Natural selection of human embryos: decidualizing endometrial stromal cells serve as sensors of embryo quality upon implantation

Abstract

Background: Pregnancy is widely viewed as dependent upon an intimate dialogue, mediated by locally secreted factors between a developmentally competent embryo and a receptive endometrium. Reproductive success in humans is however limited, largely because of the high prevalence of chromosomally abnormal preimplantation embryos. Moreover, the transient period of endometrial receptivity in humans uniquely coincides with differentiation of endometrial stromal cells (ESCs) into highly specialized decidual cells, which in the absence of pregnancy invariably triggers menstruation. The role of cyclic decidualization of the endometrium in the implantation process and the nature of the decidual cytokines and growth factors that mediate the crosstalk with the embryo are unknown.

Methodology/principal findings: We employed a human co-culture model, consisting of decidualizing ESCs and single hatched blastocysts, to identify the soluble factors involved in implantation. Over the 3-day co-culture period, approximately 75% of embryos arrested whereas the remainder showed normal development. The levels of 14 implantation factors secreted by the stromal cells were determined by multiplex immunoassay. Surprisingly, the presence of a developing embryo had no significant effect on decidual secretions, apart from a modest reduction in IL-5 levels. In contrast, arresting embryos triggered a strong response, characterized by selective inhibition of IL-1beta, -6, -10, -17, -18, eotaxin, and HB-EGF secretion. Co-cultures were repeated with undifferentiated ESCs but none of the secreted cytokines were affected by the presence of a developing or arresting embryo.

Conclusions: Human ESCs become biosensors of embryo quality upon differentiation into decidual cells. In view of the high incidence of gross chromosomal errors in human preimplantation embryos, cyclic decidualization followed by menstrual shedding may represent a mechanism of natural embryo selection that limits maternal investment in developmentally impaired pregnancies.

Figure 1. Human embryo development in co-culture.

(A) Phase contrast images of decidualizing ESCs alone (control; left) or in the presence of an arrested (middle) or developing human embryo (right) (scale bar  = 100 µm). (B) Arrested embryos (Arr) express significantly less hCG than developing embryos (Dev). Secreted hCG levels were assayed after 72 hours of co-culturing human embryos and decidualizing ESCs (P<0.01). (C) Formation of primitive endoderm in developing human embryos co-cultured with decidual ESCs. Optical cross-sections through a day 8 embryo, cultured first on a decidualizing ESC monolayer for 72 hours, demonstrates the presence of GATA-6 positive cells aligning predominantly to the blastocoelic surface of the inner cell mass, which corresponds to the location of the primitive endoderm (top panel). The lower panel represents z-projection of all the images in the stack from a top to bottom scan through the embryo (scale bar  = 50 µm).

Figure 2. Secreted decidual cytokines not regulated upon embryo co-culture.

Primary ESCs were first decidualized for 5 days and then co-cultured with human embryos or not (control cultures, Con). Over the 72-hour co-culture period, 30 embryos arrested (Arr) whereas 11 continued to develop normally (Dev). Analysis of the culture supernatants revealed that the presence of an arresting or developing human embryo had no significant impact on the secretion of the indicated factors (P>0.05).

Figure 3. Developmentally impaired human embryos inhibit the secretion of selective implantation modulators by decidualizing ESCs.

Primary ESCs were first decidualized for 5 days and then co-cultured with human embryos or not (control cultures, Con). Over the 72-hour co-culture period, 30 embryos arrested (Arr) whereas 11 continued to develop normally (Dev). Analysis of the culture supernatants revealed that the presence of an arresting embryo inhibited the secretion of the indicated factors. The letters above the box plots indicate significant differences between groups. P<0.01 for all comparisons except for IL-6 and IL-17 (P<0.05).

Figure 4. The human embryo does not elicit a secretory response in undifferentiated endometrium.

Undifferentiated primary ESCs were co-cultured with embryos or not (control cultures, Con). Over the 72-hour co-culture period, 15 embryos arrested (Arr) whereas 6 continued to develop normally (Dev). Co-culture with either an arrested or developing embryo had no impact on the secreted levels of the indicated factors (P>0.05). The concentrations of IL-5, -12, -15, -17, -18, and eotaxin in culture supernatants of undifferentiated ESCs were below the level of detection.