Gene signature associated with benign neurofibroma transformation to malignant peripheral nerve sheath tumors

Abstract

Benign neurofibromas, the main phenotypic manifestations of the rare neurological disorder neurofibromatosis type 1, degenerate to malignant tumors associated to poor prognosis in about 10% of patients. Despite efforts in the field of (epi)genomics, the lack of prognostic biomarkers with which to predict disease evolution frustrates the adoption of appropriate early therapeutic measures. To identify potential biomarkers of malignant neurofibroma transformation, we integrated four human experimental studies and one for mouse, using a gene score-based meta-analysis method, from which we obtained a score-ranked signature of 579 genes. Genes with the highest absolute scores were classified as promising disease biomarkers. By grouping genes with similar neurofibromatosis-related profiles, we derived panels of potential biomarkers. The addition of promoter methylation data to gene profiles indicated a panel of genes probably silenced by hypermethylation. To identify possible therapeutic treatments, we used the gene signature to query drug expression databases. Trichostatin A and other histone deacetylase inhibitors, as well as cantharidin and tamoxifen, were retrieved as putative therapeutic means to reverse the aberrant regulation that drives to malignant cell proliferation and metastasis. This in silico prediction corroborated reported experimental results that suggested the inclusion of these compounds in clinical trials. This experimental validation supported the suitability of the meta-analysis method used to integrate several sources of public genomic information, and the reliability of the gene signature associated to the malignant evolution of neurofibromas to generate working hypotheses for prognostic and drug-responsive biomarkers or therapeutic measures, thus showing the potential of this in silico approach for biomarker discovery.

Fig 1. Prisma flow diagram.

Fig 2. General schema of the integration of studies to generate the MPNST vs. NF gene signature and its processing by NFFinder.

The upper panel shows the five microarray studies used to compute the MPNST vs. NF gene signature by meta-analysis (central panel). Score values calculated for each gene in each study (s_ij) and for each signature gene (s_i) are shown next to rectangles that indicate the respective gene size effect or fold change (FC_ij and FC_i); red for upregulated genes and green for downregulated ones. The lower panel describes the results obtained from NFFinder when GEO and CMap-DrugMatrix databases are interrogated for direct or inverse matching of gene expression patterns, respectively, by using the signature gene names as input. Experimental validation should verify the hypotheses generated by this in-silico predictive workflow.

Fig 3. Chromosome distribution of the MPNST vs. NF gene signature.

The gene signature distribution was calculated from the 336 genes with positive score (a), and from the 243 genes with negative score (b). Bar diagrams compare the observed distribution of MPNST vs. NF gene percentage in the human chromosome arms (dark bars) with the expected distribution according to the human ENSEMBL database (light bars). Statistical significance of the gene signature over-represented chromosome arms is above the bars. Over-represented human chromosome bands in the MPNST vs. NF gene signature are shown below each chart. Their statistical significance is shown at the top right side of band names. (****) P(X≥x) < 0.0001, (***) 0.0001< P(X≥x) < 0.001, (**) 0.001< P(X≥x) < 0.01, (*) 0.01< P(X≥x) < 0.05.

Fig 4. Clustering of phenotype comparisons and of NF1-related genes.

Comparisons among MPNST, NF and control phenotypes were grouped through hierarchical clustering. Cell culture and nerve tumor comparisons are shown on the top of the upper dendrogram, and the node height scale is detailed on the left of this tree. The hierarchical relationship among gene clusters obtained by grouping the logFC_m values of 2209 NF1-related genes by the Self-Organizing Tree Algorithm (SOTA) is represented by the dendrogram on the left. Clusters are described by their SOTA centroid vectors. Color scale of logFC_m values is shown below. The right side of the Fig details the number of genes in each cluster, the gene number of the MPNST vs. NF signature in each cluster (*, > 15 genes), the percentage of genes of this signature in each cluster (grey scale shown below), the number of biological process GO terms over-represented in each cluster, and the summary of the GO term enrichment as functional characterization of clusters. A complete list of terms is shown in S9 Table.