leisen MB, Kaplan AS, Watson SB, Haynes SN, Owens JA, et al. Development and preliminary validation of a brief broad-spectrum measure of trauma exposure: the Traumatic Life Events Questionnaire. Psychological Assess. 2000;12:210.
Krinsley KE, Gallagher JG, Weathers FW, Kutter CJ, Kaloupek DG. Consistency of retrospective reporting about exposure to traumatic events. J Trauma Stress: Off Publ Int Soc Trauma Stress Stud. 2003;16:399–409.
Ramos AM, Marceau K, Neiderhiser JM, De Araujo-Greecher M, Natsuaki MN, Leve LD. Maternal consistency in recalling prenatal experiences at 6 months and 8 years postnatal. J Dev Behav Ped. 2020;41:698.
Brown J, Pirrung M, McCue LA. FQC Dashboard: integrates FastQC results into a web-based, interactive, and extensible FASTQ quality control tool. Bioinformatics. 2017;33:3137–9.
Bray NL, Pimentel H, Melsted P, Pachter L. Near-optimal probabilistic RNA-seq quantification. Nat Biotechnol. 2016;34:525–7.
Soneson C, Love MI, Robinson MD. Differential analyses for RNA-seq: transcript-level estimates improve gene-level inferences. F1000Research. 2015;4:1521.
Bryant BE, Jordan A, Clark US. Race as a social construct in psychiatry research and practice. JAMA Psych. 2022;79:93–4.
Messer LC, Laraia BA, Kaufman JS, Eyster J, Holzman C, Culhane J, et al. The development of a standardized neighborhood deprivation index. J Urban Health. 2006;83:1041–62.
Schick SF, Blount BC, Jacob P 3rd, Saliba NA, Bernert JT, El Hellani A, et al. Biomarkers of exposure to new and emerging tobacco delivery products. Am J Physiol-Lung Cell Mol Physiol. 2017;313:L425–L52.
Robinson MD, Oshlack A. A scaling normalization method for differential expression analysis of RNA-seq data. Genome Biol. 2010;11:1–9.
Baker BH, Sathyanarayana S, Szpiro AA, MacDonald J, Paquette AG RNAseqCovarImpute: a multiple imputation procedure that outperforms complete case and single imputation differential expression analysis. bioRxiv. 2023:2023.05. 11.540260.
Little RJ. Regression with missing X’s: a review. J Am Stat Assoc. 1992;87:1227–37.
Law CW, Chen Y, Shi W, Smyth GK. voom: Precision weights unlock linear model analysis tools for RNA-seq read counts. Genome Biol. 2014;15:1–17.
Smyth GK Linear models and empirical bayes methods for assessing differential expression in microarray experiments. Statistical applications in genetics and molecular biology. 2004;3.
Stekhoven DJ, Bühlmann P. MissForest—non-parametric missing value imputation for mixed-type data. Bioinformatics. 2012;28:112–8.
Benjamini Y, Hochberg Y. Controlling the false discovery rate: a practical and powerful approach to multiple testing. J R Stat Soc: Ser B 1995;57:289–300.
Alhamdoosh M, Ng M, Wilson NJ, Sheridan JM, Huynh H, Wilson MJ, et al. Combining multiple tools outperforms individual methods in gene set enrichment analyses. Bioinformatics. 2017;33:414–24.
Subramanian A, Tamayo P, Mootha VK, Mukherjee S, Ebert BL, Gillette MA, et al. Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles. Proc Natl Acad Sci. 2005;102:15545–50.
Liberzon A, Birger C, Thorvaldsdóttir H, Ghandi M, Mesirov JP, Tamayo P. The molecular signatures database hallmark gene set collection. Cell Syst. 2015;1:417–25.
Kanehisa M, Furumichi M, Sato Y, Ishiguro-Watanabe M, Tanabe M. KEGG: integrating viruses and cellular organisms. Nucleic Acids Res. 2021;49:D545–D51.
Tavazoie S, Hughes JD, Campbell MJ, Cho RJ, Church GM. Systematic determination of genetic network architecture. Nat Genet. 1999;22:281–5.
Goeman JJ, Van De Geer SA, De Kort F, Van Houwelingen HC. A global test for groups of genes: testing association with a clinical outcome. Bioinformatics. 2004;20:93–9.
Tomfohr J, Lu J, Kepler TB. Pathway level analysis of gene expression using singular value decomposition. BMC Bioinforma. 2005;6:1–11.
Barry WT, Nobel AB, Wright FA. Significance analysis of functional categories in gene expression studies: a structured permutation approach. Bioinformatics. 2005;21:1943–9.
Lee E, Chuang H-Y, Kim J-W, Ideker T, Lee D. Inferring pathway activity toward precise disease classification. PLoS Comput Biol. 2008;4:e1000217.
Barbie DA, Tamayo P, Boehm JS, Kim SY, Moody SE, Dunn IF, et al. Systematic RNA interference reveals that oncogenic KRAS-driven cancers require TBK1. Nature. 2009;462:108–12.
Wu D, Lim E, Vaillant F, Asselin-Labat M-L, Visvader JE, Smyth GK. ROAST: rotation gene set tests for complex microarray experiments. Bioinformatics. 2010;26:2176–82.
Tarca AL, Draghici S, Bhatti G, Romero R. Down-weighting overlapping genes improves gene set analysis. BMC Bioinforma. 2012;13:1–14.
Wu D, Smyth GK. Camera: a competitive gene set test accounting for inter-gene correlation. Nucleic Acids Res. 2012;40:e133. e
Luo W, Friedman MS, Shedden K, Hankenson KD, Woolf PJ. GAGE: generally applicable gene set enrichment for pathway analysis. BMC Bioinforma. 2009;10:1–17.
Uhlen M, Oksvold P, Fagerberg L, Lundberg E, Jonasson K, Forsberg M, et al. Towards a knowledge-based human protein atlas. Nat Biotechnol. 2010;28:1248–50.
Kou I, Takahashi Y, Johnson TA, Takahashi A, Guo L, Dai J, et al. Genetic variants in GPR126 are associated with adolescent idiopathic scoliosis. Nat Genet. 2013;45:676–9.
Ravenscroft G, Nolent F, Rajagopalan S, Meireles AM, Paavola KJ, Gaillard D, et al. Mutations of GPR126 are responsible for severe arthrogryposis multiplex congenita. Am J Hum Genet. 2015;96:955–61.
Torregrosa-Carrión R, Piñeiro-Sabarís R, Siguero-Álvarez M, Grego-Bessa J, Luna-Zurita L, Fernandes VS, et al. Adhesion G protein–coupled receptor Gpr126/Adgrg6 is essential for placental development. Sci Adv. 2021;7:eabj5445.
Grant BD, Donaldson JG. Pathways and mechanisms of endocytic recycling. Nat Rev Mol Cell Biol. 2009;10:597–608.
Cooke LD, Tumbarello DA, Harvey NC, Sethi JK, Lewis RM, Cleal JK. Endocytosis in the placenta: An undervalued mediator of placental transfer. Placenta. 2021;113:67–73.
Stender JD, Pascual G, Liu W, Kaikkonen MU, Do K, Spann NJ, et al. Control of proinflammatory gene programs by regulated trimethylation and demethylation of histone H4K20. Mol cell. 2012;48:28–38.
Hemati Z, Keikha M, Riahi R, Daniali SS, Goudarzi M, Kelishadi R. A systematic review on the association of month and season of birth with future anthropometric measures. Pediatr Res. 2021;89:31–45.
Buckles KS, Hungerman DM. Season of birth and later outcomes: Old questions, new answers. Rev Econ Stat. 2013;95:711–24.
Shamsi U, Hatcher J, Shamsi A, Zuberi N, Qadri Z, Saleem S. A multicentre matched case control study of risk factors for preeclampsia in healthy women in Pakistan. BMC women’s health. 2010;10:7.
Yu Y, Zhang S, Wang G, Hong X, Mallow EB, Walker SO, et al. The combined association of psychosocial stress and chronic hypertension with preeclampsia. Am J Obstet Gynecol. 2013;209:438. e1–e12.
Zhang S, Ding Z, Liu H, Chen Z, Wu J, Zhang Y, et al. Association between mental stress and gestational hypertension/preeclampsia: a meta-analysis. Obstetrical Gynecol Surv. 2013;68:825–34.
Brostrom MA, Brostrom CO. Calcium dynamics and endoplasmic reticular function in the regulation of protein synthesis: implications for cell growth and adaptability. Cell calcium. 2003;34:345–63.
Görlach A, Klappa P, Kietzmann DT. The endoplasmic reticulum: folding, calcium homeostasis, signaling, and redox control. Antioxid redox Signal. 2006;8:1391–418.
Malhotra JD, Kaufman RJ. Endoplasmic reticulum stress and oxidative stress: a vicious cycle or a double-edged sword? Antioxid redox Signal. 2007;9:2277–94.
Burton GJ, Yung H-W. Endoplasmic reticulum stress in the pathogenesis of early-onset pre-eclampsia. Pregnancy Hypertension: Int J Women’s Cardiovascular Health. 2011;1:72–8.
Yung H-w, Calabrese S, Hynx D, Hemmings BA, Cetin I, Charnock-Jones DS, et al. Evidence of placental translation inhibition and endoplasmic reticulum stress in the etiology of human intrauterine growth restriction. Am J Pathol. 2008;173:451–62.
Burton G, Yung H-W, Cindrova-Davies T, Charnock-Jones D. Placental endoplasmic reticulum stress and oxidative stress in the pathophysiology of unexplained intrauterine growth restriction and early onset preeclampsia. Placenta. 2009;30:43–8.
Castro KR, Prado KM, Lorenzon AR, Hoshida MS, Alves EA, Francisco RP, et al. Serum from preeclamptic women triggers endoplasmic reticulum stress pathway and expression of angiogenic factors in trophoblast cells. Front Physiol. 2022;12:2488.
Pantham P, Rosario FJ, Weintraub ST, Nathanielsz PW, Powell TL, Li C, et al. Down-regulation of placental transport of amino acids precedes the development of intrauterine growth restriction in maternal nutrient restricted baboons. Biol Rep. 2016;95:98, 1-9.
Canfield J, Arlier S, Mong EF, Lockhart J, VanWye J, Guzeloglu-Kayisli O, et al. Decreased LIN28B in preeclampsia impairs human trophoblast differentiation and migration. FASEB J. 2019;33:2759.
Li H, Cheung A, Tsao S, Cheung A. Expression of e-cadherin and beta-catenin in trophoblastic tissue in normal and pathological pregnancies. Int J Gynecol Pathol. 2003;22:63–70.
Du L, Kuang L, He F, Tang W, Sun W, Chen DJHR. Mesenchymal-to-epithelial transition in the placental tissues of patients with preeclampsia. Hypertension Res. 2017;40:67–72.
Ge H, Yin N, Han T-L, Huang D, Chen X, Xu P, et al. Interleukin-27 Inhibits Trophoblast Cell Invasion and Migration by Affecting the Epithelial—Mesenchymal Transition in Preeclampsia. Reprod Sci. 2019;26:928–38.
Peng P, Song H, Xie C, Zheng W, Ma H, Xin D, et al. miR-146a-5p-mediated suppression on trophoblast cell progression and epithelial-mesenchymal transition in preeclampsia. Biol Res. 2021;54:1–12.
Li P-F, Xiang Y-G, Zhang D, Lu N, Dou Q, Tan L. Downregulation of DNA ligases in trophoblasts contributes to recurrent pregnancy loss through inducing DNA damages. Placenta. 2021;106:7–14.
Dang CV. MYC on the path to cancer. Cell. 2012;149:22–35.
Rahat B, Hamid A, Ahmad Najar R, Bagga R, Kaur J. Epigenetic mechanisms regulate placental c-myc and hTERT in normal and pathological pregnancies; c-myc as a novel fetal DNA epigenetic marker for pre-eclampsia. MHR: Basic Sci Reprod Med. 2014;20:1026–40.
Vaughan OR, Fowden AL. Placental metabolism: substrate requirements and the response to stress. Reprod Domest Anim. 2016;51:25–35.
Aye IL, Aiken CE, Charnock-Jones DS, Smith GC. Placental energy metabolism in health and disease—significance of development and implications for preeclampsia. Am J Obstet Gynecol. 2022;226:S928–S44.
II Timberlake M, Dwivedi Y. Linking unfolded protein response to inflammation and depression: potential pathologic and therapeutic implications. Mol Psych. 2019;24:987–94.
Hayashi T. Conversion of psychological stress into cellular stress response: Roles of the sigma‐1 receptor in the process. Psychiatry Clin Neurosci. 2015;69:179–91.
Díaz-Hung M-L, Martínez G, Hetz C. Emerging roles of the unfolded protein response (UPR) in the nervous system: A link with adaptive behavior to environmental stress? Int Rev Cell Mol Biol. 2020;350:29–61.
Nevell L, Zhang K, Aiello AE, Koenen K, Galea S, Soliven R, et al. Elevated systemic expression of ER stress related genes is associated with stress-related mental disorders in the Detroit Neighborhood Health Study. Psychoneuroendocrinology. 2014;43:62–70.
Bown C, Wang J-F, MacQueen G, Young LT. Increased temporal cortex ER stress proteins in depressed subjects who died by suicide. Neuropsychopharmacology. 2000;22:327–32.
Jangra A, Sriram CS, Dwivedi S, Gurjar SS, Hussain MI, Borah P, et al. Sodium phenylbutyrate and edaravone abrogate chronic restraint stress-induced behavioral deficits: implication of oxido-nitrosative, endoplasmic reticulum stress cascade, and neuroinflammation. Cell Mol Neurobiol. 2017;37:65–81.
Li M-X, Li Q, Sun X-J, Luo C, Li Y, Wang Y-N, et al. Increased Homer1-mGluR5 mediates chronic stress-induced depressive-like behaviors and glutamatergic dysregulation via activation of PERK-eIF2α. Prog Neuro-Psychopharmacol Biol Psychiatry. 2019;95:109682.
Hara MR, Kovacs JJ, Whalen EJ, Rajagopal S, Strachan RT, Grant W, et al. A stress response pathway regulates DNA damage through β2-adrenoreceptors and β-arrestin-1. Nature. 2011;477:349–53.
Morath J, Moreno-Villanueva M, Hamuni G, Kolassa S, Ruf-Leuschner M, Schauer M, et al. Effects of psychotherapy on DNA strand break accumulation originating from traumatic stress. Psychother Psychosom. 2014;83:289–97.
Hay N, Sonenberg N. Upstream and downstream of mTOR. Genes Dev 2004;18:1926–45.
Sarbassov DD, Ali SM, Sabatini DM. Growing roles for the mTOR pathway. Curr Opin cell Biol. 2005;17:596–603.
Rosario FJ, Dimasuay KG, Kanai Y, Powell TL, Jansson T. Regulation of amino acid transporter trafficking by mTORC1 in primary human trophoblast cells is mediated by the ubiquitin ligase Nedd4-2. Clin Sci. 2016;130:499–512.
Roos S, Jansson N, Palmberg I, Säljö K, Powell TL, Jansson T. Mammalian target of rapamycin in the human placenta regulates leucine transport and is down‐regulated in restricted fetal growth. J Physiol. 2007;582:449–59.
Dimasuay KG, Aitken EH, Rosario F, Njie M, Glazier J, Rogerson SJ, et al. Inhibition of placental mTOR signaling provides a link between placental malaria and reduced birthweight. BMC Med. 2017;15:1–11.
Chen Y-Y, Rosario FJ, Shehab MA, Powell TL, Gupta MB, Jansson T. Increased ubiquitination and reduced plasma membrane trafficking of placental amino acid transporter SNAT-2 in human IUGR. Clin Sci. 2015;129:1131–41.
Lazo-de-la-Vega M-L, Mata-Tapia K-A, Garcia-Santillan J-A, Corona-Figueroa M-A, Gonzalez-Dominguez M-I, Gomez-Zapata H-M, et al. Association of placental nutrient sensing pathways with birth weight. Reproduction. 2020;160:455–68.
Tsai K, Tullis B, Jensen T, Graff T, Reynolds P, Arroyo J. Differential expression of mTOR related molecules in the placenta from gestational diabetes mellitus (GDM), intrauterine growth restriction (IUGR) and preeclampsia patients. Reprod Biol. 2021;21:100503.
Baar EL, Carbajal KA, Ong IM, Lamming DW. Sex‐and tissue‐specific changes in mTOR signaling with age in C57 BL/6J mice. Aging cell. 2016;15:155–66.
Francis EC, Dabelea D, Boyle KE, Jansson T, Perng W. Maternal diet quality is associated with placental proteins in the placental insulin/growth factor, environmental stress, inflammation, and mTOR signaling pathways: the healthy start ECHO cohort. J Nutr. 2022;152:816–25.
Aliyu MH, Salihu HM, Lynch ON, Alio AP, Marty PJ. Fetal sex and differential survival in preeclampsia and eclampsia. Arch Gynecol Obstet. 2012;285:361–5.
Vatten LJ, Skjærven R. Offspring sex and pregnancy outcome by length of gestation. Early Hum Dev. 2004;76:47–54.
Paquette AG, MacDonald J, Bammler T, Day DB, Loftus CT, Buth E, et al. Placental transcriptomic signatures of spontaneous preterm birth. Am J Obstet Gynecol. 2023;228:73. e1–e18.
Mukherjee S, Coxe S, Fennie K, Madhivanan P, Trepka MJ. Stressful life event experiences of pregnant women in the United States: A latent class analysis. Women’s Health Issues. 2017;27:83–92.
Smith MV, Gotman N, Yonkers KA. Early childhood adversity and pregnancy outcomes. Matern Child health J. 2016;20:790–8.
Remigio-Baker RA, Hayes DK, Reyes-Salvail F. Adverse childhood events and current depressive symptoms among women in Hawaii: 2010 BRFSS, Hawaii. Matern Child Health J. 2014;18:2300–8.
Frankenberger DJ, Clements-Nolle K, Yang W. The association between adverse childhood experiences and alcohol use during pregnancy in a representative sample of adult women. Women’s Health Issues. 2015;25:688–95.
Acknowledgements
ECHO PATHWAYS is funded by the National Institutes of Health (NIH; UG3OD023271), and data for this study were collected with support from additional NIH grants (NCATS of NIH: UL1TR002319 and NIH R01HL132338). The generation of RNA-seq data for this study was supported by the University of Washington Interdisciplinary Center for Exposures, Diseases, Genomics, and Environment funded by the National Institute of Environmental Health Sciences (NIEHS; P30ES007033). This research was conducted using specimens and data collected from the Conditions Affecting Neurocognitive Development and Learning in Early Childhood (CANDLE) study which was funded by the Urban Child Institute. This research was conducted using specimens and data collected and stored on behalf of the Global Alliance to Prevent Prematurity and Stillbirth (GAPPS) Repository. BHB was supported in part by the UW NIEHS sponsored Biostatistics, Epidemiologic and Bioinformatic Training in Environmental Health (BEBTEH) Training Grant: NIEHS T32ES015459. AGP was supported by NICHD K99/R00HD096112 and 1R01ES033785. The authors would like to thank the study staff, data teams, and co-investigators involved in the CANDLE and GAPPS cohorts as well as the ECHO-PATHWAYS consortium for their invaluable contributions. We are also grateful to the study participants who generously volunteered their time for this study. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. This manuscript has been reviewed by PATHWAYS for scientific content and consistency of data interpretation with previous PATHWAYS publications.
Author information
Authors and Affiliations
Contributions
BHB: Conceptualization, Methodology, Software, Formal analysis, Visualization, Writing – Original Draft, Writing - Review & Editing. SF: Conceptualization, Methodology, Writing - Review & Editing. JWM and TKB: Methodology, Investigation, Writing – Review & Editing. CB: Investigation, Writing – Review & Editing. KNC, DAE, CJK, KZL, QZ, NRB, and SS: Conceptualization, Supervision, Funding acquisition, Writing – Review & Editing. AGP: Conceptualization, Methodology, Visualization, Supervision, Funding acquisition, Writing – Review & Editing.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Baker, B.H., Freije, S., MacDonald, J.W. et al. Placental transcriptomic signatures of prenatal and preconceptional maternal stress. Mol Psychiatry 29, 1179–1191 (2024). https://doi.org/10.1038/s41380-023-02403-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41380-023-02403-6