Genome Fusion Detection: a novel method to detect fusion genes from SNP-array data

An integrated deep learning and dynamic programming method for predicting tumor suppressor genes, oncogenes, and fusion from PDB structures

Mutations in proto-oncogenes (ONGO) and the loss of regulatory function of tumor suppression genes (TSG) are the common underlying mechanism for uncontrolled tumor growth. While cancer is a heterogeneous complex of distinct diseases, finding the potentiality of the genes related functionality to ONGO or TSG through computational studies can help develop drugs that target the disease. This paper proposes a classification method that starts with a preprocessing stage to extract the feature map sets from the input 3D protein structural information. The next stage is a deep convolutional neural network stage (DCNN) that outputs the probability of functional classification of genes. We explored and tested two approaches: in Approach 1, all filtered and cleaned 3D-protein-structures (PDB) are pooled together, whereas in Approach 2, the primary structures and their corresponding PDBs are separated according to the genes' primary structural information. Following the DCNN stage, a dynamic programming-based method is used to determine the final prediction of the primary structures' functionality. We validated our proposed method using the COSMIC online database. For the ONGO vs TSG classification problem the AUROC of the DCNN stage for Approach 1 and Approach 2 DCNN are 0.978 and 0.765, respectively. The AUROCs of the final genes' primary structure functionality classification for Approach 1 and Approach 2 are 0.989, and 0.879, respectively. For comparison, the current state-of-the-art reported AUROC is 0.924. Our results warrant further study to apply the deep learning models to humans' (GRCh38) genes, for predicting their corresponding probabilities of functionality in the cancer drivers.

KAOS: a new automated computational method for the identification of overexpressed genes

Background

Kinase over-expression and activation as a consequence of gene amplification or gene fusion events is a well-known mechanism of tumorigenesis. The search for novel rearrangements of kinases or other druggable genes may contribute to understanding the biology of cancerogenesis, as well as lead to the identification of new candidate targets for drug discovery. However this requires the ability to query large datasets to identify rare events occurring in very small fractions (1–3 %) of different tumor subtypes. This task is different from what is normally done by conventional tools that are able to find genes differentially expressed between two experimental conditions.

Results

We propose a computational method aimed at the automatic identification of genes which are selectively over-expressed in a very small fraction of samples within a specific tissue. The method does not require a healthy counterpart or a reference sample for the analysis and can be therefore applied also to transcriptional data generated from cell lines. In our implementation the tool can use gene-expression data from microarray experiments, as well as data generated by RNASeq technologies.

Conclusions

The method was implemented as a publicly available, user-friendly tool called KAOS (Kinase Automatic Outliers Search). The tool enables the automatic execution of iterative searches for the identification of extreme outliers and for the graphical visualization of the results. Filters can be applied to select the most significant outliers. The performance of the tool was evaluated using a synthetic dataset and compared to state-of-the-art tools. KAOS performs particularly well in detecting genes that are overexpressed in few samples or when an extreme outlier stands out on a high variable expression background.

To validate the method on real case studies, we used publicly available tumor cell line microarray data, and we were able to identify genes which are known to be overexpressed in specific samples, as well as novel ones.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-016-1188-1) contains supplementary material, which is available to authorized users.

Ultra-High Density SNParray in Neuroblastoma Molecular Diagnostics

Neuroblastoma serves as a paradigm for applying tumor genomic data for determining patient prognosis and thus for treatment allocation. MYCN status, i.e., amplified vs. non-amplified, was one of the very first biomarkers in oncology to discriminate aggressive from less aggressive or even favorable clinical courses of neuroblastoma. However, MYCN amplification is by far not the only genetic change associated with unfavorable clinical courses. So called “segmental chromosomal aberrations,” (SCAs) i.e., gains or losses of chromosomal fragments, can also indicate tumor aggressiveness. The clinical use of these genomic aberrations has, however, been hampered for many years by methodical and interpretational problems. Only after reaching worldwide consensus on markers, methodology, and data interpretation, information on SCAs has recently been implemented in clinical studies. Now, a number of collaborative studies within COG, GPOH, and SIOPEN use genomic information to stratify therapy for patients with localized and metastatic disease. Recently, new types of DNA based aberrations influencing the clinical behavior of neuroblastomas have been described. Deletions or mutations of genes like ATRX and a phenomenon referred to as “chromothripsis” are all assumed to correlate with an unfavorable clinical behavior. However, these genomic aberrations need to be scrutinized in larger studies applying the most appropriate techniques. Single nucleotide polymorphism arrays have proven successful in deciphering genomic aberrations of cancer cells; these techniques, however, are usually not applied in the daily routine. Here, we present an ultra-high density (UHD) SNParray technique which is, because of its high specificity and sensitivity and the combined copy number and allele information, highly appropriate for the genomic diagnosis of neuroblastoma and other malignancies.