Receptor tyrosine kinase inhibition leads to regression of acral melanoma by targeting the tumor microenvironment

Abstract

Acral melanoma (AM) is an aggressive melanoma variant that arises from palmar, plantar, and nail unit melanocytes. Compared to non-acral cutaneous melanoma (CM), AM is biologically distinct, has an equal incidence across genetic ancestries, typically presents in advanced stage disease, is less responsive to therapy, and has an overall worse prognosis. Independent analysis of published genomic and transcriptomic sequencing identified that receptor tyrosine kinase (RTK) ligands and adapter proteins are frequently amplified, translocated, and/or overexpressed in AM. To target these unique genetic changes, a zebrafish acral melanoma model was exposed to a panel of narrow and broad spectrum multi-RTK inhibitors, revealing that dual FGFR/VEGFR inhibitors decrease acral-analogous melanocyte proliferation and migration. The potent pan-FGFR/VEGFR inhibitor, Lenvatinib, uniformly induces tumor regression in AM patient-derived xenograft (PDX) tumors but only slows tumor growth in CM models. Unlike other multi-RTK inhibitors, Lenvatinib is not directly cytotoxic to dissociated AM PDX tumor cells and instead disrupts tumor architecture and vascular networks. Considering the great difficulty in establishing AM cell culture lines, these findings suggest that AM may be more sensitive to microenvironment perturbations than CM. In conclusion, dual FGFR/VEGFR inhibition may be a viable therapeutic strategy that targets the unique biology of AM.

Figure 1:. Acral melanoma (AM) tumors highly amplify and/or upregulate RTK adapter proteins, VEGFR, FGFR, and FGF ligands

(A) From 88 tumors in the Wang 2023 cohort, the percentage of tumors bearing RTK-associated allele loss, (B) amplification, or (C) high copy-number amplification above 4x background tumor ploidy are shown. (D) Translocation events involving RTK-associated genes occur in a minority of AM per Liang 2017 and Newell 2020. In comparison to CM, AM highly express RTK and intracellular RTK adapters (CRKL and GAB2) per Weiss 2022. Certain ligands such as FGF3 and FGF19 were expressed at low levels in some AM tumors compared to lack of expression in CM. P-adjusted significance values are indicated as follows: x p=0.05–0.07, * p<0.05, **p<0.01, ***p<0.001, ****p<0.0001, † low expression gives error in p-value calculations. (E) Large insertion and deletion (InDel) events and (F) translocations infrequently involve RTK-associated genes. (G) A summary of published CNV and expression results for select genes are tabulated.

Figure 2:. Blockade of FGFR/VEGFR receptors inhibits melanogenesis in a dose-dependent fashion.

(A) Colormap representing the published IC50 values and inferred IC50 values from kinase inhibition studies for five separate multi-RTK inhibitors. (B) A premalignant mitfa-CRKL and MC-GFP zebrafish model of AM is utilized to test multi-RTK inhibitor effects against fin melanogenesis. (C-D) Phase contrast and GFP fluorescence imaging of multi-RTK treated zebrafish tails reveal that 3μM Anlotinib, Cabozantinib, or Lenvatinib induce a marked decrease in fin melanogenesis. Each grey dot in J represents an individual zebrafish, and the table underneath the summarizes each inhibitor’s potency against VEGFRs or FGFRs (+potent against only one FGFR or VEGFR protein, ++ potent against all FGFR or VEGFR proteins, - not potent). (E) Tailfin melanocyte cell area quantification at different drug doses in mitfa-CRKL MC-GFP zebrafish. Drug abbreviations: Apa – Apatinib, Anlo – Anlotinib, Lenv – Lenvatinib, Cabo – Cabozantinib, Suni - Sunitinib.

Figure 3:. Histologic and genetic characterization of AM and CM PDX tumor models.

(A) Anatomic location of AM and CM tumors. CM are labelled in blue text, acral subungal melanoma (ASM) in orange, and volar AM in red. (B) Representative clinical, low-passage, and high passage PDX tumor histology images. (C-D) Results from the Clinical Drift Score validation indicates that PDX tumors are histologically stable through multiple passages. Scores represent cytologic and histologic architecture drift from the original clinical tumor histology: none/identical (0), minimal (1), mild (2), moderate (3), and marked (4). Definitions and criteria for each classification are available in Supplemental Data 3. Four CM tumors and nine AM tumors are plotted in C-D. (E) Growth rates of representative PDX tumors. (F) Available AM PDX models encompass the spectrum of TCGA MAPK mutations. Relevant Tier 1 (pathogenic) and 2 (likely pathogenic) SNV mutations, MC1R mutations associated with melanoma predisposition, and CNV are represented in the tile plot. Black bars link PDX tumors that were collected from the same patient. (G) AM PDX models with localized highly amplified genomic regions are compared to a representative CM model.

Figure 4:. Dual FGFR/VEGFR inhibition with Lenvatinib induces tumor stasis or regression in all AM PDX tumors.

Tumor growth velocity for individual Sunitinib (daily, 40mg/kg) and Lenvatinib (daily, 50mg/kg) treated PDX tumors are represented as violin plots (A, C). The Lenvatinib-treated tumors from (A, C) are shown as bar plots that are color-coded based on depth of response (B, D). CM tumors are indicated by a checkerboard pattern. Average tumor growth of vehicle and Lenvatinib treated CM (E) and AM (F) are shown for each PDX model. Two-way ANOVA was used to determine differences between CM and AM therapy response (B-D), and student T-tests were used to compare vehicle and treatment differences within a PDX model (A, C, E-F).

Figure 5:. Dual FGFR/VEGFR is not directly cytotoxic in dissociated AM PDX tumor cells.

(A) Most AM cells cultured from PDX tumors do not grow in extended culture conditions. (B) Fresh PDX tumors were collected, dissociated into individual cells, and depleted of mouse stroma before plating for immediate and short term culture drug studies using quantitative phase imaging (QPI). Growth of AM and CM cells in (C) 0.5% DMSO; (D) 50μM Sunitinib, (E), 20μM Lenvatinib, and (F) 40μM Apatinib. (G) To facilitate comparison to PDX tumor growth velocity in Figures 4B and 4D, growth velocity was calculated by linear regression of normalized mass.

Figure 6:. Lenvatinib halts AM tumor growth or induces regression by remodeling tumor vasculature.

(A) Representative histology (H&E, 10x objective) and immunohistochemistry (IHC) images of vehicle and Lenvatinib HCI-AM087 are shown. CD31 (20x objective) and transferrin receptor 1 (TfR1, 40x objective) were stained with DAB, and MiB/Ki67 (10x objective) was stained with red chromogen. Scale bars are in microns. A pathologist quantified the (B) Ki67 IHC positive cell percentage, (C) percent necrosis from H&E-stained sections, (D) membranous TfR1 IHC scores, and (E) CD31 positive IHC vessels. Significance was determined using the Student’s t-test. (F) While CM has reduced tumor proliferation and diminished blood vessel quantity and quality on Lenvatinib therapy, these PDX tumors often continue to grow. There are no observed direct cytotoxic effects of Lenvatinib on AM cells. Instead, tumor regression or stable disease is achieved in AM tumors by reducing the blood vessel quantity and quality.