RAS signalling through PI3-Kinase controls cell migration via modulation of Reelin expression

Abstract

RAS signalling through phosphoinositide 3-kinase (PI3-Kinase) has been shown to have an essential role in tumour initiation and maintenance. RAS also regulates cell motility and tumour invasiveness, but the role of direct RAS binding to PI3-Kinase in this remains uncertain. Here, we provide evidence that disruption of RAS interaction with PI3-Kinase p110α decreases cell motility and prevents activation of Rac GTPase. Analysis of gene expression in cells lacking RAS interaction with p110α reveals increased levels of the extracellular matrix glycoprotein Reelin and activation of its downstream pathway resulting in upregulation of E-cadherin expression. Induction of the Reelin/E-cadherin axis is also observed in Kras mutant lung tumours that are regressing due to blockade of RAS interaction with PI3-Kinase. Furthermore, loss of Reelin correlates with decreased survival of lung and breast cancer patients. Reelin thus plays a role in restraining RAS and PI3-kinase promotion of cell motility and potentially tumour metastasis.

Figure 1. Removal of RAS Interaction with p110α impairs cell motility.

(a–d) Random migration of Pik3ca^WT, Pik3ca^RBD and Pik3ca^RBD containing a WT p110a was analysed by time-lapse video microscopy and cell tracing in the presence or absence of (a) PDGF (20 ng ml⁻¹); (b) EGF (20 ng ml⁻¹); (c) HGF (10 ng ml⁻¹); (d) Insulin (100 ng ml⁻¹). Cells were imaged at 10 min intervals for 18 h. Graphs show migration tracks obtained from 90 cells in each experimental condition. The data are represented as a box and whisker plot in which the box shows the interquartile range that contains values between 25th and 75th percentile. The line inside the box shows the median. The two whiskers show adjacent values. The upper adjacent value (upper mark) is the value of the largest observation that is less than or equal to the upper quartile plus 1.5 the length of the interquartile range. Analogously the lower adjacent value (lower mark) is the value of the smallest observation that is greater than or equal to the lower quartile less 1.5 times the length of interquartile range. Analysis of variance (ANOVA) statistical analysis was performed with starved cells used as reference for each condition (NS, not significant; **P<0.01; ***P<0.001). (e) Random migration assays of Pik3ca^WT and Pik3ca^RBD cells containing ER-RAS V12 (tamoxifen-inducible H-RAS V12) treated with 4-hydroxytamoxifen (TX) or vehicle control. ANOVA statistical analysis was performed with starved cells used as reference for each condition (NS, not significant; ***P<0.001). Box and whisker plot was generated as indicated for a. (f) Random migration of Pik3ca^WT and Pik3ca^RBD cells was analysed by time-lapse video microscopy and cell tracing in the presence or absence of EGF (20 ng ml⁻¹) and the p110α specific PI3-kinase inhibitor BYL-719 (500 nM). Assay was carried out as described for a. ANOVA statistical analysis was performed with starved cells used as reference for each condition (NS, not significant; ***P<0.001). Box and whisker plot was generated as indicated for a. (g) Pik3ca^WT (filled bars) and Pik3ca^RBD (empty bars) MEFs were stimulated with EGF (20 ng ml⁻¹) for the indicated time periods. RAS-GTP activity was established in pull-down assays using GST-RBD of Raf (GST-RafRBD). Both total lysates and proteins bound to GST-RafRBD were analysed by western blot to detect RAS. Lower panel, quantitation of pull-down assays. (h) Random migration of Pik3ca^WT, Pik3ca^RBD and Pik3ca^RBD cells containing ER-MyrAkt was analysed by time-lapse video microscopy and cell tracing in the presence or absence EGF (20 ng ml⁻¹) and 4-hydroxytamoxifen (TX). ANOVA statistical analysis was performed with starved cells used as reference for each condition (NS, not significant; **P<0.01; ***P<0.001). Box and whisker plot was generated as indicated for a.

Figure 2. Disruption of RAS interaction with PI3-Kinase disturbs cell polarity and invasion.

(a) Wounded Pik3ca^WT and Pik3ca^RBD MEFs monolayers were allowed to migrate for 18 h in the presence or absence EGF (20 ng ml⁻¹) or FBS (10%). Migration was analysed by time-lapse video microscopy. For each condition 90 cells were tracked and persistence in the directionality of migration was analysed using Mathematica software. Analysis of variance (ANOVA) statistical analysis was performed with starved cells used as reference for each condition (NS, not significant; **P<0.05; ***P<0.005). (b) Invasion of Pik3ca^WT and Pik3ca^RBD cells in a collagen I matrix in the presence or absence of EGF (0.5 μg ml⁻¹). Stacks are acquired from the bottom of the well over 150 μm upward. Invasion through the collagen layer was monitored in a confocal microscope and analysed using Mathematica software. ANOVA statistical analysis was performed (**P<0.05; ***P<0.005). (c) Invasion of Pik3ca^WT, Pik3ca^RBD and Pik3ca^RBD WT p110α MEFs in transwells containing a layer of matrigel (growth factor reduced matrigel). Invasion was measured in either 0.2% FBS (starved), EGF (50 ng ml⁻¹) or FBS (10%). Invasive cells (on the lower part of the transwell, attached to the membrane) were stained with crystal violet and then lysed using acetic acid. Assays were carried out in triplicate, with error bars indicating s.d. The results of two different experiments are shown. Error bars indicate s.d. (Significance using Student's t-test. NS, not significant; **P<0.05; ***P<0.005).

Figure 3. Defects in Rac-GTPase activation in Pik3ca^RBD cells.

(a) MEFs were stimulated with EGF (20 ng ml⁻¹) for the indicated time periods. Rac-GTP activity was established in pull-down assays using GST-PBD of PAK1 (GST-PBD). Both total lysates and proteins bound to GST-PBD were analysed by western blot to detect Rac. (b) MEFs were stimulated with PDGF (20 ng ml⁻¹) for the indicated time periods and pull-down assays and analysis of the results were done in the same way as described for previous panel. (c) EGF-induced random migration of Pik3ca^WT and Pik3ca^RBD cells was analysed by time-lapse video microscopy and cell tracing in the presence or absence of the Rac inhibitor EHT-1864 (5 μM). Analysis of variance (ANOVA) statistical analysis was performed with starved cells used as reference for each condition (NS, not significant; **P<0.01). Box and whisker plot was generated as indicated for Fig. 1a. (d) EGF-induced random migration of Pik3ca^WT, Pik3ca^RBD and Pik3ca^RBD+RacV12 cells was analysed by time-lapse video microscopy and cell tracing. ANOVA statistical analysis was performed with starved cells used as reference for each condition (NS, not significant; **P<0.01). Box and whisker plot was generated as indicated for Fig. 1a. (e) Pik3ca^WT and Pik3ca^RBD cells were stimulated with EGF for the denoted time points. immunofluorescence (IF) to detect Rac accumulation in the plasma membrane was performed. DAPI co-staining was carried out to distinguish individual cells. Scale bar, 10 μm. White squares indicate part of the membrane magnified in the right hand images. Arrows indicate direction of cell movement.

Figure 4. Reelin expression is regulated by RAS-PI3-Kinase pathway and is involved in migration.

(a) Graphical display of statistical analysis performed to identify genes undergoing significant changes of expression in Pik3ca^RBD cells as compared with wild-type counterparts. Statistically significant probes are shown in light blue (0.05 fdr). Reln reports are shown in red. (b) RNA from steady-state (st-st), serum-starved or EGF-treated (20 ng ml⁻¹) fibroblasts was obtained and Reln mRNA levels measured by quantitative PCR (qPCR). Actin expression was used as an internal control for normalization. Independent triplicates were used for each time point. Error bars indicate mean±s.e.m. (c) Levels of Reln expression were measured by qPCR in Pik3ca^RBD cells containing an inducible active Akt construct (ER-MyrAKT) in the presence or absence of 4-hydroxytamoxifen (TX; 100 nM). Actin expression was used as an internal control for normalization. Independent triplicates were used for each time point. Error bars indicate mean±s.e.m. (d) Random migration after Reln silencing in Pik3ca^RBD cells. Migration was analysed by time-lapse video microscopy and cell tracing in the presence or absence of EGF (20 ng ml⁻¹). Box and whisker plot was generated as indicated for Fig. 1a.ANOVA statistical analysis was performed with starved cells used as reference for each condition (NS, not significant; **P<0.01; ***P<0.001). (e) Recombinant Reln (1 μg ml⁻¹) was added to the media of Pik3ca^WT and Pik3ca^RBD cells and random migration was then analysed in the same way as described for previous panel. (f) Reln expression levels in Pik3ca^WT, Pik3ca^RBD and Pik3ca^RBD RacV12 cells. Actin expression was used as an internal control for normalization. Independent triplicates were used for each time point. (g) Rac pull-down analysis in the presence of recombinant Reln. Recombinant Reln was added to the media of Pik3ca^WT MEFs and then Rac-GTP activity was determined in pull-down assays using GST-PBD of PAK1 (GST-PBD). Both total lysates and proteins bound to GST-PBD were analysed by western blot to detect Rac. (h) Representative graph showing Reln mRNA half-life. Pik3ca^WT, Pik3ca^RBD, Pik3ca^RBD p110a WT and Pik3ca^RBD ER-myrAkt (+TX) cells were treated with actinomycin D and levels of Reln mRNA were determined by qPCR at the displayed time points. Actin expression was used as an internal control for normalization. Independent triplicates were used for each time point.

Figure 5. The Reelin pathway regulates migration in Pik3ca^RBD cells.

(a) Random migration after dab1 silencing in Pik3ca^RBD cells. Migration was analysed by time-lapse video microscopy and cell tracing in the presence or absence of EGF (20 ng ml⁻¹). Box and whisker plot was generated as indicated for Fig. 1a. Analysis of variance (ANOVA) statistical analysis was performed with starved cells used as reference for each condition (NS, not significant; ***P<0.001). (b) Random migration after Rap1 silencing in Pik3ca^RBD cells. Migration assay was performed and analysed as described for previous panel. ANOVA statistical analysis was performed with starved cells used as reference for each condition (NS, not significant; **P<0.01; ***P<0.001). (c) Representative graph showing Cdh1 expression levels in Pik3ca^WT, Pik3ca^RBD and Pik3ca^WT cells 72 h after silencing of p110α. Actin expression was used as an internal control for normalization. The assay was performed three times and each time it was performed in triplicates. Error bars indicate mean±s.e.m. (Significance using Student's t-test ***P<0.001). (d) Representative graph showing Cdh1 expression levels in Pik3ca^RBD cells 72 h after silencing of Reln, Dab1 or Rap1. Actin expression was used as an internal control for normalization. The assay was performed three times and each time it was performed in triplicates. Error bars indicate mean±s.e.m. (e) Representative graph showing Cdh1 expression levels in Pik3ca^WT, Pik3ca^RBD and Pik3ca^RBD RacV12 cells. Actin expression was used as an internal control for normalization. The assay was performed three times and each time it was performed in triplicates. Error bars indicate mean±s.e.m. (Significance using Student's t-test ***P<0.001). (f) Random migration after Cdh1 silencing in Pik3ca^RBD cells. Migration assay was performed and analysed as described for a). Box and whisker plot was generated as indicated for Fig. 1a. ANOVA statistical analysis was performed with starved cells used as reference for each condition (NS, not significant; **P<0.01).

Figure 6. Reelin expression in tumours in mice and clinical data sets.

(a) Reln expression in lung tumours from 7-week-old Pik3ca^WT/flox, Pik3ca^RBD/flox, Pik3ca^WT/− Pik3ca^RBD/− mice treated and untreated with tamoxifen. All these mice harbour an oncogenic mutation in Kras so they develop lung tumours. Tumours were collected 1 week after the end of tamoxifen treatment. Actin expression was used as an internal control for normalization. (b) E-cadherin expression in lung tumours from 7-week-old Pik3ca^WT/flox, Pik3ca^RBD/flox, Pik3ca^WT/− Pik3ca^RBD/− mice treated and untreated with tamoxifen. Tumours were collected 1 week after the end of tamoxifen treatment. Actin expression was used as an internal control for normalization. (c) Representative images of Reln and E-cadherin staining of lung sections from Pik3ca^WT/− Pik3ca^RBD/− mice. (d) Plot representing human RELN expression values from patients with the tumour types indicated in the figure. (e) Kaplan–Meier graph showing overall survival for lung adenocarcinoma patients with low and high expression of RELN. High and low RELN expression was divided by median.