SYTL4 downregulates microtubule stability and confers paclitaxel resistance in triple-negative breast cancer

Abstract

Background: Taxanes are frontline chemotherapeutic drugs for patients with triple-negative breast cancer (TNBC); however, chemoresistance reduces their effectiveness. We hypothesized that the molecular profiling of tumor samples before and after neoadjuvant chemotherapy (NAC) would help identify genes associated with drug resistance. Methods: We sequenced 10 samples by RNA-seq from 8 NAC patients with TNBC: 3 patients with a pathologic complete response (pCR) and the other 5 with non-pCR. Differentially expressed genes that predicted chemotherapy response were selected for in vitro functional screening via a small-scale siRNAs pool. The clinical and functional significance of the gene of interest in TNBC was further investigated in vitro and in vivo, and biochemical assays and imaging analysis were applied to study the mechanisms. Results: Synaptotagmin-like 4 (SYTL4), a Rab effector in vesicle transport, was identified as a leading functional candidate. High SYTL4 expression indicated a poor prognosis in multiple TNBC cohorts, specifically in taxane-treated TNBCs. SYTL4 was identified as a novel chemoresistant gene as validated in TNBC cells, a mouse model and patient-derived organoids. Mechanistically, downregulating SYTL4 stabilized the microtubule network and slowed down microtubule growth rate. Furthermore, SYTL4 colocalized with microtubules and interacted with microtubules through its middle region containing the linker and C2A domain. Finally, we found that SYTL4 was able to bind microtubules and inhibit the in vitro microtubule polymerization. Conclusion: SYTL4 is a novel chemoresistant gene in TNBC and its upregulation indicates poor prognosis in taxane-treated TNBC. Further, SYTL4 directly binds microtubules and decreases microtubule stability.

Keywords: SYTL4; Triple-negative breast cancer; microtubule polymerization; paclitaxel resistance.

Figure 1

Procedure for selecting differentially expressed genes associated with chemoresistance. (A) Schematic diagram of overlapping candidate genes from RNA-seq data of triple-negative breast cancer (TNBC) samples that underwent neoadjuvant chemotherapy (NAC). (B) Top 20 of Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways of 434 candidate genes as shown in (A). (C) Heatmap of the 30 top-ranked genes in 434 candidates above. The ranking standard was described in the methods.

Figure 2

Functional screening based on an siRNA pool assay in MDA-MB-231 cells. (A) Schematic diagram of the siRNA-based screening. Sensitization index (SI) was described in the Methods section. Higher SI indicates a higher synergistic effect of siRNA with paclitaxel. (B) Sensitization index (SI) distribution curve. Dots in red: siRNA targets with SI > 0.1. (C) Average SI of three targets of genes from (B). (D) Relative gene expression of SYTL4 in MDA-MB-231 cells after siSYTL4 treatment. Left: qRT-PCR quantification of mRNA level (mean ± SD, n = 3). 2^-∆∆Ct was used and GAPDH was set as the inner control. Right: western blot analysis of SYTL4 expression. (E) IC50 of paclitaxel in MDA-MB-231 cells with siSYTL4 knockdown. Two-way ANOVA test was used to compare the effect of siRNA2 to siNC. (F) Correlation between relative SYTL4 protein level and IC50 of paclitaxel in TNBC cells. Pearson's correlation R² was calculated and tested. SYTL4 protein level was estimated by quantification of the gray intensity of western blot bands as shown in Figure S2C. * P < 0.05; ** P < 0.01; *** P < 0.001; n.s: not significant.

Figure 3

SYTL4 correlated with poor prognosis in taxane-treated TNBC cohorts. (A-C) Survival analysis of SYTL4 expression in TNBC cohort from KM-plotter . (D-F) Survival analysis of SYTL4 expression in FUSCC TNBC cohort B (n = 232). (G) Representative images of SYTL4 expression in tumor tissue microarrays of TNBC by IHC. (H, I) Survival analysis of SYTL4 protein level and in FUSCC TNBC cohort C (n = 182). SYTL4 protein level was estimated by IHC as described in the Methods section. (J) t-SNE plot of all 1,069 classified TNBC cells, demonstrating separation of cells by cell type (left panel). Expression level and distribution of SYTL4 vary across cells (right panel). The hazard ratio (HR) was calculated by univariate Cox regression. DFS, disease-free survival; FUSCC, Fudan University Shanghai Cancer Center; IHC, immunohistochemistry; RFS, recurrence-free survival; TNBC, triple-negative breast cancer; t-SNE, t-distributed stochastic neighbor embedding.

Figure 4

Knocking down SYTL4 increased the paclitaxel sensitivity in TNBC. (A) Western blot analysis of SYTL4 expression in MDA-MB-231 and Hs578T cells. The two short hairpin RNA (shRNA) target sequences were described in the Methods section. (B) IC50 of paclitaxel in cells with SYTL4 knockdown tested by the CCK-8 assay. The data represents three independent assays (mean ± SD, n = 3). (C) SYTL4 knockdown inhibited the cell colony-formation of MDA-MB-231 and Hs578T cells under paclitaxel treatment (1 nM). The relative survival rate was calculated by dividing colony numbers under paclitaxel treatment into colony numbers under DMSO. The data represent three independent assays (right) (mean ± SD, n = 3). (D) IncuCyte-based real-time imaging analysis of cell growth with the treatment of paclitaxel. The relative cell survival rate on the Y axis was calculated by dividing the cell numbers under paclitaxel treatment by the cell numbers under DMSO treatment. (E) Rescuing SYTL4 expression increased the IC50 of paclitaxel in MDA-MB-231. Western blot analysis of SYTL4 expression (left). IC50 of paclitaxel in MDA-MB-231 (right). (F) SYTL4 knockdown inhibited tumor growth in nude mice after sequential paclitaxel (PTX) treatment. MDA-MB-231 cells with shNC or shSYTL4 were transplanted into nude mouse mammary fat pads in pairs as described in the Methods section. Arrows represent paclitaxel (10 mg/kg) treatment in tumor-bearing mice. Final tumor images were shown (left). Final tumor volume was calculated (middle) (mean ± SD, n = 4) and tested by paired t test. In vivo growth curves quantified by tumor volume were illustrated (right) and tested by two-way ANOVA test. (G) qRT-PCR analysis of the relative mRNA levels of two TNBC organoids and tested by unpaired t test (mean ± SD, n = 3). Human 18S rRNA was chosen as the reference gene. (H) Dose-response curves of organoid 1 (SYTL4 low expression) and organoid 2 (SYTL4 high expression) (mean ± SD, n = 3, two-way ANOVA test). (I) qRT-PCR analysis of the relative mRNA levels of TNBC organoid 2 with shNC or shSYTL4 and tested by unpaired t test (mean ± SD, n = 3). (J) Dose-response curves of organoid 2 (shNC vs. shSYTL4) (mean ± SD, n = 3, two-way ANOVA test). * P < 0.05; ** P < 0.01; *** P < 0.001; n.s: not significant.

Figure 5

SYTL4 colocalized and interacted with microtubules. (A) SYTL4 colocalized with microtubules in MDA-MB-231 cells. Anti-SYTL4 and anti-α-tubulin antibodies were used and are described in the Methods section. Nuclei were stained by DAPI. Images were captured and deconvolved by DeltaVision microscopy. (B) Colocalization analysis by Pearson's correlation. The colocalization of SYTL4 and α-tubulin as shown in (A) was estimated by calculating the Pearson's correlation of their fluorescence intensities. The data represents the mean ± SD estimated in at least 10 cells. (C) Coimmunoprecipitation (Co-IP) analysis of SYTL4-overexpressing MDA-MB-231 cells using anti-α-tubulin antibody. (D) Co-IP analysis of SYTL4-GFP-overexpressing MDA-MB-231 cells using anti-GFP nanobody-coated agarose beads. (E) Colocalization analysis of D1, D2 and D3 with microtubule by structured illumination microscopy (SIM) 293T cells. PM: plasma membrane. (F) Co-IP analysis of the interaction between SYTL4 D1, D2, D3 and microtubule. Co-IP assay was performed in 293T cells using anti-GFP beads. * P < 0.05; ** P < 0.01; *** P < 0.001; n.s: not significant.

Figure 6

Knocking down SYTL4 enhanced microtubule stability in TNBC. (A) Western blot analysis of microtubule acetylation in MDA-MB-231 and Hs578T cells with or without PTX (paclitaxel) treatment. Band intensity was estimated by Fiji. The data represent the band intensity of ace-tubulin relative to the baseline intensity level of shNC cells under DMSO treatment (mean ± SD, n = 3, one-way ANOVA test). GAPDH was used for normalization. (B) Western blot analysis of microtubule stability in MDA-MB-231 and Hs578T cells (left panel). The lysates were separated into pellet fractions (P) containing microtubules and supernatant fractions (S) containing soluble tubulin. The band intensity was estimated by Fiji. The percentage of assembled tubulin was calculated as follows: . The data represent the mean ± SD of three independent assays (one-way ANOVA test, right panel). (C) Immunofluorescence analysis of microtubule stability in MDA-MB-231 cells at 0 °C and 37 °C (left). Tubule-like structures were recognized by Fiji using the Tubeness plugin (middle) as described in methods. The percentage (%) of polymerized microtubules was calculated by dividing the area of tubule-like structure into the region inside the cell contour (right) (mean ± SD, n = 20, one-way ANOVA test). * P < 0.05; ** P < 0.01; *** P < 0.001; n.s: not significant.

Figure 7

SYTL4 increased microtubule dynamics via directly destabilizing microtubule polymers in TNBC. (A) Representative image of EB1 comets and track overlays in an MDA-MB-231 cell. This image is a snapshot from a 30 s time-lapse recording (scale bar, 5 µm). Spectrum lines represented overall EB1-ΔC-GFP comet movement for a 30-s time-lapse recording. Time-lapse images were acquired every 2 s for 30 s. See the Methods for a more thorough explanation. (B) Growth rates of tracks with or without paclitaxel treatment in MDA-MB-231 cells. Microtubule growth rates were calculated by directly observing the EB1-ΔC-GFP comets. Box plots indicate the 5th percentile (bottom boundary), median (middle line), 95th percentile (top boundary) and mean value (+). Points represent outliers. One-way ANOVA test. (C) Growth rates per cell means with or without paclitaxel treatment in MDA-MB-231 cells. Box plots indicate the 5th percentile (bottom boundary), median (middle line), 95th percentile (top boundary) and mean value (+) (n = 20 cells per condition). One-way ANOVA test. (D) SYTL4 directly interacted with α-tubulin. A pull-down assay was performed in a mixture of purified His-SYTL4 protein and tubulin as described in the Methods section. (E) SYTL4 inhibited in vitro microtubule polymerization. Paclitaxel was used as a positive control, and 6x His was used as a negative control. His-tagged SYTL4 was added to the microtubule polymerization solution.

Figure 8

A schematic diagram for explaining the role of SYTL4 in conferring paclitaxel resistance in TNBC. Upregulated SYTL4 expression is correlated with poor prognosis in triple-negative breast cancer (TNBC). SYTL4 directly interacts with microtubules and inhibits the microtubule polymerization, thus increasing microtubule instability. Accordingly, the acetylation level (Ac) of microtubules decreases. Unstable microtubules require higher paclitaxel concentrations to keep stabilized and induce cell death, thereby mediating TNBC paclitaxel resistance.