Dynamic intercellular transport modulates the spatial patterning of differentiation during early neural commitment

Abstract

The initiation of heterogeneity within a population of phenotypically identical progenitors is a critical event for the onset of morphogenesis and differentiation patterning. Gap junction communication within multicellular systems produces complex networks of intercellular connectivity that result in heterogeneous distributions of intracellular signaling molecules. In this study, we investigate emergent systems-level behavior of the intercellular network within embryonic stem cell (ESC) populations and corresponding spatial organization during early neural differentiation. An agent-based model incorporates experimentally-determined parameters to yield complex transport networks for delivery of pro-differentiation cues between neighboring cells, reproducing the morphogenic trajectories during retinoic acid-accelerated mouse ESC differentiation. Furthermore, the model correctly predicts the delayed differentiation and preserved spatial features of the morphogenic trajectory that occurs in response to intercellular perturbation. These findings suggest an integral role of gap junction communication in the temporal coordination of emergent patterning during early differentiation and neural commitment of pluripotent stem cells.

Fig. 1

Loss of Oct4 and maintenance of Sox2 expression during retinoic acid–induced differentiation. Oct4 expression begins to decline after 24-hour exposure to retinoic acid (1 μM), with the main transition to an Oct4- state occurring between 24 and 48 h of RA treatment. After 72 h, ~ 70% of the population retain an Oct4-Sox2 + phenotype (a, c). A schematic depicting the change in gene expression in ESC populations towards the predominant progenitor state during two differentiation protocols: LIF-withdrawal in serum-containing media and retinoic acid addition (b). Quantification of flow cytometry data in a demonstrates the maintenance of the Oct4-Sox2 + state between 48 and 72 h of RA treatment (c), n = 9 (three biological replicates, three technical replicates for each biological replicate). Scale bar: 50 µm

Fig. 2

Cx43 signal (green) increases during retinoic acid–induced differentiation, with compartmentalization of transitioning cells between 24 and 48 h. Mitotic cells are prevalent in pluripotent colonies (a) and show a diffuse ‘ring’ of Cx43 in the membrane, designated by an asterisk, that is typical of Cx43 not forming GJ plaques. After 24 h of RA treatment (b), Cx43 noticeably increased between clusters of cells with low Oct4 expression (red), characterized in d. At 48 h of treatment (c), cells that have low (but non-zero) Oct4 expression have large expression of Cx43 in the cytoplasm. Previous studies have linked an accumulation of Cx43 expression in the cytoplasm to localization in the Golgi apparatus, specifically in proliferative neural progenitor cells. The average Oct4 intensity was calculated for cells that were inside and outside the clusters displaying enhanced Cx43 at 24 h (d). Cells within the Cx43-enhanced clusters at 24 h exhibited a significant lower Oct4 expression compared to cells outside of the cluster with low Cx43 signal. Scale bar: 30 µm

Fig. 3

Analysis of intercellular transport rates as a function of cell-cycle state. a Asynchronous cell population (Async) shifted to G2-phase after nocodazole treatment (NOC), and after 45 min of recovery (NOC45) the population shifted to G1-phase. b The population distribution averages from a were calculated for the Async, NOC, and NOC45 treatment conditions. c An illustration of the GAP-FRAP technique for quantification of relative diffusion rates between adjacent cells. d A histogram of recovery time constants collected using gap-FRAP in the Async population (n = 64), where high and low recovery constants represent slow and fast transport rates, respectively. e The distributions of recovery constants for Hoechst-identified mitotic (HMI) cells (n = 26) and NOC45 (n = 28) were shifted to the right and left of the Async population, respectively, indicating slower and faster transport in these populations. f A projection of each cell cycle state onto the Async distribution using information from a and e, as described in Supplementary Figure 3

Fig. 4

Computational analysis of cell-cycle modulation on intercellular communication. a Each cell type (P, pluripotent; d, differentiated) has a base permeability, representing the average percent of gap junction hemichannels open at a cell-cell interface, with the total percent of open channels being the product of the two base permeabilities. b A function for cell-cycle modulation over time was defined based on the transport trends noted in Fig. 3, with a convolution of all possible transport profiles that two cells could experience over time for P-P, P-D, and D-D. c The intercellular transport model was implemented within an agent-based model and compared to digitized experimental colonies over time. Supplementary Movie 1 is a representative video of the progression of intracellular gradient formation and differentiation

Fig. 5

Quantification of spatial patterning during RA differentiation. a The computationally generated pattern class structures used to train the principle component analysis, derived from, were applied to 120 experimental colony structures. b The seven selected metrics were calculated from each of the training set pattern classes (8 classes x 120 colony structures) and transformed into latent variable space through principal component analysis. PC1 represents extent of differentiation (temporal), and PC2 and PC3 represent organization/stochasticity and spatial locale, respectively (spatial characteristics). c The same metrics were calculated from experimental images of 0- (n = 24), 24- (n = 113), 48- (n = 139), and 72-h (n = 22) RA-treated colonies and transformed into latent variable space. The average simulation trajectory was capable of capturing the spatiotemporal trajectory of the experimental data (see Supplementary Figure 7 for simulation data points). At 24 h there is a steep transition along both spatial axes, indicating that there is a gain in random differentiation and that it propagates along the edges of colonies. By 48 h, the majority of differentiated cells are connected within a single, asymmetrical cluster

Fig. 6

Perturbation to the intercellular network of a multicellular D3 ESC population affects RA-accelerated differentiation in a temporal manner. At 24 h, neither adenylyl cyclase (AC) inhibition (a, SQ-treatment) nor gap junction (GJ) inhibition (b, β-GA-treatment) induced a significant change in spatial or temporal characteristics of differentiation compared to the vehicle control. By 48 h, a temporal shift along PC1 is observed for both treatments (a, b), depicting a decrease in the rate of differentiation. The intercellular model accurately predicted these dynamics, represented by average values for SQ-treatment (Exp: n = 87, Sim: n = 30) and BGA-treatment (Exp: n = 62, Sim: n = 30) compared to the vehicle control (Exp: n = 87, Sim: n = 75) (a, b). A schematic diagram of our proposed mechanism for the influence of AC and GJ inhibition on differentiation potential is depicted in c. Specifically, both AC and GJ inhibition are suggested to decrease the intercellular flux between cells but via separate mechanisms: modulating the concentration gradient and the number of open channels for AC and GJ inhibition, respectively. Data clouds of a, b before averaging are shown in Supplementary Figures 8, 9