Met kinetic signature derived from the response to HGF/SF in a cellular model predicts breast cancer patient survival

Abstract

To determine the signaling pathways leading from Met activation to metastasis and poor prognosis, we measured the kinetic gene alterations in breast cancer cell lines in response to HGF/SF. Using a network inference tool we analyzed the putative protein-protein interaction pathways leading from Met to these genes and studied their specificity to Met and prognostic potential. We identified a Met kinetic signature consisting of 131 genes. The signature correlates with Met activation and with response to anti-Met therapy (p<0.005) in in-vitro models. It also identifies breast cancer patients who are at high risk to develop an aggressive disease in six large published breast cancer patient cohorts (p<0.01, N>1000). Moreover, we have identified novel putative Met pathways, which correlate with Met activity and patient prognosis. This signature may facilitate personalized therapy by identifying patients who will respond to anti-Met therapy. Moreover, this novel approach may be applied for other tyrosine kinases and other malignancies.

Figure 1. Met signature segmentation of cell line model and human breast cancer patients’ data sets.

(A) Cells from six human breast cancer cell lines (MDA231, Hs578T, BT549, MCF10, MCF7 and T47D) were incubated with purified HGF/SF labeled with biotin by a protein biotinylation kit and allowed to bind for 30 min. Cells were then fixed with 4% Paraformaldehyde, permeablized, and stained with Streptavidin-coupled QDot585. Fluorescence levels calculated by image analysis using MICA image analysis software, p<0.0001. (B) Met canonical pathway score calculated by measuring the average mRNA levels of all Met canonical pathway genes (after normalization to average = 0, stdev = 1 per-gene) in high-Met (MDA231, Hs578T and BT549) as compared to the low-Met (MCF10, MCF7 and T47D) samples, p<0.0001. A gray box denotes high Met cell line samples and a black box denotes low Met cell line samples. (C) Hierarchical clustering division of breast cancer cell lines samples using Met kinetic signature genes.

Figure 2. Molecular analysis of Met kinetic signature- mRNA and protein levels of selected genes in high and low Met expressing cells.

(A) Total cellular RNA, was isolated from low (MCF7) and high Met (MDA231) cell cultures and mRNA expression of Met, Survivin, Pbk, Cyclin E1 and Ki67 was evaluated by quantitative real time PCR and compared mRNA levels of the housekeeping GAPDH gene. The primers used for the quantification of gene expression are listed in Table S2. A gray box denotes MCF7 cell line samples and a black box denotes MDA231 cell line samples (B) Samples from low (MCF7) and high Met (MDA231) cells were subjected to western blot (WB) analysis, before and 15 min and 60 min after treatment with HGF/SF, using antibodies against Met and activated Met (p-Met) and (C) antibodies against ERK K-23, p-ERK E-4, E-Cadherin, Survivin and Actin C4. (D, E) Subcellular localization of survivin in fluorescence (IF) analysis of Low (MCF7) and high Met (MDA231) cells after treatment with HGF/SF at 0 min, 10 min, 30 min and 24 h. The cells were Immunostained using anti-Survivin antibody. Immunofluorescence was examined using a 510 Meta Zeiss confocal laser scanning microscope (CLSM). Survivin quantification was performed on at least five confocal images per slide. Cell outline was defined based on Nomarski images; nuclei were defined based on the DAPI staining. Average pixel intensity was calculated separately for the nucleus and cytoplasm areas. (F) IF analysis of temporal kinetics of Survivin protein expression following treatment with HGF/SF.

Figure 3. ANAT derived Met anchored network.

We used the network inference tool ANAT, to construct the putative protein-protein interaction pathways leading from Met to its kinetic signature genes. ANAT derived Met anchored network is depicted: green nodes– anchor, red nodes - Met kinetic signature genes, pink nodes - nodes selected by ANAT.

Figure 4. Analysis of the association between High Met kinetic signature and basal-like tumors.

Hierarchical clustering was used to divide three large breast cancer patient cohorts (Chang (A), GSE3165 (B) and GSE1456 (C)), according to Met kinetic signature genes. The resultant patient groups were analyzed for association with tumor molecular classification. A gray box denotes patients in the low Met activity group and a black box denotes patients in the high Met activity group.

Figure 5. Kaplan Meier survival analysis of Met kinetic signature’s segmentation of human breast cancer patient cohorts.

Hierarchical clustering was used to divide six large breast cancer patient cohorts into high vs. low Met kinetic signature. Kaplan Meier analysis of overall survival (A,B,C,D,E) and metastasis-free survival (F,G) of the Chang (A, F, H, I), Miller (B), GSE1456 (C), GSE3165 (D), GSE11121 (E) and van ‘t veer (G) data sets. Kaplan Meier analysis of overall survival (H) and metastasis-free survival (I) of stage-I patients in the Chang data set. A red line denotes patients with high Met kinetic signature and a blue line denotes patients with low Met kinetic signature. In Chang data set, Met kinetic signature has a positive predictive value (PPV) and negative predictive value (NPV) of 41% and 82%, respectively.