Targeting Neph1 and ZO-1 protein-protein interaction in podocytes prevents podocyte injury and preserves glomerular filtration function

Abstract

Targeting protein-protein interaction (PPI) is rapidly becoming an attractive alternative for drug development. While drug development commonly involves inhibiting a PPI, in this study, we show that stabilizing PPI may also be therapeutically beneficial. Junctional proteins Neph1 and ZO-1 and their interaction is an important determinant of the structural integrity of slit diaphragm, which is a critical component of kidney's filtration system. Since injury induces loss of this interaction, we hypothesized that strengthening this interaction may protect kidney's filtration barrier and preserve kidney function. In this study, Neph1-ZO-1 structural complex was screened for the presence of small druggable pockets formed from contributions from both proteins. One such pocket was identified and screened using a small molecule library. Isodesmosine (ISD) a rare naturally occurring amino acid and a biomarker for pulmonary arterial hypertension was selected as the best candidate and to establish the proof of concept, its ability to enhance Neph1-CD and ZO-1 binding was tested. Results from biochemical binding analysis showed that ISD enhanced Neph1 and ZO-1 interaction under in vitro and in vivo conditions. Importantly, ISD treated podocytes were resistant to injury-induced loss of transepithelial permeability. Finally, mouse and zebrafish studies show that ISD protects from injury-induced renal damage.

Figure 1

A druggable pocket is formed at the interface of Neph1-CD and ZO-1-PDZ1 complex. (A,B) Two orthogonal views of the pockets identified in the complex of Neph1 CD (red ribbons) and ZO-1-PDZ1 (blue ribbons). The pocket formed at the interface of Neph1 and ZO1-PDZ1 complex is shown in green, while all the other pockets are displayed in grey. (C) The ball and stick model shows residues from the interface pocket of Neph1-CD and ZO-1-PDZ1 complex that was used as receptor for docking simulations. The residues are labelled with a single amino acid letter code, followed by their position and the chain names a or b representing Neph1-CD and ZO-1-PDZ1, respectively. The image acquisition softwares are listed in the methods section. Final images were imported to power point, labeled and saved a tiff files.

Figure 2

The virtual ligands screening using Neph1-CD-ZO-1-PDZ1 complex interface identified six molecules. The lowest energy docked poses of Isodesmosine (ISD) (A), d-penicillamine (B), l-glutathione (C), γ-glutamyl-l-alanine (D), l-saccharopine (E) and γ-d-GAMS acid (F) are shown in a ball-and-stick representation over the receptor pocket. To indicate the ligands binding property of receptor, the receptor surface is colored with green, red and blue representing hydrophobic, hydrogen bond accepting and hydrogen bond donating residues, respectively. The docking scores are displayed at the bottom left corner of each model. The image processing details are listed in the methods section and the final images were imported in power point and saved as tiff files.

Figure 3

Interaction analysis of the best ranked compounds based on virtual ligand screening. Two dimensional representations of the interactions made by Isodesmosine (ISD) (A), d-penicillamine (B), l-glutathione (C), γ-glutamyl-l-alanine (D), l-saccharopine (E) and γ-d-GAMS acid (F) with receptor residues are shown. The ball-and-stick model shows residues involved in hydrogen bonding (green lines) with the ligand and the interatomic distances are shown in Å. The red spiked arcs represent residues contributing to hydrophobic interactions in the drug-receptor complex. Image processing details are listed in the methods section. The final images were imported to power point, labeled and saved as tiff files.

Figure 4

ISD stabilizes the Neph1-CD and ZO-1-PDZ1 complex. FPLC profiles of a binary mixture of purified Neph1-CD and ZO-1-PDZ1 proteins. (A) The plotted elution profiles show that Neph1-CD forms an efficient complex with ZO-1-PDZ1, which dissociates into individual proteins with further incubation (smaller peaks following the larger peak of 1:1 complex indicated with red boxes) in the absence of ISD (left panel). In contrast, the presence of ISD does not allow dissociation of Neph1-CD and ZO-1-PDZ1 complex (right panel). (B) Change in the area under the peak corresponding to the binary complex of Neph1 and ZO-1 in the absence or presence of various concentrations of ligands (Compound 1: ISD; Compound 2: d-penicillamine; Compound 3: l-glutathione; Compound 4: γ-glutamyl-l-alanine; Compound 5: l-saccharopine; Compound 6: γ-d-GAMS acid) were plotted and showed that the area under peak significantly decreased over time with all the compounds tested except ISD. Data obtained in the excel format was imported to Origin Lab software and the elution profiles were plotted. The final images were transferred to power point, labeled and saved as tiff files.

Figure 5

Binding between Neph1 and ZO-1 is enhanced in the presence of ISD. (A) Neph1-CD and ZO-1-PDZ1 purified proteins were mixed at equimolar concentrations in the presence or absence of ISD and Neph1 immunoprecipitation shows increased binding of ZO-1 as detected by western blotting using His antibody. (B) Densitometric analysis shows increased Neph1-CD and ZO-1-PDZ1 binding in the presence of ISD (1 nM and 5 nM). (C) Similar results were obtained when recombinant GST-Neph1 and His-ZO-1-PDZ1 proteins were incubated in the absence or presence of ISD, where Neph1 was pulled down using GST beads and bound ZO1 was detected using His antibody. (D) ELISA was performed to evaluate ISD mediated increase in Neph1 and ZO1 binding. An increase in the Neph1-CD and ZO-1-PDZ1 binding was observed with increasing amounts of ISD. (E and F) ISD enhanced the interaction between endogenous Neph1 and ZO-1 in cultured podocytes. Following treatment with ISD, the cells were lysed and immunoprecipitated with Neph1. Analysis of the complex by western blotting showed increased ZO-1 binding in the presence of 1 µM ISD.

Figure 6

Treatment of cultured podocytes with ISD prevents injury-induced mislocalization of Neph1. (A) Cultured human podocytes were treated with PAN in the absence or presence of ISD and stained with Neph1 (Alexa-488) and ZO1 (Alexa-594) antibodies. Treatment with ISD prevented PAN-induced loss of Neph1 at cell-cell junctions (lower panel). (B) Effect of ISD on PAN-induced loss of transepithelial permeability was assessed by measuring the permeability of Texas Red-labeled BSA across the podocyte monolayer using trans-epithelial filter assay. The measurements were made after 1 h and 4 h of PAN injury and treatment with ISD significantly attenuated PAN-induced loss of permeability in these cells (P < 0.05). (C) Ability of ISD to restore PAN-induced loss of TER was measured in cultured human podocytes. TER was measured in a confluent monolayer of human podocytes treated with PAN (100 μg/ml) in the absence or presence of ISD (1 μM). ISD modestly restored PAN induced loss of TER in podocytes (p < 0.05).

Figure 7

ISD attenuates Adriamycin induced death and glomerular phenotype in zebrafish: (A) Adriamycin (30.3 mg/liter) was added to zebrafish embryos (8hpf) to induce mortality and glomerular phenotype. The Kaplan-Meier survival curve shows a significant reduction in Adriamycin induced mortality in ISD treated fish (p < 0.05). (B) Adriamycin induced phenotype is categorized into normal, moderate and severe pericardial edema. Quantitative analysis suggests that ISD reduced moderate and severe phenotypes by more than 50%. (C) Histological analysis further revealed a significant reduction in the Adriamycin induced pronephric tubular dilation (a hallmark of renal injury, shown by arrow) and glomerular architecture damage (marked as G).

Figure 8

ISD attenuates NTS induced injury in mice: (A) The schematic presentation of experimental plan is shown. (B–D) Representative images of pre-injection, 24 hours and day 5 post NTS injection urine samples from NTS + vehicle and NTS + ISD mice as analyzed by SDS-PAGE and coomassie blue staining (left panel). Quantitative analysis (right panel) shows a significant decrease in urine albumin/creatinine ratio in mice treated with ISD at day 5 (p < 0.05), when compared to the vehicle control. (E) Immunofluorescence analysis of kidney sections by DAPI (Blue) and Neph1 (Green) and ZO1 (Red) antibodies shows NTS-induced mislocalization of Neph1 and ZO-1 (NTS + Vehicle), whereas treatment with ISD restored the colocalization of Neph1 and ZO-1 at podocyte cell membrane (NTS + ISD).