Deciphering the Mechanism of Gilteritinib Overcoming Lorlatinib Resistance to the Double Mutant I1171N/F1174I in Anaplastic Lymphoma Kinase

Abstract

Anaplastic lymphoma kinase (ALK) is validated as a therapeutic molecular target in multiple malignancies, such as non-small cell lung cancer (NSCLC). However, the feasibility of targeted therapies exerted by ALK inhibitors is inevitably hindered owing to drug resistance. The emergence of clinically acquired drug mutations has become a major challenge to targeted therapies and personalized medicines. Thus, elucidating the mechanism of resistance to ALK inhibitors is helpful for providing new therapeutic strategies for the design of next-generation drug. Here, we used molecular docking and multiple molecular dynamics simulations combined with correlated and energetical analyses to explore the mechanism of how gilteritinib overcomes lorlatinib resistance to the double mutant ALK I1171N/F1174I. We found that the conformational dynamics of the ALK kinase domain was reduced by the double mutations I1171N/F1174I. Moreover, energetical and structural analyses implied that the double mutations largely disturbed the conserved hydrogen bonding interactions from the hinge residues Glu1197 and Met1199 in the lorlatinib-bound state, whereas they had no discernible adverse impact on the binding affinity and stability of gilteritinib-bound state. These discrepancies created the capacity of the double mutant ALK I1171N/F1174I to confer drug resistance to lorlatinib. Our result anticipates to provide a mechanistic insight into the mechanism of drug resistance induced by ALK I1171N/F1174I that are resistant to lorlatinib treatment in NSCLC.

Keywords: anaplastic lymphoma kinase; drug resistance; molecular dynamics simulations; non-small cell lung cancer; targeted therapy.

FIGURE 1

(A) X-ray structure of ALK kinase domain in complex with lorlatinib (PDB ID: 4CLI). ALK is shown in cartoon format with the β-sheets, α-helices, and the loops coloring by cyan, pink, and gray, respectively. The critical glycine-rich loop (G-loop), the hinge domain, and the activation loop (A-loop) are coloring by orange, magenta, and yellow, respectively. (B) The detailed hydrogen bonds formed between the hinge residues Glu1197, Met1199 and lorlatinib are depicted by green dotted lines. Residues Ile1171 and Phe1194 are shown by stick models. (C) Chemical structures of lorlatinib and gilteritinib. (D) The docking pose of ALK in complex with gilteritinib. The detailed hydrogen bonds formed between the hinge residues Glu1197, Met1199 and gilteritinib are depicted by green dotted lines. Residues Ile1171 and Phe1194 are shown by stick models.

FIGURE 2

The free energy landscape of the first and second principal components (PC1 vs PC2) from MD simulations of the ALK–lorlatinib (A), ALK^{I1171N−F1174I}–lorlatinib (B), ALK–gilteritinib (C), and ALK^{I1171N−F1174I}–gilteritinib (D). The unit of free-energy values is kcal/mol.

FIGURE 3

Cross-correlation (CC _ij ) matrix computed for the ALK–lorlatinib (A), ALK^{I1171N−F1174I}–lorlatinib (B), ALK–gilteritinib (C), and ALK^{I1171N−F1174I}–gilteritinib (D). The correlated motions are colored by red (CC _ij > 0), while the anti-correlated motions are colored by blue (CC _ij < 0). Color scales are shown at the right. The CC _ij values with an absolute correlation coefficient of less than 0.3 are colored by white for clarity.

FIGURE 4

Generalized correlation (GC _ij ) matrix computed for the ALK–lorlatinib (A), ALK^{I1171N−F1174I}–lorlatinib (B), ALK–gilteritinib (C), and ALK^{I1171N−F1174I}–gilteritinib (D). Color scales are shown at the right.

FIGURE 5

Probability distribution of the normalized GCij scores for the four ALK states.

FIGURE 6

The mainly distinct residue contributions to the binding affinities of lorlatinib/gilteritinib to both the wild-type and double mutant predicted by the MM-GBSA binding free energy decomposition. The error bars represent standard deviations of per-residue energetic contribution.

FIGURE 7

The critical hydrogen bonding interactions between the hinge Glu1197, Met1199 and lorlatinib/gilteritinib in both the wild-type and the double mutant systems. The error bars represent standard deviations of the occupancy of hydrogen bonds.

FIGURE 8

The backbone superimposition of the representative conformation of double mutant I1171N/F1174I lorlatinib-bound ALK to the wild-type structural complex in the ATP-binding site (A) and the mutated site (B).

FIGURE 9

The probability distributions of the two distances (Å) between the centroid of the phenyl moiety of the lorlatinib and the Cα atoms of Leu1156 (A) and Asp1270 (B) in the wild-type and the double mutant systems.

FIGURE 10

The backbone superimposition of the representative conformation of double mutant I1171N/F1174I gilteritinib-bound ALK to the wild-type structural complex.